Information processing apparatus, information processing method, information processing system, and program

Abstract

To present a hint of a problem at an appropriate timing to a learner working on the problem.SOLUTION: An information processing device includes a controller 11 that performs control to derive a predicted correct answer probability that is a probability that a learner is predicted to correct a first problem, derive a time difference between a timing at which the first problem is presented and a timing at which hint information that is information to be a hint of the first problem is presented based on the predicted correct answer probability, and present the first problem and the hint information to the learner based on the time difference.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, an information processing system, and a program. [Background technology]

[0002] In recent years, there have been learning support systems that use computers to present problems to learners, who then practice by answering the questions. When actually practicing, learners may answer the questions while looking at supplementary materials such as hints and explanations. For example, Patent Document 1 discloses a learning support system in which, when a learner inputs a request for a hint into an information processing terminal, a server communicably connected to the information processing terminal outputs the hint. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7022431 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the system of Patent Document 1 was unable to provide hints at an appropriate time based on the learner's ability or the content of the problem.

[0005] The present invention has been made to solve the above-mentioned problems, and aims to present hints to a learner working on a problem at an appropriate timing. [Means for solving the problem]

[0006] In order to achieve the above-mentioned object, the information processing device of the present invention is characterized by comprising a control unit that derives a predicted correct answer probability, which is the probability that a learner is predicted to answer a first question correctly, derives a time difference between the timing of presenting the first question and the timing of presenting hint information, which is information that serves as a hint for the first question, based on the predicted correct answer probability, and controls the first question and the hint information to be presented to the learner based on the time difference.

[0007] In order to achieve the above object, the information processing device of the present invention is characterized by having a control unit that acquires the difficulty level of a first question to be answered by a learner, and controls the first question and hint information, which is information that serves as a hint for the first question, to be presented to the learner based on a time difference derived based on the difficulty level. [Effects of the Invention]

[0008] According to the present invention, hints for problems can be presented at appropriate times to a learner working on a problem. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram showing an outline of the overall configuration of an information processing system according to an embodiment of the present invention; [Figure 2] FIG. 2 is a block diagram showing a functional configuration of a server according to an embodiment of the present invention. [Figure 3] FIG. 2 is a block diagram showing a functional configuration of a learner terminal according to the embodiment of the present invention. [Figure 4] FIG. 10 is a diagram showing an example of answer history information according to an embodiment of the present invention. [Figure 5] 10 is a flowchart illustrating an example of a hint display process according to an embodiment of the present invention. [Figure 6] 10 is a flowchart of another example of the hint display process according to the embodiment of the present invention. [Figure 7] FIG. 10 is a diagram illustrating an example of a table of threshold conditions according to an embodiment of the present invention. [Figure 8]FIG. 10 is a diagram illustrating an example of a question and a hint according to an embodiment of the present invention. [Figure 9] FIG. 10 is a diagram showing the relationship between ability scores, difficulty levels, and correct answer probability. [Figure 10] FIG. 10 is a diagram showing threshold conditions for the difference between ability values ​​and difficulty levels. DETAILED DESCRIPTION OF THE INVENTION

[0010] An information processing system according to an embodiment of the present invention provides a service that supports learning for learners. As shown in FIG. 1, the information processing system 1 includes a server 10 (information processing device) and a learner terminal 30 that is communicatively connected to the server 10 via a network 20 such as the Internet. A plurality of learner terminals 30 are connected depending on the number of learners. The learner terminals 30 are terminal devices used by learners, such as smartphones, tablet terminals, and personal computers. The server 10 presents questions and hints to learners who operate the learner terminals 30, grades answers sent via the learner terminals 30, and presents the graded results to the learners.

[0011] 2, the server 10 includes a control unit 11, a storage unit 12, and a communication unit 13. The control unit 11 is configured, for example, with a CPU (Central Processing Unit) or the like, and executes various processes according to programs stored in the storage unit 12. The storage unit 12 includes, for example, at least one memory such as a RAM (Random Access Memory) and a ROM (Read Only Memory). The communication unit 13 includes a communication module such as a LAN, and communicates data with the learner terminal 30 via the network 20.

[0012] In FIG. 2, the control unit 11 executes a program stored in the storage unit 12 to function as a question extraction unit 111, a correct answer probability derivation unit 112, a hint extraction unit 113, and a hint timing derivation unit 114.

[0013] The problem extraction unit 111 extracts problems to be presented to the learner. The memory unit 12 includes a problem information storage unit 121 that stores problem information, which is information on multiple problems to be presented to the learner and their answers. The problems stored in the problem information storage unit 121 are, for example, proof problems in mathematics. However, the problem is not limited to this, and may also be calculation problems or questions in other subjects such as English. The problem extraction unit 111 searches the problem information storage unit 121 to extract desired problems. The extracted problems are transmitted from the communication unit 13 to the learner terminal 30 via the network 20. The desired questions are requested from the server 10 by the learner entering them into the learner terminal 30. Note that the desired questions may not be specified by the learner but may also be determined by the problem extraction unit 111. For example, the problem extraction unit 111 may randomly extract unassigned questions, or may extract previously asked questions that were answered incorrectly last time or questions that have been asked for a long time. The problem extraction unit 111 may also extract questions to be presented based on the difficulty level of the questions and the learner's ability score.

[0014] The correct answer probability derivation unit 112 derives a predicted correct answer probability, which is the probability that the learner will correctly answer the currently presented question (first question), by estimating the correct answer probability using machine learning based on the learner's answer history for questions other than the currently presented question. Specifically, when a certain learner A works on question j, a machine learning model that estimates the correct answer probability is used to estimate a predicted value of the probability that learner A will correctly answer question j. As the machine learning model, IRT (Item Response Theory) as well as its derivative models and knowledge tracing models can be applied. The storage unit 12 includes an answer history information storage unit 123 and a machine learning model storage unit 124. The answer history information storage unit 123 stores answer history information of each learner for each presented question. FIG. 4 shows an example of an answer history information table. The table stores each learner's user ID, the ID of the question posed, the date and time the question was answered, and the result of the correctness judgment for the answer, and the table is updated each time an answer is given or at regular intervals. The machine learning model storage unit 124 stores a machine learning model that inputs data from the learner's answer history and derives a predicted probability of correct answer based on the answer history data. Here, the estimation method will be described using the IRT 1PL (one-parameter logistic) model as an example. In the IRT 1PL model, the predicted probability of correct answer for question j given the learner's ability score θ is approximated by the following sigmoid function:

[0015]

number

[0016] The correct answer probability derivation unit 112 calculates model parameters based on the answer history of the learner stored in the answer history information storage unit 123 so as to satisfy the formula (1). The model parameters include an ability value and a difficulty level. The correct answer probability derivation unit 112 calculates the ability value θ and difficulty level b of the learner that satisfy the formula (1) from the answer history of a large number of learners. j For example, the estimation is performed using a statistical method such as the EM algorithm or Bayesian estimation.

[0017] The hint extraction unit 113 extracts hint information that will help learner A to answer the questions posed to learner A and presents it to learner A. The storage unit 12 includes a hint information storage unit 122 that stores hint information that serves as a hint for the questions. The hint extraction unit 113 searches the hint information storage unit 122 to extract desired hint information. A plurality of pieces of hint information are prepared for each question, and each piece of hint information has content at multiple levels according to the learner's ability. The hint information is extracted based on the predicted probability of learner A's correct answer to question j, or the ability value θ of learner A and the difficulty level of question j.

[0018] The hint timing derivation unit 114 derives the timing for presenting the hint information extracted by the hint extraction unit 113 to learner A. The timing is derived to be an appropriate time so that the learner will be able to learn effectively. The timing is derived based on the predicted probability of learner A answering question j correctly, or the ability score θ of learner A and the difficulty of question j. The hint information selected based on the derived timing is transmitted from the communication unit 13 to the learner terminal 30 via the network 20.

[0019] Next, the learner terminal 30 will be described. An application program for executing learning-related processes is installed on the learner terminal 30. As shown in Fig. 3, the learner terminal 30 includes a control unit 31, a storage unit 32, a display unit 33, a communication unit 34, and a user interface 35. The control unit 31 is composed of, for example, a CPU, and executes various processes using the application programs stored in the storage unit 32.

[0020] The storage unit 32 includes, for example, at least one memory such as a RAM and a ROM. The display unit 33 is configured with an LCD (Liquid Crystal Display), an EL (Electroluminescence) display, or the like, and performs various displays in accordance with display control signals output from the control unit 31. The communication unit 34 includes a communication module compatible with wireless LAN, mobile data communication, etc., and performs data communication with the server 10 via the network 20. The user interface 35 accepts operational inputs from the learner, or outputs images or sounds output by the control unit 31. The user interface 35 includes, for example, a touch screen and a speaker.

[0021] The control unit 31 functions as an input processing unit 311 and a display processing unit 312 by executing an application program related to learning stored in the storage unit 32. The input processing unit 311 performs processes such as sending login information to the system, requesting questions, and sending answers based on operation signals input from the user interface 35. The display processing unit 312 performs processes such as acquiring question information, hint information, and result information on whether the answer is correct or incorrect, sent from the server 10, and outputting them to the display unit 33.

[0022] When conducting a test, the learner terminal 30 obtains data on the question to be asked from the server 10 and presents the question to the learner by displaying it on the display unit 33. After a predetermined time has passed since the question was displayed, the learner terminal 30 obtains hint information for the question from the server 10 and presents the question to the learner. When the learner inputs an answer to the question, the learner terminal 30 judges whether the answer is correct or incorrect, obtains the result from the server 10, and presents it to the learner.

[0023] The processing operation of presenting hint information j_target for question j given to a learner A in the information processing system 1 described above will be described with reference to the flowcharts of Fig. 5 and Fig. 6. Fig. 5 shows an example in which the timing of presenting the hint information is controlled based on the predicted probability of correct answer, and Fig. 6 shows an example in which the timing of presenting the hint information is controlled based on the difficulty of the question.

[0024] 5, when the question extraction unit 111 of the control unit 11 of the server 10 extracts question j to be given to learner A and transmits it to the learner terminal 30, the control unit 11 specifies question j for which hint information is to be presented to the hint extraction unit 113 (S101). The correct answer probability derivation unit 112 accesses the answer history information storage unit 123 to read out answer histories of learner A for questions other than question j, and inputs the answer histories into the machine learning model (S102). The correct answer probability derivation unit 112 derives a predicted correct answer probability based on the read answer history of learner A and the machine learning model stored in the machine learning model storage unit 124 (S103). Note that the correct answer probability derivation unit 112 may derive a predicted incorrect answer probability based on the read answer history of learner A and the machine learning model stored in the machine learning model storage unit 124. If the correct answer probability derivation unit 112 derives a predicted incorrect answer probability, the predicted correct answer probability in the described flow may be replaced with the predicted incorrect answer probability for control. The machine learning model is constructed based on the answer histories of multiple learners for all questions, and the IRT model described above is applied to construct the machine learning model.

[0025] The hint extraction unit 113 compares the derived predicted correct answer probability with a threshold value and extracts hint information j_target for question j that matches the condition (S104). A plurality of hints are provided according to the level. There are multiple levels of hints available, ranging from simple hints that merely show the key points to leading to the correct answer to detailed hints that are close to the answer, and hints are extracted according to the predicted correct answer probability.

[0026] The threshold value for extracting hint information is stored in the threshold storage unit 125 of the storage unit 12. Fig. 7 shows an example of a table of threshold conditions stored in the threshold storage unit 125. The table stores the ID of a question, the ID of hint information for the question, and the threshold condition for extracting hint information. In this example, three pieces of hint information with hint IDs 1 to 3 are provided for the question with ID 1.

[0027] FIG. 8 shows an example of a problem with problem ID=1 and three hints with hint IDs=1 to 3. For the problem with problem ID=1, 2 Let's say the question is "Find the minimum value of -12x+9." Here, a mathematical calculation problem is used as an example. For this problem, the hint information for hint ID=1 is the sentence "Let's complete the square," which simply shows the key points for finding the minimum value. In contrast, the hint information for hint ID=2 is "Let's complete the square. Completing the square is y=〇(x-△) 2The hint information with hint ID=2 adds a sentence explaining the meaning of completing the square to the hint information with hint ID=1, providing more detailed information than the hint information with hint ID=1. Furthermore, the hint information with hint ID=3 adds the sentence, "Since the graph of y is U-shaped, when x = △, y is at its minimum." This additional sentence explains which part of the equation after completing the square is used to find the minimum value, providing even more detailed information than the hint information with hint ID=2. As such, each hint information has three levels of detail, with the order of Hint ID=1 < Hint ID=2 < Hint ID=3. Note that the above-mentioned hint information increases the level of detail by adding additional sentences to the hint information, but this is not limited to this. For example, with respect to the formula for deriving the answer described as hint information, as the level of detail increases, the disclosure of the formula may be made more detailed by adding intermediate calculation steps such as formula transformations. Furthermore, points for answering may be set in advance according to the level of importance, and important points may be disclosed as the level of detail of the hint information increases. In this way, by presenting less detailed hint information to a learner who is more likely to arrive at the correct answer, and more detailed hint information to a learner who is less likely to arrive at the correct answer, it is possible to improve the efficiency and effectiveness of the learner's learning.

[0028] Returning to Fig. 7, two threshold conditions are provided for each hint information in the table. Threshold condition 1 indicates the threshold condition for the prediction correct probability, and threshold condition 2 indicates the threshold condition for the difficulty level. Here, threshold condition 1 will be explained. Threshold condition 2 will be described later. Different thresholds are set for each hint information in threshold condition 1. For example, the threshold condition for the prediction correct probability p of hint ID = 1 for the problem with problem ID = 1 is 0 < p ≤ 0.3, the threshold condition for the prediction correct probability p of hint ID = 2 is 0.3 < p ≤ 0.6, and the threshold condition for the prediction correct probability p of hint ID = 3 is 0.6 < p ≤ 1.0. That is, when the prediction correct probability p is 30% or less, the hint information of hint ID = 1 is extracted, when it is 30% - 60%, the hint information of hint ID = 2 is extracted, and when it is 60% - 100%, the hint information of hint ID = 3 is extracted.

[0029] In parallel with the extraction of hint information, the hint timing derivation unit 114 derives the timing for presenting the extracted hint information to learner A (S105). The time difference t, which is the time from when learner A starts solving problem j until the hint information is presented after the problem is displayed on the display unit 33 of the learner terminal 30, is derived using the prediction correct probability. Specifically, the value obtained by multiplying the prediction correct probability by a certain fixed time value is taken as the time until the hint information is presented. For example, when the prediction correct probability is 40%, the time until the hint information is presented is 30 seconds × 0.4 = 12 seconds, and when the prediction correct probability is 10%, it is 30 seconds × 0.1 = 3 seconds. Also, if the prediction correct probability is above a specific threshold (e.g., 80%), the control unit 11 may control so that the hint information is not displayed even as time passes, judging that the learner's ability is sufficient to derive the correct answer without hint information.

[0030] When question j is transmitted to the learner terminal 30 and presented to learner A, learner A starts practicing question j (S106). When the practice starts, the control unit 11 measures the elapsed time from the start at any time (S107). The control unit 11 determines whether the measured time has passed the hint presentation time t derived by the hint timing derivation unit 114 since learner A started solving question j (S108). If the measured time has not passed the hint presentation time t (S108: No), the control unit 11 returns to step S107 and continues the measurement operation until the measured time has passed the hint presentation time t. If the measured time has passed the hint presentation time t (S108: Yes), the control unit 11 transmits the extracted hint information j_target to the learner terminal 30 and presents it to learner A (S109), and ends the process. As described above, by controlling the time for presenting hint information according to the predicted probability of correct answer, it is possible to present hint information at a timing appropriate for the learner while he or she is solving a problem, thereby improving the learner's learning efficiency and effectiveness.

[0031] Next, an example of controlling the timing of presenting hint information based on the difficulty level of the question will be described with reference to the flowchart in Fig. 6. Steps S201 to S202 are the same as steps S101 to S102 described above, so detailed description will be omitted.

[0032] The correct answer probability derivation unit 112 calculates the ability score θ of learner A and the difficulty level b of question j based on the answer histories of all the learners, including the answer history of learner A, and the machine learning model. j Here, the correct answer probability derivation unit 112 can derive the predicted correct answer probability of question j using the derived model parameters, but since the predicted correct answer probability is not used here, the predicted correct answer probability is not derived. The hint extraction unit 113 derives the derived ability score θ of learner A and the difficulty level b of question j. j The difference (θ-b j ) is judged against a threshold, and hint information j_target for question j that matches the condition is extracted (S204).

[0033] Figure 9 shows the item characteristic curves that show the results of the IRT analysis. (a) shows the level of difficulty b j If the degree of difficulty is high, j = 1.5, (b) is the difficulty level b j If the degree of difficulty is low, j =-1.5. The horizontal axis shows the learner's ability score, and the vertical axis shows the probability of correct answers. j The higher the difficulty level, the higher the ability score θ required to obtain the same probability of correct answer. j The lower the value of θ, the lower the ability score θ required to obtain the same probability of correct answer. j If the ability score θ is lower than the difficulty score b, the probability of correct answer is low and it is difficult to solve the problem correctly, so more assistance is required. j The difference (θ-b j ) is judged based on a threshold value, and hint information that matches the condition is checked against the hint information storage unit 122 and presented to the learner.

[0034] In Figure 10, the horizontal axis is (θ-b j ) and (θ-b j ) threshold condition. Here, it is assumed that threshold 1 to threshold 3 are set as thresholds. Threshold 1 to threshold 3 represent threshold condition 2 in the threshold table of FIG. 7. Threshold 1 presents hint information of hint ID=1 for the problem of problem ID=1 (θ-b j ) threshold condition, -3<θ-b j ≦-1. Threshold 2 presents hint information with hint ID=2 for problem ID=1 (θ-b j ) is the threshold condition, and -1<θ-b j ≦1. The threshold value 3 presents hint information with hint ID=3 for problem ID=1 (θ-b j ) is the threshold condition, and 1<θ-b j≦3. As mentioned above, the degree of detail of the hint information increases in the order of Hint ID=1<Hint ID=2<Hint ID=3. By presenting hint information with a low degree of detail to learners who have a high ability score relative to the difficulty level and are therefore more likely to arrive at the correct answer, and by presenting hint information with a high degree of detail to learners who have a low ability score relative to the difficulty level and are less likely to arrive at the correct answer, it is possible to improve the learning efficiency and effectiveness of learners.

[0035] In parallel with the extraction of the hint information, the hint timing derivation unit 114 derives the timing for presenting the extracted hint information to the learner (S205). The time t from when the learner A starts solving the problem j to when the hint information is presented is determined by the learner's ability score θ and the difficulty level b j The difference (θ-b j ) is used to derive the equation. For example, (θ-b j ) is set to a fixed value, and the time until the hint information is presented when (θ-b j ) is less than 0, (θ-b j The hint presentation time is calculated by subtracting the value corresponding to the magnitude of (θ-b j ) is greater than 0, (θ-b j The value obtained by adding a value according to the magnitude of (θ-b j ) is equal to or greater than a certain threshold, the control unit 11 may determine that the learner's ability is sufficient to derive the correct answer without the hint information, and may control the display of the hint information even after a certain time has passed.

[0036] Steps S206 to S209, which measure the elapsed time from the start of the practice problem and present the extracted hint information, are the same as steps S106 to S109 of the hint presentation process based on the predicted correct answer probability in FIG. 5, so detailed explanations will be omitted. j The difference (θ-b jBy controlling the time for presenting hint information according to the user's level, it is possible to present hint information at an appropriate timing for the learner while he or she is solving a problem, thereby improving the learner's learning efficiency and effectiveness.

[0037] 5 and 6, the following modifications are possible. In the example of Fig. 5, hint information according to the conditions is extracted by determining the predicted correct answer probability against a threshold in step S104, but instead, hint information according to the conditions may be extracted based on the ability value and difficulty level, which are model parameters, as in step S204 of Fig. 6. Conversely, hint information according to the conditions may be extracted based on the predicted correct answer probability in step S204 of Fig. 6, as in step S104 of Fig. 5.

[0038] 5 and 6, the time until the hint information is presented is fixed to the time derived from the difference between the predicted correct answer probability or the ability score and the difficulty level, but the time may be changed depending on the situation. For example, when the question format requires a written answer, the time from the presentation of the question to the presentation of the hint information is controlled based on the state of the learner's written answer to the question. Here, a written answer is an answer other than a multiple-choice answer selected from options, such as an answer that includes a sentence, a mathematical formula, a chemical formula, etc.

[0039] The control unit 11 of the server 10 acquires the learner's answer to the presented question, input via a touch screen or the like, from the learner's terminal 30 via the network 20. To check the learner's answer entry status, the control unit 11 measures the time from when the question is presented to when the learner's answer is received from the learner's terminal 30. When the measured time has elapsed a predetermined time that does not exceed the hint presentation time derived in step S108 of FIG. 5 and step S208 of FIG. 6, the control unit 11 checks whether the learner's answer has been acquired from the learner's terminal 30. If the answer has not been acquired after the predetermined time has elapsed, i.e., if the answer has not been input, the control unit 11 controls to change the time for presenting hint information to be shorter than the hint presentation time derived in step S108 and step S208. Since it is determined that the learner has not yet found a strategy for solving the problem, the control unit 11 presents hint information early. The learner can find a strategy for solving the problem by looking at the hint information, thereby improving learning efficiency.

[0040] Furthermore, if the server 10 receives the learner's answer within a predetermined time but finds that the degree of match between the learner's answer and the model answer falls below a predetermined percentage when scoring the answer, the server 10 determines that the learner's answer is approaching an incorrect answer and performs control to change the time for presenting the hint information to be shorter than the hint presentation time derived in steps S108 and S208. If the server 10 determines that the learner's answer is approaching an incorrect answer, it shortens the time for presenting the hint information, thereby quickly guiding the learner's answer in the correct direction and improving the learner's learning efficiency. On the other hand, if the server 10 scores the acquired learner's answer and finds that the learner's answer matches the model answer, it determines that the learner's answer is approaching the correct answer and performs control to change the time for presenting the hint information to be longer than the hint presentation time derived in steps S108 and S208. In this way, by extending the time for the learner to continue answering when it is determined that the learner's answering strategy is correct, the learner's comprehension improves. In addition to or instead of controlling to shorten the hint presentation time, if there is hint information that is more detailed than the hint information to be presented, the server 10 may control to present the hint information that is more detailed than the hint information to be presented.

[0041] In the above embodiment, the learner connects to the server 10 from the learner terminal 30 via the network 20, and the server 10 transmits hint information to the learner terminal 30, but this is not limiting. The learner terminal 30 may execute some or all of the processes that the server 10 has executed. In this case, when the control unit 11 of the learner terminal 30 executes processes such as deriving the predicted correct answer probability, deriving the difficulty level, deriving the ability score, and selecting hint information based on the predicted correct answer probability or the difficulty level, the learner terminal 30 corresponds to an "information processing device."

[0042] In the above embodiment, the CPU executes the program stored in the storage unit 12 to function as the control unit 11. However, instead of the CPU executing the program stored in the storage unit 12, dedicated hardware such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or various control circuits may be provided, and the dedicated hardware may function as the control unit 11. In this case, part of the control unit 11 may be realized by the dedicated hardware, and the other part may be realized by software or firmware.

[0043] In the above embodiment, the program may be stored in advance in the storage unit 12. Alternatively, the program may be read from a computer-readable external storage medium (such as a CD (Compact Disc)-ROM, a DVD (Digital Versatile Disc)-ROM, a memory card, or a USB memory) via a storage medium reading unit and stored in the storage unit 12. In addition, the program may be superimposed on a carrier wave and read and stored in the storage unit 12 via a communication medium such as the Internet.

[0044] The present invention allows various embodiments and modifications without departing from the broad spirit and scope of the present invention. Furthermore, the above-described embodiments are intended to explain the present invention and do not limit the scope of the present invention. That is, the scope of the present invention is defined not by the embodiments but by the claims. Various modifications made within the scope of the claims and the meaning of the invention equivalent thereto are considered to be within the scope of the present invention. [Explanation of symbols]

[0045] 1 Information processing system, 10 Server (information processing device), 11 Control unit, 12 Storage unit, 30 Learner terminal (terminal device)

Claims

1. Derive a predicted correct answer probability, which is the predicted probability that the learner will answer the first question correctly; deriving a time difference between a timing at which the first question is presented and a timing at which hint information that is information serving as a hint for the first question is presented based on the predicted correct answer probability; a control unit that controls the display device to present the first question and the hint information to the learner based on the time difference; 1. An information processing device comprising:

2. acquiring an answer history of the learner to questions other than the first question, and deriving the predicted correct answer probability based on the answer history; 2. The information processing apparatus according to claim 1, wherein:

3. Obtain the difficulty level of the first question answered by the learner; a control unit that controls the display of the first question and hint information, which is information that serves as a hint for the first question, to the learner based on a time difference derived based on the difficulty level; 1. An information processing device comprising:

4. the learner's answer to the first question is a written answer, The control unit further acquiring the entry status of the answer of the learner to the first question; changing the time difference based on the acquired entry status; 4. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

5. The control unit If an answer is not input after a predetermined time has elapsed since the first question was presented to the learner, the time difference is changed to be shorter.

5. The information processing apparatus according to claim 4,

6. The control unit determining whether the acquired answer of the learner is approaching a correct answer or an incorrect answer; If it is determined that the answer of the learner is approaching the correct answer, the time difference is changed to be longer; When it is determined that the answer of the learner is approaching an incorrect answer, the time difference is changed to be shorter.

5. The information processing apparatus according to claim 4,

7. The control unit If the predicted correct answer probability exceeds a predetermined threshold, control is performed so that the hint information is not presented to the learner.

3. The information processing apparatus according to claim 1, wherein the information processing apparatus is a computer.

8. The control unit If the difficulty level exceeds a predetermined threshold, control is performed so that the hint information is not presented to the learner.

4. The information processing apparatus according to claim 3,

9. The apparatus of claim 1; a terminal device including a display unit, receiving information from the device of claim 1 and displaying the information on the display unit; An information processing system consisting of:

10. An information processing method executed by a computer of an information processing device, Derive a predicted correct answer probability, which is the predicted probability that the learner will answer the first question correctly; deriving a time difference between a timing at which the first question is presented and a timing at which hint information that is information serving as a hint for the first question is presented based on the predicted correct answer probability; controlling the presentation of the first question and the hint information to the learner based on the time difference; An information processing method comprising:

11. An information processing method executed by a computer of an information processing device, Obtain the difficulty level of the first question answered by the learner; controlling the display of the first question and hint information, which is information that serves as a hint for the first question, to the learner based on a time difference derived based on the difficulty level; An information processing method comprising:

12. A computer provided in the information processing device a process of deriving a predicted correct answer probability, which is the predicted probability that the learner will correctly answer the first question; deriving a time difference between a timing at which the first question is presented and a timing at which hint information serving as a hint for the first question is presented based on the predicted correct answer probability; a process of controlling the presentation of the first question and the hint information to the learner based on the time difference; A program characterized by executing the following.

13. A computer provided in the information processing device A process of obtaining the difficulty level of the first question to be answered by the learner; a process of controlling the first question and hint information, which is information that serves as a hint for the first question, to be presented to the learner based on a time difference derived based on the difficulty level; A program characterized by executing the following.

Images