Method and system for matching problems based on tags

Abstract

One embodiment of the present invention provides a tag-based problem matching method performed by at least one processor. The method comprises the steps of: deriving a problem concept for a problem based on a problem representation of the problem; searching for a corresponding curriculum among a pre-established curriculum that corresponds to the problem based on the problem concept, and assigning a problem tag to the problem that has the same name as an item name of the corresponding curriculum; and matching the problem to which the problem tag is assigned to a tree node pre-established for the curriculum based on the name of the problem tag assigned to the problem.

Description

Technology Field

[0001] The present invention relates to a tag-based problem matching method and system, and more specifically, to a problem matching method and system that derives a problem concept based on a problem representation, assigns a problem tag that matches a curriculum item based on the derived problem concept, and matches a problem to a tree node based on the assigned problem tag. Background Technology

[0002] Modern educational curricula are periodically revised in response to societal demands and technological advancements. Consequently, it has become essential to reclassify or reorganize existing educational content to align with the new curriculum. However, this process is not only time-consuming and costly but also inefficient, as it is often performed manually. The need for an efficient classification system is further emphasized, particularly in situations where large-scale problem content and complex curriculum structures must be managed simultaneously.

[0003] Existing educational content classification systems have several major limitations. First, since content must be manually reclassified whenever the curriculum changes, this requires a significant amount of manpower and time. When the curriculum is frequently revised, this leads to repetitive work and results in inefficiency in content management.

[0004] Furthermore, because existing systems manage academic concepts and curriculum units separately, it is difficult to maintain consistency during the search process. When a user searches for a specific problem, search results based on academic concepts may conflict with those based on curriculum units. This causes problems that can reduce the usability of educational content.

[0005] Finally, due to the expansion of the global education market and differing national curricula, the international compatibility of educational content is emerging as a critical issue. Since national curricula possess distinct structures and standards, even the same problem requires classification into forms suitable for each country's specific curriculum. Existing systems fail to effectively reflect these international differences, which consequently weakens competitiveness in the global education market.

[0006] To address this, a method is required to efficiently reclassify existing content in response to curriculum revisions. In particular, a technical solution is needed that integrates academic concept-based search with curriculum-based search to provide users with consistent results.

[0007] Furthermore, there is a need for a problem matching method and system that enables accurate classification by considering the multiple attributes of problem content and can flexibly respond to differences in national and regional curricula. Prior art literature

[65535] Republic of Korea Registered Patent Publication No. 10-1133023 "Curriculum Management System Using Academic Classification System and Recording Medium for Executing a Program for the Method on a Computer" (Registered March 28, 2012) The problem to be solved

[0008] To solve the aforementioned technical problem, the present invention aims to provide a problem matching method and system that analyzes a problem, assigns a problem tag, and matches the problem to a tree node based on the corresponding tag.

[0009] The technical problems that the present invention aims to solve are not limited to the technical problems described above, and other technical problems of the present invention may be derived from the following description. means of solving the problem

[0010] To solve the aforementioned technical problem, one embodiment of the present invention provides a tag-based problem matching method performed by at least one processor. The method comprises the steps of: deriving a problem concept for a problem based on a problem representation of the problem; searching for a corresponding curriculum among a pre-established curriculum that corresponds to the problem based on the problem concept, and assigning a problem tag to the problem that has the same name as an item name of the corresponding curriculum; and matching the problem to which the problem tag is assigned to a tree node pre-established for the curriculum based on the name of the problem tag assigned to the problem.

[0011] Additionally, another embodiment of the present invention provides a problem matching system. The system includes a communication module, at least one processor, and a memory electrically connected to the processor and storing at least one code executed by the processor. The memory stores code that, when executed through the processor, causes the processor to derive a problem concept for the problem based on a problem representation of the problem, search for a corresponding curriculum among pre-established curricula based on the problem concept, assign a problem tag to the problem with the same name as the item name of the corresponding curriculum, and, based on the name of the problem tag assigned to the problem, cause the problem to be matched to a pre-established tree node for the curriculum. Effects of the invention

[0012] According to the means for solving the problem of the present invention described above, when the curriculum is changed, content can be automatically reclassified by modifying only the tree structure, thereby reducing time and costs associated with manual reclassification.

[0013] In addition, according to the means for solving the problem of the present invention described above, generalized classification according to certain criteria can be ensured in the classification process of educational content.

[0014] In addition, according to the means for solving the problem of the present invention described above, a dual search method can be provided by simultaneously supporting search based on the sequence of educational courses based on a tree structure and search based on academic concepts based on tags.

[0015] In addition, according to the means for solving the problem of the present invention described above, it can be flexibly applied to a new curriculum and can automatically perform classification when new problems are added.

[0016] Furthermore, according to the means for solving the problem of the present invention described above, it can be applied to various educational curricula by subject and country, and thus can be useful in the global education market.

[0017] In addition, according to the means for solving the problem of the present invention described above, the efficiency of the learning environment can be improved by automating the manual analysis and classification of problems.

[0018] In addition, according to the means for solving the problem of the present invention described above, the management efficiency of educational content can be increased, thereby promoting the standardization and uniformity of content.

[0019] The effects of the present invention are not limited to the effects described above, but include all effects understood from the following description. Brief explanation of the drawing

[0020] FIG. 1 is a drawing illustrating the detailed configuration of a problem matching device according to one embodiment of the present invention. Figure 2 is a diagram illustrating an example of a tree structure for a curriculum. FIG. 3 is a flowchart illustrating the sequence of a problem matching method according to another embodiment of the present invention. FIGS. 4 and FIGS. 5 are flowcharts illustrating the sequence of additional steps included in the problem matching method illustrated in FIGS. 3. Specific details for implementing the invention

[0021] The present invention will be described in detail below with reference to the attached drawings. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, the attached drawings are intended only to facilitate understanding of the embodiments invented in this specification, and the technical concept invented in this specification is not limited by the attached drawings. All terms used herein, including technical and scientific terms, should be interpreted in the sense generally understood by those skilled in the art to which the present invention pertains. Terms defined in advance should be interpreted as having additional meanings consistent with relevant technical literature and the currently invented content, and unless otherwise defined, should not be interpreted in a highly ideal or restrictive sense.

[0022] In order to clearly explain the invention in the drawings, parts unrelated to the explanation have been omitted, and the size, form, and shape of each component shown in the drawings may be varied. Throughout the specification, identical or similar parts are denoted by identical or similar reference numerals.

[0023] Suffixes such as "part" and "module" used for components in the following description are assigned or used interchangeably solely for the ease of drafting the specification, and do not inherently possess distinct meanings or roles. Furthermore, in describing the embodiments invented in this specification, detailed descriptions of related prior art have been omitted where it is determined that such detailed descriptions could obscure the essence of the embodiments invented in this specification.

[0024] Throughout the specification, when it is stated that a part is "connected (connected, contacted, or coupled)" to another part, this includes not only cases where they are "directly connected (connected, contacted, or coupled)," but also cases where they are "indirectly connected (connected, contacted, or coupled)" with other members interposed therebetween. Furthermore, when it is stated that a part "includes (provides, or provides)" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but rather allows for additional "included (provided, or provided)" of other components.

[0025] Terms indicating ordinal numbers, such as "first," "second," etc., used herein are used solely for the purpose of distinguishing one component from another and do not limit the order or relationship of the components. For example, the first component of the present invention may be named the second component, and similarly, the second component may be named the first component. Singular forms used herein should be interpreted as including plural forms unless explicitly to the contrary.

[0026] FIG. 1 is a drawing illustrating the detailed configuration of a problem matching device according to one embodiment of the present invention.

[0027] The problem matching device (100) includes a communication module (110), a processor (120), and a memory (130).

[0028] The problem matching device (100) can be implemented in the form of a server, a computing device, or various smart devices, and can operate in a cloud computing service model such as SaaS (Software as a Service), PaaS (Platform as a Service), or IaaS (Infrastructure as a Service). Additionally, the problem matching device (100) may be built in the form of a private cloud, a public cloud, or a hybrid cloud system, but the scope of the present invention is not limited thereto.

[0029] The communication module (110) may include a device comprising hardware and software necessary to transmit and receive signals, such as control signals or data signals, through a wired or wireless connection with another network device. It transmits and receives wireless signals with at least one of a base station, an external terminal, or a server on a mobile communication network built according to technical standards or communication methods for mobile communication used in the mobile communication module (e.g., GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), LTE (Long Term Evolution), LTEA (Long Term Evolution-Advanced), etc.).

[0030] The processor (120) may include various types of devices for controlling and processing data. The processor (120) may refer to a data processing device embedded in hardware having a physically structured circuit to perform a function expressed by code or instructions included in a program. In one example, the processor (120) may be implemented in the form of a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), etc., but the scope of the invention is not limited thereto.

[0031] The memory (130) can store at least one of the information and data input to the communication module (110), the information and data required for the function performed by the processor (120), and the data generated according to the execution of the processor (120).

[0032] Memory (130) should be interpreted as a general term for non-volatile storage devices that retain stored information even when power is not supplied, and volatile storage devices that require power to retain stored information. In addition to volatile storage devices that require power to retain stored information, memory (130) may include cloud storage, SSD, magnetic storage media, or flash storage media, but the scope of the present invention is not limited thereto.

[0033] Memory (130) is electrically connected to the processor (120) and stores at least one code that is executed by the processor (120). Memory (130) stores code that causes the processor (120) to perform the following functions and procedures when executed through the processor (120).

[0034] Memory (130) stores code that causes the processor (120) to derive a problem concept for the problem based on the problem representation of the problem.

[0035] The problem expression does not refer solely to the text of the problem itself, but can encompass all elements constituting the problem, such as the text, graphs included in the problem, sentence expressions, between the lines, and figures included in the problem. In other words, while it is possible to derive the problem concept by extracting and analyzing the text itself, it is also possible to derive a problem concept that is not directly revealed in the text from the graphs, sentence expressions, and between the lines included in the problem, without extracting the text.

[0036] The problem concept may include basic concepts necessary to solve each of the above problems, linked concepts associated with the basic concepts, and prerequisite concepts that must be learned prior to the basic concepts. When deriving the problem concept, the problem text may be analyzed using a natural language processing-based method to derive the problem concept from the analyzed problem text.

[0037] The memory (130) may further store code that causes the processor (120) to extract the text, explanation, formula, the unit to which the problem belongs, and the solution process. When extracting the formula, mathematical symbols and formulas can be recognized by utilizing OCR and a formula parser.

[0038] The memory (130) may further store code that causes the basic concept to be derived based on the text, explanation, formula, unit, and solution process extracted by the processor (120). At this time, the process is divided into cases where an explanation exists and cases where an explanation is created because no explanation exists. If an explanation exists, the basic concept is derived through natural language processing and formula recognition. If an explanation does not exist and an explanation is created, an explanation is created through an automatic explanation module, and the basic concept is derived based on natural language processing and formula recognition of the created explanation. The automatic explanation module functions specific calculations and specific explanation phrases by utilizing the fact that similar patterns are repeated during the explanation process. Subsequently, if only numbers are entered into the automatic explanation module, an explanation for a specific problem is automatically output.

[0039] The memory (130) may further store code that causes the processor (120) to derive the linked concept and the preceding concept based on the basic concept.

[0040] The memory (130) stores a code that causes the processor (120) to search for a corresponding curriculum among the pre-set curriculums based on the problem concept and to assign a problem tag with the same name as the item name of the corresponding curriculum to the problem.

[0041] The memory (130) may further store code that causes the processor (120) to search for similar problems having a similar type to the problem among the stored problems already stored in the memory (130).

[0042] The memory (130) may further store code that causes the processor (120) to assign a problem tag with the same name as the similar problem tag assigned to the similar problem to the storage problem if a similar problem exists among the storage problems. At this time, a storage problem tag with the same name as the item name of the curriculum corresponding to the storage problem may be assigned to the storage problem.

[0043] The process of assigning the above problem tag to the above problem can be performed by a pre-configured artificial intelligence model. The artificial intelligence model may be trained to use the above problem, the above stored problem, the above curriculum, the above problem tag, and the above stored problem tag as training data, and to output a recommendation tag for the above problem when the above problem is received.

[0044] The above artificial intelligence model analyzes the characteristics of the problem, text structure, keywords, etc., compares the similarity with the stored problem, and automatically classifies the problem based on the similarity with the stored problem.

[0045] In this case, the storage problem may include problems identical to the problem received by the model, problems with only the numbers modified, and similar problems.

[0046] If a received problem is identical to a stored problem or a problem with only numerical variations, the AI ​​model automatically assigns the same tags as the stored problem to that problem. Since these problems identical to the stored problem or problems with only numerical variations have a very high degree of similarity to the stored problem, the AI ​​model can efficiently assign tags without an additional tag adjustment process.

[0047] Similar problems may be those that have a high degree of similarity to the problem received by the model but differ in some ways. In this case, the AI ​​model automatically copies parts of the stored problem tags and assigns them to the received problem, while providing a tag recommendation feature that allows the user to review and semi-automatically assign the remaining tags.

[0048] Additionally, the storage problem may include problems that are dissimilar to the problem received by the model. Dissimilar problems may be problems that have low similarity to the problem received by the model and problems that have different problem concepts from the problem received by the model. In this case, the artificial intelligence model may not assign a tag to the received problem, but may allow a user of the problem matching device (100) to assign an appropriate tag to the problem, or may generate a new tree node and tag suitable for the problem.

[0049] The problem classification and tagging process using such AI models provides higher accuracy and efficiency compared to existing methods through the automation of problem data management and tagging, and is particularly useful for managing large problem sets. Furthermore, the classification accuracy of new problems can be gradually improved through the continuous learning of the AI ​​models.

[0050] Memory (130) stores code that causes the processor (120) to match the problem to which the problem tag is assigned to the problem to a tree node that is pre-set for the curriculum, based on the name of the problem tag assigned to the problem.

[0051] Tree nodes can be created according to a pre-set learning order for the curriculum. Tree nodes may include a first node and second nodes corresponding to subcategories of the first node. At least one node name identical to the item name of the curriculum may be assigned to the tree node.

[0052] The item name of the first node may be assigned a name with a non-academic meaning rather than a purely academic concept, such as '1st semester of 2nd year of middle school'. For example, multiple first nodes may be created, and the first nodes may be assigned subject classification names that are not purely academic concepts, such as '1st semester of 2nd year of middle school', 'Probability and Statistics', 'Mathematics I', 'Mathematics II', etc.

[0053] The item name for the second node may be assigned a name that includes an academic concept, such as 'operations on polynomials'. For example, multiple second nodes may be created, and actual curriculum names such as 'operations on polynomials', 'complex numbers', and 'quadratic equations' may be assigned to the second nodes.

[0054] Examples of tree nodes and the names of each node included in the tree nodes will be explained in detail below with reference to Fig. 2.

[0055] The memory (130) may further store code that causes the processor (120) to match the problem to a node among the tree nodes that is assigned the node name having the same name as the name of the problem tag.

[0056] The memory (130) may further store code that causes the processor (120) to attempt matching sequentially from the lowest node among the second nodes to the highest node when matching the problem to the tree node. This provides a tag matching rule to efficiently perform matching between the problem and the nodes of the tree structure, thereby improving the problem matching performance and accuracy.

[0057] More specifically, a matching attempt is made at the node corresponding to the second node (300) in the hierarchy of the tree structure, and to increase the efficiency of the matching process, the search begins from the node at the bottom of the second node (300). If the first match occurs at the second node (300), other nodes above it are not additionally checked, thereby simplifying the search process. This effectively reduces search time and resources. If no match occurs at the second node (300), it indicates a tag assignment error, and the error can be resolved through a process of verifying and modifying the tag data for the problem. Additionally, if a matched node exists, the matching process is repeatedly performed at the node corresponding to the sub-category of that node to verify additional suitability and increase matching accuracy.

[0058] Criteria for determining the final matching node among the nodes derived from the matching results are also defined. If the matching process is performed at a node of the lowest classification, that node is determined as the final matching node; conversely, if no additional matching occurs at nodes of lower classifications after a match is made at an intermediate classification node, that intermediate classification node is set as the final matching node. These criteria enhance the reliability of the matching results and maintain the consistency of the data structure.

[0059] A tree node may include a regular node comprising multiple second nodes to which the problem is matched, and a virtual node connected to one of the second nodes. In this case, during the process of matching the problem to the tree node, if the problem is matched to both the regular node and the virtual node connected thereto, the problem is matched only to the regular node.

[0060] More specifically, regular nodes are nodes that directly reflect learning concepts defined in the curriculum and form the basic structure where specific problems are matched. Virtual nodes are nodes intended to indicate conceptual similarities between different regular nodes; they do not directly match problems but serve as hubs that reference existing regular nodes.

[0061] Here, 'reference' is defined as follows. If a previously formed normalized node (e.g., finding the roots of a quadratic function at the middle school level) exists, and subsequently, the same problem is matched to a normalized node at a different level that is conceptually identical or similar (e.g., the basics of quadratic roots at the high school level), the later-appearing normalized node shares the same concept by referencing that node to establish a connection with the earlier normalized node. In other words, 'reference' refers to the process or state of connecting a specific node so that it can use a problem or concept identical or similar to that of an existing node.

[0062] Therefore, the high school-level "Basics of Quadratic Roots" regular node references the middle school-level "Finding Quadratic Roots" regular node to utilize the same concepts already possessed by it, and a virtual node can be established to implement this. Such a virtual node indicates that the concepts are substantially identical between nodes of different levels and contributes to reducing unnecessary redundancy in the problem matching process.

[0063] However, unlike regular nodes that directly match problems, virtual nodes do not possess problems themselves; instead, they serve the role of connecting identical concepts solely by referencing specific nodes (or nodes). Through this organic combination of regular and virtual nodes, the hierarchical structure of the curriculum can be reflected more systematically, and problem matching can be performed efficiently by utilizing the similarities between concepts.

[0064] The memory (130) can store additional code that causes the processor (120) to identify a second node that must be matched with the problem. This allows the efficiency of the matching process to be increased by omitting the search for nodes that are not needed during the matching process.

[0065] Memory (130) may further store code that causes the processor (120) to analyze the accuracy of the problem tag and the node name assigned to the node matched with the problem. This process involves verifying the association between the matched assigned node name and the problem, and if the node name assigned to the matched node does not match the text data, keywords, or categories of the problem, it is considered an error.

[0066] For example, if a specific problem is tagged as 'Factorization' but the matching node is named 'Equation', this is detected as an error, and a warning related to the tag is generated to allow the user to correct it. Additionally, if conflicting tags are assigned to the same problem during the matching process, this is detected, and the appropriate tag is maintained based on priority, or the user is requested to confirm.

[0067] Memory (130) may further store code that causes the processor (120) to analyze the matching path between the problem and the nodes matched. This is to maintain the hierarchical relationship between the problem and the nodes within the tree structure through the verification of the matching path continuity and to ensure the reliability of the matching result. In this process, for example, if a problem is matched with a second node (300) and then matches with a fourth node, which is a subcategory of the second node (300), this is considered an error because the matching with the third node was omitted.

[0068] Figure 2 is a diagram illustrating an example of a tree structure for a curriculum.

[0069] Referring to FIG. 2, the tree node of the tree structure may include a first node (200) and a second node (300) corresponding to a subcategory of the first node.

[0070] In the following, a configuration including a first node (200) and a second node (300) has been exemplified as an implementation example of a tree node, but the scope of the present invention is not limited thereto, and the node classification can be arbitrarily adjusted as needed. That is, the tree node may include a third node which is a sub-node of the second node, and a fourth node which is a sub-node of the third node. The tree node in the present invention is not limited to two classifications of nodes and may include various node classifications.

[0071] The item name of the first node (200) may consist of a grade / semester or a subject title. For example, the item name of the first node (200) may consist of subject classifications that are not purely academic concepts, such as 'Middle School 2nd Grade 1st Semester', 'Probability and Statistics', 'Mathematics 1', 'Mathematics II', etc.

[0072] The names of nodes corresponding to the subcategories from the second node downwards may consist of node names that reflect the actual learning order. For example, they may consist of actual curriculum names such as 'Polynomial Operations', 'Complex Numbers', 'Quadratic Equations', etc.

[0073] As you move from the upper classification of a tree node to the lower classification node, the item names correspond to more detailed and in-depth concepts.

[0074] Each tree node may be assigned at least one tag with the same name as a curriculum item. Each node may be assigned single tags and multiple tags; for example, single tags such as '#QuadraticEquation' and '#QuadraticFormula', and multiple tags such as '#Substitution&Factorization' may be assigned. Each node may be assigned at least one tag. All tags are treated as equal levels and exist in parallel.

[0075] Referring again to Fig. 2, we will explain an example of a tag set assigned to each node.

[0076] The node in item '03 Factorization' has the tag '#Factorization'. The node in item '09 Factorization 9 (Factor Theorem)' has the tag '#Factorization&Factor Theorem'. The node in item '01 Factor Theorem 1 (Cervical)' has the tag '#Factor Theorem&Cervical'. The node in item '07 Various Equations' has the tags '#Cervical', '#Quadrature', '#HigherOrder', and '#VariousEquations'. The node in item '01 Cubic Equation' has the tags '#CervicalEquation' and '#Equation&Cervical'. The node in item '01 Solving 1 (Finding Roots, Using Factorization Formulas)' has the tags '#FindingRoots' and '#Factorization'.

[0077] Below, we will describe an example of a problem tag assignment process using the problem matching device (100) shown in FIG. 1 and a process of matching a problem with a problem tag assigned to a tree node.

[0078] In this embodiment, Problem 1 and Problem 2 are given. Problem 1 and Problem 2 are as follows.

[0079] Problem 1. Factorize the following expression:

[0080] Problem 2. Cubic equation The year of or am. Calculate the value of.

[0081] As a result of analyzing the text of Problem 1, the problem concept of 'factorization' can be derived. Accordingly, the problem tags '#factorization', '#cubic', and '#factor theorem' are assigned to Problem 1.

[0082] As a result of analyzing the text of Problem 2, problem concepts such as 'cubic equation' and 'finding roots' can be derived. Accordingly, problem tags '#equation', '#cubic equation', '#factorization', and '#finding roots' are assigned.

[0083] Problem 1 is matched with tree nodes in the order of '01 Aspect', '03 Factorization', '01 Factorization', '09 Factorization 9', and '01 Factor Theorem (Cyclic)'. Here, the matching path is selected based on the consistency between the problem tag and the node name of the tree structure, and appropriate hierarchy of tree nodes is explored through the problem tags '#Factorization' and '#Cyclic' and finally matched with the 'Factor Theorem (Cyclic)' node.

[0084] Problem 2 is matched with tree nodes in the order of '01 Prize', '07 Various Equations', '01 Cubic Equation', '01 Solving Cubic Equations', and '01 Solving 1 (Finding Roots, Using Factorization Formulas)'. Here, based on the tags '#Cubic Equation' and '#Finding Roots', related nodes are searched in the tree structure, and the matching is completed with the node most closely related to the characteristics of the problem.

[0085] FIG. 3 is a flowchart illustrating the sequence of a problem matching method according to another embodiment of the present invention.

[0086] The method of operating a clothing label production platform described below can be performed by the problem matching device (100) described above with reference to FIG. 1.

[0087] Accordingly, the description of the embodiment of the present invention described above with reference to FIG. 1 can be applied in the same way to the embodiment described below, and any content that overlaps with the description above will be omitted. The steps described below do not necessarily have to be performed in order, and the order of the steps can be set in various ways, and the steps may be performed almost simultaneously.

[0088] Referring to FIG. 3, the problem matching method includes a problem concept derivation step (S110), a corresponding curriculum search and problem tag assignment step (S120), and a step of matching the problem to a tree node (S130).

[0089] The problem concept derivation step (S110) is a step of deriving a problem concept for the problem based on the problem expression of the problem. The problem concept may include a basic concept necessary for solving each of the problems, a linked concept linked to the basic concept, and a prior concept that must be learned prior to the learning of the basic concept.

[0090] The step of searching for a corresponding curriculum and assigning a problem tag (S120) is a step of searching for a corresponding curriculum among the pre-established curricula based on the problem concept and assigning a problem tag to the problem that has the same name as the item name of the corresponding curriculum.

[0091] The step of matching a problem to a tree node (S130) is a step of matching the problem to which the problem tag is assigned to a tree node that has been pre-set for the curriculum, based on the name of the problem tag assigned to the problem.

[0092] Tree nodes are created according to a pre-set learning order for the above curriculum and may include a first node and second nodes corresponding to subcategories of the first node. At least one node name identical to the item name of the above curriculum may be assigned to the tree nodes.

[0093] The step of matching a problem to a tree node (S130) may involve matching the problem to a node among the tree nodes that is assigned a node name identical to the name of the problem tag. When matching the problem to a tree node, the step of matching a problem to a tree node (S130) may involve attempting to match sequentially from the node located at the bottom to the node located at the top among the second nodes.

[0094] A tree node may include a regular node comprising multiple second nodes to which the problem is matched, and a virtual node connected to one of the second nodes. In this case, if the problem is matched to both the regular node and the virtual node connected thereto during the step (S130) of matching the problem to the tree node, the problem is matched only to the regular node.

[0095] Referring to FIG. 4, the problem concept derivation step (S110) may include a problem text extraction step (S111), a basic concept derivation step (S112), and a linked concept and prior concept derivation step (S113).

[0096] The problem text extraction step (S111) is a step of extracting the problem text, explanation, formula, the unit to which the problem belongs, and the solution process. The basic concept derivation step (S112) is a step of deriving the basic concept based on the extracted text, explanation, formula, unit, and solution process. The linked concept and prior concept derivation step (S113) is a step of deriving the linked concept and the prior concept based on the basic concept.

[0097] Referring to FIG. 5, the corresponding curriculum search and problem tag assignment step (S120) may include a similar problem search step (S121) and a similar problem tag and same name tag assignment step (S122).

[0098] The similar problem search step (S121) is a step of searching for similar problems among previously stored problems that have a type similar to the problem.

[0099] The step of assigning similar problem tags and identical name tags (S122) is a step of assigning a problem tag with the same name as the similar problem tag assigned to the similar problem to the problem when the similar problem exists among the stored problems. At this time, a stored problem tag with the same name as the item name of the curriculum corresponding to the stored problem may be assigned to the stored problem.

[0100] The step of searching for a corresponding curriculum and assigning a problem tag (S120) can be performed by a pre-configured artificial intelligence model. The artificial intelligence model may be trained to use the problem, the stored problem, the curriculum, the problem tag, and the stored problem tag as training data, and to output a recommendation tag for the problem when the problem is received.

[0101] The problem matching method of the embodiments of the present invention described above may also be implemented in the form of a recording medium containing computer-executable instructions, such as program modules executed by a computer. A computer-readable medium may be any available medium accessible by a computer and includes both volatile and non-volatile media, as well as removable and inseparable media. Additionally, a computer-readable medium may include a computer storage medium. A computer storage medium includes both volatile and non-volatile, removable and inseparable media implemented by any method or technique for storing information, such as computer-readable instructions, data structures, program modules, or other data.

[0102] A person skilled in the art to which the present invention pertains will understand that, based on the foregoing description, other specific forms can be easily modified without altering the technical spirit or essential features of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. The scope of the present invention is defined by the claims set forth below, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof should be interpreted as being included within the scope of the present invention. The scope of the present invention is defined by the claims set forth below rather than by the detailed description above, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof should be interpreted as being included within the scope of the present invention. Explanation of the symbols

[0103] 100: Problem Matching Device 200: Node 1 300: Node 2

Claims

Claim 1 A tag-based problem matching method performed by at least one processor comprises: a) a step of deriving a problem concept for said problem based on a problem representation of said problem; b) a step of searching for a corresponding curriculum among a pre-established curriculum that corresponds to said problem based on said problem concept, and assigning a problem tag to said problem that has the same name as an item name of said corresponding curriculum; and c) a step of matching the problem to which the problem tag is assigned to the problem to a tree node pre-configured for the curriculum based on the name of the problem tag assigned to the problem, wherein the tree node includes a first node and second nodes corresponding to subcategories of the first node, and the step c) includes a step of attempting to match sequentially from the lowest node to the highest node among the second nodes when matching the problem to the tree node, wherein if the first match occurs at the second node, the matching is terminated for the node above the matched node, and if no match occurs at the second node, it is set as a tag assignment error, and the step c) further includes a step of analyzing the accuracy of the problem tag and the node name assigned to the node matched with the problem, wherein if the node name does not match the text data, keywords, and categories of the problem, it is set as a tag assignment error, and the tree node includes a regular node including a plurality of the second nodes to which the problem is matched and a virtual node connected to one of the second nodes, and in the step c) A problem matching method in which, when the above problem is matched with a regular node and a virtual node connected thereto, it is matched only with the regular node. Claim 2 A problem matching method according to claim 1, wherein the problem concept includes a basic concept necessary for solving the problem, a linked concept linked to the basic concept, and a prior concept that must be preceded before learning the basic concept. Claim 3 A problem matching method according to claim 2, wherein step a) comprises: a-1) a step of extracting the text, explanation, formula, the unit to which the problem belongs, and the solution process of the problem; a-2) a step of deriving the basic concept based on the extracted text, explanation, formula, unit, and solution process; and a-3) a step of deriving the linked concept and the prior concept based on the basic concept. Claim 4 A problem matching method according to claim 1, wherein the tree nodes are created according to a pre-set learning order for the curriculum, and at least one node name having the same name as the item name of the curriculum is assigned to the tree nodes. Claim 5 In paragraph 4, the above step c) is a problem matching method in which the problem is matched to a node among the tree nodes to which the node name is assigned the same name as the name of the problem tag. Claim 6 delete Claim 7 delete Claim 8 delete Claim 9 In claim 1, the above step b) further comprises: b-1) a step of searching for a similar problem having a type similar to the problem among the stored problems already stored in memory; and b-2) a step of, if the similar problem exists among the stored problems, assigning a problem tag with the same name as the similar problem tag assigned to the similar problem to the problem, wherein the stored problem is assigned a stored problem tag with the same name as the item name of the curriculum corresponding to the stored problem. Claim 10 A problem matching method according to claim 9, wherein step b) is performed by a pre-established artificial intelligence model, and the artificial intelligence model is trained to use the problem, the stored problem, the curriculum, the problem tag, and the stored problem tag as training data, and to output a recommendation tag for the problem when the problem is received. Claim 11 Communication module; at least one processor; The memory includes a memory electrically connected to the processor and storing at least one code executed by the processor, wherein the memory stores a code that, when executed through the processor, causes the processor to derive a problem concept for the problem based on a problem representation of the problem, search for a corresponding curriculum among pre-established curricula based on the problem concept, assign a problem tag to the problem with a name identical to the item name of the corresponding curriculum, and, based on the name of the problem tag assigned to the problem, cause the problem to be matched to a tree node pre-established for the curriculum. The tree node includes a first node and second nodes corresponding to a subcategory of the first node. When the processor matches the problem to the tree node, the memory attempts to match sequentially from the lowest node among the second nodes to the highest node, wherein if the first match occurs at the second node, the matching is terminated for the node above the matched node, and if no match occurs at the second node, a tag is assigned. A problem matching system that stores code causing an error to be set, wherein the memory further stores code causing a node name assigned to a problem tag and a node matched to the problem to be set as a tag assignment error if the node name does not match the text data, keywords, and categories of the problem, and wherein the tree node includes a regular node comprising a plurality of second nodes to which the problem is matched and a virtual node connected to one of the second nodes, and wherein when the problem is matched to both the regular node and the virtual node connected thereto, it is matched only to the regular node. Claim 12 A problem matching system according to claim 11, wherein the problem concept includes a basic concept necessary for solving the problem, a linked concept linked to the basic concept, and a prior concept that must be preceded before learning the basic concept. Claim 13 A problem matching system according to claim 12, wherein the memory further stores code that causes the processor to extract the text, explanation, formula, the unit to which the problem belongs, and the solution process of the problem, derive the basic concept based on the extracted text, explanation, formula, unit, and solution process, and derive the linked concept and the preceding concept based on the basic concept. Claim 14 A problem matching system according to claim 11, wherein the tree nodes are generated according to a pre-set learning order for the curriculum, and at least one node name with the same name as the item name of the curriculum is assigned to the tree nodes. Claim 15 delete Claim 16 In claim 11, the memory further stores code that causes the processor to search for similar problems having a type similar to the problem among the stored problems already stored in the memory, and if the similar problem exists among the stored problems, to assign a problem tag with the same name as the similar problem tag assigned to the similar problem to the problem, and the stored problem is a problem that has been assigned a stored problem tag with the same name as the item name of the curriculum corresponding to the stored problem.

Images