Comment Output Device, Comment Output Program, Learning Support System, and Comment Output Method

Abstract

To provide a comment output device, a comment output program, a learning assistance system and a comment output method for improving the motivation of learners for learning.SOLUTION: A comment output server 1 comprises: a learning achievement information acquisition unit 11 for acquiring learning achievement information of a learner; a comment output unit 13 for selecting, from a plurality of comments stored in a comment storage unit 22, and outputting a comment regarding learning of the learner; and a learning unit 14 for performing reinforcement learning pertaining to the selection of a comment, on the basis of learning achievement information before a comment is outputted by the comment output unit 13 and learning achievement information after the comment is outputted.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to a comment output device, a comment output program, a learning support system, and a comment output method for outputting comments to a learner.

Background Art

[0002] Conventionally, efforts have been made to support learning by learners. For example, when a learner learns learning content using an analog teaching material such as a paper drill or a digital teaching material such as a tablet, a learning support device that provides appropriate learning support to each individual learner has been disclosed (for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] What is described in Patent Document 1 is, for example, for a learner to be able to learn efficiently using problems for an edited acquisition proficiency teaching material and problems for an evaluation teaching material according to the degree of understanding of the learner's learning content. As learning support, it is common to propose teaching materials based on the learner's degree of understanding, etc., as in what is described in Patent Document 1. However, no matter how many teaching materials are proposed to the learner, if the learner has no motivation to learn, it will not lead to an improvement in academic ability. Therefore, from the perspective of improving and maintaining the motivation of the learner's learning, such as remarks and advice that improve the learner's motivation to learn are also important.

[0005] Therefore, an object of the present invention is to provide a comment output device, a comment output program, a learning support system, and a comment output method for improving the motivation of a learner's learning.

Means for Solving the Problem

[0006] The present invention solves the above problems by the following means. A first invention is a comment output device comprising: learning achievement information acquisition means for acquiring learning achievement information of a learner; comment output means for selecting and outputting any one of a plurality of comments stored in a comment storage unit as a comment regarding learning for the learner; and learning means for performing reinforcement learning related to the selection of the comment based on the learning achievement information before the output of the comment by the comment output means and the learning achievement information after the output of the comment. A second invention is a comment output device according to the comment output device of the first invention, further comprising comment selection means for selecting the comment from the plurality of comments stored in the comment storage unit based on a value function updated by the learning means performing reinforcement learning, wherein the comment output means outputs the comment selected by the comment selection means. A third invention is a comment output device according to the comment output device of the second invention, wherein the comment storage unit stores the comments divided into a plurality of categories, and the learning means performs reinforcement learning related to the selection of the comment for each category. A fourth invention is a comment output device according to any one of the comment output devices of the first to third inventions, wherein the learning achievement information includes information regarding a learning achievement level, and the learning means performs reinforcement learning for giving a reward to the comment when the learning achievement level has increased as a result of comparing the learning achievement level after the output of the comment with the learning achievement level before the output of the comment. A fifth invention is a comment output device according to any one of the comment output devices of the first to fourth inventions, wherein the learning achievement information includes information regarding a learning time, and the learning means performs reinforcement learning for giving a reward to the comment when the learning time has increased as a result of comparing the learning time after the output of the comment with the learning time before the output of the comment. The sixth invention is a comment output device of the fourth invention or the fifth invention, wherein the learning means determines the magnitude of the reward according to the degree of change between the learning achievement information after the output of the comment and the learning achievement information before the output of the comment. The seventh invention is a comment output device of any one of the fourth to sixth inventions, wherein the learning means determines the magnitude of the reward according to the learning level of the learner before the output of the comment. The eighth invention is a comment output device of any one of the first to seventh inventions, comprising learner information acquisition means for acquiring learner information which is at least one of the attribute information and personality tendency of the learner, and the learning means performs reinforcement learning related to the selection of the comment for each piece of learner information acquired by the learner information acquisition means. The ninth invention is a comment output device of any one of the first to eighth inventions, comprising a problem statement storage unit for storing problem statements related to learning, and problem statement output means for extracting and outputting the problem statements from the problem statement storage unit based on the learning achievement information acquired by the learning achievement information acquisition means. The tenth invention is a comment output program for causing a computer to function as a comment output device of any one of the first to ninth inventions. The 11th invention is a learning support system in which a comment output device and a learner terminal are communicably connected. The learner terminal includes achievement information transmission means for transmitting the learner's learning achievement information. The comment output device includes learning achievement information acquisition means for acquiring the learning achievement information from the learner terminal, comment output means for selecting any one of a plurality of comments stored in a comment storage unit and outputting the comment on learning for the learner to the learner terminal, learning means for performing reinforcement learning related to the selection of the comment based on the learning achievement information acquired by the learning achievement information acquisition means before the output of the comment by the comment output means and the learning achievement information acquired by the learning achievement information acquisition means after the output of the comment, and comment selection means for selecting the comment from the plurality of comments stored in the comment storage unit based on a value function updated by the learning means performing reinforcement learning. The comment output means outputs the comment selected by the comment selection means to the learner terminal. The 12th invention is a comment output method including a learning achievement information acquisition step in which a computer acquires the learner's learning achievement information, a comment output step in which a comment on learning for the learner is selected from a plurality of comments stored in a comment storage unit and output, and a learning step in which reinforcement learning related to the selection of the comment is performed based on the learning achievement information before the output of the comment in the comment output step and the learning achievement information after the output of the comment.

Effect of the Invention

[0007] According to the present invention, it is possible to provide a comment output device, a comment output program, a learning support system, and a comment output method for improving the motivation of a learner for learning.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Mode for Carrying Out the Invention

[0009] Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings. Note that this is merely an example, and the technical scope of the present invention is not limited thereto. (Embodiment) (Overall Configuration of Learning Support System 100) FIG. 1 is a functional block diagram of a learning support system 100 according to the present embodiment. FIG. 2 is a diagram showing an example of a comment storage unit 22 of a comment output server 1 according to the present embodiment.

[0010] The learning support system 100 shown in FIG. 1 is a system in which a comment output server 1 (comment output device) acquires learning achievement information from a terminal 5 (learner terminal) and outputs a comment related to learning to the terminal 5. This comment related to learning is selected based on a value function updated by the comment output server 1 performing reinforcement learning on the relationship between the output comment and the learning achievement information before and after the output of the comment. The learning support system 100 includes a comment output server 1 and a plurality of terminals 5. The comment output server 1 and the terminal 5 are connected via a communication network N.

[0011] <Comment Output Server 1> Comment Output Server 1 is, for example, a server managed by a company that provides analog or digital learning materials, a service provider that supports learners' learning, or the like. Comment Output Server 1 receives learning achievement data (learning achievement information) from, for example, the learner's terminal 5. Then, Comment Output Server 1 outputs a comment based on the received learning achievement data to the learner's terminal 5. Initially, since the value function by learning has not been updated, the comment output by Comment Output Server 1 may be arbitrary. For example, it may be randomly selected from the comments stored in the comment storage unit 22 (described later).

[0012] Next, Comment Output Server 1 receives the learning achievement data again from the learner's terminal 5 that has output the comment. Since the learning achievement data here is the learning achievement data after the comment has been output, it is considered to have been affected by the comment to some extent. Then, Comment Output Server 1 learns the change obtained from the learning achievement data before and after the output of the comment with respect to the comment. Also, Comment Output Server 1 outputs a comment based on the received learning achievement data to the learner's terminal 5. Here, since the value function by learning has been updated, Comment Output Server 1 selects and outputs a comment from the comment storage unit 22 based on the value function.

[0013] Comment Output Server 1 includes a control unit 10, a storage unit 20, and a communication interface unit 29. The control unit 10 is a CPU (Central Processing Unit) that controls the entire Comment Output Server 1. The control unit 10 appropriately reads and executes the OS (Operating System) and various application programs stored in the storage unit 20, and cooperates with the above-described hardware to execute various functions. The control unit 10 includes a learning achievement information acquisition unit 11 (learning achievement information acquisition means), a comment selection unit 12 (comment selection means), a comment output unit 13 (comment output means), a learning unit 14 (learning means), and a problem statement output unit 15 (problem statement output means).

[0014] The learning achievement information acquisition unit 11 receives the learning achievement data transmitted by the learner's terminal 5. Here, the learning achievement data indicates, for example, the proficiency of learning, and may be the score of a test, or may be a deviation value, an evaluation value, etc. Further, the learning achievement data may be, for example, the learning time. In the case of the learning time, for example, the terminal 5 measures the time the learner uses the terminal 5 for learning, and the total usage time of the terminal 5 may be used as the learning time. The comment selection unit 12 selects a comment from a plurality of comments stored in the comment storage unit 22. Here, each comment is, for example, content that scolds and encourages the learner, and is for improving the learner's motivation for learning. The comment output unit 13 transmits the comment selected by the comment selection unit 12 to the terminal 5.

[0015] The learning unit 14 performs learning related to the selection of comments based on the learning achievement data of the learner before the comment is output and the learning achievement data of the learner after the comment is output. The learning unit 14 performs learning using, for example, reinforcement learning. Here, the basic mechanism of reinforcement learning will be described. An agent (corresponding to the comment output server 1 in the present embodiment) acquires the state of the environment (corresponding to the learner in the present embodiment), selects an action, and the environment changes based on the action. Along with the change of the environment, some reward is given, and the agent learns to select a better action (decision-making).

[0016] In reinforcement learning, by learning actions, appropriate actions are learned based on the interactions that the actions have on the environment, that is, a method of learning to maximize the future rewards is learned. In this embodiment, this represents that, for example, actions that can affect the future, such as selecting comments, which are action information for improving the learning achievement data that is the state, can be obtained.

[0017] Reinforcement learning (1) actions, (2) feedback of environmental changes and rewards due to the actions, (3) comparing the values when taking that action and when not taking it, modifying the policy, and returning to (1). Learning is carried out while repeating such cycles.

[0018] Applying the above cycle to this embodiment, the learning unit 14 (1) selects comments and outputs them to the learner, (2) from the changes in the learning achievement data before and after the comments, when the learning achievement degree improves, a large amount of rewards are given to the relevant comments, (3) updates the value function so that the learning achievement degree is maximized, Learning is carried out while repeating such cycles. Then, the learning unit 14 stores the updated value function in the value function storage unit 25 (described later).

[0019] Based on the learning achievement data received by the learning achievement information acquisition unit 11, the problem statement output unit 15 extracts a problem statement from the problem statement storage unit 23 (described later) and transmits it to the learner's terminal 5.

[0020] The storage unit 20 is a storage device such as a hard disk and a semiconductor memory element for storing programs, data, etc. necessary for the operation of the comment output server 1. Note that a computer refers to an information processing device equipped with a control unit, a storage device, etc. The comment output server 1 is an information processing device equipped with a control unit 10, a storage unit 20, etc., and is included in the concept of a computer. The storage unit 20 includes a program storage unit 21, a comment storage unit 22, a problem statement storage unit 23, and a value function storage unit 25.

[0021] The program storage unit 21 is a storage area for storing programs. The program storage unit 21 stores a comment output program 21a. The comment output program 21a is a program for executing various functions of the control unit 10. Note that instead of the comment output program 21a, a function for outputting comments and a function for learning may be provided as separate programs.

[0022] The comment storage unit 22 is a storage area for storing comments related to learning to be output to the learner. As shown in FIG. 2, the comment storage unit 22 stores by associating numbers with comment contents. The comment storage unit 22 is classified, for example, into a comment group 22a when the learning achievement level improves and a comment group 22b when the learning achievement level decreases.

[0023] The problem statement storage unit 23 is a storage area for storing problem statements. The problem statement storage unit may store problem statements of different difficulty levels in association with the learning achievement level. The value function storage unit 25 is a storage area for storing the value function updated by the learning unit 14. The value function stored in the value function storage unit 25 is updated by the learning unit 14. The communication interface unit 29 is an interface unit for communicating with the terminal 5 via the communication network N.

[0024] Note that there is no limit to the number of hardware components constituting the comment output server 1. The number of hardware components constituting the comment output server 1 may be one or more as required. Also, the hardware of the comment output server 1 may include various servers such as a web server, a DB (database) server, an application server, and a learning server as required, and may be configured by one server or by separate servers respectively. Also, the comment storage unit 22, problem statement storage unit 23, and value function storage unit 25 stored in the storage unit 20 of the comment output server 1 may be provided in a separate server. In that case, the control unit 10 of the comment output server 1 may acquire or update various data stored in the separate server by communicating with the separate server.

[0025] <Terminal 5> Terminal 5 is a terminal used by the learner. Terminal 5 is, for example, a tablet terminal. Note that Terminal 5 is not limited to a tablet terminal, and may be a PC (personal computer), a mobile terminal, or the like. Also, Terminal 5 may include a terminal used by the teacher. Although not shown, Terminal 5 includes a control unit, a storage unit, an input unit, a display unit, a communication interface unit, and the like. In the case of a tablet terminal, the input unit and the display unit of Terminal 5 are a touch panel display in which they are integrated. Also, a computer refers to an information processing device including a control unit, a storage device, etc. Terminal 5 is an information processing device including a control unit, a storage unit, etc., and is included in the concept of a computer.

[0026] The communication network N is a network between the comment output server 1 and Terminal 5, and is a communication network such as an Internet line. The communication network N may be either wired or wireless.

[0027] Next, the processing performed by the learning support system 100 will be described. <Comment output processing> FIG. 3 is a flowchart showing the comment output processing in the comment output server 1 according to the present embodiment. For example, in Terminal 5, the learner uses a learning app (not shown), which is software for learning stored in Terminal 5, to perform learning using Terminal 5 for each unit, and a confirmation test is performed at the end of each unit. This will be described.

[0028] When the learner uses the terminal 5 to conduct a confirmation test and, for example, executes a scoring process, the control unit (achievement information transmitting means) of the terminal 5 transmits learning achievement data. Then, in step S (hereinafter, "step S" will be simply referred to as "S") 11 of FIG. 3, the control unit 10 (learning achievement information acquisition unit 11) of the comment output server 1 receives learning achievement data from the terminal 5.

[0029] In S12, the control unit 10 (comment output unit 13) randomly selects one comment from the comments stored in the comment storage unit 22 and outputs it to the terminal 5. The learner views the comment displayed on the terminal 5 and conducts learning about the next unit. After the learner uses the terminal 5 to conduct a confirmation test for the next unit, the control unit (achievement information transmitting means) of the terminal 5 executes the same processing as before and transmits learning achievement data. Then, in S13, the control unit 10 (learning achievement information acquisition unit 11) receives learning achievement data from the terminal 5.

[0030] In S14, the control unit 10 (learning unit 14) conducts a learning process and updates the value function. The learning process will be described later. In S15, the control unit 10 (comment selection unit 12) selects a comment using the value function stored in the value function storage unit 25.

[0031] In S16, the control unit 10 determines whether the learning achievement degree of the received learning achievement data is less than or equal to a predetermined value. Here, the case where the learning achievement degree is less than or equal to the predetermined value means the case where the understanding of learning has not progressed. If the learning achievement degree is less than or equal to the predetermined value (S16: YES), the control unit 10 transfers the process to S17. On the other hand, if the learning achievement degree is not less than or equal to the predetermined value (S16: NO), the control unit 10 transfers the process to S19.

[0032] In S17, the control unit 10 (question sentence output unit 15) extracts a question sentence from the question sentence storage unit 23 based on the learning achievement data received in S13. In S18, the control unit 10 (comment output unit 13, problem statement output unit 15) transmits the comment selected in S15 and the problem statement extracted in the process of S17 to the terminal 5. Thereafter, the control unit 10 moves the process to S13, receives learning achievement data from the terminal 5, and repeats the process of outputting a comment. On the other hand, in S19, the control unit 10 (comment output unit 13) transmits the comment selected in S15 to the terminal 5. Thereafter, the control unit 10 moves the process to S13 and performs a repetitive process.

[0033] <Learning process> Next, a learning process related to reinforcement learning will be described. FIG. 4 is a flowchart showing a learning process in the comment output server 1 according to the present embodiment. In S21, the control unit 10 (learning unit 14) compares the learning achievement levels before and after comment transmission. In S22, the control unit 10 (learning unit 14) determines whether or not the learning achievement level has increased. The control unit 10 determines the result of the learning achievement level after comment transmission based on the learning achievement level before comment transmission. If the learning achievement level has increased (S22: YES), the control unit 10 moves the process to S23. On the other hand, if the learning achievement level has not increased (S22: NO), the control unit 10 moves the process to S26. If the learning achievement level has not changed, for example, it may be included in the case where the learning achievement level has not increased.

[0034] In S23, the control unit 10 (learning unit 14) determines whether or not the learning achievement level (learner's learning level) before comment transmission is equal to or higher than a predetermined value. If the learning achievement level before comment transmission is equal to or higher than the predetermined value (S23: YES), the control unit 10 moves the process to S24. On the other hand, if the learning achievement level before comment transmission is not equal to or higher than the predetermined value (S23: NO), the control unit 10 moves the process to S25.

[0035] In S24, the control unit 10 (learning unit 14) sets the reward to a first value. Here, the first value is a positive value. Thereafter, the control unit 10 moves the process to S27. In S25, the control unit 10 (learning unit 14) sets the reward to a second value. Here, the second value is a positive value and is smaller than the first value. Thereafter, the control unit 10 moves the process to S27. In S26, the control unit 10 (learning unit 14) sets the reward to a third value. Here, the third value is a negative value. In S27, the control unit 10 (learning unit 14) updates the value function based on the reward. Thereafter, the control unit 10 ends this process and moves the process to S15 in FIG. 3.

[0036] <Specific Example> Next, specific examples of the learning achievement level and comments will be described. FIGS. 5 to 7 are diagrams showing specific examples related to the learning achievement level and comment selection according to the present embodiment. FIG. 5(A) shows the learning achievement level of a certain learner (referred to as learner A) as graph 60. Graph 60 shows the past period 61 including this time, the current achievement level 62, the past achievement level 63 including this time, and the future transition 64 of the achievement level that is undetermined at the time of the current achievement level 62. FIG. 5(B) shows comment 221 output in the case of the current achievement level 62. If the learning achievement level after outputting comment 221 rises as shown in the future transition 64, the learning unit 14 sets the reward value for the number "C001" (see FIG. 2) in the comment storage unit 22 to a positive value and updates the value function.

[0037] FIG. 6(A) shows the learning achievement level of a certain learner (referred to as learner B) as graph 70. Graph 70 shows the past period 71 including this time, the current achievement level 72, the past achievement level 73 including this time, and the future transition 74 of the achievement level that is undetermined at the time of the current achievement level 72. FIG. 6(B) shows comment 222 output in the case of the current achievement level 72. If the learning achievement level after outputting comment 222 drops as shown in the future transition 74, the learning unit 14 sets the reward value for the number "C102" (see FIG. 2) in the comment storage unit 22 to a negative value and updates the value function.

[0038] FIG. 7(A) shows the learning achievement level of a certain learner (referred to as Learner C) as graph 80. Graph 80 shows the past period 81 including this time, the current achievement level 82, the past achievement level 83 including this time, and the future transition 84 of the achievement level that is undetermined at the time of the current achievement level 82. FIG. 7(B) is comment 223 output in the case of the current achievement level 82. If the learning achievement level drops as shown in the future transition 84 after outputting comment 223, the learning unit 14 sets the value of the reward for the number "C101" (see FIG. 2) in the comment storage unit 22 to a negative value and updates the value function.

[0039] Thus, according to this embodiment, the comment output server 1 has the following effects. (1) It acquires the learning achievement data of the learner, outputs comments related to learning to the terminal 5 of the learner, and performs reinforcement learning related to the selection of comments based on the learning achievement level before outputting the comments and the learning achievement level after outputting the comments. Therefore, it is possible to learn the change in the learner's achievement level with respect to the comments. Also, based on the value function updated by performing reinforcement learning, a comment is selected from a plurality of comments stored in the comment storage unit 22. As a result, it is possible to output to the learner a comment that improves the motivation of the learner for learning corresponding to the learning achievement level.

[0040] (2) By comparing the learning achievement level after outputting the comment with the learning achievement level before outputting the comment, reinforcement learning is performed to give a high reward when the learning achievement level increases. Therefore, the reward for the comment output before the learning achievement level increases can be set high.

[0041] (3) When the learning achievement level is below a predetermined value, a problem statement is extracted from the problem statement storage unit 23 and output to the terminal 5. Therefore, for a learner with a low learning achievement level, it is possible to prompt the improvement of the learning achievement level by outputting the problem statement.

[0042] As described above, embodiments of the present invention have been explained, but the present invention is not limited to the above-described embodiments. Also, the effects described in the embodiments merely list the most preferable effects resulting from the present invention, and the effects of the present invention are not limited to those described in the embodiments. Note that the above-described embodiments and the modified forms described later can be used in appropriate combinations, but detailed descriptions thereof are omitted.

[0043] (Modified form) (1) In this embodiment, an example has been described in which learning achievement data is obtained by receiving it from the learner's terminal, but it is not limited thereto. For example, the control unit of the comment output server may obtain the learning achievement data when a teacher inputs the learning achievement data of the learner from the teacher's terminal. Similarly, an example has been described in which comments are transmitted to the learner's terminal, but it is not limited thereto. For example, by outputting comments to the teacher's terminal, the teacher may provide guidance to the learner with reference to the output comments.

[0044] (2) In this embodiment, learning related to comment selection using the learning achievement level has been explained, but it is not limited thereto. For example, instead of the learning achievement level, or in addition to the learning achievement level, the learning time may be used. And the control unit of the comment output server may give a reward when the learning time increases. Also, regarding the reward, the magnitude of the reward may be determined according to the degree of change before and after outputting the comment and the level of the learner before outputting the comment. For example, even if the degree of change before and after outputting the comment is small, if the level of the learner before outputting the comment is high (the learner is originally good at learning), the reward may be increased. On the other hand, if the degree of change before and after outputting the comment is small and the level of the learner before outputting the comment is low, the reward may be decreased.

[0045] (3) In this embodiment, one comment storage unit is prepared, and an example of classification reflecting the learning result is described, but it is not limited to this. For example, the comment output server may divide the comment storage unit for each subject or for each category such as for each learner layer (elementary school students, junior high school students, etc.).

[0046] (4) In this embodiment, the learner is not particularly limited, but it is not limited to this. For example, learning may be performed separately for each learner information such as the learner's attribute information and personality tendency. The attribute information includes, for example, age, gender, etc., and the personality tendency is, for example, a tendency regarding learning such as whether one grows by being praised or by being scolded. In this case, the control unit (learner information acquisition means) of the comment output server acquires the learner information from the learner via a terminal, for example.

[0047] (5) In this embodiment, an example of outputting a problem sentence when the learning achievement level is below a predetermined value is described, but it is not limited to this. The problem sentence may be output regardless of the learning achievement level. Also, problem sentences with difficulty levels corresponding to the learning achievement level may be output.

[0048] (6) In this embodiment, an example of using the result of the confirmation test for each unit as learning achievement data is described, but it is not limited to this. For example, it may be correct / incorrect data of questions for preparing for a qualification exam or learning questions suitable for a child's school year, and any data related to learning can be used.

[0049] (7) In this embodiment, it is described as using a learning app, but it is not limited to this. For example, it may be something like a web service.

[0050] (8) In this embodiment, an example of the comment output server performing the learning process and the comment output process is described, but it is not limited to this. The learning process and the comment output process may be performed by separate devices respectively.

Description of Reference Numerals

[0051] 1 Comment output server 5 Terminal 10 Control Unit 11 Learning Achievement Information Acquisition Unit 12 Comment Selection Unit 13 Comment Output Unit 14 Learning Unit 15 Problem Statement Output Unit 20 Memory Unit 21a Comment Output Program 22 Comment Memory Unit 23 Problem Statement Memory Unit 25 Value Function Memory Unit 100 Learning Support System N Communication Network

Claims

1. learning achievement information acquisition means for acquiring learning achievement information including information on the learning achievement level of a learner; question sentence output means for extracting and outputting the question sentence from a question sentence storage unit that stores question sentences related to learning based on the learning achievement information when the learning achievement level of the learning achievement information acquired by the learning achievement information acquisition means is equal to or lower than a predetermined value; comment output means for selecting and outputting any one of a plurality of comments stored in a comment storage unit as a comment regarding learning for the learner; learning means for performing reinforcement learning related to the selection of the comment based on the learning achievement information before the output of the comment by the comment output means and the learning achievement information after the output of the comment; A comment output device comprising:

2. The comment output device according to claim 1, comprising comment selection means for selecting the comment from the plurality of comments stored in the comment storage unit based on a value function updated by the learning means performing reinforcement learning; The comment output means outputs the comment selected by the comment selection means. A comment output device.

3. The comment output device according to claim 2, The comment storage unit stores the comments divided into a plurality of categories, The learning means performs reinforcement learning related to the selection of the comment for each category. A comment output device.

4. In the comment output device according to any one of claims 1 to 3, The learning means performs reinforcement learning to give a reward to the comment when the learning achievement level has increased as a result of comparing the learning achievement level after the output of the comment with the learning achievement level before the output of the comment. A comment output device.

5. In the comment output device according to any one of claims 1 to 4, the learning achievement information includes information related to the learning time, The learning means performs reinforcement learning to give a reward to the comment when the learning time increases as a result of comparing the learning time after outputting the comment with the learning time before outputting the comment. A comment output device.

6. In the comment output device according to claim 4 or claim 5, The learning means determines the magnitude of the reward according to the degree of change between the learning achievement information after outputting the comment and the learning achievement information before outputting the comment. A comment output device.

7. In the comment output device according to any one of claims 4 to 6, The learning means determines the magnitude of the reward according to the learning level of the learner before outputting the comment. A comment output device.

8. In the comment output device according to any one of claims 1 to 7, It includes learner information acquisition means for acquiring learner information which is at least one of the attribute information and personality tendency of the learner, The learning means performs reinforcement learning related to the selection of the comment for each piece of learner information acquired by the learner information acquisition means. A comment output device.

9. In the comment output device according to any one of claims 1 to 8, The problem statement output means extracts and outputs the problem statement with a difficulty level corresponding to the learning achievement degree of the learning achievement information acquired by the learning achievement information acquisition means from the problem statement storage unit. A comment output device.

10. A comment output program for causing a computer to function as the comment output device according to any one of claims 1 to 9.

11. A learning support system in which a comment output device and a learner terminal are communicably connected, The learner terminal includes achievement information transmission means for transmitting learning achievement information including information on the learning achievement level of the learner, The comment output device, Learning achievement information acquisition means for acquiring the learning achievement information from the learner terminal, When the learning achievement level of the learning achievement information acquired by the learning achievement information acquisition means is equal to or lower than a predetermined value, based on the learning achievement information, question sentence output means for extracting the question sentence from a question sentence storage unit that stores question sentences related to learning and outputting the question sentence to the learner terminal, Comment output means for selecting any one of a plurality of comments stored in a comment storage unit and outputting a comment related to learning for the learner to the learner terminal, Learning means for performing reinforcement learning related to the selection of the comment based on the learning achievement information acquired by the learning achievement information acquisition means before the output of the comment by the comment output means and the learning achievement information acquired by the learning achievement information acquisition means after the output of the comment, Comment selection means for selecting the comment from the plurality of comments stored in the comment storage unit based on a value function updated by the learning means performing reinforcement learning, Comprising, The comment output means outputs the comment selected by the comment selection means to the learner terminal, a learning support system.

12. A computer, A learning achievement information acquisition step of acquiring learning achievement information including information on the learning achievement level of a learner, When the learning achievement level of the learning achievement information acquired in the learning achievement information acquisition step is equal to or lower than a predetermined value, based on the learning achievement information, a question sentence output step of extracting the question sentence from a question sentence storage unit that stores question sentences related to learning and outputting the question sentence, A comment output step of selecting and outputting any one of a plurality of comments stored in a comment storage unit as a comment regarding learning for the learner; A learning step of performing reinforcement learning related to the selection of the comment based on the learning achievement information before the output of the comment by the comment output step and the learning achievement information after the output of the comment; A comment output method including the above.

Images