Method for providing active ai-based long-term memory review service through management of individually-optimized review spacing

Abstract

A method for providing an active AI-based long-term memory review service through management of individually-optimized review spacing, according to the present invention, comprises the steps in which: (a) a data transmission and reception unit of an operation server receives learning content information from a user terminal owned by a user; (b) an artificial intelligence computing unit of the operation server generates question cards including a model question card that contains a question directly including the learning content information and a duplicate question card that contains a modified question of the model question card; (c) the data transmission and reception unit transmits the model question card generated in step (b) to the user terminal; (d) the data transmission and reception unit receives first learning result information related to the model question card from the user terminal; (e) the artificial intelligence computing unit stores the question cards by assigning same to a plurality of review boxes, which are a plurality of virtual capacity sections set in a database of the operation server, according to preset assignment criteria, on the basis of the first learning result information, wherein steps (a) to (e) are repeatedly performed, and in the repeated process, if it is determined that the capacity of any review box has reached a threshold, step (add1) is performed in which the artificial intelligence computing unit selects a question card assigned to the review box of which capacity has reached the threshold according to a preset first priority criterion, and provides the selected question card to the user terminal.

Description

A method for providing an active AI-based long-term memory review service through personalized, optimized review interval management.

[0001] The present invention relates to a method for providing a review service, and more particularly, to a method for providing a review service that can manage an optimized review interval for each individual based on active AI and provide a highly efficient learning process based on the principle of long-term memory.

[0002] In general, the Ebbinghaus forgetting curve is empirical data that shows how important it is to review learned content, and it is widely known that periodic repeated learning is more effective than anything else for long-term memory of learned content.

[0003] However, for many learners, it is not easy to successfully implement periodic repetitive learning due to various reasons such as lack of learner's will to learn and lack of execution ability.

[0004] In addition, in order to successfully memorize learning content in the long term, the amount of repetitive learning content and the repetitive learning cycle need to be set differently according to the individual capabilities of the learner. However, there is a practical problem in that it is very difficult for learners to independently determine the amount of repetitive learning and the repetitive learning cycle that are right for them.

[0005] Meanwhile, a method to support long-term memory of learning content to solve these problems has been proposed through Korean Patent No. 10-2405520.

[0006] However, even with the method presented in the patent, there are still technical limitations that are being pointed out, such as the inability of learners to directly participate in learning environment settings such as the repetition learning cycle and repetition learning amount, the inability to analyze individual learning characteristics of learners such as learning ability and learning achievement level during repetition learning, and the inability to actively set the learning environment by reflecting such individual learning characteristics of learners.

[0007] Therefore, a method to solve these problems is required.

[0008] The present invention is an invention devised to solve the problems of the above-described prior art, and has the purpose of precisely analyzing the individual learning characteristics of a learner, such as learning ability and learning achievement level, during repeated learning, and setting an optimized review interval reflecting the individual learning characteristics of the learner thus analyzed, thereby improving the learning effect.

[0009] The tasks of the present invention are not limited to the tasks mentioned above, and other tasks not mentioned will be clearly understood by those skilled in the art from the description below.

[0010] The method for providing an active AI-based long-term memory review service through personalized optimized review interval management of the present invention to achieve the above-described purpose comprises the steps of (a) in which a data transmission / reception unit of an operation server receives learning content information from a user terminal owned by a user, (b) in which an artificial intelligence operation unit of the operation server generates a question card including a model question card including questions directly including the learning content information and a duplicate question card including modified questions of the model question card, (c) in which the data transmission / reception unit transmits the model question card generated in step (b) to the user terminal, (d) in which the data transmission / reception unit receives first learning result information for the model question card from the user terminal, and (e) in which the artificial intelligence operation unit assigns and stores the question card in a plurality of review boxes, which are a plurality of virtual capacity sections set in a database of the operation server, based on the first learning result information, according to a preset assignment criterion, and steps (a) to (e) are repeatedly performed, and in the process of being repeatedly performed, any If it is determined that the capacity of the review box has reached its limit, the artificial intelligence operation unit selects the question cards assigned to the review box whose capacity has reached its limit according to the preset first priority criterion and provides them to the user terminal (add1) step.

[0011] At this time, the review box may include a third review box in which a model question card for which the first learning outcome information is an incorrect answer is stored, a fourth review box in which a model question card for which the first learning outcome information is a correct answer is stored, a first review box in which a duplicate question card corresponding to the model question card stored in the third review box is stored, and a second review box in which a duplicate question card corresponding to the model question card stored in the fourth review box is stored.

[0012] And the step (e) may include a step (e-1) in which the artificial intelligence operation unit analyzes the contents of the first learning result information, a step (e-2) in which the artificial intelligence operation unit stores the model question card in the third review box or the fourth review box according to the analysis result of the step (e-1), and a step (e-3) in which the artificial intelligence operation unit stores the duplicate question card in the first review box or the second review box according to the analysis result of the step (e-1).

[0013] In addition, the (add1) step may include a (add1-1) step in which the artificial intelligence operation unit assigns a ranking to the question cards assigned to the review box whose capacity has reached the limit according to a preset first priority criterion, a (add1-2) step in which the artificial intelligence operation unit selects the question card with the highest priority by the (add1-1) step, and a (add1-3) step in which the data transmission / reception unit transmits the question card selected by the (add1-2) step to the user terminal.

[0014] In addition, after the above step (add1), a step (add2) in which the data transmission / reception unit receives second learning result information for the question card provided by the step (add1) from the user terminal, and a step (add3) in which the artificial intelligence operation unit performs subsequent processing on the question card provided by the step (add1) according to a first movement criterion set in advance based on the second learning result information may be further performed.

[0015] At this time, the (add3) step may include a (add3-1) step in which the artificial intelligence operation unit analyzes the contents of the second learning result information, a (add3-2) step in which the artificial intelligence operation unit, based on the analysis result of the (add3-1) step, leaves the corresponding question card in the existing review box if the second learning result information is incorrect, and a (add3-3) step in which the artificial intelligence operation unit, based on the analysis result of the (add3-1) step, moves the corresponding question card to the final check box, which is a virtual capacity section set in the database, if the second learning result information is correct.

[0016] Here, the above steps (add1) to (add3) are repeatedly performed, and if it is determined that the capacity of the final inspection box has reached the limit during the repeated performance, the artificial intelligence operation unit may perform the (add4) step of selecting the question cards stored in the final inspection box whose capacity has reached the limit according to a preset second priority criterion and providing them to the user terminal.

[0017] And after the above step (add4), the data transmission / reception unit may further perform a step (add5) in which it receives third learning result information for the question card provided by the step (add4) from the user terminal, and a step (add6) in which the artificial intelligence operation unit performs subsequent processing for the question card provided by the step (add4) according to a preset second movement criterion based on the third learning result information.

[0018] At this time, the (add6) step may include a (add6-1) step in which the artificial intelligence operation unit analyzes the contents of the third learning result information, a (add6-2) step in which the artificial intelligence operation unit, based on the analysis result of the (add6-1) step, leaves the corresponding question card in the final check box if the third learning result information is incorrect, and a (add6-3) step in which the artificial intelligence operation unit, based on the analysis result of the (add6-1) step, moves the corresponding question card to the review completion box, which is a virtual capacity section set in the database, if the third learning result information is correct.

[0019] The method of providing an active AI-based long-term memory review service through personalized optimized review interval management of the present invention to solve the above-mentioned problem has the advantage of being able to maximize learning effects by precisely analyzing the individual learning characteristics of each learner and setting an optimized review interval reflecting the individual learning characteristics of each learner thus analyzed, thereby inducing long-term memory.

[0020] In particular, the present invention can prevent learners from randomly guessing or memorizing the correct answer by providing an interval between the solving activities of the question cards, and can promote reliable memory and skill improvement by providing additional learning opportunities by separating important knowledge points into model question cards and duplicate question cards.

[0021] The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

[0022] FIG. 1 is a conceptual diagram illustrating each component of a system for performing a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to a first embodiment of the present invention.

[0023] FIG. 2 is a diagram illustrating a preliminary process of a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to a first embodiment of the present invention.

[0024] FIG. 3 is a diagram illustrating a subsequent process of a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to a first embodiment of the present invention.

[0025] FIG. 4 is a drawing illustrating various boxes, which are virtual capacity sections created in a database, in a method for providing an active AI-based long-term memory review service through personalized optimized review interval management according to a first embodiment of the present invention.

[0026] FIG. 5 is a diagram showing a detailed process of step (e) in a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to a first embodiment of the present invention.

[0027] FIG. 6 is a diagram showing a detailed process of the (add1) step in a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to the first embodiment of the present invention.

[0028] FIG. 7 is a diagram showing a detailed process of step (add4) in a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to the first embodiment of the present invention.

[0029] FIG. 8 is a diagram showing a detailed process of step (add6) in a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to the first embodiment of the present invention.

[0030] FIG. 9 is a drawing showing various boxes, which are virtual capacity sections created in a database, in a method for providing an active AI-based long-term memory review service through personalized optimized review interval management according to a second embodiment of the present invention. FIG. 10 is a drawing showing various boxes, which are virtual capacity sections created in a database, in a method for providing an active AI-based long-term memory review service through personalized optimized review interval management according to a third embodiment of the present invention.

[0031] In this specification, when it is said that a component (or region, layer, portion, etc.) is “on,” “connected to,” or “coupled to” another component, it means that it can be directly disposed / connected / coupled to the other component, or a third component may be disposed between them.

[0032] Identical drawing numbers indicate identical components. Furthermore, in the drawings, the thicknesses, proportions, and dimensions of components are exaggerated for the purpose of effectively illustrating the technical content.

[0033] “And / or” includes any combination of one or more of the associated constructs that can be defined.

[0034] While terms such as "first" and "second" may be used to describe various components, these components should not be limited by these terms. These terms are used solely to distinguish one component from another. For example, without departing from the scope of the present invention, a first component may be referred to as a "second component," and similarly, a second component may also be referred to as a "first component." Singular expressions include plural expressions unless the context clearly indicates otherwise.

[0035] Additionally, terms such as "below," "lower," "above," and "upper" are used to describe the relationships between components depicted in the drawings. These terms are relative concepts and are described based on the directions indicated in the drawings.

[0036] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. Furthermore, terms defined in commonly used dictionaries should be interpreted to have a meaning consistent with their meaning in the relevant technical context, and unless interpreted in an idealized or overly formal sense, they are explicitly defined herein.

[0037] Terms such as "include" or "have" should be understood to specify the presence of a feature, number, step, operation, component, part, or combination thereof described in the specification, but not to exclude in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0038] Additionally, when it is mentioned in this specification that a first component operates or executes on a second component, it should be understood that the first component operates or executes in an environment in which the second component operates or executes, or operates or executes through direct or indirect interaction with the second component.

[0039] When a component, device, or system is referred to as including a component consisting of a program or software, even if no explicit mention is made, it should be understood that the component, device, or system includes hardware (e.g., memory, CPU, etc.) or other programs or software (e.g., an operating system or drivers necessary to operate hardware) necessary for the program or software to run or operate.

[0040] Additionally, unless specifically stated otherwise in the implementation of a component, it should be understood that the component may be implemented in software, hardware, or both software and hardware.

[0041] Additionally, the terminology used herein is for the purpose of describing embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise. As used herein, the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components.

[0042] Additionally, terms such as "part" and "device" in this specification may be intended to refer to the functional and structural combination of hardware and software driven by or for driving the hardware. For example, the hardware herein may be a data processing device including a CPU or other processor. Furthermore, software driven by the hardware may refer to a running process, object, executable, thread of execution, program, etc.

[0043] Additionally, it can be easily inferred by an average expert in the technical field of the present invention that the above terms may mean a logical unit of a given code and hardware resources for executing the given code, and do not necessarily mean physically connected code or a type of hardware.

[0044] Hereinafter, the specific technical contents to be implemented in the present invention will be described in detail with reference to the attached drawings.

[0045]

[0046] The method for providing an active AI-based long-term memory review service through personalized optimized review interval management according to the present invention is performed through an operating server that provides a program or web service for providing an active AI-based long-term memory review service through personalized optimized review interval management stored in a storage medium, and can be driven by a processor of the operating server.

[0047] And the program or web service provided by the active AI-based long-term memory review service through personalized optimized review interval management can be output through a video output device such as a display module, and can provide visible information through a visualized graphical user interface on the operating server, user terminals owned by the user who is the learning subject, etc.

[0048] In particular, a program or web service for providing an active AI-based long-term memory review service through individual optimized review interval management can be installed on an operating server, user terminal, etc. using a removable disk or communication network, and a method for providing an active AI-based long-term memory review service through individual optimized review interval management can enable the operating server, user terminal, etc. to be operated by various functional means.

[0049] In other words, the present invention specifically realizes information processing by software through hardware.

[0050] Hereinafter, with reference to the attached drawings, a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to a first embodiment of the present invention will be described.

[0051] FIG. 1 is a conceptual diagram illustrating each component of a system for performing a method for providing an active AI-based long-term memory review service through personalized optimized review interval management according to a first embodiment of the present invention. In the following description, symbols assigned to each component are based on this diagram.

[0052] As illustrated in FIG. 1, a system for performing a method for providing an active AI-based long-term memory review service through personalized optimized review interval management according to a first embodiment of the present invention includes an operation server (100), and the operation server includes a database (105), a user terminal (10), a data transmission / reception unit (110) capable of transmitting or receiving various data, and an artificial intelligence operation unit (120) for analyzing, processing, and processing various data.

[0053] Each component illustrated in FIG. 1 may be functionally and logically separated, and it will be readily apparent to an average expert in the art that this does not necessarily mean that each component is separated into a separate physical device or written in separate code.

[0054] FIG. 2 is a diagram showing a preceding process of a method for providing a long-term memory review service based on active AI through personalized optimized review interval management according to a first embodiment of the present invention, and FIG. 3 is a diagram showing a subsequent process of a method for providing a long-term memory review service based on active AI through personalized optimized review interval management according to a first embodiment of the present invention.

[0055] As illustrated in FIG. 2, the preceding process of the method for providing an active AI-based long-term memory review service through individual optimized review interval management according to the first embodiment of the present invention includes steps (a) to (e).

[0056] And as illustrated in FIG. 3, the subsequent process of the method for providing an active AI-based long-term memory review service through individual optimized review interval management according to the first embodiment of the present invention includes steps (add1) to (add6).

[0057] First, let us explain the preceding process shown in Fig. 2.

[0058] Step (a) is a process in which the data transmission / reception unit (110) of the operation server (100) receives learning content information from a user terminal (10) owned by the user.

[0059] Learning content information is information related to what the user has learned at a specific point in time, and may include information such as learning subject, learning amount, learning unit, and learning date.

[0060] In addition, the subject of learning in the present invention may be a subject such as mathematics or science that requires both understanding and memorization, but it is of course not necessarily limited thereto.

[0061] And step (b) is a process in which the artificial intelligence operation unit (120) of the operation server (100) creates a question card based on learning content information.

[0062] At this time, the question card refers to a virtual data unit that contains questions based on learning content information.

[0063] In the present embodiment, the question card may include a model question card including a question that directly includes learning content information and a duplicate question card including a modified question of the model question card.

[0064] For example, a model question card may include questions highly related to learning content information so that learning content information can be directly reviewed, and a duplicate question card may include questions for performing a similar form of learning by applying the questions included in the model question card.

[0065] And the artificial intelligence operation unit (120) may include an active artificial intelligence model, through which learning content information can be analyzed and model question cards and model question cards related thereto can be generated.

[0066] And, the number of duplicate question cards derived from each model question card can be one or more, but if the number of duplicate question cards is set too high, it can have the adverse effect of increasing user confusion and reducing learning desire, so the number of duplicate question cards can be set appropriately considering the user's characteristics.

[0067] Next, step (c) is a process in which the data transmission / reception unit (110) transmits the model question card generated in step (b) to the user terminal (10), and step (d) is a process in which the data transmission / reception unit (110) receives first learning result information for the model question card from the user terminal (10).

[0068] That is, in step (c), among the question cards generated in step (b), a model question card is sent to the user terminal (10) with priority, and the user learns this and inputs the result into the user terminal (10).

[0069] Accordingly, in step (d), the data transmission / reception unit (110) receives the first learning result information transmitted from the user terminal (10) for the question card provided in step (c), and at this time, the first learning result information may include the user's solution result for the model question card provided in step (b), i.e., information on whether the answer is incorrect or correct.

[0070] Next, step (e) is a process in which the artificial intelligence operation unit (120) assigns and stores the question cards in multiple review boxes, which are multiple virtual capacity sections set in the database (105) of the operation server (100), based on the first learning result information and according to the preset assignment criteria.

[0071] The number of review boxes and the size of storage capacity may be freely set by at least one of the operating server (100) or the user terminal (10), or may be fixed to a recommended setting.

[0072] When the set capacity of the review box is exhausted, a notification message may be sent before transmission to the user terminal (10). The notification message may notify that 'the review time has arrived'.

[0073] FIG. 4 is a drawing showing various boxes, which are virtual capacity sections created in a database (105), as an example in a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to a first embodiment of the present invention.

[0074] As illustrated in FIG. 4, the number of review boxes generated in the database (105) in this embodiment is exemplified as a total of four, including a third review box, a fourth review box, a first review box, and a second review box. Of course, this is presented as an example, and the number of review boxes may be set differently from that in this embodiment.

[0075] In this embodiment, the third review box is a review box in which model question cards with incorrect first learning outcome information are stored.

[0076] Additionally, the second review box is a review box where model question cards with correct answers are stored in the first learning outcome information.

[0077] And the first review box is a review box in which a duplicate question card corresponding to a model question card stored in the third review box is stored, and the second review box is a review box in which a duplicate question card corresponding to a model question card stored in the fourth review box is stored.

[0078] At this time, the reason why the duplicate question card is assigned to the review box with a faster number than the model question card, and also why the incorrect question card is assigned to the review box with a faster number than the correct question card, is to relatively lengthen the interval between reviewing question cards that the user has already learned or answered correctly compared to question cards that the user has not yet learned or answered correctly, so that the user can focus on learning the items that he or she is weak in.

[0079] Meanwhile, as illustrated in FIG. 4, the virtual capacity partition created in the database (105) may include a final inspection box and a review completion box in addition to the review box, but this will be described later.

[0080] FIG. 5 is a diagram showing a detailed process of step (e) in a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to a first embodiment of the present invention.

[0081] As illustrated in FIG. 5, step (e) in the present embodiment may include steps (e-1) to (e-3) in detail.

[0082] Step (e-1) is the process in which the artificial intelligence operation unit (120) analyzes the contents of the first learning result information.

[0083] That is, in this process, the artificial intelligence operation unit (120) can analyze whether the user's solution to the model question card provided in step (b) is an incorrect or correct answer.

[0084] Step (e-2) is the process in which the artificial intelligence operation unit (120) stores the model question card in the third review box or the fourth review box according to the analysis results of step (e-1).

[0085] In this process, the artificial intelligence operation unit (120) stores model question cards for which the user's solution is incorrect in the third review box, and model question cards for which the user's solution is correct in the fourth review box.

[0086] Step (e-3) is the process in which the artificial intelligence operation unit stores the duplicate question card in the first review box or the second review box based on the analysis results of step (e-1).

[0087] In this process, the artificial intelligence operation unit (120) stores a duplicate question card created to correspond to a model question card for which the user's solution is incorrect in the third review box, and also stores the original question card created to correspond to a model question card for which the user's solution is correct in the fourth review box.

[0088] According to the above process, the preceding steps (a) to (e) are completed, and a question card according to the preset assignment criteria is stored in each review box of the database (105).

[0089] And the preceding process, i.e., steps (a) to (e), can be repeatedly performed for the same learning content information or different learning content information, so that question cards can gradually accumulate in each review box according to the preset assignment criteria.

[0090] In the process of repeating the preceding process in this way, if it is determined that the capacity of the question cards stored in any review box has reached a set limit, a subsequent process including steps (add1) to (add6) may be performed.

[0091] Below, the subsequent process will be described with reference to Fig. 3.

[0092] As described above, in the process of repeatedly performing the preceding process, if it is determined that the capacity of the question cards stored in any review box has reached the set limit, the artificial intelligence operation unit (120) selects the question cards assigned to the review box whose capacity has reached the limit according to the preset first priority criterion and provides them to the user terminal (10) in the (add1) step.

[0093] That is, since it takes a certain period of time for the capacity of the review box to reach its limit, after the period has elapsed, the user is provided with a question card selected by the artificial intelligence operation unit (120) according to the first priority criterion and performs a review process.

[0094] FIG. 6 is a diagram showing a detailed process of the (add1) step in a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to the first embodiment of the present invention.

[0095] As illustrated in Fig. 6, the (add1) step may include steps (add1-1) to (add1-3) in detail.

[0096] (add1-1) Step is a process in which the artificial intelligence operation unit (120) assigns a ranking to the question cards assigned to the review box whose capacity has reached the limit, i.e., model question cards or duplicate question cards, according to the preset first priority criterion.

[0097] At this time, the question cards assigned within the same review box may each include information such as the creation date and learning performance date, and in such cases, the earlier the creation date or learning performance date, the higher the priority may be given.

[0098] In addition, when multiple review boxes reach their capacity limit at the same time, the artificial intelligence operation unit (120) can compare the creation date or learning performance date of the question cards included in each review box and give a higher priority to the review box containing the question card with the most recent date.

[0099] If the creation date or learning performance date is the same between the most recent dated question cards belonging to different review boxes, the one with the lower number in the review box may be given priority.

[0100] Step (add1-2) is a process in which the artificial intelligence operation unit (120) selects the item card with the highest priority through step (add1-1), and step (add1-3) is a process in which the data transmission / reception unit (110) transmits the item card selected through step (add1-2) to the user terminal (10).

[0101] That is, after a certain point in time has passed through the (add1) step, the user can receive a random question card to the user terminal (10) and perform learning on it.

[0102] And after the (add1) step, the data transmission / reception unit (110) may receive second learning result information for the question card provided by the (add1) step from the user terminal (10) in the (add2) step, and the artificial intelligence operation unit (120) may perform subsequent processing on the question card provided by the (add1) step according to the first movement criterion set in advance based on the second learning result information in the (add3) step.

[0103] That is, in the (add1) step, the selected question card is transmitted to the user terminal (10), and the user learns it and inputs the result into the user terminal (10).

[0104] Accordingly, in the (add2) step, the data transmission / reception unit (110) receives the second learning result information transmitted from the user terminal (10) for the question card provided in the (add1) step, and at this time, the second learning result information may include the result of the user's solution to the model question card provided in the (add1) step, i.e., information on whether the answer is incorrect or correct.

[0105] FIG. 7 is a diagram showing a detailed process of step (add3) in a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to the first embodiment of the present invention.

[0106] As illustrated in FIG. 7, in this embodiment, step (add3) may include steps (add3-1) to (add3-3) in detail.

[0107] (add3-1) Step is the process in which the artificial intelligence operation unit (120) analyzes the contents of the second learning result information.

[0108] That is, in this process, the artificial intelligence operation unit (120) can analyze whether the user's solution to the question card provided in the (add1) step is an incorrect or correct answer.

[0109] Step (add3-2) is a process in which the artificial intelligence operation unit (120) leaves the relevant question card in the existing review box if the second learning outcome information is incorrect based on the analysis result of step (add3-1), and step (add3-3) is a process in which the artificial intelligence operation unit (120) moves the relevant question card to the final review box, which is a virtual capacity section set in the database, if the second learning outcome information is correct based on the analysis result of step (add3-1).

[0110] That is, if the user's solution to the question card provided in the (add1) step is incorrect, the artificial intelligence operation unit (120) allows the question card to remain in the existing review box so that it can be reviewed again later.

[0111] And if the user's solution is correct, it is judged that the learning level for the question card has increased and it is moved to the final inspection box, which is a virtual capacity section set in the database (105).

[0112] Steps (add1) to (add3) as described above can be repeatedly performed, so that question cards according to the first movement criterion set in advance can be gradually accumulated in the final inspection box.

[0113] In this way, if it is determined that the capacity of the question card stored in the final inspection box has reached the set limit during the process of repeatedly performing steps (add1) to (add3), steps (add4) to (add6) may be additionally performed.

[0114] (add4) Step is a process in which the artificial intelligence operation unit (120) selects the question cards stored in the final inspection box whose capacity has reached the limit according to the preset second priority criterion and provides them to the user terminal (10).

[0115] That is, since it takes a certain period of time for the capacity of the final inspection box to reach the limit, after the period has elapsed, the user is provided with a question card selected by the artificial intelligence operation unit (120) according to the second priority criterion and performs the review process once again.

[0116] At this time, the second priority criterion, like the first priority criterion, can be used to compare the creation date or learning performance date of the question cards stored in the final review box, and give a higher priority to the review box containing the question card with the most recent date.

[0117] Step (add5) is a process in which the data transmission / reception unit (110) receives third learning result information for the question card provided by step (add4) from the user terminal (10), and step (add6) is a process in which the artificial intelligence operation unit (120) performs subsequent processing on the question card provided by step (add4) according to the second movement criterion set in advance based on the third learning result information.

[0118] That is, in the (add4) step, the question card selected in the final inspection box is transmitted to the user terminal (10), and the user learns it and inputs the result into the user terminal (10).

[0119] Accordingly, in step (add5), the data transmission / reception unit (110) receives third learning result information transmitted from the user terminal (10) for the question card provided in step (add4), and at this time, the third learning result information may include the user's solution result for the model question card provided in step (add4), i.e., information on whether the answer is incorrect or correct.

[0120] FIG. 8 is a diagram showing a detailed process of step (add6) in a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to the first embodiment of the present invention.

[0121] As illustrated in FIG. 8, in this embodiment, step (add6) may include steps (add6-1) to (add6-3) in detail.

[0122] (add6-1) Step is the process in which the artificial intelligence operation unit (120) analyzes the contents of the third learning result information.

[0123] That is, in this process, the artificial intelligence operation unit (120) can analyze whether the user's solution to the question card provided in step (add4) is an incorrect or correct answer.

[0124] Step (add6-2) is a process in which the artificial intelligence operation unit (120) leaves the relevant question card in the final inspection box if the third learning outcome information is incorrect based on the analysis results of step (add6-1), and step (add6-3) is a process in which the artificial intelligence operation unit (120) moves the relevant question card to the review completion box, which is a virtual capacity section set in the database (105), if the third learning outcome information is correct based on the analysis results of step (add6-1).

[0125] That is, if the user's solution to the question card provided in step (add4) is incorrect, the artificial intelligence operation unit (120) allows the question card to remain in the final inspection box so that it can be reviewed again later.

[0126] And if the user's solution is correct, it is determined that learning for the question card is complete and the question is transferred to the review completion box, which is a virtual capacity section set in the database (105).

[0127] In this way, the question cards transferred to the review completion box can be considered as having been completely learned by the user and stored in long-term memory, and thus can be excluded from future review.

[0128] As described above, the present invention can precisely analyze the individual learning characteristics of a learner and set an optimized review interval reflecting the individual learning characteristics of the learner thus analyzed, thereby maximizing the learning effect by inducing long-term memory.

[0129] In particular, the present invention can prevent learners from randomly guessing or memorizing the correct answer by providing an interval between the solving activities of the question cards, and can promote reliable memory and skill improvement by providing additional learning opportunities by separating important knowledge points into model question cards and duplicate question cards.

[0130] Hereinafter, other embodiments of the present invention will be described. In each embodiment described below, redundant descriptions of components provided in the same manner as in the first embodiment described above will be omitted.

[0131] FIG. 9 is a drawing showing various boxes, which are virtual capacity sections created in a database (105), as an example in a method for providing an active AI-based long-term memory review service through individual optimized review interval management according to a second embodiment of the present invention.

[0132] As shown in Fig. 9, the second embodiment of the present invention is performed in the same overall process as the first embodiment described above.

[0133] However, this embodiment has a feature in that multiple duplicate question cards with different difficulty levels are assigned to the first review box and the second review box in correspondence with one model question card stored in the third review box and the fourth review box among the review boxes, which are virtual capacity sections created in the database (105).

[0134] That is, in this embodiment, the artificial intelligence operation unit (120) can create a card set including multiple duplicate question information with different difficulty levels for one model question card and assign them to the first review box and the second review box so that one of them can be appropriately selected depending on the user's learning situation.

[0135] For example, the artificial intelligence operation unit (120) may select one of a plurality of card sets in the (add1) step, and may preferentially transmit the duplicate item information with the lowest difficulty level among the plurality of duplicate item information with different difficulty levels included in the card set to the user terminal (10).

[0136] If the solution result of the duplicate question information is determined to be incorrect in the subsequent (add2) and (add3) steps, the difficulty level can be maintained by re-sending the duplicate question information with the lowest difficulty level within the card set in the next learning process.

[0137] However, if the solution result of the duplicate question information is judged to be correct through steps (add2) and (add3), the difficulty level can be increased by selecting and transmitting duplicate question information with a level of difficulty higher within the card set in the next learning process.

[0138] Afterwards, if the user answers all the duplicate question information contained within the card set correctly, the card set can be transferred to the final inspection box.

[0139] FIG. 10 is a drawing illustrating various boxes, which are virtual capacity sections created in a database, in a method for providing an active AI-based long-term memory review service through personalized optimized review interval management according to a third embodiment of the present invention.

[0140] As illustrated in Fig. 10, the third embodiment of the present invention is also performed in the same overall process as the first and second embodiments described above.

[0141] However, this embodiment has a feature in that the review box, which is a virtual capacity partition created in the database (105), is arranged in a layer structure so that the review process can be repeated more times.

[0142] For example, in the example shown in Fig. 10, in addition to the first to fourth review boxes, the fifth to eighth review boxes are further created in the database (105).

[0143] At this time, the 5th review box is placed as the next review box of the 1st review box, the 6th review box is placed as the 2nd review box, the 7th review box is placed as the 3rd review box, and the 8th review box is placed as the next review box of the 4th review box.

[0144] Therefore, in the present embodiment, the question cards for which the user has answered correctly in the first to fourth review boxes are transferred to the fifth to eighth review boxes, which are the next review boxes, before being transferred to the final check box, and thus the user can perform repeated learning for each question card.

[0145] A number of layers (n is a natural number) of such a tea review box can be arranged, and the user can perform repeated learning a number of times equal to the number of layers.

[0146] As described above, preferred embodiments of the present invention have been described. It will be apparent to those skilled in the art that the present invention can be embodied in other specific forms, in addition to the embodiments described above, without departing from the spirit or scope thereof. Therefore, the above-described embodiments should be considered illustrative rather than restrictive, and accordingly, the present invention is not limited to the above description, but may be modified within the scope of the appended claims and their equivalents.

Claims

1. (a) Step in which the data transmission / reception unit of the operation server receives learning content information from a user terminal owned by the user; (b) step in which the artificial intelligence operation unit of the above-mentioned operation server generates a question card including a model question card including questions that directly include the learning content information and a duplicate question card including modified questions of the model question card; (c) step in which the data transmission / reception unit transmits the model question card generated in the (b) step to the user terminal; (d) step in which the data transmission / reception unit receives first learning result information for the model question card from the user terminal; (e) step in which the artificial intelligence operation unit assigns and stores the question cards in multiple review boxes, which are multiple virtual capacity sections set in the database of the operation server, based on the first learning result information and according to the preset assignment criteria; Including, The above steps (a) to (e) are performed repeatedly, but if it is determined that the capacity of any review box has reached the limit during the repeated performance, The step (add1) is performed in which the AI ​​operation unit selects the question cards assigned to the review box whose capacity has reached its limit according to the preset first priority criterion and provides them to the user terminal. Method for providing an active AI-based long-term memory review service through individualized optimized review interval management.

2. In paragraph 1, The above review box is, The third review box where the model question cards with incorrect answers are stored, including the first learning outcome information; The fourth review box where the model question card with the correct answer is stored, which is the first learning outcome information above; A first review box in which a duplicate question card corresponding to the model question card stored in the third review box is stored; and A second review box in which a duplicate question card corresponding to the model question card stored in the fourth review box is stored; Including, Method for providing an active AI-based long-term memory review service through individualized optimized review interval management.

3. In paragraph 2, The above step (e) is, Step (e-1) in which the above artificial intelligence operation unit analyzes the contents of the first learning result information; Step (e-2) in which the artificial intelligence operation unit stores the model question card in the third review box or the fourth review box according to the analysis result of step (e-1); and Step (e-3) in which the artificial intelligence operation unit stores the duplicate question card in the first review box or the second review box according to the analysis result of step (e-1); Including, Method for providing an active AI-based long-term memory review service through individualized optimized review interval management.

4. In paragraph 1, The above (add1) step is, Step (add1-1) in which the artificial intelligence operation unit assigns a ranking to the question cards assigned to the review box whose capacity has reached its limit according to the preset first priority criterion; The step (add1-2) in which the artificial intelligence operation unit selects the question card with the highest priority through the step (add1-1); and Step (add1-3) in which the data transmission / reception unit transmits the item card selected by step (add1-2) to the user terminal; Including, Method for providing an active AI-based long-term memory review service through individualized optimized review interval management.

5. In paragraph 1, After the above (add1) step, (add2) step in which the data transmission / reception unit receives second learning result information for the question card provided by the (add1) step from the user terminal; and A step (add3) in which the artificial intelligence operation unit performs follow-up processing on the question card provided by the step (add1) according to the first movement criterion set in advance based on the second learning result information; is performed more, Method for providing an active AI-based long-term memory review service through individualized optimized review interval management.

6. In paragraph 5, The above (add3) step is, Step (add3-1) in which the above artificial intelligence operation unit analyzes the contents of the second learning result information; The above artificial intelligence operation unit, based on the analysis results of the above (add3-1) step, processes the corresponding question card in the existing review box (add3-2) if the second learning result information is incorrect; and Step (add3-3) in which the artificial intelligence operation unit transfers the corresponding question card to the final inspection box, which is a virtual capacity section set in the database, if the second learning result information is correct based on the analysis result of step (add3-1); Including, Method for providing an active AI-based long-term memory review service through individualized optimized review interval management.

7. In paragraph 6, The above steps (add1) to (add3) are performed repeatedly, but if it is determined that the capacity of the final inspection box has reached the limit during the repeated performance, The step (add4) is performed in which the AI ​​operation unit selects the question cards stored in the final inspection box, whose capacity has reached its limit, according to the preset second priority criteria and provides them to the user terminal. Method for providing an active AI-based long-term memory review service through individualized optimized review interval management.

8. In paragraph 7, After the above (add4) step, (add5) step in which the data transmission / reception unit receives third learning result information for the question card provided by the (add4) step from the user terminal; and A step (add6) in which the artificial intelligence operation unit performs follow-up processing on the question card provided by the step (add4) based on the second movement criterion set in advance based on the third learning result information; is performed more, Method for providing an active AI-based long-term memory review service through individualized optimized review interval management.

9. In paragraph 8, The above (add6) step is, Step (add6-1) where the above artificial intelligence operation unit analyzes the contents of the third learning result information; The artificial intelligence operation unit, based on the analysis results of the step (add6-1), processes the question card in question in the final inspection box (add6-2) if the third learning result information is incorrect; and Step (add6-3) in which the artificial intelligence operation unit transfers the relevant question card to the review completion box, which is a virtual capacity section set in the database, if the third learning result information is correct based on the analysis result of step (add6-1); Including, Method for providing an active AI-based long-term memory review service through individualized optimized review interval management.

Images