JP7171053B2 - Information processing device, information processing method and information processing program - Google Patents

Description

TECHNICAL FIELD Embodiments of the present invention relate to information processing apparatuses and terminals.

In recent years, services for delivering courses such as qualification tests via the Internet have become widespread. In general, students make their own study schedules, such as weekly study hours and how to proceed for each theme, with the aim of passing the qualification exam.

In order to reduce the work of such students and guide them to pass the qualification examination, services that deliver advice to the students are spreading. For example, Patent Literature 1 discloses a technique of advising a student to increase his or her learning pace when the learning pace is behind the attendance plan.

JP-A-2004-259140

The advice disclosed in Patent Literature 1 relates to study time. Therefore, the student can grasp the delay of the learning pace, but cannot grasp the effective learning method for passing the qualification test.

The learning themes of the qualification exam are diverse. The learning themes that are easy to increase the score and the learning themes that are difficult to increase the score differ depending on the student. Therefore, it is difficult for students to pass the qualification examination unless they study effectively even if they increase their study time. It is not desirable for students to spend the same amount of time on all learning themes in order to pass the qualification exam.

In order to solve the above problems, a technology is provided that encourages course participants to take desirable actions to pass an exam.

According to the embodiment, the information processing apparatus acquires a specification unit that specifies a lesson to be taken by a subject among a plurality of lessons that constitute a course related to an exam, and information that indicates the learning effect of taking the lesson to be taken. An acquisition unit and an output unit that outputs information indicating the learning effect to the terminal of the subject.

According to the embodiment, the information processing device and the terminal display the learning effect on the display section, thereby prompting the subject to take desirable actions for passing the test.

FIG. 1 is a block diagram showing a configuration example of a course distribution system and terminals according to an embodiment. FIG. 2 is a diagram showing a configuration example of a plurality of lessons forming a target course according to the embodiment. FIG. 3 is a diagram showing a display example of the first learning effect for the target lecture according to the embodiment. FIG. 4 is a diagram illustrating the relationship between practice scores and predicted scores of a target test according to the embodiment. FIG. 5 is a diagram showing a display example of the first learning effect for the target exercise according to the embodiment. FIG. 6 is a sequence diagram showing an operation example related to the score prediction model according to the embodiment. FIG. 7 is a sequence diagram illustrating an operation example related to the learning effect 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 course distribution system 1 and terminals 2. As shown in FIG.

The course distribution system 1 will be described.
The course distribution system 1 is a system for distributing the content of a course to each student who has registered to attend a course for an examination via a network such as the Internet. Here, it is assumed that the course distribution system 1 distributes a course regarding a specific test to a terminal 2 owned by a specific student. In the following, the specific student who owns the terminal 2 is also referred to as the target student. A particular study is also referred to as a subject study. A course for a subject exam is also referred to as a subject course.

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.

Each exam course consists of a number of lessons. Each lesson is a lecture or exercise, respectively. For example, lectures are in the format of viewing and listening to video or audio. Lectures may be in the form of learning through texts on the web. Lectures may be in a course format that combines watching videos or audio and learning from texts on the web. Exercises are in the form of lectures by answering questions on the web. Exercises may partially include lectures. Each lesson is a learning unit configured according to a set of contents such as a theme. Each lesson is structured so that the time taken by a student 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.

A course distribution system 1 includes a server 3 , a server 4 and a server 5 .
Server 3, server 4 and server 5 are communicably connected to each other via a network. Server 3, server 4 and server 5 will be described later.

Terminal 2 will be described.
The terminal 2 is a device that is used by a subject to take a subject course. 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 includes a processor 21 , a ROM (Read Only Memory) 22 , a RAM (Random Access Memory) 23 , a storage device 24 , a communication interface 25 , an input device 26 and a 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 . For example, the processor 21 is a CPU (Central Processing Unit), but is not limited to this. The processor 21 may be configured with a circuit including a field programmable gate array (Field Programmable Gate Array) or the like. The processor 21 expands a program pre-stored in the ROM 22 or storage device 24 onto the RAM 23 . The processor 21 executes various operations by executing programs developed in the RAM 23 .

The ROM 22 is a non-volatile memory that stores control programs and control data in advance.

The RAM 23 is a volatile memory that temporarily stores data being processed by the processor 31 .

The storage device 24 is a device composed of a non-volatile memory that stores data, programs, and the like. For example, the storage device 24 is configured by an HDD (Hard Disk Drive) or an SSD (Solid State Drive), but is not limited to these.

The storage device 24 stores programs executed by the processor 21 . The program may be downloaded to terminal 2 via a network. The program may be one stored in a computer-readable storage medium and installed in the terminal 2 .

The communication interface 25 is an interface for wired or wireless communication. For example, the communication interface 25 includes interfaces compatible with various wired or wireless standards. Communication interface 25 enables communication between terminal 2 and other devices.

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. For example, the input device 26 receives an instruction to start the target lesson based on an operation by the target person. A target lesson is a lesson to be taken by a target person among a plurality of lessons constituting a target course. A target lesson is also referred to as a target lesson to be taken. Here, an example in which the target lesson is an unattended lesson will be described. If the target lesson is a lecture, "not taken" means "not watched". If the subject lesson is an exercise, not taking means not answering the questions provided in the exercise. In the following, if the subject lesson is a lecture, this lecture is also referred to as the subject lecture. If the subject lesson is an exercise, this exercise is also referred to as a subject exercise.

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 unit.

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 the acquisition unit 211 and the display control unit 212 by executing programs.
The acquisition unit 211 acquires various information from the server 4 . For example, the acquisition unit 211 acquires from the server 4 information indicating the learning effect of taking the target lesson. The learning effect is the effect obtained by taking the target lesson by the target person. Examples of learning effects will be described later. The information indicating the learning effect is hereinafter also referred to as learning effect information.
The display control unit 212 causes the display device 27 to display various information. For example, the display control unit 212 causes the display device 27 to display the learning effect.

The server 3 will be explained.
The server 3 is a device used for managing data relating to a plurality of students in each exam course. In the following, data relating to multiple students is also referred to as multiple student data. Here, a plurality of student data for a target course will be described as an example. An example of multiple student data for the target course will be described later.

The server 3 includes a processor 31 , ROM 32 , RAM 33 , storage device 34 and communication interface 35 . The processor 31, ROM 32, RAM 33, storage device 34 and communication interface 35 are connected to each other via a data bus or the like.
The processor 31 controls the operation of the server 3 as a whole. The processor 31 is configured with the same hardware as the processor 21 described above.
The ROM 32 is configured with the same hardware as the ROM 22 described above.
The RAM 33 is configured with the same hardware as the RAM 23 described above.
The storage device 34 is configured with the same hardware as the storage device 24 described above. The storage device 34 stores a plurality of student data for the target course. The storage device 34 stores programs executed by the processor 31 . The program may be downloaded to server 3 via a network. The program may be one stored in a computer-readable storage medium and installed in the server 3 .
The communication interface 35 is configured with the same hardware as the communication interface 25 described above.
Note that the hardware configuration of the server 3 is not limited to the configuration described above. The server 3 allows omission and modification of the above components and addition of new components as appropriate.

A plurality of student data for the target course stored in the storage device 34 will be described.
The plurality of student data includes not only data on students who have finished taking the target course, but also data on students who are currently taking the target course. For example, the data about the students who finished taking the target course may include not only the data about the students who took all the lessons that make up the target course, but also the data about the students who stopped taking the lessons in the middle of the target course. . The plurality of student data includes data regarding the subject. In the following, data relating to subjects are also referred to as subject data. A plurality of student data are updated according to the progress of students currently taking the course and the addition of new students.

The plurality of student data includes data regarding attendance history for each student.
The attendance history is a log recording the learning behavior of each lesson in which the student has taken at least part of a plurality of lessons that constitute the target course. The learning history includes not only the lessons that the student has completed, but also the learning behavior of the lessons that the student has completed. In the following, a lesson that the student has completed is also referred to as a taken lesson. A lesson that the student has taken partway through is also referred to as an incomplete lesson. Lessons that the student has not taken are also referred to as untaken lessons.

A case where the lesson is a lecture will be explained. For example, the attendance history includes, for each lesson, the progress of the lecture (completed, in progress, or not attended), video or audio playback time, and learning time using text (lecture usage time), etc. contains elements of For example, if the lecture is a study using a text, the progress of the lecture may become completed according to the input of the completion of the lecture by the student. Note that the server 3 may automatically record the learning time of the lecture, but may collect the time from the terminal according to the input by the student on the terminal. When entering the learning time of the lecture on the terminal, the student may enter the learning time of the text delivered in the course, or study the commercially available text (for example, the part of the commercially available text related to each lecture) You can also enter the time.

Explain when a lesson is an exercise. For example, the attendance history includes elements such as the progress status of exercises (completed, in progress, or not attended), exercise scores or percentage of correct answers, and exercise study time (exercise usage time) for each lesson. including. Note that when a student takes the same exercise multiple times, the attendance history includes the number of times the student has taken the exercise (for example, the first time, the second time, etc.) and the score or correct answer rate of the exercise linked. Note that the server 3 may automatically record the learning time of the exercise in the same way as the learning time of the lecture described above, but may collect from the terminal according to the input by the student on the terminal. . When students enter the study time for exercises on the terminal, they can enter not only the study time for the exercises distributed in the course, but also problems recorded in commercially available textbooks (for example, You may enter the study time of the part of the text related to each exercise).

The plurality of student data includes data regarding target test scores for students who have taken the target test.
The target test score is the result of the student actually taking the target test. Note that the score of the target test may be the result of a mock test instead of the result of the main test. For example, practice tests include tests held by external testing agencies. In this example, the results of the mock test are declared by the student. For example, practice tests include web-based tests that are included in courses. In this example, mock test results may be included in the course history.

Note that the plurality of student data may include at least one of data regarding the experience of the student and data regarding the attribute of the student for each student.

The student's experience includes the experience of actually taking the target exam in the past before the student took the target course. For example, test-taking experience includes factors such as the number of times a target test has been taken and the results of the target test. For example, the past results of the target exam may be formal results notified to the students by the administration organization of the exam, or may be the results of self-grading by the students. A student's experience includes previous learning experience for exams different from the target exam. For example, the learning experience includes factors such as the number of times a test is taken that is different from the target test.

Student attributes are student-specific characteristics. For example, student attributes include factors such as age, gender, occupation, and industry.

A plurality of student data are collected by the server 4 and stored in the server 3 . For example, the server 4 measures data on the lesson attendance history of each student according to the distribution of the contents of each lesson, and stores the data in the server 3 . For example, the server 4 collects data about the attributes of the students and the scores of the target tests from the terminals according to the input by each student on the terminal, and stores the data in the server 3 .

The server 4 will be explained.
The server 4 is a device used for processing requests from the terminal 2, storing data in the server 3, processing requests to the server 5, and the like.

The server 4 includes a processor 41 , ROM 42 , RAM 43 , storage device 44 and communication interface 45 . The processor 41, ROM 42, RAM 43, storage device 44 and communication interface 45 are connected to each other via a data bus or the like.
The processor 41 controls the operation of the server 4 as a whole. The processor 41 is configured with the same hardware as the processor 21 described above. The processor 41 executes the programs developed in the RAM 43 to implement various units, which will be described later, that perform various operations.
The ROM 42 is configured with the same hardware as the ROM 22 described above.
The RAM 43 is configured with the same hardware as the RAM 23 described above.
The storage device 44 is configured with hardware similar to the storage device 24 described above. The storage device 44 stores programs executed by the processor 41 . The program may be downloaded to server 4 via a network. The program may be installed as stored in a computer-readable storage medium.
The communication interface 45 is configured with the same hardware as the communication interface 25 described above.
Note that the hardware configuration of the server 4 is not limited to the configuration described above. The server 4 allows omission and modification of the above components and addition of new components as appropriate.

Each unit implemented in the processor 41 will be described.
The processor 41 implements a start request acquisition unit 411, a target lesson identification unit 412, a prediction request output unit 413, a prediction information acquisition unit 414, and an output unit 415 by executing programs.

The start request acquisition unit 411 acquires a target lesson start request from the terminal 2 via the communication interface 45 . For example, the target lesson start request includes information specifying the target person and information specifying the target lesson.

The target lesson identification unit 412 identifies the target lesson as exemplified below. For example, the target lesson identification unit 412 identifies the target lesson by referring to information specifying the target lesson included in the target lesson start request.

The prediction request output unit 413 outputs a prediction request for the learning effect of the target test to the server 5 via the communication interface 45 . The learning effect prediction request includes information identifying the target person and information identifying the target lesson.

The prediction information acquisition unit 414 acquires learning effect information from the server 5 via the communication interface 45 . The learning effect information is transmitted from the server 5 to the server 4 as a response to the learning effect prediction request.

The output unit 415 outputs various information and instructions to the terminal 2 .
For example, the output unit 415 outputs learning effect information to the terminal 2 via the communication interface 45 . The learning effect information includes information about a message informing the subject of the learning effect.

For example, the output unit 415 outputs to the terminal 2 an instruction to display the learning effect on the terminal 2 when the target lesson is started or completed.
An instruction to display the learning effect on the terminal 2 will be described.
If the target lesson is a lecture, for example, the start of the target lesson is the timing at which the start screen of the target lecture is displayed on the terminal 2 . For example, when the target lesson is completed, it is the timing at which the end screen of the target lecture is displayed on the terminal 2 . If the target lesson is an exercise, for example, the start of the target lesson is the timing for displaying the initial screen provided by the target exercise on the terminal 2 . When the target lesson is completed, it is the timing at which the terminal 2 displays a screen showing the score or percentage of correct answers that the target person has obtained in the questions provided in the target exercise.

For example, the output unit 415 outputs to the terminal 2 information indicating predetermined attendance standards, which will be described later. The attendance standard can also be said to be the attendance status.
Predetermined participation standards will be explained.
If the subject lesson is a lecture, the predetermined attendance criterion is that the subject completes watching the subject lecture. If the subject lesson is an exercise, the predetermined participation criteria is that the subject should obtain a first score (predetermined score) or higher or a first correct answer rate (predetermined correct answer rate) or higher in the exercise. A setting example of the first score or the first percentage of correct answers will be described later.

A case will be described where the learning effect is displayed on the terminal 2 at the start of the target lesson.
For example, the output unit 415 outputs to the terminal 2, together with the contents of the target lesson, learning effect information and an instruction to display the learning effect on the terminal 2 at the start of the target lesson. The output unit 415 may output to the terminal 2 information indicating predetermined attendance standards. Accordingly, the display control unit 212 of the terminal 2 causes the display device 27 to display the contents of the target lesson and the learning effect at the timing when the student starts the target lesson. Further, the display control unit 212 of the terminal 2 causes the display device 27 to display the predetermined participation criteria in association with the learning effect at the same timing.

A case of displaying the learning effect on the terminal 2 when the target lesson is completed will be described.
For example, after distributing the content of the target lesson to the terminal 2, the output unit 415 outputs the learning effect information and an instruction to display the learning effect on the terminal 2 at the completion of the target lesson in response to the completion of the target lesson by the student. Output to 2. Alternatively, the output unit 415 may output to the terminal 2, together with the contents of the target lesson, learning effect information in advance and an instruction to display the learning effect on the terminal 2 when the target lesson is completed. Accordingly, the display control unit 212 of the terminal 2 causes the display device 27 to display the content of the target lesson and the learning effect at the timing when the student completes the target lesson. Further, the display control unit 212 of the terminal 2 causes the display device 27 to display the predetermined participation criteria in association with the learning effect at the same timing.

The server 5 will be explained.
The server 5 is a device used for generating a score prediction model for a target test and predicting a learning effect using the score prediction model. The score prediction model is a trained model for predicting the score that the target person can obtain when the target person actually takes the target test, based on at least the attendance history of the target person. In the following, the target test score predicted by the trained model is also referred to as the predicted score.

The server 5 includes a processor 51 , ROM 52 , RAM 53 , storage device 54 and communication interface 55 . The processor 51, ROM 52, RAM 53, storage device 54 and communication interface 55 are connected to each other via a data bus or the like.
The processor 51 controls the operation of the server 5 as a whole. The processor 51 is configured with the same hardware as the processor 21 described above. The processor 51 implements the later-described units that perform various operations by executing the programs developed in the RAM 53 .
The ROM 52 is configured with the same hardware as the ROM 22 described above.
The RAM 53 is configured with the same hardware as the RAM 23 described above.
The storage device 54 is configured with the same hardware as the storage device 24 described above. The storage device 54 stores score prediction models. The storage device 54 stores programs executed by the processor 51 . The program may be downloaded to server 5 via a network. The program may be one stored in a computer-readable storage medium and installed in the server 5 .
The communication interface 55 is configured with the same hardware as the communication interface 25 described above.
Note that the hardware configuration of the server 5 is not limited to the configuration described above. The server 5 allows omission and modification of the above components and addition of new components as appropriate.

Each unit implemented in the processor 51 will be described.
Processor 51 executes a program to obtain teacher data request unit 511, teacher data acquisition unit 512, model generation unit 513, model storage unit 514, prediction request acquisition unit 515, target data request output unit 516, target data acquisition unit 517, a prediction unit 518 and a prediction information output unit 519 are implemented.

The teacher data requesting unit 511 outputs a request for teacher data to the server 3 via the communication interface 55 . For example, the teacher data request unit 511 outputs a teacher data request to the server 3 when the score prediction model is generated by the server 5 and when the score prediction model is updated. A request for teacher data includes a request for a plurality of student data for the target course. A request for a plurality of student data for the target course includes a request for data regarding the attendance history and data regarding the score of the target exam. The plurality of student data requests for the target course may include requests for at least one of student experience data and student attribute data.

A teacher data acquisition unit 512 acquires teacher data from the server 3 via the communication interface 55 . The teacher data is transmitted from the server 3 to the server 5 in response to the teacher data request. The teacher data includes data regarding attendance histories and data regarding scores of target examinations for each of a plurality of students. The teacher data may include at least one of data on student experience and data on student attributes for each of the plurality of students.

As exemplified below, the model generation unit 513 generates a score prediction model based on at least the attendance histories of the multiple students and the scores of the target exams of the multiple students included in the teacher data. Since a plurality of student data are updated as described above, the model generation unit 513 generates a score prediction model based on the updated teacher data. Note that generating the score prediction model includes updating the score prediction model. For example, the model generation unit 513 may generate the score prediction model in a nighttime batch, or may generate the score prediction model in real time at the timing of predicting the learning effect.

The model generation unit 513 uses the score of the target test as an objective variable for generating the score prediction model. The model generation unit 513 uses each element for each lesson included in the attendance history as a feature amount for generating a score prediction model. There is a certain correlation between each element of each lesson included in the attendance history and the score of the target exam.

For example, the feature amount is the progress of lectures included in the attendance history. When the lecture has been taken, the learning time of the student tends to be longer than when the lecture has not been taken. As the study time increases, the score of the target test may tend to increase. For example, the feature quantity is the playback time of video or audio included in the attendance history. As the playback time of moving images or audio becomes longer, the learning time of students tends to become longer. As the study time increases, the score of the target test may tend to increase. For example, the feature amount is the usage time of the lecture included in the attendance history. As the usage time of the lecture becomes longer, the learning time of the student tends to become longer. As the study time increases, the score of the target test may tend to increase. For example, the feature amount is the progress of exercises included in the attendance history. If the exercise has been taken, the learning time of the student tends to be longer than if the exercise has not been taken. As the study time increases, the score of the target test may tend to increase. For example, the feature amount is the score or correct answer rate of exercises included in the attendance history. Practice questions consist of past questions and questions that are likely to appear in the target exam. As practice scores or percentages of correct answers increase, students may be more likely to score similarly high on target exams. Therefore, as the practice score or correct answer rate increases, the target test score may tend to increase. For example, the feature amount is the usage time of exercises included in the attendance history. As the usage time of the exercise increases, the learning time of the student tends to increase. As the study time increases, the score of the target test may tend to increase.

The model generation unit 513 may use each element that constitutes the student's experience as a feature amount for generating a score prediction model. There is a certain correlation between the elements that make up the student's experience and the score on the target exam. For example, the feature amount is the number of times the student has taken the target test included in the student's experience. As the number of times the target exam is taken increases, the student may tend to become accustomed to taking the target exam. As students become more accustomed to taking targeted exams, their scores on targeted exams may tend to increase. For example, the feature quantity is the past result of the target exam included in the student's experience. Target test scores may tend to be higher than past results of the target test. For example, the feature quantity is the number of times a student has taken a test other than the target test included in the student's experience. Students may tend to become accustomed to taking a test as they take some test more often. As students become more familiar with taking exams, scores on target exams may tend to rise.

The model generation unit 513 may use each element that constitutes the attributes of the student as a feature amount for generating the score prediction model. There is a certain correlation between each element that constitutes the student's attributes and the score of the target exam. For example, the feature amount is the age included in the student's attributes. As we age, memory may tend to decline. As a result, subject test scores tend to decline as age increases. For example, the feature amount is the gender included in the attributes of the student. Some tests may be for men and some may be for women. As such, subject test scores may tend to differ by gender. For example, the feature amount is the occupation and industry included in the student's attributes. Exams are highly relevant by profession and industry. For example, people in ICT-related professions and industries may be more inclined to take exams related to information processing. As such, subject test scores may tend to vary by occupation and industry.

The model generation unit 513 estimates the relationship of each feature amount with respect to the objective variable by machine learning, and generates a score prediction model. The score prediction model uses various variables corresponding to each feature quantity to obtain the predicted score. For example, the score prediction model uses whether or not each lecture has been taken as a variable. For example, the score prediction model uses the score or correct answer rate of each exercise as a variable.

For example, machine learning is supervised learning. Machine learning may generate prediction models by regression techniques such as linear regression and decision trees. The regression method is not limited to these. Machine learning may generate predictive models through classification techniques such as neural networks, random forests, support vector machines, and deep learning. Classification methods are not limited to these.

Note that the model generation unit 513 has explained an example in which the score prediction model is generated using a plurality of student data by machine learning, but the score prediction model may be generated without using machine learning. For example, the model generation unit 513 selects, from among multiple student data, arbitrary student data that is correlated with the attendance history of the target student data, and generates a score prediction model based on the selected student data. may be generated.

The model storage unit 514 stores information on the score prediction model generated by the model generation unit 513 in the storage device 54 .

The prediction request acquisition unit 515 acquires a learning effect prediction request from the server 4 via the communication interface 55 . The prediction request acquisition unit 515 acquires information specifying the target person and information specifying the target lesson included in the learning effect prediction request.

The target data request output unit 516 outputs a request for data regarding the target person to the server 3 via the communication interface 55 as exemplified below. In the following, data relating to subjects are also referred to as subject data. For example, the target data request output unit 516 refers to the information specifying the target person included in the learning effect prediction request. The target data request output unit 516 specifies a target person and outputs a request for target person data to the server 3 . The request for subject data includes information identifying the subject.

The target data acquisition unit 517 acquires target person data from the server 3 via the communication interface 55 . The subject data includes data regarding the attendance history of the subject. The subject data may include at least one of data about the subject's experience of the subject and data about the subject's attributes. The subject data is transmitted from server 3 to server 5 in response to the request for subject data.

The prediction unit 518 predicts learning effects as exemplified below.
The learning effect includes any one of first to fifth learning effects exemplified below.

The first learning effect is the predicted score increase for the target test. The second learning effect is the predicted score for the subject exam if predetermined attendance criteria are met. In the following, the predicted score of the target exam when the predetermined participation criteria are met is also referred to as the first predicted score. The third learning effect is the predicted score of the target test when the first predicted score and predetermined participation criteria are not met. In the following, the predicted score of the target exam when the predetermined participation criteria are not met is also referred to as the second predicted score. The fourth learning effect is the score up to the target score when a predetermined attendance standard is satisfied. A fifth learning effect is the possibility of reaching the target score when predetermined attendance standards are met.

Prediction of the first learning effect will be described. The predicted score increase is an increase in the score of the target test that is predicted to increase as a result of taking the target lesson by the target person.
First, the prediction unit 518 predicts a first predicted score using a score prediction model. Next, the prediction unit 518 predicts a second predicted score using the score prediction model. Next, the prediction unit 518 obtains the difference between the first predicted score and the second predicted score. The difference corresponds to the expected increase score. Thereby, the prediction unit 518 can acquire information indicating the first learning effect.

The prediction of the second learning effect will be described. The prediction unit 518 predicts the first predicted score using the score prediction model. Thereby, the prediction unit 518 can acquire information indicating the second learning effect.

The prediction of the third learning effect will be described. First, the prediction unit 518 predicts a first predicted score using a score prediction model. Next, the prediction unit 518 predicts a second predicted score using the score prediction model. Thereby, the prediction unit 518 can acquire information indicating the third learning effect.

The prediction of the fourth learning effect will be described. The target score used in the fourth learning effect is the target score for passing the target test. For example, if the target exam has a fixed passing score, the target score may be the fixed passing score or a score higher than the fixed passing score. For example, if the passing score of the target test fluctuates, the target score may be the average score of the past multiple passing scores, or may be a higher score than the average score. First, the prediction unit 518 predicts a first predicted score using a score prediction model. Next, the prediction unit 518 predicts the first predicted score using the score prediction model. Next, the prediction unit 518 obtains the difference from the first predicted score to the target point. The difference corresponds to the score up to the target point. Thereby, the prediction unit 518 can acquire information indicating the fourth learning effect.

The prediction of the fifth learning effect will be described. The target point used in the fifth learning effect may be the same as the target point used in the fourth learning effect. First, the prediction unit 518 predicts a first predicted score using a score prediction model. Next, the prediction unit 518 predicts the probability of reaching the target point based on the first predicted score and the target point. In one example, the probability of reaching the target point is the pass rate. The pass rate is the ratio of the first predicted score to the target score. In this example, predictor 518 determines the ratio of the first predicted score to the target point. 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, a plurality of ranks are set according to the deviation of the first predicted score from the target score or the ratio of the first predicted score to the target score. For example, the multilevel rank includes four levels of A, B, C, and D, but is not limited thereto. In this example, the prediction unit 518 selects a rank corresponding to the difference between the first predicted score and the target score from multiple stages of ranks. Alternatively, the prediction unit 518 may select a rank corresponding to the ratio of the first prediction score to the target score from multiple ranks. Thereby, the prediction unit 518 can acquire information indicating the fifth learning effect.

The prediction information output unit 519 outputs the learning effect information acquired by the prediction unit 518 to the server 4 via the communication interface 55 . The learning effect information is transmitted from the server 5 to the server 4 as a response to the learning effect prediction request.

A configuration example of a plurality of lessons forming a target course will be described.
FIG. 2 is a diagram showing a configuration example of a plurality of lessons forming a target course.
The target course consists of x (two or more) lessons. The x lessons consist of y (one or more) lectures and y exercises. Note that the number of lectures may differ from the number of exercises. Lectures and exercises are alternately arranged, but not limited to this. Two or more lectures may be arranged in succession. Two or more exercises may be arranged in series.

An example of predicting learning effects and an example of display will be explained separately for the target lecture and target exercise.

An example of a target lecture will be explained.
Here, it is assumed that lessons 1 to 4 shown in FIG. 2 are viewed lessons. It is assumed that lessons 5 to x are unviewed lessons. It is assumed that Lecture 3 of Lesson 5 is the target lecture.

First, a prediction example of the first learning effect in the target lecture will be described.
The prediction unit 518 uses the score prediction model to predict the first prediction score when the target person completes viewing the lecture 3, which is the target lecture. A case in which the subject completes viewing and listening to lecture 3, which is the subject lecture, is an example of a case in which a predetermined attendance standard is satisfied. Here, the prediction unit 518 applies data of the subject's attendance history to the variables of the score prediction model for lessons 1 to 4, which are already taken lessons. The prediction unit 518 applies the data indicating that the lecture has been taken to variables of the score prediction model for lecture 3, which is the target lecture. The prediction unit 518 applies empty data to the variables of the score prediction model for lessons 6 to x, excluding the target lecture, among the lessons not taken. Alternatively, the prediction unit 518 may apply default data to the variables of the score prediction model for lessons 6 to x of the unattended lessons excluding the target lecture. For example, if the untaken lesson is a lecture, the default data includes data indicating that the lesson has been taken. For example, if the untaken lesson is an exercise, the default data includes data indicating a score or correct answer rate of 0 for the exercise. Alternatively, if the untaken lesson is an exercise, the default data may include data showing the exercise score or percentage correct as the average score or percentage correct for multiple first-time students. good. The prediction unit 518 applies the above data to variables of the score prediction model to predict the first predicted score.

The prediction unit 518 uses the score prediction model to predict the second predicted score when the target person has not viewed the target lecture. A case where the target person has not viewed the target lecture is an example of a case where the predetermined attendance standard is not satisfied. Here, the prediction unit 518 applies data of the subject's attendance history to the variables of the score prediction model for lessons 1 to 4, which are already taken lessons. The prediction unit 518 applies the data indicating non-attendance to variables of the score prediction model for lecture 3, which is the target lecture. The prediction unit 518 applies empty data to the variables of the score prediction model for lessons 6 to x, excluding the target lecture, among the unattended lessons. Alternatively, the prediction unit 518 may apply the default data described above to the variables of the score prediction model for lessons 6 to x of the unattended lessons excluding the target lecture. The predictor 518 applies the above data to the variables of the score prediction model to predict the second predicted score.

Note that the prediction unit 518 preferably predicts the first predicted score and the second predicted score, except for the data applied to the variables of the score prediction model for the target lecture. The reason for this is to improve the accuracy of the increase prediction score brought about by taking the target lecture by changing only the attendance standard of the target lecture.

Next, the prediction unit 518 obtains the predicted increase score, which is the difference between the first predicted score and the second predicted score, and acquires information indicating the first learning effect. Since the data applied to the variables of the score prediction model differ from student to student, the predicted score increase differs from student to student even for the same target lecture. Similarly, the predicted increase score differs for each lecture even for the same student.

The second to fifth learning effect prediction examples in the target lecture are the same as the first learning effect prediction example described above. For example, the prediction unit 518 predicts the first prediction score as described above and acquires information indicating the second learning effect. For example, the prediction unit 518 predicts the first predicted score and the second predicted score as described above, and acquires information indicating the third learning effect. For example, the prediction unit 518 predicts the first predicted score as described above, obtains the difference from the first predicted score to the target score, and acquires information indicating the fourth learning effect. For example, the prediction unit 518 predicts the first predicted score as described above, obtains the possibility of reaching the target point based on the first predicted score and the target point, and acquires information indicating the fifth learning effect. do.

Next, a display example of the first learning effect for the target lecture will be described.
FIG. 3 is a diagram showing a display example of the first learning effect for the target lecture displayed on the display device 27. As shown in FIG.

The display control unit 212 causes the display device 27 to display the content of the target lecture and the predicted score increase (for example, 8 points) at the timing when the student starts the target lesson. The display control unit 212 may cause the display device 27 to display a predetermined attendance standard in association with the predicted score increase. For example, the display control unit 212 causes the display device 27 to display a message indicating that the predicted score increase is related to completion of taking the target lecture, in association with the predicted score increase. The display mode such as the position, size, and how to display the message is not limited as long as it attracts the attention of the target person. The target person can easily understand that if the target lecture is attended, the expected increase in score can be obtained.

Alternatively, or together with this, the display control unit 212 similarly causes the display device 27 to display the content of the target lecture and the predicted score increase at the timing when the student completes the target lesson. The display control unit 212 may cause the display device 27 to display a predetermined attendance standard in association with the predicted score increase. For example, the display control unit 212 similarly causes the display device 27 to display a message indicating that the predicted score increase is related to completion of taking the target lecture, in association with the predicted score increase. The target person can easily understand that he or she has obtained an expected increase in score by attending the target lecture.

The display examples of the second to fifth learning effects are the same as the display example of the first learning effect described above. Note that when the acquisition unit 211 acquires learning effect information including two or more of the first to fifth learning effects, the display control unit 212 displays two or more of the first to fifth learning effects. It may be displayed on the device 27 .

Describe an example of a target exercise.
Here, it is assumed that lessons 1 to 5 shown in FIG. 2 are viewed lessons. Lessons 6 to x are assumed to be unviewed lessons. Exercise 3 of Lesson 6 is assumed to be the target exercise.

First, a prediction example of the first learning effect in the target exercise will be described.
The prediction unit 518 uses the score prediction model to predict the first predicted score when the subject obtains a first score or higher or a first correct answer rate or higher in exercise 3, which is the target exercise. A case in which the target person obtains a first score or higher or a first correct answer rate or higher in Exercise 3, which is the target exercise, is an example of a case in which the predetermined participation criteria are satisfied. Here, the prediction unit 518 applies data of the subject's attendance history to variables of the score prediction model for lessons 1 to 5, which are lessons already taken. The prediction unit 518 applies data indicating the first score or the first percentage of correct answers to the variables of the score prediction model for exercise 3, which is the target exercise. The prediction unit 518 applies empty data to the variables of the score prediction model for lessons 7 to x of the lessons not taken, excluding the target exercises. Alternatively, the prediction unit 518 may apply the default data described above to the variables of the score prediction model for lessons 7 to x of the untaken lessons excluding the target exercises. The prediction unit 518 applies the above data to variables of the score prediction model to predict the first predicted score.

The prediction unit 518 uses the score prediction model to predict a second predicted score when the subject obtains a second score or higher or a second correct answer rate or higher in Exercise 3, which is the target exercise. A case in which the target person obtains a second score or higher or a second correct answer rate or higher in Exercise 3, which is the target exercise, is an example of a case in which the predetermined participation criteria are not met. The second score is a score lower than the first score. The second correct answer rate is a lower correct answer rate than the first correct answer rate. The second score or second percentage of correct answers may be 0, or may be the average score or percentage of correct answers of a plurality of students at the time of the first lecture. Here, the prediction unit 518 applies data of the subject's attendance history to variables of the score prediction model for lessons 1 to 5, which are lessons already taken. The prediction unit 518 applies data indicating the second score or the second percentage of correct answers to the variables of the score prediction model for exercise 3, which is the target exercise. The prediction unit 518 applies empty data to the variables of the score prediction model for lessons 7 to x of the lessons not taken, excluding the target exercises. Alternatively, the prediction unit 518 may apply the default data described above to the variables of the score prediction model for lessons 7 to x of the untaken lessons excluding the target exercises. It should be noted that the prediction unit 518 preferably predicts the first predicted score and the second predicted score, except for the data applied to the variables of the score prediction model for the target exercise. The predictor 518 applies the above data to the variables of the score prediction model to predict the second predicted score.

The prediction unit 518 obtains a predicted increase score, which is the difference between the first predicted score and the second predicted score, and acquires information indicating the first learning effect. Since the data applied to the variables of the score prediction model differ from student to student, the expected increase in score differs from student to student even for the same target exercise. Similarly, the expected increase in score differs for each exercise even for the same student.

The second to fifth learning effect prediction examples in the target exercise are the same as the first learning effect prediction example described above. For example, the prediction unit 518 predicts the first prediction score as described above and acquires information indicating the second learning effect. For example, the prediction unit 518 predicts the first predicted score and the second predicted score as described above, and acquires information indicating the third learning effect. For example, the prediction unit 518 predicts the first predicted score as described above, obtains the difference from the first predicted score to the target score, and acquires information indicating the fourth learning effect. For example, the prediction unit 518 predicts the first predicted score as described above, obtains the possibility of reaching the target point based on the first predicted score and the target point, and acquires information indicating the fifth learning effect. do.

Here, an example of setting the first score or the first percentage of correct answers will be described using exercise 3 as an example. The maximum score for Exercise 3 shall be 100 points.
The predictor 518 predicts a plurality of predicted scores ranging from 0 to 100 points. For example, the prediction unit 518 predicts the predicted score at predetermined score intervals (eg, 5 points).

FIG. 4 is a diagram illustrating the relationship between the score of practice 3 and the predicted score.
As shown in FIG. 4, the rate of increase in predicted score decreases as the score of exercise 3 increases. For example, growth rate is the increase in predicted score for a given scoring interval. The growth rate relates to the slope of the graph of the relationship between Exercise 3 scores and predicted scores. In the range of 80 to 100 points for exercise 3, the predicted score changes little. Therefore, the prediction unit 518 sets the score (for example, 80 points) at which the rate of increase in predicted score predicted according to the score of the target exercise does not satisfy the predetermined rate of increase as the first score. In other words, the first score is a score that considers the balance between the predicted score expected by taking the target exercise and the maintenance of the target person's motivation. Similarly, the prediction unit 518 sets the correct answer rate at which the predicted score increase rate of the target test predicted according to the exercise correct answer rate does not satisfy the predetermined increase rate as the first correct answer rate. The relationship between the practice score and the predicted score differs for each student. Therefore, the first score or the first percentage of correct answers differs from student to student even for the same target exercise. The relationship between the exercise score and the predicted score varies from exercise to exercise. Therefore, the first score or the first percentage of correct answers differs for each exercise even for the same student. The first score or the first correct answer rate may be determined based on the elongation rate as described above, but may be a preset fixed value (eg 60 points or 60%). . The fixed value may be common or different for each exercise. The fixed value may be arbitrarily adjustable.

Note that the prediction unit 518 has described an example in which one first prediction score is predicted when a predetermined attendance standard is satisfied, but the present invention is not limited to this. The prediction unit 518 may predict multiple first prediction scores, as exemplified below. In this example, the predetermined attendance standards include multiple attendance standards corresponding to multiple first scores or multiple first percentages of correct answers. For example, the plurality of first scores or the plurality of first correct answer rates may or may not be evenly spaced, such as scores at 5-point intervals or correct answer rates at 5% intervals. The plurality of first scores or the plurality of first correct answer rates include scores or correct answer rates where the predicted score growth rate of the target test predicted according to the exercise score or correct answer rate does not meet the predetermined growth rate. You can stay.

The prediction unit 518 predicts a plurality of first scores or a plurality of first prediction scores according to a plurality of first percentages of correct answers. The prediction unit 518 obtains differences between the plurality of first predicted scores and the second predicted scores, and predicts a plurality of predicted increases in scores for each of the plurality of attendance standards. The prediction unit 518 acquires information indicating a first learning effect including a predicted score increase for each of a plurality of attendance standards. It should be noted that the prediction unit 518 can acquire second to fifth learning effects including values for each of a plurality of attendance standards in the same manner as the first learning effect.

Next, a display example of the first learning effect for the target exercise will be described.
FIG. 5 is a diagram showing a display example of the first learning effect for the target exercise displayed on the display device 27. As shown in FIG.

The display control unit 212 displays the predicted score increase (for example, 10 points) along with the contents of the target exercise at the timing when the student starts the target lesson. The display control unit 212 may cause the display device 27 to display a predetermined attendance standard in association with the predicted score increase. For example, the display control unit 212 causes the display device 27 to display a message indicating that the predicted increase score is related to acquisition of a first score (for example, 80 points) or higher in association with the predicted increase score. The display control unit 212 may cause the display device 27 to display a message about the first percentage of correct answers instead of the first score. The display mode such as the position, size, and how to display the message is not limited as long as it attracts the attention of the target person. The subject can easily grasp the score or correct answer rate of the subject exercise, which is the target for obtaining an increase predicted score, and can face the subject exercise.

Note that the display control unit 212 may cause the display device 27 to display a graph showing the relationship between the score of the target exercise or the percentage of correct answers and the predicted score, along with the predicted score increase. In FIG. 5, the second predicted score is an example in which the second score is set to zero. In this example, the prediction information acquisition unit 414 of the server 4 acquires from the server 5 information indicating a plurality of scores or a plurality of prediction scores of the percentage of correct answers for exercise 3 . The output unit 415 of the server 4 outputs to the terminal 2 information indicating a plurality of scores or a plurality of predicted scores of the correct answer rate of Exercise 3 together with the learning effect information including the first learning effect. The acquisition unit 211 of the terminal 2 acquires from the server 4 the learning effect information including the first learning effect as well as information indicating a plurality of scores or a plurality of predicted scores of the correct answer rate for Exercise 3 . The target person can easily grasp the transition of the expected score according to the score of the target exercise or the percentage of correct answers.

In addition, when the prediction unit 518 of the server 5 predicts the first score or a plurality of expected increase scores according to a plurality of attendance criteria with different first correct answer rates, the display control unit 212 predicts the plurality of first scores. Alternatively, the display device 27 may display a plurality of predicted increases in score in association with each of the plurality of first percentages of correct answers. In this example, the prediction information acquisition unit 414 of the server 4 acquires learning effect information including the first learning effect from the server 5 . The first learning effect includes a plurality of first predicted scores for each of the plurality of attendance criteria. The output unit 415 of the server 4 outputs learning effect information including the first learning effect to the terminal 2 . The acquisition unit 211 of the terminal 2 acquires learning effect information including the first learning effect from the server 4 . The subject can easily grasp the score of the target exercise or the expected increase in score according to the percentage of correct answers.

Alternatively, or together with this, the display control unit 212 similarly causes the display device 27 to display the content of the target exercise and the predicted score increase at the timing when the student completes the target lesson. The display control unit 212 may cause the display device 27 to display a predetermined attendance standard in association with the predicted score increase. For example, the display control unit 212 causes the display device 27 to display a message indicating that the predicted increase score is related to acquisition of a first score or more in association with the predicted increase score. The display control unit 212 may cause the display device 27 to display a message about the first percentage of correct answers instead of the first score. The target person can easily grasp the score or correct answer rate of the target exercise to obtain the expected increase in score, and can prepare for the review of the target exercise.

As described above, the display control unit 212 may cause the display device 27 to display a graph showing the relationship between the score of the target exercise or the percentage of correct answers and the predicted score, along with the predicted score increase. As described above, the display control unit 212 may cause the display device 27 to display a plurality of predicted increase scores in association with each of the plurality of first scores or the plurality of first correct answer percentages. The display control unit 212 predicts an increase corresponding to the highest first score or first correct answer rate exceeded by the subject's score or correct answer rate among the plurality of first scores or the plurality of first correct answer rates. The score may be displayed on the display device 27 . The target person can easily grasp the score of the target practice that he or she has obtained or the expected increase in score obtained from the correct answer rate.

The display examples of the second to fifth learning effects are the same as the display example of the first learning effect described above. Note that when the acquisition unit 211 acquires learning effect information including two or more of the first to fifth learning effects, the display control unit 212 displays two or more of the first to fifth learning effects. It may be displayed on the device 27 .

An example of operation related to the score prediction model described above will now be described.
FIG. 6 is a sequence diagram showing an operation example related to the score prediction model. Note that one or more operations shown in FIG. 6 may be changed or omitted as appropriate.

The teacher data requesting unit 511 outputs a request for teacher data to the server 3 via the communication interface 45 (step S101). The processor 31 acquires a request for teacher data from the server 5 via the communication interface 35 (step S102). The processor 31 extracts the teaching data from the storage device 34 and outputs the teaching data to the server 5 via the communication interface 35 (step S103). The teacher data acquisition unit 512 acquires the teacher data from the server 3 via the communication interface 55 (step S104). The model generation unit 513 generates a score prediction model based on the teacher data (step S105). The model storage unit 514 stores the score prediction model in the storage device 54 (step S106).

An operation example related to the learning effect described above will be described.
FIG. 7 is a sequence diagram showing an operation example related to the learning effect. Note that one or more operations shown in FIG. 7 may be changed or omitted as appropriate.

The processor 21 outputs a target lesson start request to the server 4 via the communication interface 25 in response to the subject's input for starting the target lesson through the input device 26 (step S201). The start request acquisition unit 411 acquires a start request for the target lesson from the terminal 2 via the communication interface 45 (step S202). The target lesson identification unit 412 refers to the target lesson start request and identifies the target lesson (step S203). The prediction request output unit 413 outputs a learning effect prediction request to the server 5 via the communication interface 45 (step S204).

The prediction request acquisition unit 515 acquires a learning effect prediction request from the server 4 via the communication interface 55 (step S205). The target data request output unit 516 outputs a request for target person data to the server 3 via the communication interface 55 (step S206).

The processor 31 acquires a request for subject data from the server 5 via the communication interface 35 (step S207). The processor 31 extracts the subject data from the storage device 34 and outputs the subject data to the server 5 via the communication interface 35 (step S208).

The target data acquisition unit 517 acquires the target person data from the server 3 via the communication interface 55 (step S209). The prediction unit 518 predicts the learning effect using the score prediction model (step S210). The prediction information output unit 519 outputs the learning effect information to the server 4 via the communication interface 55 (step S211).

The prediction information acquisition unit 414 acquires learning effect information from the server 5 via the communication interface 45 (step S212). The output unit 415 outputs the learning effect information to the terminal 2 via the communication interface 45 (step S213). The acquisition unit 211 acquires the learning effect information from the server 4 via the communication interface 25 (step S214). The display control unit 212 causes the display device 27 to display the learning effect (step S215).

Note that the output unit 415 may switch whether or not to output the learning effect information according to the learning effect. In this example, output unit 415 compares the learning effect to a predetermined criterion. The predetermined standard is a standard for judging the magnitude of the learning effect, and the predetermined standard can be arbitrarily changed. The output unit 415 switches whether or not to output the learning effect information according to the comparison result. For example, in the first learning effect, the output unit 415 compares the expected increase score with a predetermined criterion. When the predicted increase score is equal to or higher than the predetermined reference, the output unit 415 determines that display of the predicted increase score is necessary, and outputs the learning effect information to the terminal 2 . When the predicted increase score is less than the predetermined reference, the output unit 415 determines that display of the predicted increase score is unnecessary, and omits output of the learning effect information. Note that the output unit 415 may compare the first predicted score with a predetermined standard for the second learning effect. For the second learning effect, the output unit 415 may compare at least one of the first predicted score and the second predicted score with a predetermined standard. For the third learning effect, the output unit 415 may compare the score up to the target point with a predetermined standard. The output unit 415 may compare the probability of reaching the target point to a predetermined criterion.

According to the embodiment, the server 4 can output learning effect information to the terminal 2 . The terminal 2 can display the learning effect on the display device 27 . Although the learning effect differs from lesson to lesson, the subject can be aware of the learning effect for each lesson. By being conscious of the learning effect, the target person can work on the target lesson with strength according to the learning effect. For example, the subject can avoid spending too much time on lessons that have a low contribution to the score of the subject exam. Therefore, the subject can efficiently take each lesson. In addition, since the subject can be conscious of the learning effect of each lesson as a short-term goal, it is possible to maintain the motivation to take each lesson. In this way, the server 4 and the terminal 2 can prompt the subject to take desirable actions in order to pass the subject test.

According to embodiments, the learning effect includes at least one of the first to fifth learning effects described above. The subject can grasp the learning effect of the subject lesson with various indexes.

According to embodiments, the increased predicted score is the difference between the first predicted score and the second predicted score. As a result, the server 4 can acquire a highly accurate predicted score increase related to the target lesson.

According to embodiments, the predetermined attendance criterion is that the subject completes viewing the subject lecture. According to this example, the server 4 can acquire a highly accurate predicted score increase related to completion of viewing of the target lecture. According to embodiments, the predetermined attendance criterion is that the subject achieves a first score or better or a first correct answer rate or better in the target exercise. According to this example, the server 4 can obtain a highly accurate predicted increase score associated with obtaining a first score or higher or a first correct answer rate or higher in the target exercise.

According to embodiments, a first predicted score and a predicted increased score are predicted for each of a plurality of attendance criteria. The target person can easily grasp the learning effect according to the score or correct answer rate of the target exercise.

According to the embodiment, the first score or the first correct answer rate is the score or the correct answer rate at which the predicted score increase rate predicted according to the target exercise score or correct answer rate no longer satisfies a predetermined increase rate. . Alternatively, the plurality of first scores or the plurality of first correct answer rates include scores or correct answer rates at which the predicted score growth rate predicted according to the practice score or correct answer rate does not satisfy a predetermined growth rate. For example, if the target exercise has a perfect score, the maximum learning effect is expected. However, if the subject sets the goal of getting a perfect score in every exercise, the subject's motivation decreases. On the other hand, even if the target exercise score is not perfect, the learning effect may be almost the same as when the target exercise score is perfect. The target person can take each exercise without difficulty by aiming for the first score that considers the balance between the learning effect points expected by taking the target exercise and the maintenance of the target person's motivation.

According to embodiments, the learning effect is predicted based on at least the subject's attendance history and the different attendance criteria of the subject lesson. The learning history of the target person and the different learning standards of the target lesson are used to predict the learning effect by the score prediction model, as described above. As a result, the server 4 can obtain a predicted increase score with high accuracy. According to embodiments, the learning effect is predicted based on at least the subject's attendance history, the different attendance criteria of the subject lesson, the attendance history of the plurality of students, and the subject test scores of the plurality of students. The attendance histories of the multiple students and the scores of the target exams by the multiple students are used to generate the score prediction model as described above. As a result, the server 4 can obtain a predicted increase score with high accuracy.

According to the embodiment, the server 4 outputs an instruction to the terminal 2 to display the learning effect on the terminal 2 at the start or completion of the target lesson. This allows the subject to be aware of how much the subject lesson contributes to the score of the subject exam before taking the subject lesson. The target person can work on the target lesson with strength according to the learning effect, or increase the motivation to attend the target lecture. After taking the target lesson, the target person can be aware of how much the target lesson contributes to the score of the target test. The target person can work on reviewing the target lesson by adding strength and weakness according to the learning effect.

According to the embodiment, the server 4 outputs to the terminal 2 information indicating the predetermined attendance criteria. As a result, the subject learns the predetermined participation criteria displayed on the display device 27, and can take the target lesson with an awareness of meeting the predetermined participation criteria in order to obtain a learning effect.

According to the embodiment, the server 4 switches whether or not to output the learning effect information according to the learning effect. As a result, the server 4 can notify the target person of the magnitude of the effect obtained from the target lesson, depending on whether the learning effect is displayed or not. The target person can take each lesson efficiently by adjusting how to deal with each lesson depending on whether the learning effect is displayed or not.

Although an example in which the server 4 is a separate device from the servers 2 and 5 has been described, the present invention is not limited to this. Server 4 may be a device integrated with at least one of server 2 and server 5 . In the case where the server 4 is configured as a device integrated with the server 2, the server 4 stores data on the students of the target course. When the server 4 is configured as a device integrated with the server 5 , the processor 41 of the server 4 implements each unit described with reference to the processor 51 as appropriate.

In short, the present invention is not limited to the present 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]
a specifying unit that specifies a lesson to be taken by a target person among a plurality of lessons that constitute a course related to an exam;
an acquisition unit that acquires information indicating a learning effect of taking the lesson to be taken;
an output unit that outputs information indicating the learning effect to the subject's terminal;
Information processing device.
[C2]
an acquisition unit that acquires information indicating a learning effect of a subject who has taken a subject lesson from among a plurality of lessons that constitute a course related to an exam;
a display control unit for displaying the learning effect on a display unit;
terminal with
[C3]
The learning effect is an increase predicted score of the test, a first predicted score of the test when predetermined participation standards are met, the first predicted score and the first prediction score of the test when the predetermined participation standards are not satisfied A predicted score of 2, a score to a target score if the predetermined attendance criteria are met, and at least one of the possibility of reaching the target score if the predetermined attendance criteria are met, [ C1] or the terminal according to [C2].
[C4]
The information processing device according to [C3] or the terminal according to [C3], wherein the predicted increase score is a difference between the first predicted score and the second predicted score.
[C5]
The information processing device according to [C3] or the terminal according to [C3], wherein the score to the target point is a difference from the first predicted score to the target point.
[C6]
The information processing device according to [C3] or the terminal according to [C3], wherein the possibility of reaching the target point is predicted based on the first predicted score and the target point.
[C7]
7. The information processing apparatus according to any one of claims 3 to 6, wherein when the lesson to be attended is a lecture, the predetermined attendance criterion is that the subject completes viewing and listening to the lecture. The terminal according to any one of [C3] to [C6].
[C8]
If the lesson to be attended is an exercise, the predetermined participation criterion is that the target person acquires a predetermined score or higher or a predetermined correct answer rate or higher in the exercise, any of [C3] to [C6]. 1. The information processing apparatus according to 1 or the terminal according to any one of [C3] to [C6].
[C9]
The predetermined score or the predetermined correct answer rate is a score or a correct answer rate at which the predicted score growth rate of the test predicted according to the exercise score or correct answer rate does not satisfy a predetermined growth rate, [C8 ] or the terminal according to [C8].
[C10]
The predetermined participation standards include a plurality of participation standards according to a plurality of scores or a plurality of correct answer rates,
The information processing device according to [C8] or the terminal according to [C8], wherein the first predicted score is predicted for each of the plurality of attendance standards.
[C11]
The predetermined participation standards include a plurality of participation standards according to a plurality of scores or a plurality of correct answer rates,
The information processing device according to [C8] or the terminal according to [C8], wherein the predicted increase score is predicted for each of the plurality of attendance standards.
[C12]
The plurality of scores or the plurality of correct answer rates include a score or a correct answer rate at which the predicted score growth rate of the test predicted according to the exercise score or correct answer rate does not meet a predetermined growth rate, [C10 ] or the information processing apparatus according to [C11] or the terminal according to [C10] or [C11].
[C13]
The information processing device according to [C1] or the terminal according to [C2], wherein the learning effect is predicted based on at least the learning history of the subject and different learning criteria of the lesson to be taken.
[C14]
The learning effect is predicted based on at least the attendance history of the subject, the different attendance standards of the lesson to be taken, the attendance history of the plurality of students, and the test scores of the plurality of students, [C1] The information processing device described in 1. or the terminal described in [C2].
[C15]
The information processing apparatus according to [C1], wherein the output unit outputs to the terminal an instruction to display the learning effect on the terminal when the lesson to be taken is started or completed.
[C16]
The information processing apparatus according to any one of [C3] to [C6], wherein the output unit outputs information indicating the predetermined attendance criteria to the terminal.
[C17]
The information processing apparatus according to [C1], wherein the output unit switches whether or not to output information indicating the learning effect according to the learning effect.

DESCRIPTION OF SYMBOLS 1... Lecture distribution system 2... Terminal 3... Server 4... Server 5... Server 21... Processor 22... ROM 23... RAM 24... Storage device 25... Communication interface 26... Input device 27 Display device 31 Processor 32 ROM 33 RAM 34 Storage device 35 Communication interface 41 Processor 42 ROM 43 RAM 44 Storage device 45 Communication interface 51 Processor, 52... ROM, 53... RAM, 54... Storage device, 55... Communication interface, 211... Acquisition unit, 212... Display control unit, 411... Start request acquisition unit, 412... Target lesson identification unit, 413... Prediction request output Unit 414 Prediction information acquisition unit 415 Output unit 511 Teacher data request unit 512 Teacher data acquisition unit 513 Model generation unit 514 Model storage unit 515 Prediction request acquisition unit 516 Target Data request output unit, 517...target data acquisition unit, 518...prediction unit, 519...prediction information output unit.

Claims (10)

Based on student data of a plurality of students who have taken a course related to a prescribed exam, including attendance history and scores of the prescribed exam for each lesson among the plurality of lessons that constitute the course Using a score prediction model generated by the An information processing device comprising a prediction unit that predicts a first prediction score that can be obtained in a predetermined test. The prediction unit uses the score prediction model to predict a second predicted score that can be obtained in the predetermined test when the lesson to be taken does not satisfy the learning standard, and calculates the first predicted score and the first predicted score. 2. The information processing apparatus according to claim 1, wherein information indicating a predicted score increase of said lesson to be taken, which is a difference from the predicted score of No. 2, is acquired as information indicating a learning effect. The information processing apparatus according to claim 1, wherein said prediction unit acquires information indicating said first predicted score as information indicating a learning effect. The prediction unit uses the score prediction model to predict a second predicted score that can be obtained in the predetermined test when the lesson to be taken does not satisfy the learning standard, and calculates the first predicted score and the second predicted score. 2. The information processing apparatus according to claim 1, wherein the information indicating the predicted score of 2 is obtained as the information indicating the learning effect. The information processing apparatus according to claim 1, wherein said prediction unit acquires information indicating a score from said first predicted score to a target score as information indicating a learning effect. The information processing apparatus according to claim 1, wherein the prediction unit acquires information indicating a possibility of reaching the target point predicted based on the first prediction score and the target point as information indicating a learning effect. . The predetermined attendance standards include a plurality of attendance standards,
The first predicted score is predicted for each of the plurality of attendance standards,
The information processing apparatus according to any one of claims 1 to 6 . When the lesson to be attended is an exercise, the attendance criterion is that the target person acquires a predetermined score or higher or a predetermined correct answer rate or higher in the exercise.
The information processing apparatus according to any one of claims 1 to 6. An information processing method executed by an information processing device,
Based on student data of a plurality of students who have taken a course related to a prescribed exam, including attendance history and scores of the prescribed exam for each lesson among the plurality of lessons that constitute the course Using a score prediction model generated by the A method of information processing comprising predicting a first predictive score obtainable in a given test. 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 8.

Images