Learning support information processing system using generative ai

Abstract

To provide a learning support system using a generative AI that provides a user with a timely answer that is accurate to a certain degree or more according to a learning history of the user.SOLUTION: In an information processing system for learning support using a generative AI, one or more information processing devices includes: learning data provision means for providing a user with learning data associated with user information; input data acquisition means for acquiring a learning history of a user identified from the learning data and input data from the user associated with the learning history; prompt acquisition means for acquiring a prompt including an instruction to generate an answer according to the learning history based on data including the input data; and answer data generation means that allows the generative AI to generate answer data according to the learning history based on the prompt. The generative AI refers to data, including the learning data and related data associated with the learning data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing system for learning support that uses generative AI. [Background technology]

[0002] Advances in communication technology have led to the emergence of systems that offer online lectures and learning opportunities. However, due to the complexity of the content, particularly in specialized lectures, it is necessary to enable two-way communication between users and instructors, such as online question and answer sessions.

[0003] Methods by which users can ask teachers questions online include, for example, a learning support system (see Patent Document 1) consisting of a student terminal having a question sending means for issuing a question to the teacher terminal and sending it by email via a LAN, and an answer receiving means for receiving an answer from the teacher terminal, and a teacher terminal having a question receiving means for receiving a question from the student terminal and an answer sending means for sending the answer by email via the LAN to the student terminal, and a learning support system (see Patent Document 2) that has a control unit 15 that selects an answerer suitable for answering a learner's question by referring to an answerer database 10, and retrieves the learner's learning history from a learning history database 11 along with the content of the question and sends it to the selected answerer. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 09-185598 [Patent Document 2] Japanese Patent Application Laid-Open No. 2003-281285 DISCLOSURE OF THE INVENTION [Problem to be solved by the invention]

[0005] The learning support system disclosed in Patent Document 1 requires the teacher to respond to questions individually, which can make it difficult to respond in a timely manner. The learning support system disclosed in Patent Document 2 requires the respondent to answer questions that are not stored in a question and answer database that accumulates past question data and answer data, which may prevent a timely response. Furthermore, with the current serious labor shortage, it is difficult to secure teachers who can properly respond to specialized questions. Furthermore, there is a possibility that answers may contain knowledge and information that the user has not learned. Furthermore, Patent Documents 1 and 2 do not mention inquiries other than questions from users, such as evaluation of assignments created as part of learning.

[0006] As described above, the main purpose of the present invention is to provide an information processing system for learning support that uses generative AI that can provide users with timely answers to data entered by the user that have a certain level of accuracy or higher according to the user's learning history (course completion status).

[0007] Another main objective of the present invention is to provide an information processing system for learning support that uses generative AI to provide users with timely recommendation information for answers to assignments submitted by the user, in accordance with the user's learning history and with a certain level of accuracy based on predetermined assignment answer index evaluations, etc.

[0008] Another main objective of the present invention is to provide an information processing system for learning support that uses generative AI to provide users with timely answers to questions that are based on the user's learning history and have a certain level of accuracy or higher.

[0009] Another main object of the present invention is to provide an information processing system for learning support that uses generative AI to provide users with a timely summary of a question based on the user's learning history, an answer to the question or hint information for the question, and additional information related to the answer to the question.

[0010] Another main object of the present invention is to provide a learning support information processing system that uses generative AI to provide users with the results of a source code review in a timely manner based on the user's learning history and predetermined rules, for source code entered by the user in accordance with predetermined program specifications, and additional review-related information if the predetermined rules are satisfied.

[0011] Another main object of the present invention is to provide an information processing system for learning support that uses generative AI to provide users with timely answers based on the information contained in images in response to input data from the user, including images. [Means for solving the problem]

[0012] In order to achieve the above object, the present invention includes the following aspects.

[0013] (1) An information processing system for learning support using a generative AI, comprising one or more information processing devices, the information processing devices comprising: a learning data providing means for providing a user with learning data linked to user information; an input data acquiring means for acquiring the user's learning history identified from the learning data and input data from the user linked to the learning history; a prompt acquiring means for acquiring a prompt including an instruction to generate an answer corresponding to the learning history based on data including the input data; and an answer data generating means for causing a generative AI to generate answer data corresponding to the learning history based on the prompt, wherein the generative AI references data including the learning data and related data linked to the learning data.

[0014] (2) In the configuration described in (1) above, the generative AI is configured to refer to data including assignment data linked to the learning data, and correct answer data and assignment answer evaluation index data linked to the assignment data, as the related data; the learning data providing means further provides the assignment data to a user; the input data acquiring means acquires assignment answer data from the user corresponding to the assignment data as the input data; the prompt acquiring means acquires the prompt including an instruction to generate the answer including recommendation information based on the correct answer data for the assignment answer data and the assignment answer evaluation index data; and the answer data generating means causes the generative AI to generate the answer data based on the prompt.

[0015] (3) In the configuration described in (1) above, the generative AI refers to data including question-and-answer format data linked to the learning data as the related data, the input data acquisition means acquires question data from a user as the input data, the prompt acquisition means acquires the prompt including an instruction to generate an answer including a question and answer based on the question-and-answer format data for the question data, and the answer data generation means causes the generative AI to generate the answer data based on the prompt.

[0016] (4) In the configuration described in (1) above, the input data acquisition means acquires question data from a user as the input data, the prompt acquisition means acquires from the question data the prompt including an instruction to generate the answer including a summary of the question, an answer to the question or hint information for the question, and question-related additional information related to the answer to the question or hint information, and the answer data generation means causes the generative AI to generate the answer data based on the prompt.

[0017] (5) In the configuration described in (1) above, the generative AI refers to data including program specification data linked to the learning data, source code linked to the program specification data, and pass review data that specifies rules that the source code must satisfy, as the related data; An information processing system for learning support using a generative AI, in which the input data acquisition means acquires source code entered by a user based on predetermined program specification data as the input data, the prompt acquisition means determines whether the source code entered by the user satisfies rules specified in the passing review data and acquires the prompt including instructions to generate the answer including review-related additional information if the rules are satisfied, and the answer data generation means causes the generative AI to generate the answer data based on the prompt.

[0018] (6) A learning support information processing system using a generative AI, in the configuration described in any one of (1) to (5) above, wherein the input data acquisition means acquires the input data including image data, the prompt acquisition means acquires the prompt including an instruction to generate the answer including an answer based on information extracted from the image data, and the answer data generation means causes the generative AI to generate the answer data based on the prompt.

[0019] (7) An information processing device for learning support using a generative AI, comprising: a learning data providing means for providing a user with learning data linked to user information; an input data acquiring means for acquiring the user's learning history identified from the learning data and input data from the user linked to the learning history; a prompt acquiring means for acquiring a prompt including an instruction to generate an answer according to the learning history based on data including the input data; and an answer data generating means for causing a generative AI to generate answer data according to the learning history based on the prompt, wherein the generative AI references data including the learning data and related data linked to the learning data.

[0020] (8) In the configuration described in (7) above, the generative AI is configured to refer to data including assignment data linked to the learning data, and correct answer data and assignment answer evaluation index data linked to the assignment data, as the related data; the learning data providing means further provides the assignment data to a user; the input data acquiring means acquires assignment answer data from the user corresponding to the assignment data as the input data; the prompt acquiring means acquires the prompt including an instruction to generate the answer including recommendation information based on the correct answer data for the assignment answer data and the assignment answer evaluation index data; and the answer data generating means causes the generative AI to generate the answer data based on the prompt.

[0021] (9) In the configuration described in (7) above, the generative AI refers to data including question-and-answer format data linked to the learning data as the related data, the input data acquisition means acquires question data from a user as the input data, the prompt acquisition means acquires the prompt including an instruction to generate an answer including a question and answer based on the question-and-answer format data for the question data, and the answer data generation means causes the generative AI to generate the answer data based on the prompt.

[0022] (10) In the configuration described in (7) above, an information processing device for learning support using a generative AI, wherein the input data acquisition means acquires question data from a user as the input data, the prompt acquisition means acquires from the question data the prompt including an instruction to generate the answer including a summary of the question, an answer to the question or hint information for the question, and question-related additional information related to the answer to the question or hint information, and the answer data generation means causes the generative AI to generate the answer data based on the prompt.

[0023] (11) In the configuration described in (7) above, the generative AI refers to data including program specification data linked to the learning data, source code linked to the program specification data, and pass review data that specifies rules that the source code must satisfy, as the related data; An information processing device for learning support using a generative AI, wherein the input data acquisition means acquires source code entered by a user based on predetermined program specification data as the input data, the prompt acquisition means determines whether the source code entered by the user satisfies rules specified in the passing review data and acquires the prompt including instructions to generate the answer including review-related additional information if the rules are satisfied, and the answer data generation means causes the generative AI to generate the answer data based on the prompt.

[0024] (12) A learning support information processing device using a generative AI, in the configuration described in any one of (7) to (11) above, wherein the input data acquisition means acquires the input data including image data, the prompt acquisition means acquires the prompt including an instruction to generate the answer including an answer based on information extracted from the image data, and the answer data generation means causes the generative AI to generate the answer data based on the prompt.

[0025] (13) An information processing program for learning support using a generative AI, which causes one or more information processing devices to execute the steps of: providing a user with learning data linked to user information; acquiring the user's learning history identified from the learning data and input data from the user linked to the learning history; acquiring a prompt including instructions to generate an answer corresponding to the learning history based on data including the input data; and causing a generative AI to generate answer data corresponding to the learning history based on the prompt, wherein the generative AI references data including the learning data and related data linked to the learning data.

[0026] (14) In the configuration described in (13) above, the generative AI is configured to refer to data including assignment data linked to the learning data, and correct answer data and assignment answer evaluation index data linked to the assignment data, as the related data, and the information processing device provides the assignment data to a user along with the learning data, and when assignment answer data from the user corresponding to the assignment data is obtained as the input data, an information processing program for learning support using a generative AI is caused to execute a process of obtaining the prompt including an instruction to generate the answer including recommendation information based on the correct answer data for the assignment answer data and the assignment answer evaluation index data.

[0027] (15) In the configuration described in (13) above, the generative AI is configured to refer to data including question and answer format data linked to the learning data as the related data, and the information processing device executes a process of acquiring question data from a user as the input data and acquiring the prompt including an instruction to generate the answer including a question and answer based on the question and answer format data for the question data.

[0028] (16) In the configuration described in (13) above, an information processing program for learning support using a generative AI, which causes the information processing device to acquire question data from a user as the input data and acquire from the question data the prompt including an instruction to generate the answer including a summary of the question, an answer to the question or hint information for the question, and question-related additional information related to the answer or hint information.

[0029] (17) In the configuration described in (13) above, the generative AI is configured to refer to data including program specification data linked to the learning data, source code linked to the program specification data, and passing review data that specifies the rules that the source code must satisfy as the related data, and the information processing device is caused to execute a process of acquiring source code entered by a user based on predetermined program specification data as the input data, determining whether the source code entered by the user satisfies the rules specified in the passing review data, and acquiring the prompt including an instruction to generate the answer including review-related additional information if the rules are satisfied.

[0030] (18) An information processing program for learning support using a generative AI, in the configuration described in any one of (13) to (17) above, which causes the information processing device to execute a process of acquiring the input data including image data and acquiring the prompt including an instruction to generate the answer including an answer based on information extracted from the image data.

[0031] (19) An information processing method for learning support using a generative AI, comprising: a step of providing a user with learning data linked to user information; a step of acquiring the user's learning history identified from the learning data and input data from the user linked to the learning history; a step of acquiring a prompt including instructions to generate an answer corresponding to the learning history based on data including the input data; and a step of causing a generative AI to generate answer data corresponding to the learning history based on the prompt, wherein the generative AI references data including the learning data and related data linked to the learning data.

[0032] (20) In the configuration described in (19) above, the generative AI is configured to refer to data including assignment data linked to the learning data, and correct answer data and assignment answer evaluation index data linked to the assignment data, as the related data, and the assignment data is provided to a user along with the learning data, and assignment answer data from the user corresponding to the assignment data is obtained as the input data. An information processing method for learning support using a generative AI, which obtains the prompt including an instruction to generate the answer including recommendation information based on the correct answer data for the assignment answer data and the assignment answer evaluation index data.

[0033] (21) In the configuration described in (19) above, the generative AI is configured to refer to data including question and answer format data linked to the learning data as the related data, and the information processing device acquires question data from a user as the input data and acquires the prompt including an instruction to generate the answer including a question and answer based on the question and answer format data for the question data.

[0034] (22) An information processing method for learning support using a generative AI, in the configuration described in (19) above, which obtains question data from a user as the input data, and obtains from the question data the prompt including an instruction to generate the answer, which includes a summary of the question, an answer to the question or hint information for the question, and question-related additional information related to the answer or hint information.

[0035] (23) In the configuration described in (19) above, the generative AI is configured to refer to data including program specification data linked to the learning data, source code linked to the program specification data, and passing review data that specifies the rules that the source code must satisfy as the related data, and obtains source code entered by a user based on specified program specification data as the input data, determines whether the source code entered by the user satisfies the rules specified in the passing review data, and obtains the prompt including an instruction to generate the answer including review-related additional information if the rules are satisfied.

[0036] (24) An information processing method for learning support using a generative AI, in the configuration described in any one of (19) to (23) above, which acquires the input data including image data, and acquires the prompt including an instruction to generate the answer, including an answer based on information extracted from the image data. [Effects of the Invention]

[0037] According to the present invention, it is possible to provide an information processing system for learning support that uses generative AI to provide users with answers in a timely manner that have a certain level of accuracy or higher in response to data entered by the user, based on the user's learning history.

[0038] Furthermore, according to the present invention, it is possible to provide an information processing system for learning support that uses generative AI to provide users with timely recommendation information for answers to assignments submitted by the user, which is based on the user's learning history and has a certain level of accuracy or higher, based on predetermined assignment answer index evaluations, etc.

[0039] Furthermore, according to the present invention, it is possible to provide an information processing system for learning support that uses generative AI to provide users with timely answers to questions that are based on the user's learning history and have a certain level of accuracy or higher in response to questions from the user.

[0040] Furthermore, according to the present invention, it is possible to provide a learning support information processing system that uses generative AI to respond to a question from a user in a timely manner, according to the user's learning history, and to provide the user with a summary of the question, an answer to the question or hint information to the question, and additional information related to the answer to the question, etc.

[0041] Furthermore, according to the present invention, it is possible to provide a learning support information processing system that uses generative AI to provide a user with a source code review in a timely manner based on the user's learning history and predetermined rules for source code entered by the user in accordance with predetermined program specifications, and additional review-related information if the predetermined rules are satisfied.

[0042] Furthermore, according to the present invention, it is possible to provide an information processing system for learning support that uses generative AI to provide a user with a timely answer based on the information contained in an image in response to input data from the user that includes an image. [Brief explanation of the drawings]

[0043] [Figure 1] 1 is a diagram showing a schematic overall configuration of an information processing system according to a first embodiment. [Figure 2] FIG. 2 is a functional block diagram of a user terminal according to the embodiment. [Figure 3] FIG. 2 is a functional block diagram of a server according to the embodiment. [Figure 4] In this embodiment, Figure 4(a) is a table showing an example of checkpoints for evaluating task answers included in task answer evaluation index data, and Figure 4(b) is a table showing an example of expected task answer evaluation data. [Figure 5] 10 is a flowchart showing the overall flow of information processing in the embodiment. [Figure 6] FIG. 10 is a diagram showing a display screen of a user terminal when inputting assignment answer information in the embodiment. [Figure 7] FIG. 10 is a diagram showing an example of a prompt display screen in the embodiment. [Figure 8] FIG. 10 is a diagram showing an example of a display screen of answer information displayed on a user terminal in the embodiment. [Figure 9] 10 is a flowchart showing the overall flow of information processing according to the second embodiment. [Figure 10] FIG. 10 is a diagram showing a display screen of a user terminal including a question form in the embodiment. [Figure 11] FIG. 10 is a diagram showing an example of a prompt display screen in the embodiment. [Figure 12] FIG. 10 is a diagram showing an example of a display screen of answer information displayed on a user terminal in the embodiment. [Figure 13] FIG. 11 is a diagram illustrating a display screen of a user terminal including a question form according to the third embodiment. [Figure 14] FIG. 10 is a diagram showing a display screen of a user terminal in which question information has been input into a question form in the embodiment. [Figure 15] FIG. 10 is a diagram showing an example of a display screen of answer information displayed on a user terminal in the embodiment. [Figure 16] FIG. 10 is a diagram showing a display screen (1) of a predetermined program specification displayed on a user terminal according to the fourth embodiment. [Figure 17] FIG. 10 is a diagram showing a display screen (2) of a predetermined program specification displayed on a user terminal in the embodiment. [Figure 18] FIG. 10 is a diagram showing an example of a display screen of answer information (when a predetermined rule is not satisfied) displayed on a user terminal in the embodiment. [Figure 19] FIG. 10 is a diagram showing an example of a display screen of answer information (when a predetermined rule is satisfied) displayed on a user terminal in the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0044] Hereinafter, one embodiment of the present invention will be described with reference to the drawings.

[0045] 1. First embodiment <Outline of the information processing system> A learning support information processing system 1 (hereinafter referred to as "system 1") using generative AI according to this embodiment is a system that supports user learning, and as shown in Fig. 1, a user terminal 20, a server 30, and a generative AI 40 are connected via a communication network (hereinafter referred to as "network 10"). There may be multiple user terminals 20 and multiple servers 30.

[0046] The network 10 may be a wired communication means, a wireless communication means, or a combination of these.

[0047] <User terminal 20> The user terminal 20 is, for example, an information processing device such as a PC, a tablet terminal, or a smartphone. The user terminal 20 includes a control unit 210, a communication unit 220, an input unit 230, an output unit 240, and a storage unit 250, which are connected to each other via a signal line 260 (see FIG. 2).

[0048] The control unit 210 includes one or more processors including, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). The control unit 210 has a function of controlling, processing, and managing the overall operation of the user terminal 20 by referring to a program stored in the storage unit 250 .

[0049] The control unit 210 has the following functions. A function of requesting the server 30 to access the learning data, and based on the learning data including the learning content data and learning division data obtained from the server 30 in response to the request, displaying learning information, for example, a learning video on the output unit 240 to allow the user to carry out the learning, and also displaying the division information on the output unit 240 at a predetermined timing (for example, at the learning division of the learning content identified by the learning division data). A function to acquire a learning log, such as a learning history, generated by the user's learning activities. The learning history corresponds to the learning segment data received from the server 30, and identifies the learning content the user has studied and their progress. A function to acquire task answer data input by the user via the input unit 230 and link the task answer data to the learning history. Also, a function to acquire other input data. A function of transmitting data to an external device including the server 30 via the communication unit 220 and receiving data from the external device. - Function to convert data to be sent and received into a specified format. A function of executing a process of displaying on the output unit 240 data input via the input unit 230 and data received from the external device. A function for executing a process of displaying a user-operable graphical user interface (GUI) screen on the output unit 240 when data is input or output to the user terminal 20. A function of storing data acquired and generated by the user terminal 20 and data transmitted and received via the communication unit 220 in the storage unit 250.

[0050] The communication unit 220 is a communication means that connects the user terminal 20 to the network 10 and executes communication. The communication may be performed either wired or wirelessly. There are no particular limitations on the communication protocol. Data received by the communication unit 220 is sent to the control unit 210 via a signal line 260.

[0051] The input unit 230 may be built into the user terminal 20 or may be externally attached. The input unit 230 is, for example, a mouse, buttons, a keyboard, a scanner, a microphone capable of voice input, or a touch panel integrated with the output unit 240. The input unit 230 has a function of accepting data input operations by the user.

[0052] The output unit 240 may be built into the user terminal 20 or may be externally attached. The output unit 240 is, for example, a display (including the above-mentioned touch panel), a speaker, a printer, a head-mounted display, etc. The output unit 240 has the function of displaying data on a screen, outputting audio, printing out, etc.

[0053] The storage unit 250 is a storage device such as a RAM, a ROM, or a storage, and may be provided inside the user terminal 20 or may be externally attached. The storage unit 250 stores data sent and received by the user terminal 20, programs referenced to execute each process, data acquired and generated by each process, etc. Note that this data includes data that is temporarily stored.

[0054] The user terminal 20 configured in this manner requests access to the server 30, and in response, has the user study based on the study data acquired from the server 30, provides assignment information to the user at a predetermined timing, and upon receiving an input operation of assignment answer information from the user, links the acquired assignment answer data to the user's study history and transmits it to the server 30. The user terminal 20 also outputs and displays answer information based on the answer data acquired from the server 30 on the output unit 240.

[0055] <Server 30> The server 30 is an information processing device. The server 30 includes a control unit 310, a communication unit 320, and a storage unit 330, which are connected to each other via a signal line 340 (see FIG. 3). As described above, the server 30 is also connected to the generation system AI 40 via the network 10.

[0056] The control unit 310 includes one or more processors, such as a CPU or an MPU. The control unit 310 has the function of controlling, processing, and managing the overall operation of the server 30 by referring to the programs stored in the storage unit 330. Furthermore, the control unit 310 stores data transmitted and received via the communication unit 320 in the storage unit 330 .

[0057] The control unit 310 also functions as a user terminal identification unit 312 , a learning data control unit 314 , a prompt creation unit 316 , and an answer generation control unit 318 .

[0058] The user terminal identification unit 312 has a function of, upon receiving an access request from a user terminal 20, identifying the user terminal 20 to which the learning data and assignment data should be transmitted, based on the user terminal information stored in the user DB 332 of the storage unit 330. The user terminal identification unit 312 also has a function of storing a learning log (learning history) acquired from the user terminal 20 in the user DB 332 of the storage unit 330.

[0059] The learning data control unit 314 has a function of identifying the learning data and assignment data to be transmitted to the identified user terminal 20 by referring to the learning data and assignment data stored in the learning DB 334 of the storage unit 330 .

[0060] Upon receiving the assignment answer data from the user terminal 20, the prompt creation unit 316 has a function of creating a prompt by referring to the assignment answer data, the learning division data, assignment data, correct answer data, and assignment answer evaluation index data stored in the learning DB 334 of the storage unit 330, and the instruction condition data stored in the instruction condition DB 336. Note that the prompt creation unit 316 may be configured to select a predetermined instruction condition from the instruction condition data according to, for example, the type of learning data (e.g., learning subject) corresponding to the assignment answer data.

[0061] The answer generation control unit 318 has a function of transmitting the prompt created by the prompt creation unit 316 to the generation AI 40 via the network 10, and causing the generation AI 40 to create answer data based on the prompt.

[0062] The control unit 310 also has the function of sending learning data to a specified user terminal 20 via the communication unit 320, the function of receiving various data including learning logs and task answer data from the user terminal 20, the function of receiving answer data generated by the generation system AI 40, the function of sending and receiving specified data other than these, and the function of converting the data to be sent and received into a specified format.

[0063] The communication unit 320 is a communication means that connects the server 30 to the network 10 and executes communication. The communication may be performed either wired or wirelessly. There are no particular limitations on the communication protocol. Data received by the communication unit 320 is sent to the control unit 310 via a signal line 340.

[0064] The memory unit 330 is a storage device such as RAM, ROM, or storage, and may be installed inside the server 30 or connected to the server 30 via the network 10. The memory unit 330 stores data sent and received by the server 30, programs referenced to execute each process, data generated by each process, etc. This data, etc. includes data that is stored temporarily. The storage unit 330 also includes a user DB 332 , a learning DB 334 , an instruction condition DB 336 , and a response DB 338 .

[0065] The user DB 332 stores information for identifying the user terminal 20 (such as a user ID assigned to each user), information on obtainable learning data, a learning log obtained from the user terminal 20, and the like.

[0066] The learning DB 334 stores the following information: Learning content data, learning data including learning division data linked to the learning content (e.g., divisions such as Chapter 1, Part 1), and assignment data linked to the learning data. Correct answer data linked to the above task data. The correct answer data is model answer information corresponding to the task. - Task answer evaluation index data linked to the above task data. The task answer evaluation index data includes evaluation manual data, which includes viewpoints, checkpoints, and methods for evaluating task answers from users, and expected task answer evaluation data, which includes expected task answers from users and expected evaluations of those answers. An example of the data (table) included in the task answer evaluation index data is shown in Figure 4.

[0067] The instruction condition DB 336 stores predetermined instruction condition data that is referenced when creating a prompt. Examples of the predetermined instruction conditions include the following conditions: Answers are generated within the scope of the learning content that corresponds to the learning history of the user terminal 20 that is acquired. Generate answers that do not include the correct answers to the assignments themselves, but include recommendation information that references the correct answer data and assignment answer evaluation index data. - Output the answer in the specified output format. The recommendation information is information that includes hints and recommendations for solving the problem from the user, and is information that supports the user in arriving at the model answer.

[0068] The response DB 338 stores the response data received from the generation system AI 40.

[0069] When the server 30 configured in this way receives an access request from a user terminal 20, it identifies the user terminal 20 that made the access request and transmits predetermined learning data and assignment data to that user terminal 20. In addition, when the server 30 acquires task answer data from the user terminal 20, it creates a predetermined prompt by referring to the task answer data, learning division data, task data, correct answer data, task answer evaluation index data, and instruction condition data, sends this to the generation system AI 40, causes the generation system AI 40 to generate answer data based on the prompt, and receives the answer data generated by the generation system AI 40.

[0070] <Generation AI40> The generative AI 40 is a type of artificial intelligence technology and is an information processing device capable of learning large amounts of data and generating sentences, etc. In this embodiment, the generative AI 40 additionally learns data including the training data, the assignment data, the correct answer data, and the assignment answer evaluation index data in order to refer to these data. Additional learning refers to, for example, transfer learning and fine tuning. Note that the data may also include other data. Furthermore, the generation AI 40 may refer to the correct answer data, etc. by performing so-called RAG (Retrieval-Augmented Generation), which searches an external database that stores the correct answer data, etc. The same applies to other embodiments.

[0071] When the generation AI 40 receives the prompt from the server 30, it generates answer data based on the prompt that corresponds to the user's learning history and includes the recommendation information that references the correct answer data and the problem answer evaluation index data, and transmits the generated answer data to the server 30.

[0072] <Information processing method> An information processing method using the system 1 will be described below (see FIG. 5).

[0073] First, the user terminal 20 accesses the server 30 via a predetermined application (not shown) and requests the server 30 to access the learning data (step S102).

[0074] When the control unit 310 of the server 30 receives an access request from a user terminal 20 (step S202), it identifies the user terminal 20 to which the learning data and assignment data are to be transmitted (step S204) based on the user terminal information stored in the user DB 332 of the storage unit 330. The control unit 310 refers to the learning DB 334 of the storage unit 330 to identify the learning data and assignment data to be transmitted to the identified user terminal 20 (step S206), and transmits them to the user terminal 20 (step S208).

[0075] The control unit 210 of the user terminal 20 receives the learning data and assignment data from the server 30 (step S104), and causes the output unit 240 to display learning information, such as learning videos, based on the learning content data included in the received learning data, to allow the user to study (step S106). Note that, during the learning process, the learning videos are processed so as to be streamed. Additionally, while learning is in progress, the control unit 210 may acquire the learning log (learning history) of the user terminal 20 each time, temporarily store the acquired learning history in the storage unit 250, and transmit it to the server 30 as appropriate. The learning history corresponds to the learning division data received from the server 30, which identifies the learning content the user has studied and their progress.

[0076] The control unit 210 of the user terminal 20 displays assignment information on the output unit 240 based on the assignment data received from the server 30 during the learning process or at a learning break based on the received learning break data (step S108). In this embodiment, the assignment is to create source code based on predetermined conditions. That is, at a learning break of a predetermined learning content, the control unit 210 causes the output unit 240 to display the corresponding assignment information (creating source code) (see FIG. 6). An example of displaying assignment information on the output unit 240 at the break between Chapter 1 and Part 2 will be described below.

[0077] When the user operates the input unit 230 of the user terminal 20 to input task answer information corresponding to the above task into the input form of Figure 6 and clicks the send button, the control unit 210 of the user terminal 20 links the learning history (Chapter 1, Part 2) to the above task answer data obtained thereby and sends it to the server 30 (step S112).

[0078] When the control unit 310 of the server 30 receives the above task answer data linked to the learning history from the user terminal 20 (step S210), it creates a prompt to cause the generation system AI 40 to generate answer data by referring to the task answer data, the learning division data, task data, correct answer data, and task answer evaluation index data stored in the learning DB 334 of the memory unit 330, and the instruction condition data stored in the instruction condition DB 336 (step S212, see Figure 7). The above prompts are created based on instruction conditions such as, for example, "generate answers within the scope of the learning content corresponding to the learning history (learning division) of the user terminal 20 to be acquired," "generate answers that do not include the correct answer to the assignment itself, but include correct answer data and recommendation information that references the above assignment answer evaluation index data," and "output answers in a specified format."

[0079] The control unit 310 of the server 30 transmits the created prompt to the generation system AI 40 (step S214).

[0080] When the generation AI 40 receives a prompt from the server 30 (step S302), it analyzes the prompt (step S304), and generates answer data based on the analysis results (step S306).

[0081] The generation AI 40 transmits the generated answer data to the server 30 (step S308). The generated answer data is generated within the scope of the learning content corresponding to the learning history of the user terminal 20, and while it does not include the correct answer to the assignment itself, it does include recommendation information that references the correct answer data and the assignment answer evaluation index data, and is output in a predetermined format.

[0082] The control unit 310 of the server 30 receives the answer data from the generation AI 40 (step S216), converts the received answer data into a predetermined format (step S218), and transmits the converted data to the user terminal 20 (step S220).

[0083] The control unit 210 of the user terminal 20 receives the response data from the server 30 (step S114), and outputs and displays the response information on the output unit 240 based on the received response data (step S116, see FIG. 8).

[0084] As described above, according to this embodiment, answers to questions from users are provided within the scope of the learning content corresponding to the learning history of the user terminal 20, making it possible to provide the user with answers that correspond to the user's learning level. Furthermore, the server 30 generates answer data from the generative AI 40, which has been additionally trained to refer to data including the learning data, the assignment data, the correct answer data, and the assignment answer evaluation index data, so that even for specialized assignments, the system 1 can provide users with appropriate answers in a timely manner that are based on an analysis of their assignment answers while maintaining a certain level of accuracy and consistency. This enables the system 1 to provide convenient learning support to many users, regardless of the time. Furthermore, while the above answers do not contain the correct answers to the tasks themselves, they do contain recommendation information, i.e., hints and recommendations from the user for answering the tasks, to support the user in arriving at the model answer, thereby giving the user an opportunity to think for themselves and supporting their growth.

[0085] 2. Second embodiment The same reference numerals are used for components that are the same as or similar to those in the first embodiment, and detailed descriptions other than those for the different parts will be omitted.

[0086] In this embodiment, question form data is transmitted from the server 30 to the user terminal 20. It should be noted that transmission of assignment data to the user terminal 20 is optional.

[0087] <User terminal 20> When the control unit 210 of the user terminal 20 receives the above-mentioned question form data, it displays the question form on the output unit 240 at a predetermined timing, and the input unit 230 of the user terminal 20 is configured to accept input of question information from the user in the question form. Furthermore, the control unit 210 associates the learning history with question data acquired by inputting question information from the user, and transmits this to the server 30 via the communication unit 320.

[0088] <Server 30> When the control unit 310 (user terminal identification unit 312) of the server 30 receives an access request from the user terminal 20, it has the function of identifying the user terminal 20 to which the learning data and question form data should be sent based on the user terminal information stored in the user DB 332 of the memory unit 330.

[0089] The prompt generator 316 has a function of acquiring question data from the user terminal 20, and then generating a prompt by referring to the question data, learning delimiter data, question and answer format data, and instruction condition data stored in the instruction condition DB 336.

[0090] The learning DB 334 of the storage unit 330 further stores question and answer format data for generating answers based on predetermined conditions. The question and answer format data includes, for example, information for improving the accuracy of answers, such as data linking the type of learning data (learning subject), keyword conditions included in the question, and information to be included in the answer. That is, for example, the data includes information such as "learning subject: creating a programming calculator app; keyword conditions: including 'error', 'calculation', and 'output'; answer: generate an answer based on the type of operator, type of code, and order of the code for performing arithmetic operations."

[0091] The instruction condition DB 336 includes, as predetermined instruction condition data, an instruction to generate an answer including a question and an answer that references question and answer format data. In this embodiment, the instruction condition DB 336 is configured to include, in addition to the question and answer, an instruction to generate an answer including additional information related to the question (simply referred to as "additional information" in this embodiment).

[0092] When the server 30 configured in this way receives an access request from a user terminal 20, it identifies the user terminal 20 that made the access request and transmits predetermined learning data and question form data to that user terminal 20. In addition, when the server 30 acquires question data from the user terminal 20, it creates a predetermined prompt by referring to the question data, learning division data, question and answer format data, and instruction condition data, sends this to the generation system AI 40, and receives answer data generated by the generation system AI 40 based on the prompt.

[0093] <Generation AI40> In this embodiment, the generative AI 40 is trained by additionally learning data including the above-mentioned question and answer format data in order to refer to the data. Note that the above-mentioned data may also include other data.

[0094] When the generation AI 40 receives the prompt from the server 30, it generates answer data based on the prompt, including a question and answer and additional information that corresponds to the user's learning history and references the question and answer format data, and transmits the generated answer data to the server 30.

[0095] <Information processing method> The following describes an information processing method using the system 1 (see FIG. 9). Note that the description of the same processes as those in the first embodiment will be omitted where appropriate.

[0096] First, the user terminal 20 accesses the server 30 and requests the server 30 to access the learning data (step S402).

[0097] When the control unit 310 of the server 30 receives an access request from a user terminal 20 (step S402), it identifies the user terminal 20 to which the learning data and question form data are to be transmitted (step S404) based on the user terminal information stored in the user DB 332 of the storage unit 330. The control unit 310 then refers to the learning DB 334 of the storage unit 330 to identify the learning data and question form data to be transmitted to the identified user terminal 20 (step S506), and transmits them to the user terminal 20 (step S508).

[0098] The control unit 210 of the user terminal 20 receives the learning data and question form data from the server 30 (step S404), and based on the learning content data included in the received learning data, displays the learning video on the output unit 240 to allow the user to perform learning (step S406).

[0099] During the learning process or in a learning segment based on the received learning segment data, the control unit 210 of the user terminal 20 displays a question form on the output unit 240 based on the question form data received from the server 30 (step S408). In this embodiment, control unit 210 causes output unit 240 to display a question form at a learning break (e.g., Chapter 1, Part 2) of a predetermined study content (see FIG. 10). Below, an example will be described in which a question form (input form) is displayed on output unit 240 at the break of Chapter 1, Part 2.

[0100] When the user operates the input unit 230 of the user terminal 20 to input question information into the input form of Figure 10 and clicks the send button, the control unit 210 of the user terminal 20 links the learning history (Chapter 1, Part 2) to the question data thus obtained and sends it to the server 30 (step S412).

[0101] When the control unit 310 of the server 30 receives the question data linked to the learning history from the user terminal 20 (step S510), it creates a prompt to cause the generation system AI 40 to generate answer data by referring to the question data, learning division data, question and answer format data, and instruction condition data stored in the instruction condition DB 336 (step S512, see Figure 11). The above prompts are created based on instruction condition data such as, for example, "generate answers to questions within the scope of learning data corresponding to the learning history of the user terminal 20 to be acquired," "generate answers to questions by referencing question-answer format data," "include additional information related to the question in the answers to questions," and "output answers in a specified output format."

[0102] The control unit 310 of the server 30 transmits the created prompt to the generation AI 40 (step S514).

[0103] When the generation AI 40 receives the prompt from the server 30 (step S602), it analyzes the prompt (step S604), and generates answer data based on the analysis results (step S606).

[0104] Generation AI 40 transmits the generated answer data to server 30 (step S608). The generated answer data is generated within the scope of the learning content corresponding to the learning history of user terminal 20, includes answers to questions that reference the question and answer format data, and additional information, and is output in a predetermined format.

[0105] The control unit 310 of the server 30 receives the answer data from the generation AI 40 (step S516), converts the received answer data into a predetermined format (step S518), and transmits the converted data to the user terminal 20 (step S520).

[0106] The control unit 210 of the user terminal 20 receives the response data from the server 30 (step S114), and outputs and displays the response information on the output unit 240 based on the received response data (step S416, see FIG. 12).

[0107] As described above, according to this embodiment, answers to questions from users are provided within the scope of the learning content corresponding to the learning history of the user terminal 20, making it possible to provide the user with answers that are appropriate to the user's learning level. Furthermore, the server 30 causes the generative AI 40, which has been trained with data including the learning data and the question and answer format data, to generate answer data, so that even for specialized questions, appropriate answers can be provided to users in a timely manner while maintaining a certain level of accuracy and consistency. This enables the system 1 to provide highly convenient learning support to many users, regardless of the time. Furthermore, the answer includes additional information related to the question from the user, which gives the user an opportunity to think for himself / herself and can support the user's growth.

[0108] 3. Third embodiment The same reference numerals are used for components that are the same as or similar to those in the first and second embodiments, and detailed descriptions other than those of the different parts will be omitted.

[0109] In this embodiment, as in the second embodiment, question form data is sent from the server 30 to the user terminal 20. The question form displayed on the output unit 240 of the user terminal 20 allows the user to enter the following items for each question: "What you want to solve," "Prerequisites," "What you have tried and understood so far," and "Additional information" (see FIG. 13).

[0110] <Server 30> When the server receives question data from the user terminal 20, the prompt creation unit 316 has a function of creating a prompt by referring to the question data, learning division data, question and answer format data, and instruction condition data stored in the instruction condition DB 336. The prompt includes an instruction to create answer data from the question, including a "question summary," an "answer to the question or hint information for the question," and "question-related additional information related to the answer to the question or hint information." The "answer to the question or hint information for the question" is either a direct answer to the question or hint information that does not directly answer the question but leads the user to the answer, and either is selected based on the type of learning data (e.g., learning subject) by, for example, a program stored in the storage unit 330. In this embodiment, the answer data is configured to include a direct answer to the question.

[0111] If the answer data includes hint information for the question, the prompt creation unit 316 may refer to hint information data stored in the learning DB 334 of the storage unit 330 to generate a prompt for obtaining the hint information. The hint information data includes, for example, information on the thinking steps required to arrive at an answer to the user's question, such as "answer generation conditions: learning about Eclipse; question includes keywords "screen," "arrow," "panel," and "layout; hint information: includes an explanation of the Perspective function."

[0112] When the server 30 configured in this manner acquires question data from the user terminal 20, it creates a predetermined prompt by referring to the question data, learning division data, and instruction condition data, sends this to the generation system AI 40, and receives answer data generated by the generation system AI 40 based on the prompt.

[0113] <Generation AI40> When the generation AI 40 receives the above prompt from the server 30, it generates answer data based on the prompt that corresponds to the user's learning history and includes a ``summary of the question,'' ``an answer to the question or hint information for the question,'' and ``additional question-related information related to the answer to the question or hint information,'' and transmits the generated answer data to the server 30.

[0114] <Information processing method> The following describes an information processing method using the system 1. Since the overall flow of information processing in this embodiment is the same as that in the second embodiment, the description will be made using Fig. 9. Also, the description of processes that are the same as those in the first and second embodiments will be omitted as appropriate.

[0115] First, the user terminal 20 accesses the server 30 and requests the server 30 to access the learning data (step S402).

[0116] When the control unit 310 of the server 30 receives an access request from a user terminal 20 (step S502), it identifies the user terminal 20 to which the learning data and question form data are to be transmitted (step S504) based on the user terminal information stored in the user DB 332 of the storage unit 330. The control unit 310 then refers to the learning DB 334 of the storage unit 330 to identify the learning data and question form data to be transmitted to the identified user terminal 20 (step S506), and transmits them to the user terminal 20 (step S508).

[0117] The control unit 210 of the user terminal 20 receives the learning data and question form data from the server 30 (step S304), and based on the learning content data included in the received learning data, displays the learning video on the output unit 240 to allow the user to perform learning (step S406).

[0118] During the learning process or in a learning segment based on the received learning segment data, the control unit 210 of the user terminal 20 displays a question form on the output unit 240 based on the question form data received from the server 30 (step S108). In this embodiment, control unit 210 causes output unit 240 to display a question form at a learning break (e.g., Chapter 1, Part 3) of a predetermined study content (see FIG. 13). Below, an example will be described in which a question form (input form) is displayed on output unit 240 at the break of Chapter 1, Part 3.

[0119] When the user operates the input unit 230 of the user terminal 20 to input question information into the input form and clicks the send button (see FIG. 14), the control unit 210 of the user terminal 20 links the acquired question data with the learning history (Chapter 1, Part 3) and transmits the data to the server 30 (step S412). In this embodiment, the input form allows the user to enter items such as "What to Solve," "Prerequisites," "What Have Been Tried / Understood," and "Supplementary Information" for each item. This allows the generative AI 40 to generate a more accurate summary of the question, etc.

[0120] When the control unit 310 of the server 30 receives the question data linked to the learning history from the user terminal 20 (step S510), it creates a prompt to cause the generation system AI 40 to generate answer data by referring to the question data, the learning division data, and the instruction condition data stored in the instruction condition DB 336. The above prompts are created based on instruction condition data such as, for example, "generate answers to questions within the scope of learning data corresponding to the learning history of the user terminal 20 to be acquired," "generate a summary of the questions, answers to the questions, and additional information related to the answers to the questions from the questions," and "output answers to the questions in a specified output format."

[0121] The control unit 310 of the server 30 transmits the created prompt to the generation AI 40 (step S514).

[0122] When the generation AI 40 receives the prompt from the server 30 (step S602), it analyzes the prompt (step S604), and generates answer data based on the analysis results (step S606).

[0123] Generation AI 40 transmits the generated answer data to server 30 (step S608). The generated answer data is generated within the scope of the learning content corresponding to the learning history of user terminal 20, includes a summary of the question, the answer to the question, and additional question-related information related to the answer to the question, and is output in a predetermined format.

[0124] The control unit 310 of the server 30 receives the answer data from the generation AI 40 (step S516), converts the received answer data into a predetermined format (step S518), and transmits the converted data to the user terminal 20 (step S520).

[0125] The control unit 210 of the user terminal 20 receives the response data from the server 30 (step S414), and outputs and displays the response information on the output unit 240 based on the received response data (step S416, see FIG. 15).

[0126] As described above, according to this embodiment, answers to questions from users are provided within the scope of the learning content corresponding to the learning history of the user terminal 20, making it possible to provide the user with answers that are appropriate to the user's learning level. Furthermore, the server 30 generates answer data from the generative AI 40, which has additionally learned data including the learning data, so that even for specialized questions, appropriate answers can be provided to users in a timely manner while maintaining a certain level of accuracy and consistency. This enables the system 1 to provide highly convenient learning support to many users, regardless of the time. Furthermore, the answer includes a summary of the question and the answer to the question or hint information for the question and additional information related to the answer to the question, so that an answer that is easy for the user to understand can be provided and the user can be given an opportunity to think for themselves, thereby supporting the user's growth.

[0127] 4. Fourth Embodiment The same reference numerals are used for components that are the same as or similar to those in the first embodiment, and detailed descriptions other than those for the different parts will be omitted.

[0128] In this embodiment, data for inputting source code linked to a predetermined program specification as the assignment data is transmitted from the server 30 to the user terminal 20, and the input unit 230 of the user terminal 20 accepts input of the source code based on the predetermined program specification from the user. Note that, hereinafter, the source code input by the user will be referred to as "user-input source code."

[0129] <Server 30> When the prompt creation unit 316 acquires user-input source code from the user terminal 20, it has the function of creating a prompt by referring to the user-input source code, learning delimiter data, program specification data linked to the learning data, source code linked to the program specification data and passing review data that specifies the rules that the source code must satisfy, and instruction condition data stored in the instruction condition DB 336.

[0130] The learning DB 334 of the storage unit 330 stores program specification data linked to the learning data, source code linked to the program specification data, and pass review data that specifies the rules that the source code must satisfy. The pass review data is evaluation data that includes, for example, the following viewpoints: - Does the user-entered source code allow the program to be executed (does the program work)? Does the user-entered source code meet the requirements of the corresponding program specification? - Is the user-entered source code consistent? -Does the user-entered source code conform to the prescribed style?

[0131] The instruction condition DB336 stores, as specified instruction condition data, instructions to determine whether the user-input source code satisfies the rules specified in the accepted review data, and if the rules are satisfied, to generate an answer including additional information (review-related additional information) regarding the related program specification data and the source code linked to it.

[0132] When the server 30 configured in this manner acquires user-input source code from the user terminal 20, it creates a predetermined prompt by referring to the user-input source code, learning delimiter data, etc., and instruction condition data, sends this to the generation system AI 40, and receives answer data generated by the generation system AI 40 based on the prompt.

[0133] <Generation AI40> When the generation system AI 40 receives the above prompt from the server 30, it generates answer data based on the prompt, according to the user's learning history, and including the judgment result of whether the user-input source code satisfies the rules specified in the passing review data, and the above additional information if the rules are satisfied, and transmits the generated answer data to the server 30.

[0134] <Information processing method> The following describes an information processing method using the system 1. Since the overall flow of information processing in this embodiment is the same as that in the first embodiment, the description will be made using Fig. 5. Also, the description of the same processes as in the first embodiment will be omitted as appropriate.

[0135] First, the user terminal 20 accesses the server 30 and requests the server 30 to access the learning data (step S102).

[0136] When the control unit 310 of the server 30 receives an access request from a user (step S202), it identifies the user terminal 20 to which the learning data and assignment data are to be transmitted (step S204) based on the user terminal information stored in the user DB 332 of the storage unit 330. The control unit 310 refers to the learning DB 334 of the storage unit 330 to identify the learning data and assignment data to be transmitted to the identified user terminal 20 (step S206), and transmits them to the user terminal 20 (step S208).

[0137] The control unit 210 of the user terminal 20 receives the learning data and assignment data from the server 30 (step S104), and based on the learning content data included in the received learning data, displays the learning video on the output unit 240 to allow the user to perform the learning (step S106).

[0138] The control unit 210 of the user terminal 20 displays assignment information on the output unit 240 based on the assignment data received from the server 30 during the learning process or at a learning break based on the received learning break data (step S108). In this embodiment, the assignment is to create source code based on predetermined program specifications (source code for creating a web application with predetermined functions), and the control unit 210 displays a corresponding source code creation screen (assignment information) on the output unit 240 at the learning break of the predetermined learning content (see FIGS. 16 and 17). An example in which assignment information is displayed on the output unit 240 at the break of Chapter 1, Part 4 will be described below.

[0139] When the user operates the input unit 230 of the user terminal 20 to input source code based on the above assignment (predetermined program specifications) into an input form (not shown) and clicks the send button, the control unit 210 of the user terminal 20 links the input source code, i.e., the user-input source code, with the learning history (Chapter 1, Part 4) and transmits it to the server 30 (step S112). The user-input source code may also be input by uploading an electronic file.

[0140] When the control unit 310 of the server 30 receives the above-mentioned user-input source code linked to the learning history from the user terminal 20 (step S210), it creates a prompt to cause the generation system AI 40 to generate answer data by referring to the user-input source code, learning delimiter data, program specification data linked to the learning data, source code linked to the program specification data and passing review data that specifies the rules that the source code must satisfy, and instruction condition data stored in the instruction condition DB 336. The above prompts are created based on instruction conditions such as, for example, "generate an answer within the scope of the learning content corresponding to the learning history of the user terminal 20 being acquired," "determine whether the input source code satisfies the rules that source code linked to the corresponding program specifications must satisfy, and generate additional information related to the program specifications and the source code linked thereto only if the rules are satisfied, and if the rules are not satisfied, generate an answer including the parts that are not satisfied, the reasons for the non-satisfaction, and suggested modifications."

[0141] The control unit 310 of the server 30 transmits the created prompt to the generation system AI 40 (step S214).

[0142] When the generation AI 40 receives a prompt from the server 30 (step S302), it analyzes the prompt (step S304), and generates answer data based on the analysis results (step S306).

[0143] Generative AI 40 transmits the generated answer data to server 30 (step S308). The generated answer data is generated within the scope of the learning content corresponding to the learning history of user terminal 20, and if the user-input source code satisfies the rules that source code linked to the corresponding program specifications must satisfy, it includes additional information (review additional information) related to the program specifications and the source code linked thereto, and if the rules are not satisfied, it includes the non-satisfied parts, the reasons for the non-satisfaction, and suggested modifications, and is output in a predetermined format.

[0144] The control unit 310 of the server 30 receives the answer data from the generation AI 40 (step S216), converts the received answer data into a predetermined format (step S218), and transmits the converted data to the user terminal 20 (step S220).

[0145] The control unit 210 of the user terminal 20 receives the response data from the server 30 (step S114), and outputs and displays the response information on the output unit 240 based on the received response data (step S116, see FIGS. 18 and 19). That is, when the user-input source code does not satisfy the rules that source code linked to the corresponding program specification should satisfy, the answer information displayed on the output unit 240 is as shown in Fig. 18. In this embodiment, the user-input source code can be input multiple times, and when the user-input source code input again satisfies the above rules, the answer information displayed on the output unit 240 is as shown in Fig. 19.

[0146] As described above, according to this embodiment, answers are provided to the user input source code within the scope of the learning content corresponding to the learning history of the user terminal 20, making it possible to provide the user with answers that correspond to the user's learning level. Furthermore, the server 30 causes the generative AI 40, which has been trained with data including program specification data linked to the learning data, source code linked to the program specification data, and pass review data that specifies the rules that the source code must satisfy, to generate answer data, so that the system 1 can provide users with timely and appropriate reviews (answers) based on predetermined rules for the user-entered source code while maintaining a certain level of accuracy and identity. This enables the system 1 to provide convenient learning support to many users, regardless of time. Furthermore, if the user-entered source code satisfies the rules that source code linked to the corresponding program specifications must satisfy, the response will include additional information (additional review information) related to the program specifications and the source code linked to them; if the rules are not satisfied, the response will include the non-satisfied parts, the reasons for the non-satisfaction, and suggested modifications. This will help the user to arrive at source code that satisfies the rules themselves, and will also provide advanced information according to the level the user has achieved (after understanding the source code rules), thereby making it possible to appropriately support the user's growth.

[0147] 5. Modifications of the First to Fourth Embodiments At least one of the assignment answer information, question information, and user input source code may be configured to be input as image data. In this case, the prompt generation unit 316 of the server 30 is configured to analyze the text information, image information, etc. contained in the image data, and generate a prompt including an instruction to generate an answer based on the analysis results. Alternatively, for example, a trained AI trained using image analysis data may be stored in the memory unit 330 of the server 30, and an image recognition unit (not shown) provided in the server 30 may use the trained AI to analyze the text information and image information contained in the image data, and the prompt creation unit 316 may be configured to generate a prompt including instructions for generating an answer based on the analysis results.

[0148] Also, for example, before creating a prompt, the control unit 310 of the server 30 may be configured to cause the generative AI 40 or another generative AI to analyze the image data, and the prompt creation unit 316 may be configured to generate a prompt based on the results of the analysis.

[0149] 6. Other Modifications The timing at which each input form is displayed on the output unit 240 of the user terminal 20 and the timing at which the assignment answer information, question information, and user input source code are input into each input form can be changed as appropriate.

[0150] Furthermore, the function of the prompt generating unit 316 of the control unit 310 of the server 30 can be performed by another server (not shown) via an API (Application Programming Interface). Furthermore, the generation AI 40 may be adjusted to generate other answer data by referring to previously generated answer data (history).

[0151] The prompt generator 316 of the server 30 may also be configured to generate prompts repeatedly, i.e., when the prompt generator 316 generates a first prompt, it causes the generation AI 40 to generate initial answer data based on the first prompt. Furthermore, when the server 30 receives the initial answer data, the prompt creation unit 316 checks whether there are any improvements to be made to the initial answer data, creates a prompt (first improvement prompt) for creating answer data based on the improvements, and causes the generation system AI 40 to generate first improvement answer data based on the first improvement prompt. When the server 30 receives the first improvement response data, the prompt creation unit 316 checks whether there are any improvements to be made to the first improvement response data, creates a prompt (second improvement prompt) for creating response data based on the improvements, and causes the generation system AI 40 to generate the first improvement response data based on the second improvement prompt. In this case, the number of times that the prompt creation unit 316 creates an improvement prompt is controlled based on the program stored in the memory unit 330, and when the prompt creation unit 316 creates an improvement prompt, it is configured to refer to the improvement prompt data stored in the instruction condition DB of the memory unit 330.

[0152] The program of this embodiment is a program that causes the user terminal 20 and the server 30 to execute the above-mentioned processes. The information processing device of this embodiment is an information processing device that executes the above-described processing.

[0153] It should be noted that the present invention is not limited to the above-described embodiment, and various modifications are possible without departing from the gist of the present invention. [Explanation of symbols]

[0154] 1. Learning support information processing system using generative AI (system) 10...Network (communication network) 20...User terminal 30...server 40 ...Generative AI

Claims

1. One or more information processing devices are provided, The information processing device includes: a learning data providing means for providing the user with learning data linked to the user information; an input data acquisition means for acquiring a learning history of a user identified from the learning data and input data from the user linked to the learning history; a prompt acquisition means for acquiring a prompt including an instruction to generate an answer according to the learning history based on data including the input data; and an answer data generating means for causing the generating AI to generate answer data according to the learning history based on the prompt, An information processing system for learning support that uses generative AI, wherein the generative AI references data including the learning data and related data linked to the learning data.

2. The generative AI is configured to refer to data including assignment data linked to the learning data, and correct answer data and assignment answer evaluation index data linked to the assignment data, as the related data, the learning data providing means further provides the task data to the user; the input data acquisition means acquires, as the input data, task answer data from the user corresponding to the task data; the prompt acquisition means acquires the prompt including an instruction to generate the answer including recommendation information based on the correct answer data for the assignment answer data and the assignment answer evaluation index data; 2. The information processing system for learning support using generative AI according to claim 1, wherein the answer data generation means causes the generative AI to generate the answer data based on the prompt.

3. the generative AI is configured to refer to data including question and answer format data linked to the learning data as the related data, the input data acquisition means acquires question data from a user as the input data, the prompt acquisition means acquires the prompt including an instruction to generate an answer including a question answer based on the question and answer format data for the question data; 2. The information processing system for learning support using generative AI according to claim 1, wherein the answer data generation means causes the generative AI to generate the answer data based on the prompt.

4. the input data acquisition means acquires question data from a user as the input data, the prompt acquisition means acquires the prompt including an instruction to generate the answer, which includes a summary of the question, an answer to the question or hint information for the question, and question-related additional information related to the answer or hint information, from the question data; 2. The information processing system for learning support using generative AI according to claim 1, wherein the answer data generation means causes the generative AI to generate the answer data based on the prompt.

5. The generative AI refers to data including program specification data linked to the learning data, source code linked to the program specification data, and pass review data that specifies rules that the source code must satisfy, as the related data; the input data acquisition means acquires, as the input data, a source code input by a user based on predetermined program specification data; the prompt acquisition means acquires the prompt including an instruction to determine whether the source code input by the user satisfies a rule defined in the accepted review data, and generate the answer including review-related additional information if the rule is satisfied; 2. The information processing system for learning support using generative AI according to claim 1, wherein the answer data generation means causes the generative AI to generate the answer data based on the prompt.

6. the input data acquisition means acquires the input data including image data, the prompt acquisition means acquires the prompt including an instruction to generate the answer, the answer including an answer based on information extracted from the image data; 2. The information processing system for learning support using generative AI according to claim 1, wherein the answer data generation means causes the generative AI to generate the answer data based on the prompt.

Images