JP7311212B2 - Information processing device, information processing method and information processing program - Google Patents

Description

Application of Article 30, Paragraph 2 of the Patent Law 1. May 30, 2019 https://www. Kiyo-learning. com/news/20190530. html https://studying. jp/www/20190530_ai. pdf https://studying. jp/ai. 2. May 30, 2019 https://member. studying. jp/login/? Published on page=/shindanshi/ 3. May 30, 2019 https://studying. Announced at jp/shindanshi/ 4. June 8, 2019 Studing Small and Medium Enterprise Management Consultant Course [E-mail Magazine Passed EXPRESS] vol. Announced at 248

The present disclosure relates to an information processing device and an information processing method that support learning.

In recent years, services for delivering courses such as qualification tests via the Internet have become widespread. A learner attends a course within a limited time with the aim of passing the qualification examination.

For example, Patent Literature 1 discloses a technique of "recommending" the learning plan with the longest standard learning time among the learning plans within the learner's remaining studyable time.

JP 2009-47804 A

In general, there are a wide variety of themes that appear in the qualification exam. The themes that are easy to increase the score and the themes that are difficult to increase the score differ depending on the learner. Therefore, with the technology disclosed in Patent Document 1, the learner can grasp the learning plan that can be completed within the remaining learning time, but it is difficult to determine whether the learning plan is effective for the learner. hard to grasp.

SUMMARY OF THE INVENTION Accordingly, it is an object of the present invention to provide a technique for assisting a learner to effectively take a course within a limited time.

The information processing device according to the present disclosure includes an acquisition unit that acquires a study schedule of a learner, a calculation unit that calculates the total study time from the study start date to the study end date based on the study schedule, and the total study time an allocating unit for allocating an allocated learning time to each of a plurality of lessons based on a plurality of lessons, a simulation unit for simulating a learning effect according to the allotted learning time, and an output unit for outputting a result of the simulation by the simulation unit. .

The information processing apparatus and information processing method according to the present disclosure can assist learners in taking effective courses in a limited amount of time by simulating predicted test scores.

FIG. 1 is a block diagram illustrating a configuration example of a server and terminals according to the embodiment. FIG. 2 is a diagram exemplifying a screen regarding essential items according to the embodiment. FIG. 3 is a diagram exemplifying a screen regarding detailed setting of the available learning time according to the embodiment. FIG. 4 is a diagram illustrating a screen regarding optional items according to the embodiment. FIG. 5 is a diagram exemplifying a screen relating to the ability diagnostic test according to the embodiment. FIG. 6 is a diagram illustrating a screen regarding test results according to the embodiment. FIG. 7 is a diagram illustrating a screen regarding simulation results according to the embodiment. FIG. 8 is a diagram illustrating an example of a screen regarding details of simulation results according to the embodiment. FIG. 9 is a diagram illustrating another example of a screen regarding details of simulation results according to the embodiment. 10 is a flowchart illustrating an operation example of the server according to the embodiment; FIG. FIG. 11 is a diagram illustrating a configuration example of a course according to the embodiment; FIG. 12 is a diagram exemplifying a formula for calculating a predicted test score according to the embodiment. FIG. 13 is a diagram exemplifying a lesson-based point allotment table according to the embodiment. FIG. 14 is a diagram illustrating a proficiency curve according to the embodiment; FIG. 15 is a diagram illustrating a predicted test score based on the total standard study time and a predicted test score based on the total standard study time and one credit time according to the embodiment. FIG. 16 is a diagram exemplifying a predicted test score based on the sum of the standard study time and one credit time and a predicted test score based on the sum of the standard study time and two credit hours according to the embodiment. FIG. 17 is a diagram illustrating predicted test scores based on total study time according to the embodiment. 18 is a flowchart illustrating an example of a simulation operation by the server according to the embodiment; FIG. FIG. 19 is a diagram illustrating a simulation example of a predicted score of a test after taking a course taking forgetting into account according to the embodiment; FIG. 20 is a diagram illustrating a simulation example of a predicted score of a test after taking a course considering forgetting according to the embodiment. FIG. 21 is a diagram exemplifying the transition of the expected score for each lesson considering the forgetting curve according to the embodiment. FIG. 22 is a diagram illustrating a screen regarding progress management according to the embodiment.

Hereinafter, embodiments will be described in detail with reference to the drawings.
FIG. 1 is a block diagram showing a configuration example of a server 1 and terminals 2. As shown in FIG.

The server 1 will be explained.
The server 1 can simulate effective course attendance according to the learner before or after applying for attendance at the examination course. The server 1 can also distribute the content of the course to learners who have applied for the course through a network such as the Internet. The server 1 is an example of an information processing device. Here, a certain learner is taken as an example. In the following, a learner is also referred to as a subject. Here, the primary exam for Small and Medium Enterprise Management Consultant will be described as an example of the exam, but the exam is not limited to this. The primary exam for Small and Medium Enterprise Management Consultants is a total of 700 points, with a total of 700 points out of 100 points for each of the seven subjects.

Typically, the server 1 simulates learning effects, as described below. The learning effect is an effect according to the learning that the subject is expected to acquire if it is assumed that the subject has taken the test. Learning effects include predictive test scores. The expected test score is the total test score that the subject is expected to obtain if the subject were to take the test. The predicted test score includes the predicted test score after taking the course. Predicted post-course test score is the total test score that the subject is expected to obtain if the subject were to take the test after taking the last lesson of the course. After taking the course, it may be the day after taking the last lesson. For example, after taking a course, it may be the test date after taking the last lesson. For example, after taking a course may be the day immediately after taking the last lesson. For example, after taking a course may be the day after an arbitrarily set number of days have passed since taking the last lesson. Predicted test scores may include predicted pre-course test scores. Predicted Pre-Course Test Score is the total test score that the subject is expected to obtain if the subject were to take the test prior to the course. Before the course is the point in time before the subject starts taking the course (for example, the first lesson). Before taking a course corresponds to a case where the learning time of the course is 0 hours. The predicted test score may include the predicted test score after taking each lesson. Predicted test score after taking the lesson is the total test score that the subject is expected to obtain if the subject were to take the test after taking the lesson. The learning effect may include the expected score range of the test. The predicted test score range is a range defined by the lower limit and upper limit of the predicted test score. The term forecast is intended to include predictions.

The test may be a test whose final result is pass/fail, or a test whose final result is a score, and is not limited. For example, a pass/fail test is a qualification test. Examinations for conferring qualifications may be examinations for conferring national qualifications or examinations for conferring private qualifications. For example, a test whose final result is a score is a language test. Testing includes tests and certifications, and the like.

Each exam course consists of a number of lessons. Each lesson is an input-learning lesson or an output-learning lesson, respectively. In the following, input learning lessons are also referred to as input lessons. Output learning lessons are also referred to as output lessons. A plurality of lessons constituting a course includes a plurality of input lessons. A plurality of lessons constituting a course includes a plurality of output lessons.

An input lesson is a lesson for the subject to take in knowledge. In one example, the input lesson is a form of attendance on the web. The input lesson may be in the form of learning by watching video or audio. Input lessons may be in the form of lectures using electronic texts on the web. Input lessons may be in the form of lectures that combine viewing video or audio and using digitized texts on the web. In this example, the server 1 can acquire the input lesson attendance time of the subject by taking the subject's attendance log. In another example, the input lesson may be taken in the form of a paper medium text such as a booklet. In this example, the server 1 can acquire the input lesson attendance time of the subject based on the input by the subject.

The output lesson is a lesson for confirming the fixation of knowledge by the subject solving problems. An output lesson may partially include input learning. In one example, the output lesson is a form of attendance by answering questions on the web. In this example, the server 1 can acquire the time spent in the output lesson by the subject and the score the subject earned in the output lesson by logging the subject. In another example, an output lesson is a form of attendance by answering questions in an actual text such as a booklet. In this example, the server 1 can obtain, based on the input by the subject, the time spent in the output lesson by the subject and the score the subject earned in the output lesson. In yet another example, the output lesson is a form of taking a written question or answering a correction assignment. In this example, subjects can submit answers to short-answer or correction tasks online by uploading document data or completing web forms. The instructor grades and corrects the answers online, and can return the grading results to the subject, including the score the subject has earned in the output lesson. The server 1 can acquire the score obtained by the subject in the output lesson based on the online grading by the instructor. The server 1 can acquire the lesson attendance time of the output lesson by the subject based on the input by the subject.

Each lesson is composed according to a set of contents such as a theme. When a course is structured in a form of taking lessons on the web, each lesson is structured so that the time taken by a learner to take one lesson is relatively short. As a result, the subject can efficiently take each lesson using the terminal 2 and using the spare time.

The server 1 includes a processor 11 , a ROM (Read Only Memory) 12 , a RAM (Random Access Memory) 13 , a storage device 14 and a communication interface 15 . The processor 11, ROM 12, RAM 13, storage device 14 and communication interface 15 are connected to each other via a data bus or the like. In FIG. 1, the communication interface is described as "communication I/F".

The processor 11 controls the operation of the server 1 as a whole. For example, the processor 11 is a CPU (Central Processing Unit), but is not limited to this. The processor 11 may be configured with a circuit including a field programmable gate array (Field Programmable Gate Array) or the like. The processor 11 expands a program pre-stored in the ROM 12 or storage device 14 onto the RAM 13 . The processor 11 implements each unit described later and executes various operations by executing the program developed in the RAM 13 .

The ROM 12 is a non-volatile memory that stores control programs and control data in advance.

The RAM 13 is a volatile memory that temporarily stores data being processed by the processor 11 .

The storage device 14 is a device composed of a non-volatile memory that stores data, programs, and the like. For example, the storage device 14 is configured by an HDD (Hard Disk Drive) or an SSD (Solid State Drive), but is not limited to these. The storage device 14 stores programs executed by the processor 11 .

The communication interface 15 is an interface for wired or wireless communication. For example, the communication interface 15 includes interfaces compatible with various wired or wireless standards. A communication interface 15 enables communication between the server 1 and the terminal 2 .

Note that the hardware configuration of the server 1 is not limited to the configuration described above. The server 1 allows omission and modification of the above components and addition of new components as appropriate.

Each unit implemented in the processor 11 will be described.
The processor 11 includes an input item output unit 111, an input information acquisition unit 112, a test output unit 113, an answer information acquisition unit 114, a test result output unit 115, a calculation unit 116, an allocation unit 117, an acquisition unit 118, a simulation unit 119, and a simulation unit. A result output unit 120 is implemented.

The input item output unit 111 outputs data regarding input items to the terminal 2 via the communication interface 15 in response to a simulation start request from the subject. The request to start the simulation by the subject may be made before applying for the course or after applying for the course. The subject may request to start the simulation after applying for the course, before taking the course, or during the course. In the following, data relating to input items are also referred to as input item data.

The input item data is data related to display including input fields for allowing the subject to input information for each item. Input item data is an example of display data. The input item data includes data on mandatory items and data on optional items. In the following, data relating to mandatory fields are also referred to as mandatory field data. Data relating to optional items is also referred to as optional item data.

The required item data is data related to display including input fields for required items. A mandatory item is an item that must be input by the subject. The required items include a "target qualification" item, a "pass target test" item, and an "allowable study time" item. The "target qualification" item is an item for inputting qualifications to be taken for the examination. The "passing target test" item is an item for inputting the scheduled time to take the test entered in the "target qualification" item. The scheduled exam time is the timing of the exam that the subject is planning to take. The item "test for passing target" may also serve as an input for a course that has already been applied for or is scheduled to be applied for. The item "learnable time" is an item for inputting the number of hours the subject can study. In one example, the item "Available hours for learning" is an item for inputting the number of hours each of weekdays and weekends (days other than weekdays) that can be learned. In another example, the item "available hours for learning" is an item for inputting the number of hours available for learning for each day of the week. The item "Available hours for learning" may allow changing the number of hours available for learning on a daily basis.

The optional item data is data relating to display including input fields for optional items. An optional item is an item that is arbitrarily entered by the subject. Optional items are items related to attributes of the subject. For example, optional items include ``Previous exam experience'', ``Previous learning experience'', ``Existence of study companions'', ``Other qualifications'', ``Occupation'', ``Lifestyle'', and `` "Personality diagnosis" items, etc., but are not limited to these.

The "previous test experience" item is an item for inputting the test experience input in the "target qualification" item. For example, the "previous exam experience" item includes items such as the presence or absence of exam experience, exam timing, and subject scores at the time of the exam. The "previous learning experience" item is an item for inputting the learning experience of the exam entered in the "target qualification" item. For example, the "previous learning experience" item includes items such as the presence or absence of learning experience, subject level self-evaluation, and the like. The item "presence of study companions" is an item for inputting the presence or absence of study companions. The "Other Acquired Qualifications" item is an item for entering qualifications that have already been acquired through examinations other than the examinations entered in the "Target Qualifications" item. The "occupation" item is an item for inputting the subject's occupation. The "lifestyle" item is an item for inputting the subject's lifestyle. For example, the lifestyle is the time to wake up and the time to go to bed. The "personality diagnosis" item is an item for inputting the subject's personality.

The input information acquisition unit 112 acquires the required item input information from the terminal 2 via the communication interface 15 . The required item input information is input information for the required items entered by the learner on the required item screen displayed on the terminal 2 based on the required item data. The required item input information includes input information for the "target qualification" item, input information for the "pass target test" item, and input information for the "allowable study time" item. The input information for the item "Available time to study" can also be said to be the subject's study schedule. The input information acquisition unit 112 stores the required item input information in the storage device 14 .

The input information acquisition unit 112 acquires optional item input information from the terminal 2 via the communication interface 15 . The optional item input information is input information for optional items input by the learner on the optional item screen displayed on the terminal 2 based on the optional item data. The input information acquisition unit 112 stores the optional item input information in the storage device 14 .

The test output unit 113 outputs data related to the ability diagnosis test to the terminal 2 via the communication interface 15 . In the following, data relating to proficiency tests are also referred to as proficiency test data. The ability diagnosis test is a test for diagnosing the ability of the subject before taking the course. For example, the ability diagnostic test includes a plurality of questions for each subject in order to diagnose ability for each subject. Note that the ability diagnosis test may include all the theme questions that appear in the actual exam for each subject, or may omit one or more theme questions. For example, the ability diagnosis test is a test with a total of 700 points, 100 points for each of seven subjects. The ability diagnostic test data is data relating to display including input fields for inputting questions and answers of the subject to the questions. For example, the question is alternative. The input field includes options that are candidate answers to the question. The input field may include an option that the answer is not known. As a result, it is possible to reduce the possibility that the target person forcibly selects an option that is an answer candidate for the question. As a result, the diagnostic accuracy of the subject's ability by the ability diagnosis test is improved. The ability diagnosis test data is an example of display data. The ability diagnostic test data may include, in addition to the data of the normal version of the test, the data of the simplified version of the test with fewer questions than the normal version.

The answer information acquisition unit 114 acquires answer information from the terminal 2 via the communication interface 15 . The answer information is information indicating the answer of the ability diagnosis test input by the learner on the screen of the ability diagnosis test displayed on the terminal 2 based on the ability diagnosis test data.

The test result output unit 115 calculates test results as exemplified below, and outputs data regarding the test results to the terminal 2 via the communication interface 15 .
An example of test result calculation by the test result output unit 115 will be described. First, the test result output unit 115 determines whether the subject's answer is correct or incorrect based on the answer information. Next, the test result output unit 115 calculates the result of the ability diagnostic test based on the correctness of the answers. The results of the ability diagnosis test include the score for each subject (score out of 100 points) and the total score for each subject (score out of 700 points). Next, the test result output unit 115 calculates the predicted score for each subject before taking the course (predicted score out of 100 points) in consideration of the relationship between the difficulty level of the ability diagnosis test and the difficulty level of the actual test. calculate. The predicted score for each subject before taking the course is the test score for each subject that the subject is expected to obtain if it is assumed that the subject has taken the exam before attending the course. Note that if the ability diagnostic test does not include one or more thematic questions that are set in the actual exam for each subject, the test result output unit 115 supplements as appropriate and predicts the score for each subject before taking the course. may be calculated. Next, the test result output unit 115 adds up the predicted scores for each subject before attending the course, and calculates the predicted score of the test before attending the course (predicted score out of 700 points).

The test results include predicted test scores before taking the course and predicted scores for each subject before taking the course. The test results may include the results of the ability diagnosis test instead of the predicted scores of the test before taking the course and the predicted scores for each subject before taking the course. In the following, data relating to test results are also referred to as test result data. The test result data is data relating to the display of the results of the ability diagnosis test. Test result data is an example of display data.

As exemplified below, the calculation unit 116 calculates the total learning time from the learning start date to the learning end date based on the input information for the “learnable time” item. The total study time is the sum of the number of studyable hours per day from the study start date to the study end date. First, the calculation unit 116 identifies the learning start date. For example, the calculation unit 116 sets a predetermined date such as the current date or the day after the current date as the learning start date. Alternatively, the calculation unit 116 may set the date set by the subject as the learning start date. Next, the calculation unit 116 identifies the study end date. For example, the calculation unit 116 sets a predetermined date such as the day or the day before the test to be taken based on the information input in the “passing target test” item as the learning end date. Alternatively, the calculation unit 116 may set the date set by the subject as the learning end date. Next, the calculation unit 116 calculates the total study time by totaling the number of studyable hours for the period from the study start date to the study end date, based on the input information for the “learnable time” item. The total study time calculated by the calculator 116 is the total study time based on the subject's study schedule. Hereinafter, the total study time based on the subject's study schedule is also simply referred to as "total study time".

The allocation unit 117 allocates study time to each of the plurality of lessons included in the course based on the total study time. In the following, the study time assigned to each lesson is also referred to as assigned study time. Finally, the allocation unit 117 allocates the total learning time to each lesson, and allocates the allocated learning time to each lesson so that the sum of the allocated learning time of each lesson is the total learning time. In a typical example, the allocation unit 117 allocates the allocated learning time to each lesson so that the predicted score of the exam after taking the course is maximized under the condition that the sum of the allocated learning time of each lesson is the total learning time. The allocation unit 117 operates in cooperation with the acquisition unit 118 and the simulation unit 119 . An operation example of the allocation unit 117 will be described later.

Acquisition unit 118 acquires the result of the lesson according to the allotted learning time of each lesson. A lesson outcome is a predicted outcome obtained by the subject taking the lesson. In the following, lesson outcomes are also referred to as lesson outcomes. The lesson outcomes are used to simulate expected test scores. For example, the lesson result is represented by a score out of 100 points. If the lesson is an output lesson, the lesson outcome is obtainable for each output lesson according to the allotted study time, depending on the relationship between the study time for each output lesson and the score expected to be obtained by the learner for each output lesson. It is a score that is predicted to be. In the following, the expected score obtainable for the output lesson is also referred to as the expected score for the output lesson. If the lesson is an input lesson, the lesson outcome is 0 points. This is because active learning such as output learning tends to contribute more to actual test scores than passive learning such as input learning. It should be noted that the input lessons contribute to some extent to the actual exam scores as they are used by the subject to capture knowledge. Therefore, if the lesson is an input lesson, the lesson outcome may be given a score other than 0 points. The score given as a lesson result may be different for each input lesson. The score given as the lesson result may differ according to the length of the allotted learning time. Acquisition unit 118 operates in cooperation with allocation unit 117 and simulation unit 119 . An operation example of the acquisition unit 118 will be described later.

The simulation unit 119 simulates learning effects according to the allotted learning time for each lesson. In a typical example, the simulation unit 119 simulates the learning effect based on the lesson results corresponding to the allotted learning time for each lesson. Ultimately, the simulation unit 119 simulates the learning effect under the condition that the total learning time assigned to each lesson is the total learning time. Hereinafter, the learning effect under the condition that the total learning time assigned to each lesson is equal to the total learning time is also referred to as the learning effect based on the total learning time. In the following, the predicted test score will be described as an example of the learning effect. The simulation unit 119 simulates the predicted score of the exam after taking the course based on the total study time. In a typical example, the simulation unit 119 simulates the maximum predicted score of the exam after taking the course based on the total study time. The simulation unit 119 may simulate the predicted score of the test before taking the course based on the total study time. The simulation unit 119 may simulate the predicted score of the test after taking each lesson based on the total study time. The simulation unit 119 may simulate the predicted score range of the test based on the total study time. The simulation unit 119 may set a score obtained by subtracting a predetermined number of points from the predicted test score based on the total study time as the lower limit value, and may set a score obtained by adding a predetermined number of points to the predicted test score based on the total study time as the upper limit value. The predetermined number of points can be set arbitrarily. The simulation unit 119 operates in cooperation with the allocation unit 117 and the acquisition unit 118 . An example of operation by the simulation unit 119 will be described later.

The simulation unit 119 may simulate the learning effect under the condition that the total learning time allocated for each lesson is different from the total learning time. Hereinafter, the learning effect under the condition that the sum of the assigned learning time for each lesson is the other total learning time is also referred to as another learning effect based on the other total learning time. For example, the simulation unit 119 simulates a predicted score for a test based on another total study time. In this example, first, allocation section 117 sets one or more other total learning times. The allocation unit 117 may obtain another total learning time longer than the total learning time. The simulation unit 119 may obtain another total learning time shorter than the total learning time. Next, the allocating unit 117 allocates the allocated learning time to each lesson so that the total of the allocated learning time of each lesson becomes another total learning time. In a typical example, the allocating unit 117 allocates learning time to each lesson so that the predicted score of the exam after taking the course is maximized under the condition that the sum of the allocating learning time of each lesson is equal to the total learning time of other lessons. assign. Next, the obtaining unit 118 obtains the lesson result corresponding to the allotted study time for each lesson. Next, the simulation unit 119 simulates test scores based on other total study times according to the assigned study time of each lesson. The simulation unit 119 simulates the predicted score of the exam after taking the course based on other total study hours. In a typical example, the simulation unit 119 simulates the maximum value of the predicted score of the exam after taking the course based on other total study hours. The simulation unit 119 may simulate the predicted score of the exam before taking the course based on other total study hours. The simulation unit 119 may simulate the predicted score of the test after taking each lesson based on another total study time. Note that the simulation unit 119 may simulate another predicted score range of the test based on the total study time.

The simulation result output unit 120 outputs data regarding the simulation result by the simulation unit 119 to the terminal 2 via the communication interface 15 . Simulation results include learning effects based on total learning time. For example, simulation results include predicted test scores based on total learning time. Simulation results include predicted post-course test scores based on total learning time. Typically, the predicted post-course test score based on total study time is the maximum of the predicted post-course test scores based on total study time. The simulation results may include an increase or decrease value of a predetermined number of points centered on the predicted score of the exam after taking the course based on the total study time. The predetermined number of points can be set arbitrarily. The simulation results may include a predicted post-course test score range based on total study time instead of a predicted post-course test score based on total study time. The simulation results may include a predicted pre-course test score based on total study time. Simulation results may include a predicted test score after each lesson based on total study time.

The simulation results include the allotted learning time for each lesson based on the total learning time. In a typical example, the simulation results include the allotted learning time for each lesson that maximizes the predicted score for the post-course exam under the condition that the sum of the allotted learning time for each lesson equals the total learning time. .

Simulation results may include other learning effects based on other total learning time. For example, simulation results include predicted scores for exams based on other total learning hours. Simulation results include predicted scores for post-course exams based on other total study hours. Typically, the predicted post-course test score based on other total study time is the maximum of the predicted post-course test scores based on other total study time. The simulation results may include a predetermined score increase or decrease value centered on the predicted score of the post-course exam based on other total study hours. The predetermined number of points can be set arbitrarily. The simulation results may include a range of predicted post-course test scores based on other total study hours instead of predicted post-course exam scores based on other total study hours. Simulation results may include predicted scores for pre-course tests based on other total learning hours. Simulation results may include predicted scores for exams after taking each lesson based on other total study hours.

The simulation results include the allotted learning time for each lesson based on other total learning times. In a typical example, the simulation result is the allotted study time for each lesson that maximizes the predicted score for the post-course exam under the condition that the sum of the allotted study time for each lesson is the total study time for all other lessons. including.

In the following, data on simulation results are also referred to as simulation result data. The simulation result data is data relating to the display of simulation results. Simulation result data is an example of display data.

Terminal 2 will be described.
The terminal 2 can provide the server 1 with information used in the simulation by the server 1 before or after applying for the course. The terminal 2 may be used for taking a course by a subject. For example, the terminal 2 is a PC (Personal Computer), but may be a smart phone, a tablet, or the like, and is not limited to these. The terminal 2 may display using a web browser, or may display using an application.

The terminal 2 includes a processor 21 , ROM 22 , RAM 23 , storage device 24 , communication interface 25 , input device 26 and display device 27 . The processor 21, ROM 22, RAM 23, storage device 24, communication interface 25, input device 26 and display device 27 are connected to each other via a data bus or the like. In FIG. 1, the communication interface is described as "communication I/F".

Processor 21 controls the overall operation of terminal 2 . The processor 21 is configured with the same hardware as the processor 11 described above. The processor 21 implements each unit described later and executes various operations by executing the program developed in the RAM 23 .
The ROM 22 is configured with the same hardware as the ROM 12 described above.
The RAM 23 is configured with the same hardware as the RAM 13 described above.
The storage device 24 is configured with the same hardware as the storage device 14 described above. The program may be downloaded to terminal 2 via a network. The program may be one stored in a computer-readable storage medium such as a CD-ROM and installed in the terminal 2 .
The communication interface 25 is configured with the same hardware as the communication interface 15 described above.
The input device 26 is a device that receives an instruction based on an operation by the subject. For example, input device 26 may be, but is not limited to, a keyboard or touchpad.
The display device 27 is a device that displays various screens. For example, the display device 27 is a liquid crystal display, but is not limited to this. The display device 27 is an example of a display section.
Note that the hardware configuration of the terminal 2 is not limited to the configuration described above. The terminal 2 allows omission and modification of the above components and addition of new components as appropriate.

Each unit implemented in the processor 21 will be described.
The processor 21 implements an acquisition unit 211, a display control unit 212, and an output unit 213 by executing programs.

The acquisition unit 211 acquires various display data from the server 1 via the communication interface 25 . For example, the acquisition unit 211 acquires input item data from the server 1 . For example, the acquisition unit 211 acquires ability diagnostic test data from the server 1 . For example, the acquisition unit 211 acquires test result data from the server 1 . For example, the acquisition unit 211 acquires simulation result data from the server 1 .

The display control unit 212 causes the display device 27 to display various screens based on various display data. For example, the display control unit 212 causes the display device 27 to display the required item screen based on the required item data included in the input item data. Screen examples of essential items will be described later. For example, the display control unit 212 causes the display device 27 to display a screen of optional items based on optional item data included in the input item data. Screen examples of optional items will be described later. For example, the display control unit 212 causes the display device 27 to display the screen of the ability diagnosis test based on the ability diagnosis test data. A screen example of the ability diagnosis test will be described later. For example, the display control unit 212 causes the display device 27 to display a test result screen based on the test result data. An example of the test result screen will be described later. For example, the display control unit 212 causes the display device 27 to display a simulation result screen based on the simulation result data. A screen example of the simulation result will be described later.

The output unit 213 outputs information input by the learner on various screens to the server 1 via the communication interface 25 . For example, the output unit 213 outputs the required item input information input by the learner on the required item screen to the server 1 . For example, the output unit 213 outputs to the server 1 optional item input information input by the learner on the optional item screen. For example, the output unit 213 outputs the answer information input by the learner on the screen of the ability diagnostic test to the server 1 .

A screen example of the essential items described above will be described.
The acquisition unit 211 acquires input item data output from the input item output unit 111 of the server 1 from the server 1 . The display control unit 212 causes the display device 27 to display the required item screen based on the required item data included in the input item data.

FIG. 2 is a diagram illustrating a screen regarding essential items.
The screen related to the required items displays input fields for the items "Eligibility,""Passing target test," and "Available study time." Here, it is assumed that the target person has entered a Small and Medium Enterprise Management Consultant in the entry field of the "target qualification" item. It is assumed that the subject has entered the October 2020 exam in the input field of "passing target exam".

A display example of the input field for the item "learnable time" will be described.
The screen related to essential items displays input fields for the number of hours available for study in the morning, daytime, and evening for weekdays and weekends (days other than weekdays). Additionally or alternatively, the mandatory items screen displays input fields for the number of hours available for study in the morning, day, and evening for each day of the week.

FIG. 3 is a diagram exemplifying a screen for detailed setting of the available learning time.
For example, the screen regarding the detailed setting of the available study time may be transitioned based on the subject's clicking of the "Enter detailed schedule in the calendar" button on the screen regarding the required items illustrated in FIG. The screen for detailed settings of available time for learning reflects the information entered in the entry field for the item "available time for learning" shown in FIG. The learner can change the number of hours that can be learned for each day by clicking the cell of each day on the calendar.
The output unit 213 outputs required item input information to the server 1 based on completion of input by the learner on the screen regarding required items.

Screen examples relating to the optional items described above will be described.
FIG. 4 is a diagram illustrating a screen regarding optional items.
For example, the display control unit 212 displays a screen related to optional items based on optional item data included in the input item data based on the click of the "proceed to next" button on the screen related to essential items illustrated in FIG. 27.
The screen for optional items displays input fields such as "Previous Test Experience" item and "Previous Study Experience" item. The entry field for the "previous examination experience" item includes entry fields for items such as the presence or absence of examination experience, the timing of the examination, and the score for each subject at the time of the examination. On the optional item screen, the entry field for the "previous learning experience" item includes items such as the presence or absence of learning experience and self-evaluation levels for each subject.
The output unit 213 outputs optional item input information to the server 1 based on completion of input by the learner on the screen regarding the optional item.

An example of a screen relating to the ability diagnosis test described above will be described.
The acquisition unit 211 acquires from the server 1 the ability diagnosis test data output from the test output unit 113 of the server 1 . The display control unit 212 causes the display device 27 to display a screen regarding the ability diagnosis test based on the ability diagnosis test data.

FIG. 5 is a diagram exemplifying a screen relating to the ability diagnosis test.
For example, the screen regarding the ability diagnosis test may transition from the screen regarding the optional item illustrated in FIG.
Here, the screen regarding the ability diagnosis test is displayed so that the normal version of the test or the simplified version of the test can be selected.
The output unit 213 outputs the answer information to the server 1 based on the completion of input by the learner on the screen regarding the ability diagnosis test.

A screen example relating to the test results described above will be described.
The acquisition unit 211 acquires from the server 1 the test result data output from the test result output unit 115 of the server 1 . The display control unit 212 causes the display device 27 to display a screen regarding the results of the ability diagnosis test based on the test result data.

FIG. 6 is a diagram illustrating a screen regarding test results.
For example, the screen regarding test results may transition from the screen regarding arbitrary items illustrated in FIG.
The test result screen displays the predicted score (318 points) of the pre-course test out of a maximum of 700 points. The test result screen displays the predicted score for each subject before taking the course, which is a breakdown of the predicted score for the exam after taking the course. Instead of the predicted score of the test before taking the course and the predicted score for each subject before taking the course, the test result screen shows the result of the ability diagnosis test itself (score by subject (score out of 100 points) and (score out of 700 points)) may be displayed.

Some examples of screens relating to the above simulation results will now be described.
The acquisition unit 211 acquires from the server 1 the simulation result data output from the simulation result output unit 120 of the server 1 . The display control unit 212 causes the display device 27 to display a screen regarding the simulation result based on the simulation result data.

FIG. 7 is a diagram showing an example of a screen regarding simulation results.
For example, the screen regarding the simulation result illustrated in FIG. 7 may be changed based on the subject's clicking of the "proceed to simulation result" button on the screen regarding the test result illustrated in FIG.

The simulation result screen displays the "Simulation 1" column for the total learning time. The "simulation 1" column includes columns of "total learning time", "passing target", "predicted score", and "predicted passing rate". The "total study time" column displays the total study time (780 hours). The "passing target" column displays the scheduled examination time (2020 exam) entered by the subject in the above-mentioned "passing target test" item. The "predicted score" column displays the predicted score (400 points) of the exam after taking the course based on the total study time. In the "predicted score" column, instead of the predicted score of the exam after taking the course based on the total learning time, a predetermined increase or decrease value (for example, 400 ±20 points) may be displayed. The "predicted score" column displays the predicted score range (for example, 380-420 points) of the exam after taking the course based on the total study time instead of the expected score of the exam after taking the course based on the total study time. good too. The "predicted pass rate" column displays the pass rate (25%). The pass rate may be simulated by the simulation unit 119 based on the predicted score of the test after taking the course, the passing score of the test, and the like. By confirming the learning effect based on the total study time, the subject can grasp the test results expected to be obtained by effectively attending the course in the total study time.

The simulation results screen can display other information about the total learning time. In the example of FIG. 7, the simulation result screen displays information about three other total study times, but may display information about one, two, or four or more other total study times. The "Simulation 2" column includes columns for "Total Other Learning Time", "Predicted Score", and "Predicted Pass Rate". The "total other study hours" column displays other total study hours (900 hours). The "predicted score" column displays the predicted score (420 points) of the exam after taking the course based on other total study hours. In the "predicted score" column, instead of the predicted score of the exam after taking the course based on another total study time, the value of a predetermined increase or decrease in points centered on the predicted score of the exam after taking the course based on another total study time (eg, 420±20 points) may be displayed. In the "predicted score" column, instead of the predicted score of the exam after taking the course based on another total study time, the expected score range of the exam after taking the course based on other total study time (for example, 400-440 points) may be displayed. The "predicted pass rate" column displays the pass rate (35%). The "Simulation 3" column and the "Simulation 4" column are the same as the "Simulation 2" column. By confirming the other learning effects based on the other total study hours, the subject can grasp the test results expected to be obtained by effectively taking the course in the other total study hours. This allows the subject to behave appropriately, such as spending more time studying to pass the exam.

FIG. 8 is a diagram showing an example of a screen regarding details of simulation results.
For example, the screen regarding the details of the simulation result illustrated in FIG. 8 may transition based on the click of the “select” button by the subject on the screen regarding the screen simulation result illustrated in FIG. 7 .

The screen regarding the simulation results illustrated in FIG. 8 displays information regarding some lessons that constitute the subject 1 "Corporate Management Theory" among the SME management consultants. The column for each lesson includes columns for "Allocated Study Time" and "Predicted Score". The "allocated learning time" column displays the allocated learning time for each lesson. The "predicted score" column is the predicted score of the exam after taking the lesson. For example, in the lesson "Smart question collection: 1-1 Overview of management and strategy", the "predicted score" column displays 319 points, which is the predicted score of the exam after taking this lesson. The score displayed in the "predicted score" column increases as the lesson progresses to the second half. Therefore, the score displayed in the "predicted score" column of the last lesson that constitutes the course corresponds to the expected score of the exam after taking the course. By checking the allotted learning time for each lesson, the subject can grasp how much time should be spent on each lesson in order to effectively take the course.

FIG. 9 is a diagram showing another example of a screen regarding details of simulation results.
For example, the screen regarding the details of the simulation result illustrated in FIG. 9 may transition from the screen illustrated in FIG.

The simulation result screen illustrated in FIG. 9 displays a cell for each day of the calendar and displays lesson assignments for each day. Each day's cell displays available study time and lesson name. The available study time for each day is based on the input information for the “available study time” item of the required input items. Each lesson is assigned to each day according to a predetermined taking order so that the sum of the assigned learning time of one or more lessons assigned to each day is equal to or less than the available learning time of the corresponding day. The target person can easily grasp when and which lesson should be taken.

An operation example of the server 1 will be described.
FIG. 10 is a flowchart showing an operation example of the server 1. FIG. Note that one or more operations shown in FIG. 10 may be changed or omitted as appropriate.

The processor 11 acquires a simulation start request from the terminal 2 via the communication interface 15 (step S101). The input item output unit 111 outputs the input item data to the terminal 2 via the communication interface 15 (step S102). The input information acquisition unit 112 acquires the required item input information from the terminal 2 via the communication interface 15 (step S103). The input information acquisition unit 112 acquires the optional item input information from the terminal 2 via the communication interface 15 (step S104). It should be noted that if the optional item has not been input by the subject, the input information acquiring unit 112 omits the process of step S104.

The test output unit 113 outputs the ability diagnosis test data to the terminal 2 via the communication interface 15 (step S105). The answer information acquisition unit 114 acquires answer information from the terminal 2 via the communication interface 15 (step S106). The test result output unit 115 outputs the test result data to the terminal 2 via the communication interface 15 (step S107). The calculation unit 116 calculates the total learning time from the learning start date to the learning end date based on the input information for the "learnable time" item included in the required item input information (step S108).

The allocation unit 117 allocates the allocated study time to each of the plurality of lessons based on the total study time (step S109). The acquiring unit 118 acquires the lesson result corresponding to the allotted study time for each lesson (step S110). The simulation unit 119 simulates the learning effect based on the lesson results corresponding to the allotted learning time for each lesson (step S111). The simulation result output unit 120 outputs the simulation result data to the terminal 2 via the communication interface 15 (step S112).

According to the embodiment, the server 1 can support the subject to effectively take the course within the limited time by simulating the learning effect based on the total learning time. In addition, the server 1 can support more effective course attendance by simulating the predicted score (preferably the maximum score) of the exam after taking the course based on the total study time.

A simulation example of a predicted test score will be described.
First, a configuration example of a course to be simulated will be described.
FIG. 11 is a diagram showing a configuration example of a course. Here, the course of the small and medium enterprise management consultant is taken as an example and explained.

A course consists of a plurality of (m) lessons. Numbers 1 to m shown in FIG. 11 indicate lesson numbers. The lesson numbers correspond to the order in which they were taken. Multiple lessons include multiple input lessons. Multiple lessons include multiple output lessons. The course is divided into 7 subjects from 1 to 7. Each subject consists of multiple lessons. Subject 1 consists of 12 lesson units from "1-1" to "1-12". A lesson unit is a group divided according to the subject 1 theme. Each lesson unit consists of one input lesson and two output lessons. "I" in FIG. 11 indicates an input lesson. "O" in FIG. 11 indicates an output lesson. "O1" in FIG. 11 indicates an output lesson containing basic questions. For example, the base problem is the original problem. "O2" in FIG. 11 indicates an output lesson containing past questions. "O1" and "O2" may be divided according to the degree of difficulty. Each lesson unit may contain more than one input lesson, or no input lesson at all. Each lesson unit may contain one output lesson, or three or more output lessons.

Next, the formula for calculating the predicted test score will be described.
FIG. 12 is a diagram illustrating a formula for calculating the predicted test score.
The formulas for calculating the predicted test score are shown in formulas (1) to (4).

Predicted score for each lesson unit = Simple average of predicted scores for each output lesson included in the lesson unit Equation (1)
Predicted score after rate adjustment = Predicted score for each lesson unit x percentage of allotted points...Formula (2)
Predicted score by subject = Sum of predicted scores by subject after rate adjustment (Equation (3))
Predicted Test Score = Total Predicted Score by Subject Equation (4)

The predicted score of the output lesson in Equation (1) is determined based on the allotted learning time of the output lesson and the proficiency curve described later. The predicted score of the output lesson changes according to the allotted study time, as will be described later. For example, the predicted score for an output lesson is the predicted score out of 100 possible points.
The predicted score for each lesson unit in formulas (1) and (2) is a predicted score obtained by simply averaging the predicted scores of each output lesson included in the lesson unit. For example, the predicted score for each lesson unit is a predicted score out of 100 points.
The percentage of allotted points in Equation (2) is the percentage of allotted points assigned to the theme of each lesson unit to the full score (100 points) of the subject. The allotted points ratio is managed by a lesson-by-lesson point allotted table, which will be described later.
The rate-adjusted predicted score in formulas (2) and (3) is the predicted score for each lesson unit after adjusting the predicted score for each lesson unit according to the allocation ratio.
The predicted scores by subject in equations (3) and (4) are obtained by summing the proportion-adjusted predicted scores and are the predicted scores for subjects that the subject is expected to achieve. For example, the predicted score for each subject is the predicted score out of 100 points.

As can be seen from equations (1)-(4), taking an output lesson contributes to the predicted test score. Therefore, if the allotted learning time for one output lesson changes, the predicted score for this output lesson will change, and as a result, the predicted score for the exam will also change.

In equation (1), the predicted score for each lesson unit is a simple average of the predicted scores of each output lesson included in the lesson unit, but it is not limited to this.
In one example, the predicted score for each lesson unit may be obtained by correcting each output lesson predicted score with a coefficient and simply averaging the corrected predicted scores of each output lesson. The coefficient is set in consideration of the relationship between the difficulty level of the output lesson and the difficulty level of the actual exam. For example, the coefficient of past question output lessons may be greater than the coefficient of basic question output lessons. The coefficients of the basic questions and the coefficients of the past questions may be shared between lesson units, or may be set for each lesson unit. This improves the simulation accuracy of the test score predictions.

In another example, a predicted score for each lesson unit may be derived using a machine learning predictive model. The explanatory variable of the prediction model is the predicted score of each output lesson included in the lesson unit, and the objective variable is the score of the lesson unit. For example, the processor 11 may generate a prediction model in advance by machine learning using data of a plurality of learners including predicted scores of each output lesson and scores of practice tests or actual test scores. Note that the processor 11 may update the prediction model as appropriate. This improves the simulation accuracy of the test score predictions.

Note that, in formula (1), taking input lessons is not taken into account. This is because taking an input lesson tends to be less reflected in actual test scores than taking an output lesson. However, because the input lessons are used by the subject to capture knowledge, they contribute to some extent to the actual exam scores. Therefore, equation (1) may be modified so that the attendance of each input lesson included in the lesson unit contributes to the predicted score for each lesson unit. In this example, the points given to each input lesson may be appropriately set according to the length of the allotted learning time.

Next, the point allocation table for each lesson will be described. The lesson-by-lesson point allocation table shows the percentage of allotted points assigned to the theme of each lesson unit with respect to the full score (100 points) of the subject. In the following, the allotted points ratio is also referred to as the allotted points ratio. The storage device 14 stores a lesson-based point allotment table for each subject.

FIG. 13 is a diagram exemplifying a lesson-by-lesson point allotment table for subject 1. As shown in FIG.
The lesson-by-lesson point allocation table for subject 1 associates the lesson units of "1-1" to "1-12" with the allocation ratio. In the subject 1 lesson-by-lesson point allocation table, a theme that is not mentioned in any of the lesson units "1-1" to "1-12" is set as "other", and the "other" is associated with the allocation ratio. The percentage of allotted points may be determined based on the number of questions with reference to the past questions, or may be determined based on the allotted points with reference to the past questions. The lesson-by-lesson point allotment table for subject 1 may be updated as appropriate. Although the lesson point allocation table for subject 1 has been described as an example, the lesson point allocation tables for subjects 2 to 7 are configured in the same manner as the lesson point allocation table for subject 1 .

Next, the proficiency curve will be explained. The proficiency curve is a curve showing the relationship between the learning time of the output lesson and the predicted score of the output lesson.

FIG. 14 is a diagram illustrating a proficiency curve.
The horizontal axis indicates the learning time of the output lesson. The vertical axis indicates the predicted score of the output lesson. The upper limit of predicted scores for output lessons is 100 points. In a typical proficiency curve, as exemplified in FIG. 14, the increase effect (growth rate) of the predicted score per predetermined period of time soon after the start of learning is large. As time elapses from the start of learning, the predicted score itself increases, but the effect of increasing the predicted score per predetermined period of time decreases. Ultimately, the predicted score remains a certain score no matter how long the learning time is. Alternatively, the predicted score reaches a perfect score at a certain timing, and remains perfect no matter how long the learning time is. Thus, the effect of increasing the predicted score becomes smaller as time passes from the start of learning.

A proficiency curve is created by processor 11 for each output lesson, as described below. First, the processor 11 obtains the predicted score of each output lesson when the learning time is 0 hours. For example, the processor 11 can determine the predicted score for each output lesson when the study time is 0 hours based on the test results. In this example, the processor 11 adjusts the predicted score of the exam when the learning time is 0 hours, which is obtained using the formulas (1) to (4), to match the predicted score of the pre-course exam based on the ability diagnostic test. Next, find the predicted score for each output lesson when the learning time is 0 hours. The predicted score for each output lesson when the learning time is 0 hours may be the same for each output lesson, but may also be different. For a plurality of output lessons included in a lesson unit, the predicted score of each output lesson when the learning time is 0 hours may be the same.

Processor 11 then sets the trajectory of the proficiency curve. For example, the simulation unit 119 may set the trajectory of the proficiency curve based on the optional item input information. In one example, processor 11 may use a predictive model based on machine learning to set the trajectory of the proficiency curve based on optional input information. In this example, the processor 11 uses machine learning based on the past learning histories of all or a plurality of students, past score histories, attributes specified in arbitrary item input information, etc., as the learning time increases. A predictive model of the proficiency curve can be generated that predicts how much the predicted score of the output lesson will improve. For example, the past learning history includes the learning time of each output lesson. For example, past score history includes scores for each output lesson, and so on. Processor 11 may update the prediction model accordingly.
In another example, the processor 11 may refer to a database that associates the optional item input information with the trajectory of the proficiency curve, and select the proficiency curve from the database based on the subject's optional item input information. In this example, a database may be prepared for each output lesson. Processor 11 may search a database for optional inputs that match or are similar to the subject's optional inputs and select a proficiency curve from the database.

Attributes specified in the optional item input information are factors that affect the relationship between study time and score of the output lesson. For example, people with previous test experience or previous learning experience are more likely to be more likely than people with no previous test experience or previous learning experience, even if they have the same score at 0 hours of study time for the output lesson. The growth rate of people in Therefore, the proficiency curve can be the same or different for each output lesson, even if the score is the same when the learning time is 0 hours. The same applies to the proficiency curves of multiple output lessons included in a lesson unit.

In this way, the processor 11 can obtain a mastery curve for each output lesson rather than a uniform mastery curve for all output lessons. For example, for a difficult output lesson, the processor 11 can determine a proficiency curve with slow proficiency (eg, a gradual increase in predicted score per predetermined period of time soon after learning begins). For example, for a simple output lesson, the processor 11 can determine a proficiency curve with fast proficiency (eg, rapid increase in predicted score per predetermined time period soon after learning begins). Moreover, the processor 11 can acquire a different proficiency curve for each student even for the same output lesson.

Next, the simulation operation of the test score prediction will be described.
First, the allocation unit 117 allocates a predetermined standard study time to each lesson. The standard study time is the minimum time required to take each lesson. The standard study time can be updated as appropriate. The standard study time may be different or the same for each lesson. For example, the standard study time may be different or the same for each input lesson. For example, the standard study time may be different or the same for each output lesson. For example, if a lesson unit includes multiple output lessons, the standard study time for each of the multiple output learning lessons may be different or the same. At this point, the total allocated study time for each lesson corresponds to the total standard study time for each lesson.

Next, the simulation unit 119 determines one lesson suitable for the first addition of one unit time among the plurality of lessons constituting the course, as exemplified below. For example, the unit time is 10 minutes, but is not limited to this. The unit time can be changed as appropriate. Here, first, the allocation unit 117 adds one credit time to the allocated learning time of the first lesson. At this point, the allotted learning time for the first lesson is the sum of the standard learning time and one credit time. The acquisition unit 118 acquires a predicted score for each output lesson using the proficiency curve for each output lesson. The simulation unit 119 simulates the predicted scores of the test using the formulas (1) to (4). The simulation unit 119 substitutes the predicted score of each output lesson according to the allotted learning time into Equation (1), and simulates the predicted score of the exam after taking the course. In this example, the acquisition unit 118 acquires the predicted score of each output lesson according to the allotted learning time using the proficiency curve of each output lesson.

The simulation unit 119 can substitute the predicted score of each output lesson when the learning time of each output lesson is 0 hours into the equation (1) to simulate the predicted score of the test before taking the course. In this example, the acquisition unit 118 uses the proficiency curve of each output lesson to acquire the predicted score of the output lesson when the learning time of each output lesson is 0 hours.

The simulation unit 119 may simulate the predicted score of the test after taking the lesson.
In one example, the simulation unit 119 may calculate the predicted score for each lesson unit as exemplified below, and simulate the predicted score of the exam after taking the lesson based on equations (2) to (4). The predicted test score obtained by Equation (4) corresponds to the predicted test score after taking the lesson. Here, an example of obtaining a predicted score for each lesson unit after taking output lesson A will be described. The simulation unit 119 extracts an output lesson that has been taken most recently among output lessons included in a certain lesson unit. The simulation unit 119 obtains the predicted score of the output lesson according to the allotted study time by using the proficiency curve of the most recently completed output lesson. The simulation unit 119 uses the obtained predicted score of the output lesson as the predicted score for each lesson. In other words, even if this lesson unit includes an unattended output lesson, the predicted score of the lesson unit is not affected by the unattended output lesson and does not change. The simulation unit 119 obtains predicted scores for each lesson in the same manner as described above for all lesson units.
In another example, the simulation unit 119 appropriately substitutes the predicted score of the output lesson according to the allotted learning time and the predicted score of the output lesson when the learning time of the output lesson is 0 hours into the formula (1). Predicted scores for later tests may be simulated. For example, the simulation unit 119 calculates the predicted score of the output lesson according to the assigned learning time of the second and third lessons and the predicted score of the output lesson when the learning time of the fourth and subsequent lessons is 0 hours by the formula (1 ) to simulate the expected test score after taking the third lesson. In this example, the acquisition unit 118 uses the proficiency curve of each output lesson to acquire the predicted score of the output lesson according to the allotted learning time of the second and third lessons. Using the proficiency curve of each output lesson, the acquisition unit 118 predicts the score of the output lesson when the learning time is 0 hours for the fourth and subsequent lessons.

The simulation unit 119 stores the predicted test score in the storage device 14 in association with the lesson number to which one credit time is added. The allocation unit 117 subtracts one credit time from the allocated study time of the first lesson. At this point, the assigned study time for the first lesson returns to the standard study time.

Next, the allocation unit 117 adds one credit time to the allocated study time of the second lesson. At this point, the allotted learning time for the second lesson is the sum of the standard learning time and one credit time. The acquisition unit 118 acquires a predicted score for each output lesson using the proficiency curve for each output lesson. The simulation unit 119 simulates the predicted test score. The simulation unit 119 stores the predicted test score in the storage device 14 in association with the lesson number to which one credit time is added. The allocating unit 117 subtracts one credit time from the allotted study time for the second lesson. At this point, the allotted study time for the second lesson reverts to the standard study time.
Similarly, the simulation unit 119 repeats the simulation of the predicted test score in accordance with the addition of one credit time to the allotted learning time of any one lesson. That is, the simulation unit 119 repeats the simulation of the predicted test score m times.

Next, the simulation unit 119 refers to the storage device 14 and compares the expected scores of the exam after taking m courses. The simulation unit 119 extracts the largest predicted score of the post-course exam from among the m predicted scores of the post-course exam. The simulation unit 119 refers to the storage device 14 and extracts the lesson number associated with the highest expected score of the exam after taking the course. As a result, the simulation unit 119 determines one lesson that maximizes the predicted score of the exam after taking the course by adding one credit time. The allocating unit 117 adds one credit time to the allotted learning time of the lesson that maximizes the predicted score of the exam after taking the course among the plurality of lessons that constitute the course. Here, it is assumed that the allocating unit 117 adds one credit time to the allotted learning time for the "7-12 O2" lesson. At this point, the total allocated learning time for each lesson corresponds to the sum of the standard learning time and one credit time for each lesson. The simulation unit 119 adopts, from the predicted test scores stored in the storage device 14, the predicted test score associated with the “7-12 O2” lesson with one credit time added. The simulation unit 119 deletes from the storage device 14 the predicted test scores associated with lessons other than the “7-12 O2” lesson.

Note that the allocation unit 117 may omit the addition of one credit time to the allocated learning time of the input lesson. In this example, the simulation unit 119 can reduce the number of simulations of the predicted test score.

Next, when the sum of the assigned learning time for each lesson (the sum of the standard learning time and one credit time for each lesson) has not reached the total learning time, the simulation unit 119 adds the first one credit time and Similarly, one lesson suitable for adding one unit time for the second time is determined from among the plurality of lessons constituting the course. Here, it is assumed that the simulation unit 119 has determined that the "1-12 O2" lesson is the lesson that gives the highest predicted score in the exam after taking the course by adding one credit time. The allocation unit 117 adds one credit time to the allocated learning time for the "1-12 O2" lesson. At this point, the total allocated learning time for each lesson corresponds to the sum of the standard learning time for each lesson and two credit hours. The simulation unit 119 adopts, from the predicted test scores stored in the storage device 14, the predicted test score associated with the “1-12 O2” lesson with one credit time added. The simulation unit 119 deletes from the storage device 14 the predicted test scores associated with lessons other than the “1-12 O2” lesson.

The allocation unit 117 repeats adding one credit time to the allocated learning time of any one of the plurality of lessons constituting the course until the total of the allocated learning time of each lesson reaches the total learning time. For example, initially, the allocator 117 may continuously allocate one unit of time to the output lessons that are most effective in increasing the predicted score of the test by adding one unit of time. However, as the allocation unit 117 repeats adding one unit time to this output lesson, the effect of raising the predicted score of this output lesson gradually decreases, as can be seen from the example of FIG. As a result, the effect of increasing the test's predictive score gradually decreases. In other words, the allocating unit 117 can make the effect of increasing the predicted score of the test relatively higher by adding one unit of time to another output lesson than by adding one unit of time to this output lesson. Therefore, after that, the allocation unit 117 adds one credit time to another output lesson. In this way, the allocator 117 repeats the addition of one unit of time to the output lesson, which is most effective in raising the expected test score. Ultimately, the allocation unit 117 allocates the allocated learning time to each lesson so that the sum of the allocated learning time of each lesson becomes the total learning time. The allocating unit 117 can realize allocation of the allotted learning time to each lesson that maximizes the predicted test score. The simulation unit 119 simulates the predicted test score based on the total study time.

Next, with reference to FIGS. 15 to 17, the change from the predicted test score based on the total standard study time to the predicted score based on the total study time will be described.

FIG. 15 is a diagram exemplifying the predicted test score based on the total standard study time of each lesson and the predicted test score based on the total standard study time and one credit time of each lesson.
The horizontal axis indicates each lesson. The left vertical axis indicates the learning time. The vertical axis on the right shows the predicted score of the test. The bar graph shows the allotted learning time for each lesson. The solid line portion of the bar graph indicates the standard study time. The dashed line attached to the bar graph of the "7-12 O2" lesson indicates the first addition of 1 time unit.

A cross indicates the predicted test score based on the total standard study time. In other words, the cross marks are examples in which the total allocated study time for each lesson corresponds to the total standard study time for each lesson. The cross marks on the vertical axis on the left side indicate the predicted score of the exam before taking the course, with the standard study time assigned to each lesson. The crosses associated with each lesson indicate the predicted test score after taking each lesson, given that each lesson has been assigned a standard study time. For example, a cross associated with the "7-12 O2" lesson indicates the predicted test score after taking the "7-12 O2" lesson. The predicted test score after taking the "7-12 O2" lesson corresponds to the predicted test score after taking the course.

The circle indicates the expected test score based on the sum of the standard study time and one credit time for each lesson. In other words, the circle indicates an example in which the total allocated learning time for each lesson corresponds to the sum of the standard learning time for each lesson and one credit time. The circles on the vertical axis on the left indicate the predicted test scores before taking the course, with standard study time assigned to each lesson and one credit hour added to the "7-12 O2" lesson. . The circles associated with each lesson are the predicted exams after each lesson, given that each lesson has been assigned a standard study time plus one credit hour added to the "7-12 O2" lesson. Show the score. For example, the circle associated with the "7-12 O2" lesson indicates the predicted test score after taking the "7-12 O2" lesson.

Compare the predicted test score based on the sum of the standard study time for each lesson with the predicted test score based on the sum of the standard study time and one credit time for each lesson. Since the allotted study time for the "1-1 I" through "7-12 O1" lessons is the same in both cases, the predicted test score after each lesson is the same in both cases. Predicted scores for post-course exams are increased by adding one credit hour to the allotted study time for the "7-12 O2" lesson.

FIG. 16 is a diagram illustrating predicted test scores based on the sum of the standard study time and one credit time for each lesson and predicted test scores based on the sum of the standard study time and two credit hours for each lesson.
The horizontal axis indicates each lesson. The left vertical axis indicates the learning time. The vertical axis on the right shows the predicted score of the test. The bar graph shows the allotted learning time for each lesson. The solid line portion of the bar graph indicates the standard study time. The dashed line attached to the bar graph of the "7-12 O2" lesson indicates the first addition of 1 time unit. The dashed-dotted line attached to the bar graph of the "1-12 O2" lesson indicates the second addition of one time unit.

As in FIG. 15, the circle indicates the predicted test score based on the sum of the standard study time and one credit time for each lesson.
The triangle indicates the expected test score based on the sum of standard study time and 2 credit hours for each lesson. That is, the triangular mark is an example in which the total allocated study time for each lesson corresponds to the sum of the standard study time and two credit hours for each lesson. The triangle mark on the left vertical axis indicates the course in a state in which standard study time is assigned to each lesson, and one credit time is added to each of the "1-12 O2" lesson and the "7-12 O2" lesson. Shows the predicted score of the pre-attendance test. The triangle associated with each lesson indicates that each lesson is assigned standard study time, and one credit time is added to each of the "1-12 O2" lesson and the "7-12 O2" lesson. , indicates the predicted test score after taking each lesson. For example, the triangle associated with the "7-12 O2" lesson indicates the predicted test score after taking the "7-12 O2" lesson.

Compare the predicted test score based on the sum of the standard study time and 1 credit time for each lesson with the predicted test score based on the sum of the standard study time and 2 credit hours for each lesson. Since the allotted study time for the previous lesson from the ``1-1 I'' lesson to the ``1-12 O2'' lesson is the same in both cases, the predicted score for the exam after taking each lesson is the same in both cases. be. The predicted score for the exam after taking the "1-12 O2" lesson is increased by adding one credit hour to the allotted study time for the "1-12 O2" lesson. The increase in score due to the addition of one credit time to the allotted learning time of the "1-12 O2" lesson also contributes to the predicted score of the exam after taking the lesson after the "1-12 O2" lesson. As a result, the predicted score for the post-course exam based on the sum of the standard study time and 2 credit hours for each lesson is higher than the predicted score for the post-course exam based on the sum of the standard study time and 1 credit time for each lesson. also increases.

FIG. 17 is a diagram illustrating predicted test scores based on total study time.
The horizontal axis indicates each lesson. The left vertical axis indicates the learning time. The vertical axis on the right shows the predicted score of the test. The bar graph shows the allotted learning time for each lesson. The solid line portion of the bar graph indicates the standard study time. A hatched block attached to the bar graph indicates one unit of time added to each lesson. Thus, typically each output lesson has one or more credit hours added to the standard study time. Also, the number of 1 credit hours added to each output lesson is different for each output lesson.
As can be seen from equations (1)-(4), taking an input lesson does not contribute to the expected test score, so each input lesson does not add one credit hour. When equations (1)-(4) are modified to take into account the attendance of input lessons (eg, the hours taken), each input lesson may add one or more credit hours.

Squares indicate predicted test scores based on total study time. The square mark on the left vertical axis indicates the predicted score of the test before taking the course in a state in which each lesson is assigned an allotted study time so that the sum of the allotted study time for each lesson is the total study time. The squares associated with each lesson are the predicted scores for the exam after taking each lesson, with allotted learning time allocated to each lesson so that the sum of allotted learning time for each lesson equals the total learning time. indicates For example, a square associated with the "7-12 O2" lesson indicates the predicted test score after taking the "7-12 O2" lesson.

As can be seen from FIGS. 15 to 17, as the allocator 117 repeats adding one credit time to the allotted study time for one lesson, the predicted score for the exam after taking the course gradually increases.

FIG. 18 is a flow chart showing an example of a simulation operation by the server 1. FIG. The flowchart illustrated in FIG. 18 shows a detailed example of steps S109 to S111 illustrated in FIG.

First, the allocation unit 117 allocates a predetermined standard study time to each lesson (step S201). Next, the allocation unit 117 sets 1 to the variable i indicating the lesson number (step S202). The allocation unit 117 adds one credit time to the allocated learning time of the first lesson (step S203).

The acquiring unit 118 acquires the lesson result corresponding to the allotted study time for each lesson (step S204). The simulation unit 119 simulates the predicted test score based on the lesson results corresponding to the allotted study time for each lesson (step S205). The simulation unit 119 stores the predicted test score in the storage device 14 in association with the lesson number to which one credit time is added (step S206). The allocation unit 117 subtracts one credit time from the allocated learning time of the first lesson (step S207). The allocation unit 117 determines whether i=m (step S208). If i is not equal to m (step S208, No), the allocation unit 117 increments the value of variable i (step S209).

If i=m (step S208, Yes), the assignment unit 117 assigns learning to any one of the plurality of lessons that constitute the course based on the comparison of the expected test scores after taking the course. One unit of time is added to the time (step S210). The simulation unit 119 adopts the predicted test score associated with the lesson to which one credit time is added from the predicted test scores stored in the storage device 14 (step S211).

The simulation unit 119 determines whether or not the sum of the allotted learning time for each lesson has reached the total learning time (step S212). If the sum of allotted learning time for each lesson has not reached the total learning time (step S212, No), the processor 11 repeats steps S202 to S212. When the sum of allotted learning time for each lesson reaches the total learning time (step S212, Yes), the processor 11 terminates the simulation operation. Ultimately, the allocation unit 117 can allocate the allocated learning time to each lesson so that the sum of the allocated learning time of each lesson is the total learning time. The simulation unit 119 can simulate the predicted test score based on the total study time.

In the example of FIG. 18, the processor 11 repeats adding one unit of time to the allotted learning time of any one lesson until the total allotted learning time of each lesson reaches the total learning time. It is not limited to this. The processor 11 may finish adding one unit of time to the allotted study time for any one lesson before the total allotted study time for each lesson reaches the total study time. For example, if the processor 11 determines that even if one credit time is added to the allotted learning time of any one lesson, it becomes difficult for the predicted score of the exam after taking the course to increase, the processor 11 adds one credit time after the next lesson. can be finished adding. For example, if the difference in the predicted score of the exam after taking the course before and after adding 1 credit time to the allocated learning time of any one lesson is less than a predetermined point, the processor 11 adds 1 credit time to the next and subsequent lessons. may be terminated. For example, if the rate of increase in the predicted score of the exam after taking the course before and after adding one credit time to the allotted learning time of any one lesson is less than a predetermined rate, the processor 11 adds one credit time after the next lesson. may be terminated.

If the processor 11 finishes adding one credit time before the total learning time assigned to each lesson reaches the total learning time, the processor 11 can process as follows. For example, the processor 11 may output to the terminal 2 via the communication interface 15 information indicating the total allocated study time for each lesson. As a result, the terminal 2 can display the total allocated learning time for each lesson together with the total learning time, and notify the subject of the total allocated learning time for each lesson. For example, processor 11 may divide the remaining time by the number of lessons and evenly allocate each lesson the time. For example, the processor 11 may secure the remaining time as review time. For example, the lesson that the subject takes during the review time is a subject or theme lesson that the subject is not good at, or a subject or theme lesson that the subject wants to improve his/her score. The lessons that the subject takes during the review time may be selected by the subject or recommended by the processor 11 .

As described above, the simulation unit 119 can improve the simulation accuracy of the predicted test score by simulating the predicted test score using a relationship such as a proficiency curve.

Next, a modified example will be described.
Processor 11 may use a forgetting curve to simulate an expected test score. For example, the processor 11 simulates the predicted score of the exam after taking the course in step S205 of FIG. 18 described above.
FIG. 19 and FIG. 20 are diagrams showing examples of simulations of predicted scores of exams after taking a course, taking forgetting into account. FIG. 19 shows an example in which the processor 11 simulates the predicted score of the exam after taking the course before adding one credit time to the allotted learning time of the "1-1 O2" lesson in the ability training period in step S203. FIG. 20 shows an example in which the processor 11 adds 1 credit time to the allotted learning time of the "1-1 O2" lesson in the ability training period in step S203, and then simulates the predicted score of the exam after taking the course.

First, an example of the configuration of a course for small and medium enterprise management consultants to be simulated will be described. The course consists of a basic skill training period and a skill training period in that order. The basic ability training period and ability training period are each composed of subjects 1 to 7, as in the example shown in FIG. Each subject consists of multiple lessons. Subject 1 consists of 12 lesson units from "1-1" to "1-12". Each lesson unit contains two output lessons. "O1" indicates an output lesson containing basic questions. "O2" indicates an output lesson containing past questions. In this way, students take output lessons of the same lesson unit in both the basic ability training period and the ability training period. For example, a student takes an output lesson of lesson unit "1-1" of subject 1 in the basic ability training period, and takes an output lesson of lesson unit "1-1" of subject 1 even in the ability training period. Hereinafter, the "1-1 O1" lesson in the basic ability training period is also referred to as the previous "1-1 O1" lesson. The "1-1 O2" lesson in the basic ability training period is also called the previous "1-1 O2" lesson. The "1-1 O1" lesson in the ability training period is also called the "1-1 O1" lesson later. The "1-1 O2" lesson in the ability training period is also called the "1-1 O2" lesson later. The “7-12 O2” lesson during the ability training period is also called the “7-12 O2” lesson later.

Next, the formula for calculating the predicted score of the exam after taking the course will be described.
Formulas (5) to (6) are formulas for calculating the predicted score of the exam after taking the course.
Predicted score after rate adjustment = Predicted score for each lesson unit after taking the course × Percentage of allotted points (Formula (5)) Predicted score for exam after taking the course = Total predicted score after rate adjustment (Formula (6))

The predicted score for each lesson unit after taking the course in Equation (5) is the predicted score for each lesson unit at an arbitrary timing after taking the course. The predicted score for each lesson unit after taking the course is the predicted score out of 100 points. The predicted score for each lesson unit changes over time. For example, the predicted score for each lesson unit increases along the proficiency curve by taking output lessons according to the allotted learning time. For example, the predicted score for each lesson unit decreases along the forgetting curve as the learner forgets according to the number of days after taking the output lesson. A simulation example of the predicted score for each lesson will be described later.

As described above, the allotted points ratio in Equation (5) is the percentage of allotted points assigned to the theme of each lesson unit with respect to the full score (100 points) of the subject.
The rate-adjusted predicted score in equations (5) and (6) is the predicted score for each lesson unit after adjusting the predicted score for each lesson unit after taking the course according to the allocated point ratio.

As shown in FIGS. 19 and 20, the predicted score of the lesson unit "1-1" after taking the later "1-1 O2" lesson is 1 to the allotted learning time of the later "1-1 O2" lesson. By adding unit time, the score increases from 58 points to 83 points. The predicted score for the lesson unit "1-1" gradually decreases according to the number of days from after taking the next "1-1 O2" lesson to after taking the last lesson "7-12 O2". . The predicted score of the lesson unit "1-1" shown in FIG. 19 gradually decreases from 58 points to 50 points. The predicted score of the lesson unit "1-1" shown in FIG. 20 gradually decreases from 83 points to 75 points. In this way, the predicted score for the lesson unit "1-1" after taking the course rises from 50 points to 75 points due to the addition of one credit time to the allotted learning time for the later "1-1 O2" lesson. . As a result, the predicted score for the exam after taking the course increases from 199 points to 200 points.

A simulation example of predicted score for each lesson unit will be described.
FIG. 21 is a diagram exemplifying the transition of expected scores for each lesson unit considering the forgetting curve. FIG. 21 exemplifies transition of the predicted score for the lesson unit "1-1". The horizontal axis indicates the number of days that have passed since taking the “1-1 O1” lesson in the basic ability training period. The vertical axis indicates the predicted score of the lesson unit "1-1". Here, it is assumed that the previous "1-1 O1" lesson and the previous "1-1 O1" lesson are taken without an interval. It is assumed that the later "1-1 O1" lesson and the later "1-1 O1" lesson are attended without leaving an interval.

First, the acquisition unit 118 acquires the predicted score (10 points) of the lesson unit "1-1" before taking the previous "1-1 O1" lesson derived based on the test result. Next, the acquisition unit 118 acquires the predicted score (30 points) of the previous "1-1 O1" lesson according to the allocated learning time using the proficiency curve of the previous "1-1 O1" lesson. . The predicted score of the previous "1-1 O1" lesson according to the allotted learning time corresponds to the predicted score of the lesson unit "1-1" after taking the previous "1-1 O1" lesson. Thus, the predicted score of the lesson unit "1-1" increases from 10 points to 30 points as a result of taking the previous "1-1 O1" lesson according to the allotted learning time.

Next, the acquisition unit 118 acquires the predicted score (50 points) of the previous “1-1 O2” lesson according to the allocated study time using the proficiency curve of the previous “1-1 O2” lesson. . Here, the acquisition unit 118 considers that the target person has taken the previous "1-1 O1" lesson before the previous "1-1 O2" lesson, and A modified proficiency curve for the lesson may be used. The predicted score of the previous "1-1 O2" lesson corresponding to the allotted learning time corresponds to the predicted score of the lesson unit "1-1" after taking the previous "1-1 O2" lesson. Thus, the predicted score of the lesson unit "1-1" increases from 30 points to 50 points as a result of taking the previous "1-1 O2" lesson according to the allotted learning time.

Next, the simulation unit 119 sets the predicted score of the lesson unit "1-1" to 50 according to the number of days from after taking the previous "1-1 O2" lesson to before taking the later "1-1 O1" lesson. Gradually decrease from point to 20 points. Here, the simulation unit 119 uses a forgetting curve. A forgetting curve shows a relationship in which the content once memorized is gradually forgotten from memory as time elapses. Therefore, the forgetting curve shows a relationship in which the predicted score of the lesson unit "1-1" gradually decreases as time elapses. Forgetting curves may differ from person to person, or may be the same. The forgetting curve may be different or the same for each lesson unit. The forgetting curve may be updated accordingly. Note that the forgetting curve may be obtained using machine learning. In this example, the processor 11 predicts a forgetting curve that predicts how much the score per lesson will decrease over time based on the past learning histories and past score histories of all or a plurality of students. A model can be generated. For example, the past learning history includes the learning date and time of each output lesson and the learning time of each output lesson. For example, past score history includes scores for each output lesson, and so on. When generating this predictive model, the processor 11 can add the number of repetitions, attributes of the student, etc. to the explanatory variables. For example, the number of repetitions is the number of times the output lesson included in the lesson unit is taken, and corresponds to the number of output lessons included in the lesson unit. This allows the processor 11 to generate a predictive model of the forgetting curve for each iteration number or for each individual. Processor 11 may update the prediction model accordingly.

Next, the acquiring unit 118 acquires the predicted score (50 points) of the later "1-1 O1" lesson according to the allocated learning time using the proficiency curve of the later "1-1 O1" lesson. . Here, the acquiring unit 118 considers that the target person has taken the earlier "1-1 O2" lesson before the later "1-1 O1" lesson, and the later "1-1 O1" lesson A modified proficiency curve for the lesson may be used. The predicted score of the "1-1 O1" lesson after taking the allotted learning time corresponds to the predicted score of the lesson unit "1-1" after taking the later "1-1 O1" lesson. Thus, the predicted score for the lesson unit "1-1" rises from 20 points to 50 points as a result of taking the "1-1 O1" lesson later according to the allotted learning time.

Next, the acquiring unit 118 acquires the predicted score (83 points) of the later "1-1 O2" lesson according to the allocated learning time using the proficiency curve of the later "1-1 O2" lesson. . Here, the acquiring unit 118 considers that the target person has taken the later "1-1 O1" lesson before the later "1-1 O1" lesson, and the later "1-1 O2 A modified proficiency curve for the lesson may be used. The predicted score of the "1-1 O2" lesson after the assigned study time corresponds to the predicted score of the lesson unit "1-1" after taking the later "1-1 O2" lesson. Thus, the predicted score for the lesson unit "1-1" rises from 50 points to 83 points as a result of taking the "1-1 O2" lesson later according to the allotted learning time.

Next, the simulation unit 119 sets the predicted score of the lesson unit "1-1" to 83 according to the number of days from after taking the later "1-1 O2" lesson to after taking the later "7-12 O2" lesson. point to 75 points. Here, the simulation unit 119 uses a different forgetting curve from the forgetting curve used for the period from after taking the previous "1-1 O2" lesson to before taking the later "1-1 O1" lesson. The forgetting curve used in the period from after taking the later "1-1 O2" lesson to after taking the later "7-12 O2" lesson is the 1 O1” This is a curve in which the predicted score decreases more moderately than the forgetting curve used in the period before taking the lesson. The reason for this is that, by repeatedly studying the same lesson unit content with a gap in time, the subject learners are less likely to forget the lesson unit content.

By considering the forgetting curve, the simulation unit 119 can improve the simulation accuracy of the predicted test score.

Next, progress management by the server 1 after the start of taking a course will be described.
The server 1 manages the progress after the subject starts taking the course based on the simulation results. For example, the server 1 manages the progress along the simulation result regarding the total study time according to the selection of the simulation result regarding the total study time by the subject. For example, the server 1 manages the progress along the simulation results regarding the other total study time according to the subject's selection of the simulation results regarding the other total study time.

FIG. 22 is a diagram illustrating a screen regarding progress management displayed on the terminal 2. As shown in FIG.
The processor 11 generates data on progress management illustrated in FIG. 22 and outputs the data on progress management to the terminal 2 via the communication interface 15 .

Progress management includes "Lesson" item, "Status" item, "Scheduled end date", "End date" item, "Allocated learning time" item, "Actual learning time" item, "Target score" item, "Actual score" items, a "predicted score" item, an "actual predicted score" item, a "current actual predicted score" item, and a "current actual learning time" item.

The "lesson" item indicates the title of each lesson that constitutes the course. The "state" item indicates the state of taking each lesson. The attendance status is one of completed, learning, or not attended. End indicates that the subject has finished taking the lesson. Learning indicates that the subject is taking part of the lesson. Not attended indicates that the subject has not started taking the lesson. The “scheduled end date” item indicates the scheduled date of attendance for each lesson assigned by the simulation of the server 1 . The "end date" item indicates the date when the subject actually finished taking the lesson. The “allocated learning time” item indicates the allocated learning time allocated to each lesson by the server 1 simulation. The item "actual learning time" indicates the time the subject actually took the lesson. Note that if the course is in a form of taking classes on the web, the server 1 can acquire the actual learning time of each lesson by taking a log of the subject. In the case where the course is a lecture format using texts on a paper medium such as a booklet, the server 1 can acquire the actual learning time of each lesson based on the input by the subject. The "target score" item shows the expected score for each output lesson according to the allotted learning time. The "achievement score" item indicates the score of each output lesson actually acquired by the subject. In addition, when the course is a lecture format on the web, the server 1 can acquire the achievement score of each lesson by taking a log of the subject. In the case where the course is a lecture format using paper medium text such as a booklet, the server 1 can acquire the performance score of each lesson based on the input by the subject. The "predicted score" item indicates the predicted score of the test after taking each lesson based on the server 1 simulation. The "Actual Predicted Score" item indicates the predicted test score after each lesson taking into consideration the score of each output lesson actually obtained by the subject. A performance prediction score is simulated by the server 1 . A simulation example of the actual predicted score will be described later. The item "predicted current performance score" indicates the predicted score of the test after taking the last lesson that the subject finished taking. The "current actual learning time" item indicates the total actual learning time of lessons that the subject has finished taking.

A simulation example of the actual predicted score by the server 1 will be described.
The simulation unit 119 substitutes the score of each output lesson actually obtained by the subject shown in the item "achievement score" into the equation (1) for the lessons that the subject has finished taking from the first lesson. In this example, the score for each output lesson is an example of the lesson outcome. The simulation unit 119 calculates the predicted score of each output lesson according to the allotted learning time indicated by the "target score" item for the next lesson to the last lesson of the lesson that the subject has finished taking, using formula (1). substitute. As a result, the simulation unit 119 can use equations (1) to (4) to simulate the performance prediction score that takes into consideration the performance of the lessons that the subject has finished taking.

It should be noted that the progress management is not limited to the example of FIG. 22, and may be configured using a Gantt chart or the like.

It should be noted that the learning effect is not limited to the predicted test score or the range of predicted test scores described above. A learning effect may include the likelihood of reaching a target score. For example, the target score may be a passing score on an exam. In one example, the probability of reaching the target point is the pass rate. The pass rate is the ratio of the test's expected score to the target score. In another example, the probability of reaching the target point is a passing call. The pass judgment is a rank selected from a plurality of ranks. For example, multiple ranks are set according to the deviation of the predicted test score from the target score or the ratio of the predicted test score to the target score. For example, the multilevel rank includes four levels of A, B, C, and D, but is not limited thereto.

It should be noted that the above-described units implemented by the processor 11 of the server 1 may be implemented in a plurality of servers in a distributed manner.

In addition, although the example of the simulation by the server 1 was demonstrated, it is not limited to this. The terminal 2 includes the input item output unit 111, the input information acquisition unit 112, the test output unit 113, the answer information acquisition unit 114, the test result output unit 115, the calculation unit 116, the allocation unit 117, the acquisition unit 118, and the simulation unit 119. and a simulation result output unit 120 may be implemented. In this example, the terminal 2 is an example of an information processing device.

In short, the present invention is not limited to this embodiment as it is, and can be embodied by modifying the constituent elements without departing from the scope of the present invention at the implementation stage. Also, various inventions can be formed by appropriate combinations of a plurality of constituent elements disclosed in this embodiment. For example, some components may be deleted from all the components shown in this embodiment. Furthermore, constituent elements across different embodiments may be combined as appropriate.
The description of the scope of claims as originally filed for this application will be added below.
[C1]
an acquisition unit that acquires the learning schedule of the learner;
a calculation unit that calculates the total learning time from the learning start date to the learning end date based on the learning schedule;
an allocation unit that allocates an allocated learning time to each of a plurality of lessons based on the total learning time;
a simulation unit for simulating a learning effect according to the allocated learning time; an output unit for outputting a simulation result by the simulation unit;
Information processing device.
[C2]
The information processing device according to [C1], wherein the learning effect includes a predicted test score or a predicted test score range.
[C3]
The simulation result includes the learning effect,
The information processing device according to [C1].
[C4]
the simulation results include the allotted learning time for each lesson;
The information processing device according to [C1].
[C5]
The information processing apparatus according to [C1], wherein the simulation unit simulates the learning effect based on the result of each lesson according to the allotted learning time.
[C6]
the plurality of lessons includes a plurality of output learning lessons;
The information processing apparatus according to [C5], wherein the result is a score that is predicted to be obtainable in each output learning lesson corresponding to the allotted learning time.
[C7]
The information processing device according to [C1], wherein the simulation unit simulates the learning effect using a forgetting curve.
[C8]
The simulation unit simulates another learning effect based on another total learning time different from the total learning time,
The simulation result includes the learning effect based on the total learning time and the other learning effect based on the other total learning time,
The information processing device according to claim 1 .
[C9]
obtaining a study schedule for the learner;
calculating the total study time from the study start date to the study end date based on the study schedule;
allocating an allotted learning time to each of a plurality of lessons based on the total learning time;
simulating a learning effect according to the allocated learning time;
outputting simulation results;
An information processing method comprising:

Reference Signs List 1 server 2 terminal 11 processor 12 ROM 13 RAM 14 storage device 15 communication interface 21 processor 22 ROM 23 RAM 24 storage device 25 communication Interface 26 Input device 27 Display device 111 Input item output unit 112 Input information acquisition unit 113 Test output unit 114 Answer information acquisition unit 115 Test result output unit 116 Calculation unit , 117... Allocation unit, 118... Acquisition unit, 119... Simulation unit, 120... Simulation result output unit, 211... Acquisition unit, 212... Display control unit, 213... Output unit.

Claims (6)

an acquisition unit that acquires the learning schedule of the learner;
a calculation unit that calculates a total learning time that can be learned based on the learning schedule;
a simulation unit that determines one lesson that maximizes the predicted total score of the exam after taking the course by adding one credit time out of a plurality of lessons that constitute a course of the exam;
an allocation unit allocating an allocation learning time to each of the plurality of lessons by repeating adding one credit time to one lesson determined by the simulation unit;
an output unit that outputs the allocated learning time for each lesson based on the total learning time;
Information processing device. 2. The information processing apparatus according to claim 1, wherein said allocating unit repeats adding one credit time until the total of said allotted learning time of each lesson reaches said total learning time. 3. The information processing apparatus according to claim 1, wherein said output unit outputs a predicted total score of said test after taking said course based on said total study time or a predicted total score range of said test after taking said course. . The output unit outputs a predicted total score of the test after taking the course or a predicted total score range of the test after taking the course based on a total learning time different from the total learning time. The information processing apparatus according to claim 3. An information processing method executed by an information processing device,
obtaining a study schedule for the learner;
calculating a total study time available for study based on the study schedule;
Determining one lesson that maximizes the predicted total score of the exam after taking the course by adding one credit time among a plurality of lessons that constitute a course of the exam;
assigning an allotted learning time to each of the plurality of lessons by repeating adding one credit time to the determined one lesson;
outputting the allocated learning time for each lesson based on the total learning time;
An information processing method comprising: An information processing program that causes a computer to execute processing by each unit included in the information processing apparatus according to any one of claims 1 to 4.