Learning feature analysis and learning environment adjustment method using artificial intelligence, and server for providing service therefor

Abstract

The invention discloses a learning feature analysis and learning environment adjustment method using artificial intelligence and a server for providing service for the method. According to the invention, the learning content stored in the first storage area in the plurality of storage areas is sent to the terminal of the learner, and the response information of the learner to the learning content is received from the terminal of the learner; and determines whether to execute a process of moving and storing the learning content from the first storage area to the second storage area based on the response information of the learner, and analyzing the learning characteristics of the learner based on the response information of the learner. According to the invention, not only can the individual learning features of the learner such as learning ability and learning achievement level in the repeated learning process be accurately analyzed through artificial intelligence, but also the individual learning features of the learner analyzed through artificial intelligence can be reflected, so that the learning environment of the learner can be actively set.

Description

Technical Field

[0001] The present invention relates to a method for analyzing learning characteristics and adjusting learning environment using artificial intelligence and a server for providing services therefor. More specifically, the present invention relates to a method for analyzing learning characteristics and adjusting learning environment using artificial intelligence, which can not only accurately analyze individual learning characteristics of learners such as learning ability and level of learning outcomes in a repeated learning process through artificial intelligence, but also reflect the individual learning characteristics of learners analyzed through artificial intelligence, so that the learner's learning environment can be actively set. The method and a server for providing services therefor. Background Art

[0002] The Ebbinghaus Forgetting Curve is empirical data that proves how important it is to review what you have learned. It is well known that periodic repetition of learning is more effective than any other method for long-term memory of what you have learned.

[0003] However, due to various problems such as learners' lack of willingness to learn and insufficient execution, it is difficult to successfully carry out cyclical repetition of learning content.

[0004] Not only that, in order to successfully memorize the learning content for a long time, the amount of repeated learning content and the repeated learning cycle must be differentiated according to the learners' personal abilities, but the reality is that it is difficult for learners to decide by themselves the amount of repeated learning and the repeated learning cycle that are suitable for them.

[0005] On the other hand, in order to solve such problems, Korean Patent No. 10-2405520 proposes a method of supporting long-term memory of learning content.

[0006] However, even in this case, learners cannot directly participate in the setting of the learning environment such as repeated learning cycles and repeated learning volume, and it is impossible to analyze the learners' individual learning characteristics such as learning ability and level of learning outcomes during the repeated learning process. Technical limitations such as the inability to actively set up the learning environment to reflect the learners' individual learning characteristics are still pointed out. Summary of the invention

[0007] Technical issues

[0008] Therefore, the purpose of the present invention is to provide a method for learning feature analysis and learning environment adjustment using artificial intelligence and a server for providing services therefor, so that not only can the individual learning characteristics of learners such as learning ability and learning achievement level in the repeated learning process be accurately analyzed through artificial intelligence, but also the individual learning characteristics of learners analyzed through artificial intelligence can be reflected, so that the learner's learning environment can be actively set.

[0009] Problems to be solved by the present invention are not limited to the mentioned problems, and include technical problems that can be clearly understood by those skilled in the art from the following description.

[0010] Means of solving the problem

[0011] In order to achieve the above-mentioned purpose, the learning feature analysis and learning environment adjustment method using artificial intelligence according to the present invention includes: (a) a step in which a server providing services receives detailed adjustment quota times for the learning environment for each learning object category from an administrator terminal; (b) a step in which the server providing services receives the learner's response information to the learning content from the learner's terminal; (c) a step in which the server providing services determines whether to move the learning content from a first storage area and store it in a second storage area based on the learner's response information; and (d) a step in which the server providing services analyzes the learner's learning features based on the learner's response information.

[0012] Preferably, the method further comprises the step of (e) the server providing the service adjusting at least one of the learner's repeated learning cycle and the amount of repeated learning at one time based on the learning characteristic analysis result of the learner.

[0013] In addition, the server providing services according to the present invention includes: a sending unit, which sends the learning content stored in the first storage area of ​​multiple storage areas to the learner's terminal; a receiving unit, which receives the learner's response information to the learning content from the learner's terminal; and a computing unit, which analyzes the learner's learning characteristics based on the learner's response information.

[0014] Preferably, the calculation unit is configured to adjust at least one of a repetitive learning cycle and a repetitive learning amount of the learner based on a learning characteristic analysis result of the learner.

[0015] Effects of the Invention

[0016] According to the present invention, not only can individual learning characteristics of learners such as learning ability and level of learning outcomes in the process of repeated learning be accurately analyzed through artificial intelligence, but also individual learning characteristics of learners analyzed through artificial intelligence can be reflected, so that the learning environment of learners can be actively set.

[0017] The effects involved in the present invention are not limited to the mentioned effects, and include other effects that can be clearly understood by those skilled in the art from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a structural diagram of a learning feature analysis and learning environment adjustment system using artificial intelligence according to an embodiment of the present invention,

[0019] Figure 2 is a functional block diagram showing the structure of a server providing services for executing a learning feature analysis and learning environment adjustment method using artificial intelligence according to an embodiment of the present invention,

[0020] Figure 3 is a signal flow chart illustrating the execution process of a method for analyzing learning characteristics and adjusting learning environment using artificial intelligence according to an embodiment of the present invention, and

[0021] Figure 4 It is a flowchart of the detailed process of the method for learning feature analysis and learning environment adjustment using artificial intelligence according to one embodiment of the present invention. DETAILED DESCRIPTION

[0022] Hereinafter, the present invention will be described in more detail with reference to the accompanying drawings. It should be noted that the same components are represented by the same symbols everywhere in the accompanying drawings. In addition, the detailed description of the known functions and structures that may unnecessarily obscure the gist of the present invention is omitted.

[0023] Figure 1 1 is a diagram showing a system for analyzing learning characteristics and adjusting learning environment using artificial intelligence according to an embodiment of the present invention. Figure 1 According to an embodiment of the present invention, a learning feature analysis and learning environment adjustment system using artificial intelligence may include a learner terminal 100 and a server 200 providing services, and may further include an administrator terminal 300.

[0024] The learner terminal 100 is a wireless communication terminal such as a personal computer or smart phone held by a learner who uses the learning feature analysis and learning environment adjustment services using artificial intelligence according to the present invention. Such a learner terminal 100 can be installed with certain learner applications required for using the learning feature analysis and learning environment adjustment services using artificial intelligence according to the present invention.

[0025] The server 200 providing services is a server installed and operated by an operator who provides learning feature analysis and learning environment adjustment services using artificial intelligence according to the present invention. Such a server 200 providing services sends the learning content stored in the first storage area of ​​multiple storage areas to the learner terminal 100 in sequence, receives the learner's response information to the learning content from the learner terminal 100, and decides whether to move the learning content from the first storage area and store it in the second storage area based on the learner's response information, and analyzes the learner's learning features based on the learner's response information, and based on the analysis results of the learner's learning features, adjusts the learner's repeated learning cycle and at least one of the repeated learning amount.

[0026] The administrator terminal 300 is a wireless communication terminal such as a personal computer or smart phone held by an administrator such as a teacher or lecturer who manages the learners' learning. Such an administrator terminal 300 can be installed with certain administrator applications required for using the learning feature analysis and learning environment adjustment services using artificial intelligence according to the present invention.

[0027] In addition, the server 200 providing services is configured to communicate with the learner terminal 100 and the administrator terminal 300 through a communication network. The communication network provides a connection path so that the server 200 providing services, the learner terminal 100 and the administrator terminal 300 can transmit and receive packet data after being connected to each other.

[0028] The communication network may include wired networks such as LANs (Local Area Networks), WANs (Wide Area Networks), MANs (Metropolitan Area Networks) and ISDNs (Integrated Service Digital Networks), or wireless networks such as wireless LANs, CDMA, Bluetooth and satellite communications, but the scope of the present invention is not limited thereto.

[0029] In addition, the server 200 providing the service may provide an application program (App) or a network environment for implementing the service according to the present invention.

[0030] The service provided by the server 200 providing the service may be provided by an application installed on the learner terminal 100 , and the application may refer to an application such as an App running on a mobile terminal (smartphone).

[0031] Figure 2 1 is a functional block diagram showing the structure of a server that provides services for performing a learning feature analysis and learning environment adjustment method using artificial intelligence according to an embodiment of the present invention. Figure 2 According to an embodiment of the present invention, a server 200 provided by a method for performing learning feature analysis and learning environment adjustment using artificial intelligence includes a receiving unit 210, a storage unit 230, a computing unit 250 and a sending unit 270.

[0032] The receiving unit 210 of the server 200 providing the service receives the learning object category selection information and the response information for the learning content from the learner terminal 100 , and may receive the learning content of each category from the administrator terminal 300 .

[0033] The computing unit 250 of the server 200 providing the service decides whether to move the learning content from the first storage area and store it in the second storage area based on the learner's response information to the learning content, analyzes the learner's learning characteristics based on the learner's response information, and adjusts at least one of the learner's repeated learning cycle and the amount of repeated learning at one time based on the analysis result of the learner's learning characteristics.

[0034] The common storage space of the storage unit 230 of the server 200 providing the service stores the learning content for each learning object category, and the separate storage space allocated to each learner account is provided with a plurality of storage areas. The sending unit 270 of the server 200 providing the service sends the learning content stored in the plurality of storage areas in the learner's individual storage space to the learner terminal 100 in sequence.

[0035] Figure 3 1 is a signal flow chart illustrating the execution process of the method for analyzing learning characteristics and adjusting learning environment using artificial intelligence according to an embodiment of the present invention. Figures 1 to 3 , describes in detail the execution process of the method of using artificial intelligence to analyze learning characteristics and adjust the learning environment according to one embodiment of the present invention.

[0036] The storage unit 230 of the service-providing server 200 stores learning content for each learning object category. When implementing the present invention, the service-providing server 200 may also receive and store such learning content for each category from the administrator terminal 300 ( S405 ).

[0037] In addition, when implementing the present invention, the learning content stored in the storage unit 230 can be constituted in the form of memo-type learning cards according to the learning progress, and can also be constituted in the form of question-type learning cards that record questions related to the learning object content.

[0038] In addition, when the learning content is constituted in the form of a problem-based learning card, the correct answer information corresponding to the problem recorded in the problem-based learning card is stored in association in the storage unit 230 of the server 200 providing the service.

[0039] In addition, as the learner selects a learning category (eg, intermediate English) through an application installed on the learner terminal 100 , the server 200 providing a service may receive category selection information from the learner terminal 100 .

[0040] In addition, the learner terminal 100 may also transmit the learning goal setting information including the target learning time and the target learning amount input by the learner together with the category selection information to the server 200 providing the service ( S410 ).

[0041] In this regard, the server 200 providing the service may set the number of multiple storage areas in the separate storage space allocated to the learner account, the storage capacity of each storage area, and the repeated learning cycle based on the category selection information and target learning time information received from the learner terminal 100 (S415).

[0042] To this end, the storage unit 230 of the server 200 providing the service may store setting information for the number (N) of storage areas (i.e., the number of repeated learning times), each storage capacity (e.g., the storage limit of a learning card), and a repeated learning cycle (T) according to the learning object category and the target learning time (P) as shown in Table 1 below.

[0043] [Table 1]

[0044] category P N Learning card storage quota for each storage area T English for beginners 1 month 3 1(100),2(100),3(infinite) 1 week English for beginners 2 months 4 1(100),2(100),3(200),4(unlimited) 2 weeks Intermediate English 1 month 5 1(100),2(100),3(200),4(400),5(unlimited) 1 week Intermediate English 2 months 5 1(100),2(100),3(200),4(400),5(unlimited) 2 weeks Advanced English 1 month 6 1(100),2(100),3(200),4(400),5(400),6(unlimited) 1 week High School English 2 months 7 1(100),2(100),3(200),4(400),5(400),6(800),7(unlimited) 2 weeks

[0045] In addition, when implementing the present invention, the server 200 providing services can set the number of multiple storage areas in the separate storage space allocated to the learner account, the storage capacity of each storage area, and the repeated learning cycle (S415) based on the category selection information and target learning amount information (for example, 100 English words) received from the learner terminal 100.

[0046] To this end, the storage unit 230 of the server 200 providing the service may store setting information for the number (N) of storage areas according to the learning object category and the target learning amount (S), each storage capacity (e.g., the storage limit of a learning card), and a repeated learning cycle (T) as shown in Table 2 below.

[0047] [Table 2]

[0048]

[0049]

[0050] As such, according to the present invention, the learner can directly participate in setting the learning environment such as the repeated learning cycle and the repeated learning amount by inputting the target learning time and the target learning amount through the learner terminal 100 .

[0051] In addition, the learning cards corresponding to the category selected by the learner (or the learning cards corresponding to the learning amount selected by the learner among all the learning cards corresponding to the category selected by the learner) stored in the public storage space of the storage unit 230 of the server 200 providing the service are stored according to the storage quota of the first storage area among the multiple storage areas set in the learner's individual storage space, so that learning content can be created for the learner (S420).

[0052] In addition, in the above step S410, because the learner selects the learning object category together, when the learning start time (for example, 5 pm) received and stored by the server 200 providing services from the learner terminal 100 arrives, the server 200 providing services will send the learning cards stored in the first storage area to the learner terminal 100 in sequence (S425).

[0053] In this regard, the learner who confirms the content of the learning card through the learner terminal 100 inputs the response information about the content of the learning card into the application installed on the learner terminal 100, and the server 200 providing the service receives the learner's response information from the learner terminal 100 in turn (S430).

[0054] Specifically, when the learning card is a memo-style learning card, when the learner judges that he has fully mastered the content of the learning card within a certain time limit (for example, 1 minute), he selects the "Complete Mastery" button; if it is judged that he has not fully mastered it within the limited time, he can select the "Incomplete Mastery" button to input the response information into the learner terminal 100.

[0055] In addition, if the learning card is a question-based learning card, the learner can input the response information into the learner terminal 100 by inputting the answer to the question of the learning card.

[0056] In addition, the calculation unit 250 of the server 200 providing the service decides whether to perform movement and storage of the learning card from the first storage area to the second storage area based on the learner's response information to the learning card transmitted to the learner terminal 100 (S435).

[0057] Specifically, when the learning card is a memo-style learning card, the computing unit 250 of the server 200 providing the service moves the learning card from the first storage area and stores it in the second storage area (i.e., deletes it from the first storage area and stores it in the second storage area) when the response information is "mastered". When the response information is "mastered not completed" or no response information is received from the learner terminal 100 within a certain time limit, the learning card may not be moved and stored and the storage status may be maintained in the first storage area previously stored.

[0058] In addition, when the learning card is a question-based learning card, the computing unit 250 of the service-providing server 200 compares the response information received from the learner terminal 100 with the correct answer information stored in association with the learning card. If the two are consistent, the learning card is moved from the first storage area and stored in the second storage area (i.e., the first storage area is deleted and the second storage area is stored). If the two are inconsistent, the learning card is not moved and stored and the storage state can be maintained in the first storage area previously stored.

[0059] In this way, the first round of learning is completed as the plurality of learning cards stored in the first storage area sequentially send and receive the response information for each learning card.

[0060] Thus, when implementing the present invention, preferably, the server 200 providing services sequentially sends the learning cards stored in the storage area for executing sequential sending of learning cards and receives the response information for each learning card, and then ends the corresponding round of learning.

[0061] In addition, when implementing the present invention, the server 200 providing services may also send information including learning cards sent to learners during the execution of the first round of learning, response information for each learning card, and learner information of the total execution ratio moved and stored according to each response information to the administrator terminal 300 (S440) responsible for the learner's learning.

[0062] After completing the first round of learning, the server 200 providing services selects the learner together with the learning goal in the above-mentioned step S410. When the repeated learning cycle (for example, 2 days) received and stored by the server 200 providing services from the learner terminal 100 arrives, the learning cards corresponding to the category selected by the learner in the public storage space of the storage unit 230 are added to the first storage area according to the remaining storage amount of the first storage area, thereby generating the second round of learning content, and then repeating the above-mentioned steps S425 to S440.

[0063] In addition, the server 200 providing the service calculates the remaining storage capacity in the second storage area (S445) together with performing the mobile storage from the first storage area to the second storage area, and can send a guidance message about the remaining storage capacity information calculated in this manner (for example, the second storage area can currently store an additional 5 learning cards, and when the storage capacity of the second storage area is exhausted, the learning in the first storage area stops and the transfer of the learning cards stored in the second storage area begins) to the learner terminal 100.

[0064] In addition, after confirming such guidance information, the learner may also input a modification setting request regarding the number of storage areas and storage capacity set in the above step S415 through the learner terminal 100 (S450).

[0065] For example, if the learner wants to temporarily stop repeated learning in the second storage area and continue learning in the first storage area, he can input a modification setting request about the storage capacity in the second storage area (for example, 100→200). If the learner does not want to perform unnecessary repeated learning due to too many storage areas, he can input a modification setting request about the number of storage areas (for example, 7→5).

[0066] In addition, when implementing the present invention, the server 200 providing the service may also send a setting information modification approval request including the setting modification request received from the learner terminal 100 in the above-mentioned step S445 to the administrator terminal 300 (S455).

[0067] In this regard, the administrator can also decide whether to approve the modification of the setting information based on the learning information of the learner received from the server 200 providing the service in the above-mentioned step S440, and input the decision result (yes (Y) / no (N)) to the administrator terminal 300. The server 200 providing the service can perform the modification of the setting based on the reply information (Y / N) received from the administrator terminal 300 regarding whether to approve the modification of the setting information, thereby granting the administrator the approval authority for the modification of the setting (S460).

[0068] In addition, based on the learner's learning information received from the service server 200 in the above step S440, the administrator can also send the customized learning content for the learner to the service server 200 through the administrator terminal 300 (S465). In response, the service server 200 will give priority to the customized learning content received from the administrator terminal 300 over the learning content already stored in the service server 200 and add it to the learner's first learning area according to the remaining storage amount of the first storage area. After generating customized learning content for the learner, the above steps S425 to S440 can be repeated.

[0069] In addition, the computing unit 250 of the server 200 providing the service calculates the remaining storage capacity in the second storage area and determines whether the remaining storage capacity in the second storage area is completely exhausted (S470). When the remaining storage capacity in the second storage area is completely exhausted, the sending of the learning cards stored in the first storage area is stopped, and the learning cards stored in the second storage area are sent to the learner terminal 100 in sequence, thereby starting repeated learning in the second storage area (S475).

[0070] Specifically, preferably, the server 200 providing the service executes the above-mentioned step S445 to send the multiple learning cards accumulated and stored in the second storage area to the learner terminal 100 in the storage order, so as to perform repeated learning on the learning cards learned first (S480).

[0071] As the learner inputs the response information for the learning card stored in the second storage area into the learner terminal 100, based on the response information received from the learner terminal 100, the computing unit 250 of the server 200 providing the service performs the movement and storage from the second storage area to the third storage area and repeats the related processes in the same manner as the above-mentioned steps S435 to S450 (S485).

[0072] Specifically, when the server 200 providing the service determines that the remaining storage capacity in the third storage area is completely exhausted, it can stop sending the learning cards stored in the second storage area, and send the learning cards stored in the third storage area to the learner terminal 100 in sequence, thereby starting repeated learning in the third storage area.

[0073] When the present invention is implemented in this way, when the remaining storage capacity in the Nth storage area is exhausted, the server 200 providing services stops sending the learning cards stored in the N-1th storage area, and sends the learning cards stored in the Nth storage area to the learner terminal 100 in sequence, so that repeated learning in the Nth storage area is started first, thereby maximizing the learning content processed as growth-term memory through repeated learning.

[0074] In addition, when implementing the present invention, when the server 200 providing the service starts the next round of learning after completing a specific round of learning, until all the learning content related to the category stored in the storage unit 230 is used up, it is preferred that the learning content is additionally stored in the first storage area according to the remaining storage capacity of the first storage area, and then the learning cards stored in the first storage area are sent in sequence to start the next round of learning. When all the learning content related to the category stored in the storage unit 230 is used up, it is preferred that the learning card is extracted from a plurality of storage areas and then the learning cards stored in the storage area with the earliest arrangement order are sent in sequence in the extracted storage area to start the next round of learning.

[0075] As described above, by repeatedly moving and storing in sequence in multiple storage areas, the learning is repeated until all learning cards related to the corresponding category provided by the server 200 providing the service are stored in the last storage area, thereby supporting long-term memory of the learning content.

[0076] In addition, when implementing the present invention, the server 200 providing services resets the number of storage areas, storage capacity and repeated learning cycles set in the above step S415 based on the various learning information of the learners as described above, so that the learner's learning environment (S490) can be adjusted in detail.

[0077] Figure 4 1 is a flowchart of the detailed process of the method for analyzing learning features using artificial intelligence according to an embodiment of the present invention. Figure 4 The detailed process of the learning feature analysis method using artificial intelligence according to one embodiment of the present invention is described.

[0078] First, the computing unit 250 of the server 200 providing the service can measure and analyze the time required from the time when the learning content stored in the first storage area is first sent to the learner terminal 100 until the multiple learning cards stored in the first storage area are sent in sequence and all response information for each learning card is received (i.e., the time required for the first round of learning in the first storage area) (S491).

[0079] Specifically, when the time required for a first round of learning exceeds a predetermined reference time (for example, 30 minutes), the computing unit 250 of the server 200 providing the service resets the storage capacity from the second storage area to its subsequent storage areas (except the last storage area), but resets the storage capacity of each storage area to be inversely proportional to the amount of time required for one round of learning that exceeds the reference time, so that if the learner's learning speed is slow, the amount of repeated learning according to the round can be reduced.

[0080] In addition, when the time required for the first round of learning is less than a predetermined standard required time (for example, 30 minutes), the computing unit 250 of the server 200 providing the service resets the storage capacity from the second storage area to its subsequent storage areas (except the last storage area), but resets the storage capacity of each storage area to be proportional to the portion (absolute value) of the time required for one round of learning that is not reached compared to the standard required time, so that if the learner's learning speed is faster, the amount of repeated learning in each round can be increased.

[0081] In addition, when implementing the present invention, the standard required time required for each round of learning may also be included in the learning goal setting information received from the learner terminal 100 in the above step S410.

[0082] In addition, if the time required for one round of learning exceeds the predetermined standard time (for example, 30 minutes), the computing unit 250 of the server 200 providing the service resets the learner's repeated learning cycle, but resets the repeated learning cycle to be inversely proportional to the portion of the time required for one round of learning that exceeds the standard time, thereby reducing the repeated learning cycle if the learner's learning speed is slow (i.e., the learner's memory is not clear during repeated learning).

[0083] In addition, if the time required for one round of learning is less than the predetermined reference time (for example, 30 minutes), the computing unit 250 of the server 200 providing the service resets the learner's repeated learning cycle, but resets the repeated learning cycle to be proportional to the portion (absolute value) of the time required for one round of learning that is less than the reference time, so that if the learner's learning speed is faster (that is, the learner's memory is vivid in repeated learning), the repeated learning cycle can be increased.

[0084] Thus, according to the present invention, by analyzing the individual learning characteristics of each learner, the most optimized review interval can be provided for each individual.

[0085] In addition, the computing unit 250 of the server 200 providing the service can measure and analyze the time taken from the time when the learning content stored in the first storage area is first sent to the learner terminal 100 to the time when the remaining storage capacity of the second storage area is determined to be 0 in the above-mentioned step S470 (i.e., the time required from starting learning in the first storage area to satisfying the requirements for starting learning in the second storage area, 'storage area moving time') (S493).

[0086] Specifically, when the storage area moving time exceeds a predetermined reference required time (for example, 2 weeks), the computing unit 250 of the server 200 providing the service resets the storage capacity from the third storage area to its subsequent storage areas (except the last storage area), but resets the storage capacity of each storage area to be inversely proportional to the excess of the storage area moving time relative to the reference required time, thereby reducing the amount of repeated learning if the learner's repeated learning speed is slow.

[0087] In addition, when the storage area moving time is less than the predetermined reference required time (for example, 2 weeks), the calculation unit 250 of the server 200 providing the service resets the storage capacity from the third storage area to its subsequent storage areas (except the last storage area), but resets the storage capacity of each storage area to be proportional to the share (absolute value) of the storage area moving time that has not been reached relative to the required reference required time, so that if the learner's repeated learning speed is faster, the amount of repeated learning can be increased.

[0088] When implementing the present invention, the reference required time may also be included in the learning goal setting information received from the learner terminal 100 in the above step S410.

[0089] In addition, when the storage area moving time exceeds the predetermined reference required time (for example, 2 weeks), the calculation unit 250 of the server 200 providing the service resets the learner's repeated learning cycle, but resets the repeated learning cycle to be inversely proportional to the excess of the reference required time of the storage area moving time, so that if the learner's repeated learning speed is slow (for example, the same problem repeatedly makes mistakes), the repeated learning cycle can be reduced.

[0090] In addition, when the storage area moving time is less than the predetermined reference required time (for example, 2 weeks), the calculation unit 250 of the server 200 providing the service resets the learner's repeated learning cycle, but resets the repeated learning cycle to be proportional to the part (absolute value) of the storage area moving time that is not reached compared with the reference required time, so that if the learner's repeated learning speed is faster, the repeated learning cycle can be increased.

[0091] In addition, when determining whether to move and store in the above-mentioned step S435, the server 200 providing the service calculates the "cumulative number of wrong answers" by calculating the number of times the learner's response information for the same learning card is "incomplete mastery" or the response information is inconsistent with the correct answer. This can be analyzed to adjust the learner's learning environment in detail (S495).

[0092] Specifically, the computing unit 250 of the server 200 providing the service resets the storage capacity of each storage area to be inversely proportional to the cumulative number of incorrect answers, so that if the more repeated incorrect answers to the same question, the less the amount of repeated learning in the round, because the repeated learning cycle is reset to be inversely proportional to the cumulative number of incorrect answers, the more repeated incorrect answers to the same question, the shorter the repeated learning cycle can be.

[0093] In addition, the computing unit 250 of the server 200 providing the service measures, for each learning card, the time required for a response from the time when the learning content (specific learning card) is sent in the above-mentioned steps S425 and S480 to the time when the response information (response to the learning card) is received in the above-mentioned steps S430 and S485, and calculates the average of these times to analyze the learner's response speed and adjust the learning environment in detail based on this (S497).

[0094] Specifically, the computing unit 250 of the server 200 providing the service resets the storage capacity of each storage area to be inversely proportional to the average value of the time required for the response, thereby reducing the amount of repeated learning in each round for learners who take longer to respond. By resetting the repeated learning cycle to be inversely proportional to the average value of the time required for the response, the repeated learning cycle can be shortened for learners who take longer to respond.

[0095] In addition, when implementing the present invention, the calculation unit 250 of the server 200 providing the service resets the respective reference required times in the above-mentioned steps S491 and S493 to be proportional to the average value of the accumulated number of incorrect answers in the above-mentioned step S495 and the required response time in the above-mentioned step S497, thereby increasing the reference required time (S499) for learners who give the same question multiple times with repeated incorrect answers and learners who take a long time to respond.

[0096] In addition, when implementing the present invention, the server 200 providing services can repeatedly perform the detailed adjustment process of the learning environment as described above when each round of learning is completed or when the requirements for starting learning in each storage area are met, and the number of detailed adjustments to the learning environment as described above can be limited according to the category of the learning object.

[0097] Specifically, the server 200 providing the service receives and stores the detailed adjustment quota times of the learning content of each learning object category and the learning environment in the category from the administrator terminal 300 in the above step S405, based on which the adjustment times (for example, 5 times) for each learning object category can be limited.

[0098] In addition, for this purpose, the storage unit 230 of the server 200 providing the service may store information on the number of adjustments allowed for each learning object category as shown in Table 3 below.

[0099] [Table 3]

[0100] category Number of adjustments allowed Elementary English A 4 Elementary English B 5 Intermediate English A 6 Intermediate English B 7 Advanced English A 8 Advanced English B 9

[0101] As described above, in the present invention, the number of times the learning environment is allowed to be adjusted in detail is set differently according to the characteristics of the learning object category, so that each learning environment is adjusted in detail by reflecting the characteristics of the learning object category.

[0102] In addition, when implementing the present invention, as in the above steps S491 to S499, the computing unit 250 of the server 200 providing the service applies the detailed adjustment results of the learning environment for a specific learning object category (e.g., Intermediate English A) to the learning environment of other learning object categories (e.g., Intermediate English B) of the learner, thereby preliminarily setting the number of storage areas, storage capacity, and repeated learning cycles for other learning object categories in the above step S415, such as Figure 4 As shown, the analysis results of a learner's learning characteristics can be preliminarily applied to other types of learning for the learner.

[0103] In addition, when the learner's previous learning feature analysis results are used to set up a learning environment in other learning object categories, the server 200 providing the service sends a learning environment automatic setting approval request message to the learner terminal 100 (for example, do you want to use a learning environment based on the learning feature analysis results of previous learning?), and when the approval message is received from the learner terminal 100, the previous learning feature analysis results can be used to set up a learning environment in other learning object categories.

[0104] In addition, when implementing the present invention, the computing unit 250 of the server 200 providing the service will Figure 4 The number of storage areas, storage capacity and each adjustment ratio in the repeated learning cycle (for example, increase or decrease by 10%) that are adjusted in detail according to the learning environment are also applicable to the number of storage areas, storage capacity and repeated learning cycle set based on Table 1 and Table 2 in the above-mentioned step S415, so that the learning environment in other learning object categories can be set using the learner's previous learning feature analysis results.

[0105] In this way, according to the present invention, not only can the individual learning characteristics of learners such as learning ability and level of learning outcomes in the process of repeated learning be accurately analyzed through artificial intelligence, but the individual learning characteristics of learners analyzed through artificial intelligence can also be reflected, and the learning environment of learners can be actively set.

[0106] Specifically, in the present invention, when the server 200 providing services analyzes the individual learning characteristics of learners through artificial intelligence, machine learning can be used. To this end, the storage unit 230 of the server 200 providing services can store a learning model for analyzing the time required for learning, the storage area moving time, the learner's response information and the response speed.

[0107] In addition, the learning model of the present invention analyzes the learner's learning characteristics based on the time required for learning, the storage area movement time, the learner's response information and the response speed in the above-mentioned calculation unit 250, and based on the learner's learning characteristic analysis results, it can be composed of a calculation algorithm that adjusts the learner's repeated learning cycle and the amount of repeated learning at one time, and can also be formed by neural networks of various structures.

[0108] Specifically, such a learning model can perform machine learning based on the learning time required, storage area movement time, learner's response information and response speed accumulated and stored in the storage unit 230, and the repeated learning cycle created based on this and the adjustment value of one repeated learning amount.

[0109] In addition, when implementing the present invention, the server 200 providing services can generate reward information for learners based on the total learning time or total learning times required until all learning cards related to the category are saved in the last storage area (S500).

[0110] Specifically, the computing unit 250 of the server 200 providing the service can motivate learners to complete repeated learning of long-term memory in a short period of time by creating learning reward points that are inversely proportional to the total number of learning times.

[0111] In addition, the computing unit 250 of the server 200 providing the service sets the storage capacity inversely proportional to the total number of learning times performed by the learner in the previous repeated learning process, and sets the number of storage areas in proportion to the total number of learning times, and sets the storage capacity in proportion to the total correct answer ratio performed in the previous repeated learning process, and sets the number of storage areas inversely proportional to the total correct answer ratio, for the learner who restarts the repeated learning process in the future, when resetting the number of storage areas and the storage capacity in the above-mentioned step S415, thereby providing a long-term prayer support service customized in consideration of the learner's learning ability.

[0112] In addition, when implementing the present invention, the computing unit 250 of the server 200 providing the service generates billing information for the learner in proportion to the number of learning cards stored in the last storage area when the use of the service according to the present invention is finished, so that the learner can pay reasonable fees in proportion to his or her learning outcomes (S500).

[0113] In addition, when implementing the present invention, the computing unit 250 of the server 200 providing the service generates billing information for the learner in proportion to the total learning time required or the total number of learning times when all learning cards related to the category are stored in the last storage area. A usage fee can be charged in proportion to the usage time and number of times the service is used, while also encouraging learners to complete repeated learning as soon as possible through honest learning.

[0114] In addition, when implementing the present invention, a program that executes the method of learning feature analysis and learning environment adjustment using artificial intelligence according to the present invention is installed on the server 200 that provides services according to the present invention or is recorded on various computer-readable recording media, or can be stored on a server that sends the program via a network.

[0115] In addition, the program according to the present invention can be distributed in a computer system connected to a network, and computer-readable codes can be stored and executed in a distributed manner, and the functional programs, codes, and code segments for implementing the present invention can be easily understood by those skilled in the art to which the present invention belongs.

[0116] In addition, the order of the above steps in the present invention is only an example and is not limited thereto. That is, the order of the above steps can be changed, and some steps can be executed simultaneously or deleted.

[0117] The terms used in the present invention are only used to describe specific embodiments and are not intended to limit the present invention. Unless the context clearly indicates otherwise for singular meaning, plural meaning is included. In this application, the terms "including" or "having" are intended to indicate the presence of features, numbers, steps, operations, constituent elements, parts or combinations thereof recorded in the specification, and it should be understood that this does not preclude the presence or additional possibility of one or more other features, numbers, steps, operations, constituent elements, parts or combinations thereof.

[0118] The preferred embodiments and application examples of the present invention are shown and described above, but the present invention is not limited to the above-mentioned specific embodiments and application examples. Those skilled in the art can not only make various modified implementations without departing from the main purpose of the present invention as claimed in the claims, but also these modified implementations should not be understood separately from the technical ideas or prospects of the present invention.

[0119] Industrial Applicability

[0120] The present invention is recognized to have industrial applicability in the field of education industry using artificial intelligence.

Claims

1. A method for learning feature analysis and learning environment adjustment using artificial intelligence, comprising the following steps: (a) a step of sending the learning content stored in a first storage area among a plurality of storage areas to a learner's terminal by a server providing a service; (b) the server providing the service receives the learner's response information to the learning content from the learner's terminal; (c) the server providing the service determines whether to execute the step of moving the learning content from the first storage area and storing it in the second storage area based on the response information of the learner; as well as (d) A step in which the server providing the service analyzes the learning characteristics of the learner based on the learner's response information.

2. The method for analyzing learning characteristics and adjusting learning environment using artificial intelligence according to claim 1, further comprising: (e) The server providing the service adjusts at least one of the learner's repetitive learning cycle and the amount of repetitive learning at one time based on the learning characteristic analysis result of the learner.

3. A server providing services, comprising: A sending unit, which sends the learning content stored in the first storage area of ​​the plurality of storage areas to the learner's terminal; A receiving unit, receiving the learner's response information to the learning content from the learner terminal; The computing unit is configured to analyze the learning characteristics of the learner based on the response information of the learner.

4. The server providing services according to claim 3, wherein: The calculation unit adjusts at least one of a repetitive learning cycle and a repetitive learning amount of the learner based on a learning characteristic analysis result of the learner.

Images