JP7542164B1 - Program, method, information processing device, and system - Google Patents

Abstract

[Problem] There is a problem that it is not possible to output explanatory sentences suitable for a user's learning. [Solution] A program to be executed by a computer having a processor and a storage unit, the program executing an attribute acquisition step in which the processor acquires attribute information related to a first user, and an explanatory sentence acquisition step in which an explanatory sentence related to the first user is acquired from a large-scale language model based on the attribute information related to the first user. [Selected Figure] Figure 12

Description

This disclosure relates to a program, a method, an information processing device, and a system.

2. Description of the Related Art Learning support techniques using information processing terminals are known.
Patent Document 1 discloses a technique for evaluating the content of a learner's answers and providing appropriate information to the learner and a learning supporter.
Patent Document 2 discloses a learning support technology that can increase the learning motivation of registered users (students) and improve the learning effect.

JP 2023-080493 A Japanese Patent Application Publication No. 2013-142718

There is a problem in that it is not possible to output explanatory text suitable for the user's learning.
Therefore, the present disclosure has been made to solve the above problem, and has an object to provide a technology for outputting an explanatory text suitable for a user's learning.

A program to be executed by a computer having a processor and a storage unit, the program executing an attribute acquisition step in which the processor acquires attribute information about a first user, and an explanatory text acquisition step in which explanatory text related to the first user is acquired from a large-scale language model based on the attribute information about the first user.

According to the present disclosure, it is possible to output explanatory text suitable for the user's learning.

FIG. 2 is a block diagram showing the functional configuration of the system 1. FIG. 2 is a block diagram showing the functional configuration of the server 10. FIG. 2 is a block diagram showing a functional configuration of a first user terminal 20. FIG. 2 is a block diagram showing a functional configuration of a second user terminal 30. FIG. 13 is a diagram showing the data structure of a user table 1012. FIG. 11 is a diagram showing the data structure of a group table 1013. FIG. 10 is a diagram showing the data structure of a homework table 1014. FIG. 10 is a diagram showing the data structure of a teaching material master 1021. 13 is a flowchart showing an operation of a grouping process. 13 is a flowchart showing the operation of an explanation creation process. 13 is a flowchart showing the operation of a question setting process. 13 is a screen example showing the operation of the explanation creation process. 11 is a screen example showing the operation of a question setting process. 11 is a screen example showing the operation of a learning material presentation process. FIG. 2 is a block diagram showing the basic hardware configuration of a computer 90.

Embodiments of the present disclosure will be described below with reference to the drawings. In all figures describing the embodiments, common components are given the same reference numerals, and repeated explanations will be omitted. Note that the following embodiments do not unduly limit the contents of the present disclosure described in the claims. Furthermore, not all components shown in the embodiments are necessarily essential components of the present disclosure. Furthermore, each figure is a schematic diagram, and is not necessarily a precise illustration.

<Configuration of System 1>
The system 1 in the present disclosure is an information processing system that supports educational services provided by teachers who provide instruction to students in educational institutions such as schools and cram schools.
The system 1 includes information processing devices, namely, a server 10, a first user terminal 20, a second user terminal 30, and a large-scale language model 50, which are connected via a network N.
FIG. 1 is a block diagram showing the functional configuration of the system 1.
FIG. 2 is a block diagram showing the functional configuration of the server 10. As shown in FIG.
FIG. 3 is a block diagram showing the functional configuration of the first user terminal 20. As shown in FIG.
FIG. 4 is a block diagram showing the functional configuration of the second user terminal 30. As shown in FIG.

Each information processing device is configured by a computer equipped with an arithmetic unit and a storage device. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by the hardware configuration will be described later. For each of the server 10, the first user terminal 20, the second user terminal 30, and the large-scale language model 50, explanations that overlap with the basic hardware configuration and basic functional configuration of the computer described later will be omitted.

<Configuration of Server 10>
The server 10 is an information processing device that supports educational services provided by teachers to students.
The server 10 includes a memory unit 101 and a control unit 104 .

<Configuration of storage unit 101 of server 10>
The storage unit 101 of the server 10 includes an application program 1011 , a user table 1012 , a group table 1013 , a homework table 1014 , and a teaching material master 1021 .

The application program 1011 is a program for causing the control unit 104 of the server 10 to function as each functional unit.
The application programs 1011 include applications such as a web browser application.

The user table 1012 is a table that stores and manages information on member users (hereinafter, users) who use the service. When a user registers to use the service, the user's information is stored in a new record in the user table 1012. This allows the user to use the service according to the present disclosure. In the present disclosure, user information on users such as students (first users), teachers (second users), and administrators of the information processing service according to the present disclosure (administrator users) is stored.
The user table 1012 is a table having a user ID as a primary key, and columns of user ID, user name, attribute data, and group ID.
FIG. 5 is a diagram showing the data structure of the user table 1012. As shown in FIG.

The user ID is an item for storing user identification information for identifying a user. The user identification information is an item for which a unique value is set for each user.
The user name is an item for storing the name of the user. The user name may be set to any character string such as a nickname instead of a name.
The attribute data includes the following information: In particular, the attribute data includes information regarding the proficiency level of the learning content.
・Personal information: name, date of birth, gender, nationality/ethnicity ・Contact information: address, phone number, email address ・Answer information: grade/class, subjects taken, proficiency, learning progress, test scores/evaluations, attendance ・Health information: allergies, medical history, special health considerations ・Psychological characteristics: learning style ・Interests/hobbies: club activities, hobbies and areas of interest ・Educational considerations: information on the presence or absence of learning disabilities, language disorders, intellectual disabilities, etc. Proficiency is an indicator of the extent to which a student has understood and acquired the learning content of a specific learning unit. Proficiency is used in online learning services to evaluate the learning progress of each student and provide appropriate learning support. Proficiency is an indicator calculated based on data (answer information such as correct/incorrect answers and answer time) obtained in the process of a student solving problems and assignments in a unit, viewing and reading learning materials, etc.
Specifically, the proficiency level includes answer information such as information on the correctness of the answer when the student solves each problem, the time it took to solve the problem, etc. The proficiency level may include a multi-level index/rank that is evaluated based on the answer information, such as A (good understanding), B (general understanding), C (not very good understanding), and D (hardly understood).
The group ID is an item for storing group identification information for identifying a group. The group identification information is an item in which a unique value is set for each piece of group information.

The group table 1013 is a table for storing and managing information relating to groups (group information).
The group table 1013 is a table having a group ID as a primary key, and columns of group ID, group name, feature amount, and description.
FIG. 6 is a diagram showing the data structure of the group table 1013. As shown in FIG.

The group ID is an item for storing group identification information for identifying a group. The group identification information is an item in which a unique value is set for each piece of group information.
The group name is an item for storing the name of the group. Any character string can be set as the group name.
The feature amount is an item that stores statistics and state amounts that characterize a group.
Specifically, the feature amount is calculated based on one or more attribute data of a plurality of users included in the group and a combination thereof.
The feature amount is calculated based on answer information such as correct answers and answer times of multiple users included in the group. The feature amount may include averages of scores (correct answer rate) and answer times for each learning unit of multiple users included in the group. The feature amount may include an average rank (A to D) of multiple users included in the group. In addition, the feature amount may include information indicating the degree of proficiency of multiple users included in the group, such as high proficiency, medium proficiency, and low proficiency.
The explanatory text includes information on study topics and recommended questions related to one or more users included in the group.
Specifically, the learning tasks are based on the user's current learning subjects and content, including achievement tasks based on the user's strengths and weaknesses, ongoing curriculum, or specific assessment criteria. The recommended questions correspond to these learning tasks and include learning materials to help the user deepen their understanding and improve their learning proficiency.
The explanatory text may include study advice, feedback, study guidance, study progress, future study plans or ways to improve study, recommendations for additional study materials, etc. for one or more users in the group.

The homework table 1014 is a table for storing and managing homework (learning materials) given to students (first users) and information (homework information) relating to the contents of the answers to the homework.
The homework table 1014 is a table having columns for homework ID, question setter ID, student ID, teaching material ID, and answer data.
FIG. 7 is a diagram showing the data structure of the homework table 1014. As shown in FIG.

The homework ID is an item for storing homework identification information for identifying homework. The homework identification information is an item for which a unique value is set for each piece of homework information.
The question setter ID is an item that stores user identification information of the question setter (teacher, second user).
The student ID is an item that stores user identification information of a student (first user).
The learning material ID is an item for storing learning material identification information for identifying learning materials.
The answer data is an item that stores the content of the student's answer to the learning material.
The answer data may include answer information such as whether the student answered the learning material correctly or incorrectly, and the time it took to answer.

The learning material master 1021 is a table for storing and managing information related to learning materials (learning material information).
The teaching material master 1021 is a table having a teaching material ID as a primary key and columns of teaching material ID and teaching material data.
FIG. 8 is a diagram showing the data structure of the teaching material master 1021. As shown in FIG.

The learning material ID is an item for storing learning material identification information for identifying learning material. The learning material identification information is an item for which a unique value is set for each piece of learning material information.
The learning material data is an item for storing information about learning materials.
Specifically, the teaching material data includes the following information:
・Textbooks: Materials that describe the basic content of each subject ・Workbooks/exercise books: Materials to deepen learning through problem exercises and practical practice

<Configuration of control unit 104 of server 10>
The control unit 104 of the server 10 includes a user registration control unit 1041, a grouping unit 1042, an explanation creation unit 1043, and a question setting unit 1044. The control unit 104 executes an application program 1011 stored in the storage unit 101, thereby realizing each functional unit.

The user registration control unit 1041 performs processing to store information about users who wish to use the service according to the present disclosure in the user table 1012 .
The information stored in the user table 1012 is generated when a user opens a web page operated by a service provider from any information processing terminal, inputs information into a specific input form, and transmits the information to the server 10. The user registration control unit 1041 stores the received information in a new record in the user table 1012, completing the user registration. This allows the user stored in the user table 1012 to use the service.
Before the user registration control unit 1041 registers user information in the user table 1012, the service provider may carry out a predetermined examination to restrict whether or not the user is permitted to use the service.
The user ID may be any character string or number that can identify the user, any character string or number desired by the user, or an arbitrary character string or number may be automatically set by the user registration control unit 1041.

The grouping unit 1042 executes the grouping process. Details will be described later.

The description creation unit 1043 executes the description creation process. Details will be described later.

The question setting unit 1044 executes the question setting process. Details will be described later.

<Configuration of First User Terminal 20>
The first user terminal 20 is an information processing device operated by a user who uses the service. The first user terminal 20 may be, for example, a mobile terminal such as a smartphone or a tablet, a stationary personal computer (PC) or a laptop PC, or a wearable terminal such as a head mounted display (HMD) or a wristwatch terminal.
The first user terminal 20 includes a storage unit 201 , a control unit 204 , an input device 206 , and an output device 208 .

<Configuration of the storage unit 201 of the first user terminal 20>
The storage unit 201 of the first user terminal 20 includes a first user ID 2011 and an application program 2012 .

The first user ID 2011 is the account ID of the first user. The user transmits the first user ID 2011 from the first user terminal 20 to the server 10. The server 10 identifies the user based on the first user ID 2011 and provides the user with the services disclosed herein. The first user ID 2011 includes information such as a session ID that is temporarily assigned by the server 10 when identifying the user using the first user terminal 20.

The application program 2012 may be pre-stored in the storage unit 201, or may be configured to be downloaded from a web server operated by a service provider via a communication IF.
The application programs 2012 include applications such as a web browser application.
The application program 2012 includes an interpreted programming language such as JavaScript (registered trademark) that runs on a web browser application stored on the first user terminal 20 .

<Configuration of the control unit 204 of the first user terminal 20>
The control unit 204 of the first user terminal 20 includes an input control unit 2041 and an output control unit 2042. The control unit 204 executes an application program 2012 stored in the storage unit 201, thereby realizing each functional unit.

<Configuration of the input device 206 of the first user terminal 20>
The input device 206 of the first user terminal 20 includes a camera 2061 , a microphone 2062 , a position information sensor 2063 , a motion sensor 2064 , and a touch device 2065 .

<Configuration of the output device 208 of the first user terminal 20>
The output device 208 of the first user terminal 20 includes a display 2081 and a speaker 2082 .

<Configuration of second user terminal 30>
The second user terminal 30 is an information processing device operated by a user who uses the service. The second user terminal 30 may be, for example, a mobile terminal such as a smartphone or a tablet, a stationary personal computer (PC) or a laptop PC, or a wearable terminal such as a head mounted display (HMD) or a wristwatch terminal.
The second user terminal 30 includes a storage unit 301 , a control unit 304 , an input device 306 , and an output device 308 .

<Configuration of the storage unit 301 of the second user terminal 30>
The storage unit 301 of the second user terminal 30 includes a second user ID 3011 and an application program 3012 .

The second user ID 3011 is the account ID of the second user. The user transmits the second user ID 3011 from the second user terminal 30 to the server 10. The server 10 identifies the user based on the second user ID 3011 and provides the user with the services disclosed herein. The second user ID 3011 includes information such as a session ID that is temporarily assigned by the server 10 to identify the user who is using the second user terminal 30.

The application program 3012 may be pre-stored in the storage unit 301, or may be configured to be downloaded from a web server operated by a service provider via a communication IF.
Application programs 3012 include applications such as a web browser application.
The application program 3012 includes an interpreted programming language such as JavaScript (registered trademark) that runs on a web browser application stored on the second user terminal 30 .

<Configuration of the control unit 304 of the second user terminal 30>
The control unit 304 of the second user terminal 30 includes an input control unit 3041 and an output control unit 3042. The control unit 304 executes an application program 3012 stored in the storage unit 301, thereby realizing each functional unit.

<Configuration of the input device 306 of the second user terminal 30>
The input device 306 of the second user terminal 30 includes a camera 3061 , a microphone 3062 , a position information sensor 3063 , a motion sensor 3064 , and a touch device 3065 .

<Configuration of the output device 308 of the second user terminal 30>
The output device 308 of the second user terminal 30 includes a display 3081 and a speaker 3082 .

<Configuration of Large-Scale Language Model 50>
The large-scale language model 50 is an artificial intelligence system that learns from a wide range of text data and exhibits high performance in various language-related tasks such as natural language understanding and generation. The large-scale language model 50 analyzes large amounts of document and conversation data and has the capabilities of context understanding, sentence generation, question answering, translation, summarization, etc.
The large-scale language model 50 includes, for example, ChatGPT developed by OpenAI, Inc., GoogleBard developed by Google, Inc., and the like.

<Operation of System 1>
Each process of the system 1 will be described below.
FIG. 9 is a flowchart showing the operation of the grouping process.
FIG. 10 is a flowchart showing the operation of the explanation creation process.
FIG. 11 is a flowchart showing the operation of the question setting process.
FIG. 12 is a screen example showing the operation of the explanation creation process.
FIG. 13 is a screen example showing the operation of the question setting process.
FIG. 14 is a screen example showing the operation of the learning material presentation process.

<Grouping process>
The grouping process is a process of classifying a plurality of students (first users) into a plurality of groups according to the similarity of the attribute data of the students.

<Overview of grouping process>
The grouping process is a series of processes that acquires attribute data of multiple students, performs clustering processing according to the similarity of the attribute data, classifies the multiple students into multiple groups, and calculates the feature amount for each group.

The grouping process may be performed at the following times:
In the information processing service according to the present disclosure, the grouping unit 1042 of the server 10 may perform grouping processing after presenting a test such as an assignment or a problem to the student (first user) and confirming a specific range of learning effect. After confirming the progress of learning effect in daily lessons before and after the test, the first user is automatically associated with multiple groups. The first user can be grouped into a more suitable group according to the latest attribute information. By the question setting processing described later, learning materials can be provided collectively for multiple first users having the same learning proficiency.
The information processing apparatus may be configured to execute the grouping process in response to an input operation by a user of an administrator of the information processing service according to the present disclosure.
The grouping unit 1042 of the server 10 may execute the grouping process for each predetermined period (hourly, daily, weekly, monthly, etc.).

<Details of grouping process>
The grouping process will be described in detail below.

In step S101, the grouping unit 1042 of the server 10 executes an attribute acquiring step of acquiring attribute information including information regarding the mastery level of the learning content of the learning material related to the first user. The attribute acquiring step acquires attribute information related to a plurality of first users.
Specifically, the grouping unit 1042 of the server 10 refers to the user table 1012 to acquire attribute data for each of the students. The grouping unit 1042 of the server 10 may be configured to filter the students according to predetermined attribute data such as grade and class included in the attribute data, and acquire the attribute data of the students. In other words, the grouping unit 1042 of the server 10 may execute grouping processing for some students who belong to a predetermined grade and a predetermined class.

In step S102, the grouping unit 1042 of the server 10 executes a group step of associating the first users with one or more groups based on the attribute information acquired in the attribute acquisition step. The group step associates the first users with one or more groups according to the similarity of the attribute information of the first users.
Specifically, the grouping unit 1042 of the server 10 regards the attribute data as a vector having values for each of a plurality of elements included in the attribute data. The grouping unit 1042 of the server 10 calculates the distance between the vectors based on the attribute data of each student by a method such as Euclidean distance, Manhattan distance, cosine similarity, or Jaccard similarity.
In particular, it is preferable that the grouping unit 1042 of the server 10 calculates the similarity of a vector consisting of the similarity of answer information such as the first user's level of proficiency, whether the question was correct or incorrect, and the answering time.
The grouping unit 1042 of the server 10 classifies (clusters) the multiple first users into multiple groups using the following methods (one or more methods or a combination of them) depending on the similarity of the attribute data of the multiple first users acquired.
The grouping unit 1042 of the server 10 may apply any processing such as a normalization method to vector components of attribute data, proficiency, etc. In this case, the processed vector is also included in the attribute data of the student.

K-means method: In this method, multiple students are classified into K clusters (groups). First, K cluster centers are randomly selected. Then, each student is assigned to the closest cluster center and the cluster centers are updated. This process is repeated until no cluster centers change.
In this method, a plurality of first users can be classified by specifying a plurality of cluster numbers (group numbers).
Hierarchical clustering: In this method, each student is initially considered as a separate cluster (group), and similar clusters are gradually merged. The similarity between clusters is calculated using criteria such as the shortest distance, the longest distance, or the average distance.
This is suitable when the number of clusters is unknown in advance or when you want to understand the structure of the data in detail.
Density-based clustering (such as DBSCAN)
This method forms clusters (groups) based on density (concentration of data points). Areas with a certain density or higher are considered clusters, and surrounding low-density areas are treated as noise.
It works well when the clusters are irregularly shaped or the data is noisy.
Spectral Clustering: In this method, dimensionality is reduced using a similarity matrix of the data, and then clustering is performed using a method such as K-means. The similarity matrix represents the similarity (or distance) between data points.
It is suitable for graph-structured data and data with nonlinear structures.

The grouping unit 1042 of the server 10 classifies the multiple students acquired in step S102 into multiple groups. For example, the grouping unit 1042 of the server 10 classifies multiple students (Student A, Student B, Student C, Student D) into Group A (Student A, Student C), Group B (Student B), Group C (Student D), etc.

In step S102, a group step executes a step of associating the first users with one or more groups after the first users confirm a learning effect in a certain range.
Specifically, in the information processing service according to the present disclosure, the grouping unit 1042 of the server 10 may present tests (tests) such as assignments or questions to students (first users), confirm the learning effect in a specific range, and then perform the clustering process in step S102.

In step S103, the grouping unit 1042 of the server 10 calculates a feature amount for each cluster (group) classified in step S102.
Specifically, the grouping unit 1042 of the server 10 aggregates the characteristics of data points within a cluster (vectors based on the attribute data, proficiency, and answer information of one or more students belonging to the cluster) and calculates a feature (representative vector) that represents the characteristics of the entire cluster.

For example, the grouping unit 1042 of the server 10 may include a feature calculated by the following method in the feature for each cluster: The grouping unit 1042 of the server 10 calculates a feature based on one or more vectors of attribute data, proficiency, and answer information of one or more students belonging to a cluster.
・Average vector (mean vector, median vector, mode vector)
Calculate the average (statistical value such as mean, median, mode, etc.) of the vectors of all students belonging to the cluster.
Each student's vector contains as elements the student's proficiency scores for each learning unit.
Each element of the means vector reflects the average proficiency of students in that cluster.
Instead of the average, any statistical value such as a maximum value or a minimum value may be used.
Variance and standard deviation Calculate the variance and standard deviation of attribute data, proficiency, answer information, and vectors within a cluster.
It shows how much variation there is in the proficiency levels of students within a cluster.
- Range (maximum and minimum values)
Calculate the difference between the highest and lowest proficiency scores in the cluster.
Indicates the range of proficiency levels of students within a cluster.
Features Based on Specific Indicators For example, any parameter based on a specific indicator, such as the average correct answer rate or the average answer time in a specific learning unit, may be included in the features.

The grouping unit 1042 of the server 10 associates the classification created in step S102 with the feature amount calculated in step S103, and stores the association in the group name and feature amount items of a new record in the group table 1013. As a result, group information for classifying students is stored in the group table 1013.
The grouping unit 1042 of the server 10 associates and stores in the user table 1012 the group ID of the group to which the student is classified (the group ID of the record newly created in the group table 1013) in the group ID field of the record identified based on the user ID of the student classified in step S102.
This expresses an association between a student and the groups to which the student belongs, and also identifies which groups the student is included in.

<Explanatory text creation process>
The explanation creation process is a process for creating an explanation for each group.

<Outline of explanation creation process>
The description creation process is a series of processes that acquire features for each group, create a prompt (an input sentence for creating a description for the group) that will be an input sentence to the large-scale language model based on the features, send the created prompt to the large-scale language model, acquire the description from the large-scale language model, and store the acquired description. The description creation unit 1043 of the server 10 executes the description creation process for each of the multiple group information stored in the group table 1013, associates the description with the group information, and stores it in the description item of the group table 1013.

<Details of the description creation process>
The explanation text creation process will be described in detail below.

In step S301, the description creation unit 1043 of the server 10 executes a group information acquisition step in which the description creation unit 1043 refers to the group table 1013 and acquires group information including the group name and features.

In step S302, the explanatory text creation unit 1043 of the server 10 executes a prompt creation step to create a prompt (an input sentence including an instruction sentence and a command sentence for creating an explanatory text regarding the group) that will be an input sentence to the large-scale language model, based on the group information including the features acquired in step S301.
The explanation creation unit 1043 of the server 10 inputs input data including statistics for each element and the contents of the element included in attribute information on one or more first users associated with a predetermined group into the large-scale language model.

Specifically, the explanation creation unit 1043 of the server 10 creates the prompt shown below based on the features acquired in step S301. Note that the prompt below is an example, and the prompt is not limited to the prompt described below. The features include statistics for each element included in the attribute data related to the student and the contents of the element.

〔prompt〕
#Order:
The following information is about the learning proficiency of a specific group of students classified according to their learning proficiency. Please output explanatory text including information about the assignments and recommended questions based on the learning proficiency of the following groups.
# Group A learning proficiency:
Problem A: Average correct answer rate (%) Average answer time (seconds) Variance Standard deviation Problem B: Average correct answer rate (%) Average answer time (seconds) Variance Standard deviation Problem C: Average correct answer rate (%) Average answer time (seconds) Variance Standard deviation Study unit A: Average correct answer rate (%) Average answer time (seconds) Variance Standard deviation Study unit B: Average correct answer rate (%) Average answer time (seconds) Variance Standard deviation Study unit C: Average correct answer rate (%) Average answer time (seconds) Variance Standard deviation

# Problems that Group A struggles with: Contents of Problem A...
The contents of problem B...
The contents of problem C...
#Basic problems that group A solves to overcome their weaknesses. Contents of problem A...
The contents of problem B...
The contents of problem C...
#Other related questions Contents of question A...
The contents of problem B...
The contents of problem C...
#Description:

The prompt may include attribute data of the multiple students belonging to the group, instead of the learning proficiency of the multiple students belonging to the group. The prompt may include information on the assignments, questions, answer information for each unit, and learning proficiency related to the learning materials.
Specifically, the prompts may include tasks and questions related to the learning proficiency of each group.

The explanation creation unit 1043 of the server 10 may not input attribute information regarding one or more first users associated with a predetermined group into the large-scale language model.
Specifically, the explanation creation unit 1043 of the server 10 may include features calculated based on the attribute data of multiple students in the prompt, but it is preferable to configure the prompt not to include the attribute data, proficiency level, answer information, etc. of individual students. This allows the explanation creation unit 1043 of the server 10 to avoid transmitting the attribute data, proficiency level, answer information, etc., which are personal information of individual students, to the external large-scale language model 50. For example, it is possible to prevent personal information of students from being transmitted to the outside, thereby reducing the risk of personal information leakage, etc.

In step S303, the explanation creation unit 1043 of the server 10 executes a prompt sending step of sending the prompt created in the prompt creating step to the large-scale language model 50.
Specifically, the explanation creation unit 1043 of the server 10 sends a request including the prompt created in step S302 to an endpoint (URL) that accepts input of a prompt provided by the large-scale language model 50.
The explanation creation unit 1043 of the server 10 may include in the request to the endpoint hyperparameters for controlling the answer sentence from the large-scale language model 50, such as the model name of the large-scale language model 50 to be used and temperature, other than the prompt.

In step S304, the explanation creation unit 1043 of the server 10 executes an explanation acquisition step of acquiring an explanation related to the first user from the large-scale language model based on attribute information related to the first user. The explanation acquisition step acquires an explanation including information on the assignments and recommended questions for the first user. The explanation acquisition step also acquires an explanation including information on the assignments and recommended questions for each learning unit for the first user.
Specifically, in response to the request sent to the large-scale language model 50 in step S303, the explanation creation unit 1043 of the server 10 receives and acquires a response including an explanation output by the large-scale language model 50. The acquired explanation is an explanation output by the large-scale language model 50 based on the student's attribute data, proficiency level, answer information, and the like.
The explanatory text includes information about the assignments and recommended questions. The explanatory text may include information about the assignments and recommended questions for each learning unit. An example of the explanatory text is shown below.

[Explanation]
#Description:
#Challenge: Students in this group understand the degree of polynomials and the degree of monomials. However, their ability to express coefficients, especially positive integers and -1, is low. They also have a somewhat low ability to determine whether an equation is of degree n.
#Recommended questions: The weak questions for this group are questions D, E, L, etc. Specifically, this group lacks understanding of knowledge F, M, and P. Recommended questions for acquiring these knowledge include Q and R.

The explanation creation unit 1043 of the server 10 stores the explanation output in step S304 in the explanation item of the record of the group information of the group for which the prompt is created in the group table 1013. As a result, an explanation is stored in association with each piece of group information.
The explanation creation unit 1043 of the server 10 may present the explanation acquired in the explanation acquisition step.

Specifically, the second user operates the input device 306 of the second user terminal 30, executes a browser application or the like, and opens the explanation presentation page D1 by inputting the URL or the like of a web page (explanation presentation page) for executing the explanation presentation process. The control unit 304 of the second user terminal 30 transmits a request including the second user ID 3011 to the server 10 to open the explanation presentation page.

When the server 10 receives the request, it generates an explanation presentation page and transmits it to the second user terminal 30. The control unit 304 of the second user terminal 30 displays the explanation presentation page on the display 3081 of the second user terminal 30 and presents it.
12 is a screen example of an explanation presentation screen in the explanation presentation process. An explanation presentation page D1 is displayed on the display 3081 of the second user terminal 30. The explanation presentation page D1 includes group information D11, D12, D13, . . .
The group information D11 includes a group name D111, an explanatory text D112, the names of students included in the group (username of the first user) D113, the number of students D114, and a question button D115. Similarly, the group information D12 and D13 include group names D121 and D131, explanatory text D122 and D132, the names of students included in the group (username of the first user) D123 and D133, the numbers of students D124 and D134, and question buttons D125 and D135.

<Question processing>
The question setting process is a process of setting study material questions collectively to multiple students (first users) included in a group.

<Outline of question setting process>
The question setting process is a series of processes that accept a selection of one or more groups from a teacher (second user), accept a selection of one or more learning materials from the teacher, assign the one or more learning materials selected to one or more groups, and present the assigned one or more learning materials to the students.

<Details of question setting process>
The question setting process will be described in detail below.

In step S501, the question setting unit 1044 of the server 10 executes a learning material receiving step of receiving, from a second user for a predetermined group, a selection of one or more learning materials corresponding to the explanatory text acquired in the explanatory text acquiring step.
Specifically, on the explanation presentation page D1, the teacher selects the question button D115, D125, D135 of the group for which he/she wishes to carry out the question setting process, from among the groups included in the group information D11, D12, D13, . . .

The question setting unit 1044 of the server 10 refers to the teaching material master 1021 to obtain teaching material information including a teaching material ID and teaching material data. The question setting unit 1044 of the server 10 may be configured to filter multiple learning materials according to predetermined attribute data such as the grade and class of the group related to the selected question setting button D115, D125, D135, and obtain and identify teaching material information related to the learning material. In other words, teaching material information unrelated to the grade and class of the group may be excluded to obtain and identify teaching material information.

The question setting unit 1044 of the server 10 generates a question page based on the acquired teaching material information related to the learning material, and transmits the question page to the second user terminal 30. The control unit 304 of the second user terminal 30 displays and presents the question page on the display 3081 of the second user terminal 30.
13 is an example of a question screen in the question setting process. A question setting page D3 is displayed on the display 3081 of the second user terminal 30. The question setting page D3 includes questions D301, D302, D303, etc. for each unit. The questions D301, D302, D303, etc. include question names D3011, D3021, D3031, etc., check boxes D3012, D3022, D3032, etc., and an assignment button D31. The question setting page D3 displays a list of questions (learning materials) for each unit. Each of the questions D301, D302, D303, etc. is associated with a material ID, etc., of the material information obtained from the material master 1021.

In addition, the control unit 304 of the second user terminal 30 may present questions to the teacher in a state in which the check boxes D3012, D3022, D3032... for questions D301, D302, D303... related to recommended questions included in the explanatory texts D112, D122, D132 are selected.
This allows teachers to omit the cumbersome task of selecting recommended questions, and reduces the input workload of teachers.

In step S502, the question setting unit 1044 of the server 10 executes a learning material receiving step of receiving a selection of one or more learning materials from the second user for a predetermined group.
Specifically, the second user operates the input device 306 of the second user terminal 30 to select check boxes D3012, D3022, D3032, .... This allows the second user to select one or more learning materials from the learning materials listed on the question page D3.

In step S503, the question setting unit 1044 of the server 10 executes a learning material providing step of providing one or more learning materials received in the learning material receiving step collectively to one or more first users associated with a predetermined group.
Specifically, the second user selects the assignment button D31 by operating the input device 306 of the second user terminal 30. The control unit 304 of the second user terminal 30 transmits a request to the server 10 to assign learning materials to multiple students for each group. The request includes the second user ID 3011, the first user IDs of one or more first users included in the group selected in step S501, and one or more teaching material IDs specified based on the check boxes D3012, D3022, D3032... selected in step S502.
The question setting unit 1044 of the server 10 stores the second user ID 3011, the multiple first user IDs, and one or multiple teaching material IDs included in the request in the question setter ID, student ID, and teaching material ID fields of a new record in the homework table 1014. Specifically, the question setting unit 1044 of the server 10 stores multiple records in the homework table 1014 according to the multiple first user IDs and multiple teaching material IDs. This allows multiple learning materials to be collectively set to one or multiple students belonging to the group selected by the teacher in step S501.

In step S504, the question setting unit 1044 of the server 10 executes a learning material presenting process to present learning materials identified based on the learning material ID stored in the homework table 1014 to the first user.
Specifically, the first user operates the input device 206 of the first user terminal 20 to execute a browser application or the like, and opens the learning material presentation page D5 by inputting the URL or the like of a web page (learning material presentation page) for executing the learning material presentation process. The control unit 204 of the first user terminal 20 transmits a request including the first user ID 2011 for opening the learning material presentation page to the server 10.

When the question setting unit 1044 of the server 10 receives the request, it searches the student ID field in the homework table 1014 based on the first user ID 2011, and acquires and specifies the homework information. Note that the question setting unit 1044 of the server 10 may acquire only records in which nothing is stored in the answer data field (null values or blanks, etc.), and may specify the homework information by excluding records in which information is stored in the answer data field (where the student has already answered). The question setting unit 1044 of the server 10 searches the teaching material ID field in the teaching material master 1021 based on the acquired teaching material ID, and acquires teaching material information including teaching material data.
The question setting unit 1044 of the server 10 generates a learning material presentation page based on the acquired homework information and learning material information, and transmits the learning material presentation page to the first user terminal 20. The control unit 204 of the first user terminal 20 displays and presents the learning material presentation page D5 on the display 2081 of the first user terminal 20.
14 is an example of a learning material presentation screen in the learning material presentation process. A learning material presentation page D5 is displayed on the display 2081 of the first user terminal 20. The learning material presentation page D5 includes learning materials D51, D52, D53, etc. The learning material D51 includes a question D511 and an answer input field D512. The learning materials D51, D52, D53, etc. are drawn based on the learning material data included in the learning material information.
The first user operates the input device 206 of the first user terminal 20 to input an answer to the question D511 in the answer input field D512. The control unit 204 of the first user terminal 20 transmits a request including the answer content input in the answer input field D512 and the homework ID related to the question D511 to the server 10. The question setting unit 1044 of the server 10 searches the homework ID field in the homework table 1014 based on the homework ID included in the request received from the first user terminal 20, and stores the answer content input in the answer input field D512 in the answer data field of the identified record. This makes it possible to store the answer content for each question set to the student in association with each other.

<Basic computer hardware configuration>
15 is a block diagram showing the basic hardware configuration of a computer 90. The computer 90 includes at least a processor 901, a main storage device 902, an auxiliary storage device 903, and a communication IF 991 (interface). These are electrically connected to each other by a communication bus 921.

The processor 901 is hardware for executing a set of instructions written in a program. The processor 901 is composed of an arithmetic unit, registers, peripheral circuits, etc.

The main memory device 902 is used to temporarily store programs and data processed by the programs. For example, it is a volatile memory such as a DRAM (Dynamic Random Access Memory).

The auxiliary storage device 903 is a storage device for storing data and programs. For example, it is a flash memory, a hard disk drive (HDD), a magneto-optical disk, a CD-ROM, a DVD-ROM, a semiconductor memory, etc.

The communication IF 991 is an interface for inputting and outputting signals for communicating with other computers via a network using a wired or wireless communication standard.
The network is composed of various mobile communication systems constructed by the Internet, LAN, wireless base stations, etc. For example, the network includes 3G, 4G, 5G mobile communication systems, LTE (Long Term Evolution), wireless networks that can connect to the Internet through a predetermined access point (e.g., Wi-Fi (registered trademark)), etc. In the case of wireless connection, communication protocols include, for example, Z-Wave (registered trademark), ZigBee (registered trademark), Bluetooth (registered trademark), etc. In the case of wired connection, the network also includes one directly connected by a USB (Universal Serial Bus) cable, etc.

The computer 90 can be realized virtually by distributing all or part of each hardware configuration across multiple computers 90 and connecting them together via a network. In this way, the concept of computer 90 includes not only a computer 90 housed in a single housing or case, but also a virtualized computer system.

<Basic Functional Configuration of Computer 90>
A description will now be given of the functional configuration of a computer realized by the basic hardware configuration (FIG. 15) of a computer 90. The computer includes at least the functional units of a control unit, a storage unit, and a communication unit.

The functional units of the computer 90 can also be realized by distributing all or part of each functional unit across multiple computers 90 connected to each other via a network. The concept of computer 90 includes not only a single computer 90 but also a virtualized computer system.

The control unit is realized by the processor 901 reading various programs stored in the auxiliary storage device 903, expanding them in the main storage device 902, and executing processing in accordance with the programs. The control unit can realize functional units that perform various information processing depending on the type of program. In this way, the computer is realized as an information processing device that performs information processing.

The storage unit is realized by a main storage device 902 and an auxiliary storage device 903. The storage unit stores data, various programs, and various databases. Furthermore, the processor 901 can secure a storage area corresponding to the storage unit in the main storage device 902 or the auxiliary storage device 903 in accordance with a program. Furthermore, the control unit can cause the processor 901 to execute processes for adding, updating, and deleting data stored in the storage unit in accordance with various programs.

The term database refers to a relational database, which is used to manage sets of data called masters and tables in a tabular format structurally defined by rows and columns, by associating them with each other. In a database, a table is called a table or master, a column in a table is called a column, and a row in a table is called a record. In a relational database, relationships between tables and masters can be set and associated.
Usually, a column that serves as a primary key for uniquely identifying a record is set in each table and each master, but setting a primary key to a column is not essential. The control unit can cause the processor 901 to add, delete, or update records in a specific table or master stored in the storage unit according to various programs.
Furthermore, by storing data, various programs, and various databases in the storage unit, it can be considered that the information processing device and information processing system according to the present disclosure have been manufactured.

In addition, the databases and masters in this disclosure may include any data structure (such as a list, dictionary, associative array, or object) in which information is structurally defined. Data structures also include data that can be considered as data structures by combining data with functions, classes, methods, etc. written in any programming language.

The communication unit is realized by the communication IF 991. The communication unit realizes the function of communicating with other computers 90 via a network. The communication unit can receive information transmitted from other computers 90 and input the information to the control unit. The control unit can cause the processor 901 to execute information processing on the received information in accordance with various programs. In addition, the communication unit can transmit information output from the control unit to other computers 90.

<Additional Notes>
The matters described in the above embodiments will be supplemented below.

(Appendix 1)
A program to be executed on a computer having a processor and a memory unit, the program executing an attribute acquisition step (S101) in which the processor acquires attribute information about a first user, and an explanatory sentence acquisition step (S304) in which an explanatory sentence related to the first user is acquired from a large-scale language model based on the attribute information about the first user.
This makes it possible to obtain an explanatory text suitable for the learning of the first user (student) according to the attribute information of the first user.

(Appendix 2)
The program according to claim 1, wherein the attribute acquisition step (S101) is a step of acquiring attribute information including information regarding the first user's level of mastery of the learning content of the learning material.
This makes it possible to obtain explanatory text suitable for the first user's learning depending on the first user's learning proficiency.

(Appendix 3)
The program according to claim 1, wherein the explanatory text acquisition step (S304) is a step of acquiring an explanatory text including information regarding the first user's assignment and recommended problems.
This makes it possible to obtain explanatory texts including tasks and recommended questions (promised questions) suitable for the first user's study based on the attribute information of the first user.

(Appendix 4)
The program according to claim 3, wherein the explanatory text acquisition step (S304) is a step of acquiring explanatory text including information regarding the assignments and recommended questions for each learning unit of the first user.
This makes it possible to obtain assignments for each learning unit suitable for the first user's learning based on the attribute information of the first user, and explanatory text including recommended questions (proposed questions).

(Appendix 5)
The program described in Appendix 1, wherein the attribute acquisition step (S101) is a step of acquiring attribute information regarding a plurality of first users, and the processor executes a group step (S102) of associating the plurality of first users with one or more groups based on the attribute information acquired in the attribute acquisition step, and the explanatory text acquisition step (S304) is a step of acquiring explanatory text regarding a specified group from a large-scale language model based on attribute information regarding one or more first users associated with the specified group.
This makes it possible to group the first users based on the attribute information and obtain an explanation suitable for learning for each group.

(Appendix 6)
The program described in Appendix 5, wherein the explanatory text acquisition step (S304) is a step of acquiring explanatory text relating to a specified group by inputting input data including statistics for each element and the contents of the elements contained in attribute information relating to one or more first users associated with a specified group into a large-scale language model.
This makes it possible to obtain an explanatory text for a specific group using statistics (features) for each individual element included in the attribute information of an individual first user, the contents (definitions) of the elements, and the like as input data.
The instructions may include information about assignments and suggested questions for each learning unit.

(Appendix 7)
The program according to claim 6, wherein the explanatory text acquisition step (S304) is a step of not inputting attribute information regarding one or more first users associated with a predetermined group into a large-scale language model.
This makes it possible to obtain an explanatory text for a specific group without inputting personal information, such as attribute information, of individual first users into a large-scale language model.
A suitable explanation can be obtained for each group according to the attribute information of each first user without transmitting the attribute information of each first user to an external large-scale language model or the like.

(Appendix 8)
The program described in Appendix 7, in which a processor executes a teaching material reception step (S502) in which a selection of one or more learning materials is received from a second user for a specified group in accordance with an explanatory text acquired in the explanatory text acquisition step, and a teaching material provision step (S503) in which the one or more learning materials received in the teaching material reception step are provided collectively to one or more first users associated with the specified group.
This allows the second user (teacher) to select learning materials for each of the multiple first users included in the group based on the obtained explanatory text, and to provide the selected learning materials collectively for each group.

(Appendix 9)
The program described in Appendix 1, in which the attribute acquisition step (S101) is a step of acquiring attribute information regarding a plurality of first users, and the processor executes a group step (S102) of associating the plurality of first users with one or more groups based on the attribute information acquired in the attribute acquisition step, and a teaching material provision step (S503) of collectively providing learning materials to the one or more first users associated with a specified group.
This makes it possible to provide study materials collectively to each of a plurality of first users included in a group based on attribute information.

(Appendix 10)
A program as described in Appendix 9, in which a processor executes a teaching material reception step (S501) in which a selection of one or more learning materials is received from a second user for a specified group, and a teaching material provision step (S503) is a step in which the one or more learning materials received in the teaching material reception step are provided collectively to one or more first users associated with the specified group.
This allows the second user (teacher) to select learning materials for each of the multiple first users included in the group, and to provide the selected learning materials collectively for each group.

(Appendix 11)
The program according to claim 5 or 10, wherein the group step (S102) is a step of associating a plurality of first users with one or a plurality of groups according to a similarity of attribute information of the plurality of first users.
This allows the first users to be grouped according to the similarity of the attribute information of the first users. For example, a plurality of first users having a similar learning proficiency can be grouped into the same group according to the similarity of the learning proficiency of the first users. In addition, learning materials and the like can be provided collectively for each of the plurality of first users having a similar learning proficiency.

(Appendix 12)
The program according to claim 5 or 10, wherein the group step (S102) is a step of associating the multiple first users with one or more groups after the multiple first users have confirmed a learning effect within a specific range.
In this way, the first user is automatically associated with multiple groups after the test is conducted and after the progress of the learning effect is confirmed in daily lessons. For example, a configuration in which the attribute information (learning proficiency) of the first user is updated at the time of the test is preferable.
In this case, the first users can be grouped into groups that are more suitable for them according to the latest attribute information. Learning materials and the like can be provided collectively to a plurality of first users having the same learning proficiency.

(Appendix 13)
A method implemented on a computer having a processor and a memory, the processor performing all of the steps performed in the invention according to any one of claims 1 to 10.
This makes it possible to obtain an explanatory text suitable for the learning of the first user (student) according to the attribute information of the first user.

(Appendix 14)
An information processing device comprising a control unit and a memory unit, wherein the control unit executes all of the steps executed in the invention according to any one of Supplementary Note 1 to Supplementary Note 10.
This makes it possible to obtain an explanatory text suitable for the learning of the first user (student) according to the attribute information of the first user.

(Appendix 15)
A system comprising means for performing all the steps performed in any of the inventions according to any one of appendixes 1 to 10.
This makes it possible to obtain an explanatory text suitable for the learning of the first user (student) according to the attribute information of the first user.

1 System, 10 Server, 101 Memory unit, 104 Control unit, 106 Input device, 108 Output device, 20 First user terminal, 201 Memory unit, 204 Control unit, 206 Input device, 208 Output device, 30 Second user terminal, 301 Memory unit, 304 Control unit, 306 Input device, 308 Output device, 50 Large-scale language model, 501 Memory unit, 504 Control unit, 506 Input device, 508 Output device

Claims (14)

A program to be executed by a computer having a processor and a storage unit, the processor comprising:
A proficiency acquisition step of acquiring information regarding the first user's proficiency including a correct answer rate for questions in the learning material and correct answers to the questions;
An explanatory text acquisition step of acquiring explanatory text regarding the first user's learning task or recommended learning content from a large-scale language model based on the proficiency level of the first user. The program according to claim 1, wherein the explanatory text acquisition step is a step of acquiring the explanatory text including information about the study task or recommended questions of the first user. The program according to claim 2, wherein the explanatory text acquisition step is a step of acquiring the explanatory text including information about a learning task or recommended questions for each learning unit of the first user. A program to be executed by a computer having a processor and a storage unit, the processor comprising:
A proficiency level acquisition step of acquiring information regarding learning proficiency levels of a plurality of first users;
a group step of associating the first users with one or more groups based on the proficiency acquired in the proficiency acquisition step;
and acquiring explanatory text related to a learning task or recommended learning content of the predetermined group from a large-scale language model based on the proficiency level related to one or more of the first users associated with the predetermined group;
The explanatory text acquisition step is a step of acquiring the explanatory text related to the specified group by inputting input data including statistics based on the proficiency level related to the one or more first users associated with the specified group into the large-scale language model, the program. The program according to claim 4, wherein the explanatory text acquisition step is a step of acquiring the explanatory text for the specified group by inputting input data including statistics for each element included in the proficiency level for the one or more first users associated with the specified group and the contents of the elements into the large-scale language model. The program according to claim 4, wherein the explanatory text acquisition step is a step of not inputting personal information of the one or more first users associated with the predetermined group into the large-scale language model. The processor,
a learning material receiving step of receiving, from a second user of the predetermined group, a selection of one or more learning materials corresponding to the explanatory text acquired in the explanatory text acquisition step;
and a teaching material providing step of providing the one or more learning materials received in the teaching material receiving step collectively to the one or more first users associated with the predetermined group. The proficiency level acquisition step is a step of acquiring the proficiency levels related to a plurality of the first users, and the processor:
a group step of associating the first users with one or more groups based on the proficiency acquired in the proficiency acquisition step;
The program according to claim 1 , further comprising: a teaching material providing step of collectively providing learning teaching materials to one or more of the first users associated with a predetermined group. The processor,
a learning material receiving step of receiving a selection of one or more learning materials from a second user for the predetermined group;
9. The program according to claim 8, wherein the teaching material providing step is a step of providing the one or more learning materials received in the teaching material receiving step collectively to the one or more first users associated with a predetermined group. The program according to any one of claims 4 to 9, wherein the group step is a step of associating the first users with one or more groups according to the similarity of the proficiency levels of the first users. The program according to any one of claims 4 to 9, wherein the group step is a step of associating the first users with one or more groups after the first users have confirmed a learning effect within a specific range. A method implemented on a computer having a processor and a memory, comprising:
A method in which the processor executes all of the steps performed in any one of claims 1 to 9. An information processing device including a control unit and a storage unit,
10. An information processing device, wherein the control unit executes all of the steps executed in the invention according to any one of claims 1 to 9. A system having means for executing all steps performed in any one of claims 1 to 9.