Support device, support method, and support program

Abstract

This enables learning support tailored to the user's learning progress. [Solution] The support device 100 assigns a user to a first team or a second team and designs the teams based on the user's learning status, which is determined by information about the user's learning that includes learning materials used for learning, learning history, learning goals, and conversation history related to the user who uses the ebook for learning. The support device 100 then constructs an execution environment for the designed first team and second team to perform hacking exercises, according to the user's learning status.

Description

Technical Field

[0004] , ,

[0005] , ,

[0001] The present invention relates to a support device, a support method, and a support program.

Background Art

[0002] For learners who study languages, programming, qualification exams, etc. (hereinafter sometimes simply referred to as "users"), learning support using Internet technology may be provided. For example, there is a known prior art that identifies the lesson to be attended by a target person among a plurality of lessons constituting a lecture on a test and outputs information indicating the learning effect of the lesson to the terminal of the target person (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the prior art has problems in supporting learning according to the learning situation of the user. For example, since the prior art only shows information indicating the learning effect based on the correct answer rate of the user for the questions given after the lesson, there is a problem in providing learning support according to the learning situation of the user who is learning.

Means for Solving the Problems

[0006] This invention has the effect of enabling learning support tailored to the user's learning progress. [Brief explanation of the drawing]

[0007] [Figure 1] Figure 1 is a diagram showing an overview of the learning support according to the embodiment. [Figure 2] Figure 2 shows an example of the configuration of the support device according to the first embodiment. [Figure 3] Figure 3 is a table diagram showing an example of teaching material information according to the first embodiment. [Figure 4] Figure 4 is a table diagram showing an example of user learning information according to the first embodiment. [Figure 5] Figure 5 shows an example of a reception screen according to the first embodiment. [Figure 6] Figure 6 shows a series of steps for the generation process and output process according to the first embodiment. [Figure 7] Figure 7 shows an example of a prompt related to the first example. [Figure 8] Figure 8 shows an example of a prompt related to the first example. [Figure 9] Figure 9 shows an example of the output of learning support information in chat format related to the first example. [Figure 10]FIG. 10 is a diagram showing an example of a prompt according to the second example. [Figure 11] FIG. 11 is a diagram showing an example of an output in a chat format of learning support information according to the second example. [Figure 12] FIG. 12 is a diagram showing an example of a prompt used for coaching optimization according to the second example. [Figure 13] FIG. 13 is a diagram showing an example of a prompt according to the third example. [Figure 14] FIG. 14 is a diagram showing an example of an output in a chat format of learning support information according to the third example. [Figure 15] FIG. 15 is a flowchart of the processing of the support device according to the first embodiment. [Figure 16] FIG. 16 is a diagram showing an example of the configuration of the support device according to the second embodiment. [Figure 17] FIG. 17 is a table diagram showing an example of result information according to the second embodiment. [Figure 18] FIG. 18 is a diagram showing an example of the processing of the support device according to the second embodiment. [Figure 19] FIG. 19 is a diagram showing an example of a hacking exercise screen according to the second embodiment. [Figure 20] FIG. 20 is a flowchart of the processing of the support device according to the second embodiment. [Figure 21] FIG. 21 is a diagram showing an example of the hardware configuration of a computer that realizes the support device according to the embodiment. Embodiments for Carrying Out the Invention

[0008] Hereinafter, embodiments for carrying out the present invention (hereinafter referred to as "embodiments") will be described with reference to the drawings. Note that each embodiment is not limited to the content described below.

[0009] <Prelude> (Background) Users who engage in learning languages, programming, taking qualification exams, etc. can now learn online due to the recent development of Internet technology. In online learning, various forms of learning support may be provided according to the user's learning situation. For example, there is a known reference technique that outputs the learning effect of a course to the target person based on the user's progress in solving the problems of the lessons that make up the course on the exam.

[0010] However, the above-mentioned reference technique only shows information indicating the learning effect based on the user's correct answer rate, etc. for the questions in the course. Therefore, there are problems in providing learning support according to the learning situation of the users who are learning.

[0011] (Processing by Support Device 100) Therefore, the support device 100 according to the present embodiment realizes appropriate learning support such as teaching, coaching, presenting questions suitable for the user, and following up, according to the user's learning situation.

[0012] Here, an overview of the processing by the support device 100 will be described. FIG. 1 is a diagram showing an overview of the learning support according to the embodiment. The support device 100 shown in FIG. 1 is an example of a computer that provides a technique for realizing the information processing described below.

[0013] In the present embodiment, a situation where the support device 100 provides predetermined learning support to a user who uses an e-book for learning will be described as an example. The above-mentioned "e-book" is a predetermined learning material provided as digital content, and includes, for example, the digitized book itself, and still images or moving images that explain the book.

[0014] The support device 100 inputs information about the learning status of user 10, who is learning using ebooks (shown as "User 10's Learning Status" in Figure 1 (1-1)) into a large-scale language model as prior knowledge (Figure 1 (1-2)). Based on the learning status of user 10 input as prior knowledge, the support device 100 performs teaching and coaching for user 10, answers questions from user 10, and presents problems.

[0015] For example, the support device 100, in accordance with the user 10's learning status, creates a learning plan to help the user 10 learn efficiently, manages the progress of learning based on that learning plan, and provides encouragement and motivation to the user 10 ("coaching" as shown in (2-1) of Figure 1). The support device 100 also provides practice problems tailored to the user 10's academic level and learning progress, and provides support for answers to the practice problems ("teaching" as shown in (2-2) of Figure 1). On the other hand, the support device 100 outputs answers to "questions" ((2-3) of Figure 1) input by the user 10, in accordance with the user 10's learning status and the e-books, etc., that the user 10 is using ("answers" as shown in (2-4) of Figure 1).

[0016] Furthermore, the support device 100 can implement the above-mentioned "coaching (Figure 1 (2-1))", "teaching (Figure 1 (2-2))", and "answering (Figure 1 (2-4))" through a natural language dialogue format (chat format), as shown in Figure 1 (3).

[0017] In this way, the support device 100 according to this embodiment has the effect of enabling learning support tailored to the user's learning situation by providing teaching, coaching, answering questions from the user, etc., according to the user's learning situation.

[0018] <First Embodiment> From here, a first embodiment realized by the support device 100 will be described. The first embodiment is an embodiment in which the support device 100 generates and outputs to the user coaching to support the user's learning progress, teaching which presents practice problems generated according to the user, answers to questions from the user, etc., according to the user's learning status.

[0019] (Support device 100) First, the support device 100 according to the first embodiment will be described in detail. Figure 2 is a diagram showing an example of the configuration of the support device 100 according to the first embodiment. As shown in Figure 2, the support device 100 according to the first embodiment includes a communication unit 110, a storage unit 120, and a control unit 130.

[0020] Although not shown in Figure 2, the support device 100 may be equipped with an input unit such as a keyboard or mouse to receive input from an administrator or other user. Furthermore, the support device 100 may be equipped with a display unit such as a screen to show the administrator educational material information, user learning information, etc., stored in the storage unit 120.

[0021] (Communications Department 110) The communications unit 110 performs data communication related to the output of generated user learning support information (hereinafter sometimes referred to as "user learning information"), including information on the learning status of users who are learning using ebooks, input of information on natural language conversations related to teaching and coaching from the user, answers to practice problems, questions, etc., and output of such information to terminal devices, etc.

[0022] The communication unit 110 is implemented, for example, by a NIC (Network Interface Card) or a network interface controller. The communication unit 110 is connected to a network (e.g., the Internet) by wire or wireless connection. The communication unit 110 then sends and receives information to and from external devices via the network.

[0023] The communication unit 110 may also transmit and receive information using any communication standard or technology, such as Wi-Fi (registered trademark), Bluetooth (registered trademark), SIM (Subscriber Identity Module), or LPWA (Low Power Wide Area).

[0024] (Storage unit 120) The storage unit 120 stores data and programs used for various processes by the control unit 130, as well as various data acquired through the operation of the control unit 130. The storage unit 120 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or storage devices such as hard disks and optical discs. As shown in Figure 2, the storage unit 120 also includes a teaching material information DB 121, a user learning information DB 122, and a generation model DB 123.

[0025] (Teaching material information DB121) The Educational Materials Information DB121 is a database that stores educational materials such as ebooks used by users for learning. Specifically, the Educational Materials Information DB121 stores educational material information such as the title of the ebook used by the user for learning (title), link information for accessing the ebook stored in a designated storage device (link), information indicating the display order when displaying a list of educational materials (order), information indicating the number of contents of a predetermined granularity within the ebook (number of contents), information regarding practice problems associated with the ebook (assignments), and information indicating the publication type of the educational material (type).

[0026] Here, we will explain an example of teaching material information stored in the teaching material information DB121. Figure 3 is a table diagram showing an example of teaching material information according to the first embodiment. The teaching material information DB121 stores items such as "title," "link," "order," "number of content items," "assignment," and "type," as well as information related to those items, in a table format or the like, associated with "No," which is information that identifies individual teaching material information.

[0027] For example, as shown in Figure 3, the teaching material information DB121 stores the following items in association with each other: Title "A", Link "B", Order "C", Number of Contents "D", Assignment "E", and Type "F", each identified by No. "1". Note that the letters "A through F" above are legend information for each item of the individual teaching material information stored in the teaching material information DB121, and the actual information stored is not particularly limited.

[0028] Furthermore, using the teaching material information stored in the teaching material information DB121, the support device 100 can display the information to users and administrators in a list format that includes items such as "type," "thumbnail," "title," "order," "chapter," "section," and "assignment," as shown in Figure 3(1).

[0029] The "Title" mentioned above is information that identifies the e-book used by the user for learning, and includes information such as the title, volume number, and issue number of the e-book, expressed in natural language such as text, numbers, and symbols. The "Link" is information for accessing the storage medium that stores the e-book itself or its thumbnail information, and includes information such as the URL (Uniform Resource Locator) associated with each e-book. The "Order" is information used to define the display order when listing e-books that are educational materials.

[0030] "Number of Content Items" refers to the number of content items grouped at a predetermined level of detail within the ebook, such as the number of chapters or sections. "Assignments" correspond to the chapters and sections within the ebook and refer to information about assignments such as practice problems presented to the user, including the content and correct answers of the practice problems, and the number of practice problems. "Type" indicates the publication status of the ebook, such as "Public," which is available to all registered users, or "Limited," which is available only to specific users.

[0031] (User learning information DB122) The User Learning Information DB122 is a database that stores information related to user learning (user learning information), including information such as the learning status of users who use e-books for learning. Specifically, the User Learning Information DB122 stores user learning information such as information that identifies the user (user identification information), learning materials used by the user (learning materials), the user's learning history (learning history), the user's learning goals (learning goals), and the history of conversations between the user and the support device 100 (conversation history).

[0032] Here, we will explain an example of user learning information stored in the user learning information DB122. Figure 4 is a table diagram showing an example of user learning information according to the first embodiment. The user learning information DB122 stores items such as "user identification information," "materials used," "learning history," "learning objectives," and "conversation history," as well as information related to those items, in a table format or the like, associated with "No," which is information that identifies individual user learning information.

[0033] For example, as shown in Figure 4, the user learning information DB122 stores the user identification information "User 10," identified by No. "1," the learning materials used "G," the learning history "H," the learning objectives "I," and the conversation history "J," each associated with the others. The letters "G through J" above are legends for each item of individual user learning information stored in the user learning information DB122, and the actual information stored is not particularly limited.

[0034] Furthermore, using the user learning information stored in the user learning information DB122, the support device 100 can display the information to users and administrators in a list format that includes items such as "chapter," "section," "task," "type," "correct answer rate," and "result," as shown in Figure 4 (1).

[0035] The "user identification information" mentioned above refers to information that identifies an individual user who uses ebooks for learning, and includes, for example, the user's name or nickname, telephone number, membership number for a service, and other user-specific identification information. The user learning information DB122 can store user identification information while protecting personal information by deleting or replacing information that could identify an individual user based on publicly known technologies.

[0036] "Materials Used" is information used to identify the materials used by the user for learning, and includes, for example, information identifying the "title" of the material information stored in the material information DB121. "Learning History" is history information of the user's learning using ebooks, and includes, for example, information on the learning date, learning time, and learning progress. "Learning Objectives" is information on learning objectives set by the user learning using ebooks, and includes, for example, objectives such as "Complete learning content XX by XX / XX" or "Study for XX hours per week." "Conversation History" is history information (past conversation data) of natural language conversations between the learning user and the support device 100.

[0037] (Generative model DB123) The Generative Model DB 123 is a database that stores predetermined generative models used to generate user learning support information by the generation unit 132, described later. For example, the Generative Model DB 123 can store large-scale language models as generative models. Specifically, the support device 100 can use a large-scale language model with general-purpose knowledge, such as "ChatGPT®," as the large-scale language model (see, for example, Reference 1).

[0038] (Reference 1):ChatGPT(OpenAI),<URL:https: / / openai.com / chatgpt> ,<Searched on September 3, 2020>

[0039] (Control unit 130) Now, let's return to Figure 2 and continue the explanation. The control unit 130 is realized when a processor, MPU (Micro Processing Unit), CPU (Central Processing Unit), etc., executes various programs stored in the memory unit 120 using RAM as a working area.

[0040] The control unit 130 is implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array). As shown in Figure 2, the control unit 130 includes a receiving unit 131, a generation unit 132, and an output unit 133.

[0041] (Reception desk 131) The reception unit 131 receives information such as conversations related to teaching and coaching, answers to practice problems, and questions entered by the user in chat format, etc. The reception unit 131 also receives information that the generation unit 132 (described later) uses to generate practice problems.

[0042] Here, using Figure 5, an example of a reception screen for information used to generate practice problems and answers to the generated practice problems, as performed by the reception unit 131, will be explained. Figure 5 is a diagram showing an example of a reception screen according to the first embodiment.

[0043] As shown in Figure 5, the reception unit 131 receives the conditions for generating practice problems from administrators, etc., via the practice problem generation conditions reception screen shown in Figure 5 (1). For example, the reception unit 131 receives conditions for which content of the teaching materials, such as "teaching materials," "chapters," and "sections," should be used to generate practice problems (Figure 5 (1-1)). The reception unit 131 can also display a preview screen of the content identified based on the conditions shown in Figure 5 (1-1) (Figure 5 (1-2)). Furthermore, the reception unit 131 receives conditions such as "number of choices" and "number of problems to create" (Figure 5 (1-3)).

[0044] The reception unit 131 can then receive answers from users to the practice problems presented via the practice problem screen shown in Figure 5 (2). In addition to the practice problem screen (Figure 5 (2)), the reception unit 131 can also, of course, accept answers to the practice problems via chat.

[0045] (Generation unit 132) The generation unit 132 inputs user learning information of users who use ebooks for learning into a large-scale language model and generates user learning support information according to the user's learning status. Specifically, the generation unit 132 inputs user learning information, which includes at least one of the following: the ebooks used by the user, the user's learning history, the user's learning goals, and past conversation data, into a large-scale language model and generates user learning support information.

[0046] Specifically, the generation unit 132 generates user learning support information, including messages to support the user's learning (hereinafter referred to as "learning support messages"), answers to questions, practice problems presented to the user, and information to follow up on the answers to those practice problems. The generation process by the generation unit 132 will be explained in the following sections using specific prompt examples.

[0047] (Output section 133) The output unit 133 outputs the generated user learning support information. For example, the output unit 133 outputs the generated user learning support information to the user in chat format. The output processing by the output unit 133 will be explained in the following sections using specific prompt examples to illustrate the output of generated information.

[0048] (An example of the overall processing flow) From here, an example of the generation and output of learning support information by the support device 100 will be described. First, the flow of generation and output of learning support information by the support device 100 will be explained using Figure 6. Figure 6 is a diagram showing a series of generation and output processes according to the first embodiment. Figure 6 shows a terminal device 200 operated by the user and a support device 100 that performs the generation and output processes of the user's learning support information.

[0049] The terminal device 200 transmits learning-related input information received from the user, such as "coaching / teaching consultations" and "answers to practice problems," to the support device 100 (Figure 6 (1)).

[0050] The support device 100 processes the generation of user learning support information in response to learning-related input information received from the terminal device 200. First, the support device 100 (generation unit) generates a prompt that includes a command to assign a predetermined role to the large-scale language model, a command to input user learning information, and a command to generate user learning support information (Figure 6 (2-1)). Next, the support device 100 (generation unit) inputs the generated prompt to the large-scale language model (Figure 6 (2-2)). Then, the support device 100 (generation unit) generates user learning support information based on the generated prompt.

[0051] Specifically, the support device 100 (generation unit) inputs prompts into the large-scale language model and sets predetermined roles such as "AI instructor who supports the user." The support device 100 (generation unit) also causes the large-scale language model to acquire user learning information from the user learning information DB 122 (Figure 6 (3-1)).

[0052] The support device 100 (generation unit) then uses the acquired user learning information to cause the large-scale language model to generate learning support information (Figure 6 (3-2)). For example, the support device 100 (generation unit) causes the large-scale language model to generate "learning support messages (Figure 6 (3-3))" and "answers to questions (Figure 6 (3-4))" as learning support information related to coaching. The support device 100 (generation unit) also causes the large-scale language model to generate "practice problems (Figure 6 (3-5))" and "scoring and follow-up of answers (Figure 6 (3-6))" as learning support information related to teaching.

[0053] The support device 100 (output unit) outputs the generated learning support information to the terminal device 200 (Figure 6 (4)). As a result, the terminal device 200 can display information such as "learning support messages," "answers to user questions," and "practice problems and answer information" to the user as learning support information (Figure 6 (5)).

[0054] From here, we will explain an example of the generation and output processing of learning support information by the support device 100, using Figures 7 to 14, with more specific prompts and output screens as examples.

[0055] (Example 1: Generating and outputting learning support messages) First, we will explain an example in which the support device 100 generates a "learning support message" as learning support information and outputs it to the user. In the first example, the support device 100 generates a "learning support message," which is a message that supports the user's learning to progress effectively, according to the user's learning status, and outputs it to the user.

[0056] Specifically, the support device 100 (generation unit) inputs a command to a large-scale language model to generate a user learning support message that includes at least one of the following: words of encouragement for the user according to the user's learning progress, a summary of the user's learning content, and a message confirming whether or not there are any questions. The device then generates the user learning support message as user learning support information.

[0057] Here, examples of input prompts and output in the processing related to the first example will be explained using Figures 7 and 8. Figures 7 and 8 show examples of prompts related to the first example.

[0058] Figure 7 shows an example of a prompt (Figure 7(1)) for generating learning support messages from a large-scale language model based on the user's learning progress, and an example of a learning support message (Figure 7(2)) generated and output based on that prompt. The prompt shown in Figure 7(1) includes "#Background Information (Figure 7(1-1))", "#Status (Figure 7(1-2))", and "#Command (Figure 7(1-3))".

[0059] "#Background information" refers to instructions used by administrators and others to assign desired roles to a large-scale language model. For example, the instructions shown in (1-1) of Figure 7 allow the support device 100 (generation unit) to assign the roles of "being an AI instructor that supports learning users," "having the role of increasing the user's motivation to continue learning," and "generating information (#command) according to the user's learning status (#status) described in the prompt."

[0060] "#Status" is information that expresses the user's learning status in natural language, and is recorded based on information stored in the user learning information DB122. For example, the information shown in (1-2) of Figure 7 is that "User A" has "Theme <1> This means "it has learned up to that point."

[0061] A "#command" is a directive that causes a large-scale language model to perform a predetermined process. For example, the command shown in (1-3) of Figure 7 allows the support device 100 (generation unit) to cause the large-scale language model to perform tasks such as "generating a message for the user to perform the same learning as the previous day, according to the user's learning status," "generating a message to encourage the user," "summarizing the learning content from the previous day," and "generating a message to check whether there are any questions."

[0062] The support device 100 (output unit) then outputs a learning support message generated based on the prompt shown in Figure 7(1), as shown in Figure 7(2).

[0063] Next, we will explain an example of generating a learning plan tailored to the user's learning progress using a large-scale language model, with reference to Figure 8. Figure 8 shows an example of a prompt (Figure 8(1)) for generating a learning plan tailored to the user's learning progress using a large-scale language model, and an example of a learning plan generated and output based on that prompt (Figure 8(2)).

[0064] The prompt shown in Figure 8(1) includes "#Background Information", "#Command (Figure 8(1-1))", "#Constraints (Figure 8(1-2))", "#Functions Usable for Learning (Figure 8(1-3))", "#Personal Assignment Data (Figure 8(1-4))", and "#Learning Progress Data (Figure 8(1-5))". Note that "#Background Information" is processed in the same way as in Figure 7 based on the command described in Figure 8, so its explanation is omitted.

[0065] "#command" is a directive that causes a large-scale language model to perform a predetermined process, similar to the example in Figure 7. For example, the directive shown in (1-1) of Figure 8 allows the support device 100 (generation unit) to cause the large-scale language model to perform tasks such as "comparing the user's personal task data and learning progress data while strictly adhering to the set constraints, and generating advice for the user's learning progress."

[0066] "#Constraints" are instructions that define (restrict) the execution method of processing by a large-scale language model. For example, the instructions shown in (1-2) of Figure 8 allow the support device 100 (generation unit) to impose constraints on the large-scale language model when generating a learning plan, such as "generating a learning plan using only functions that can be used for learning," "character limit," "modification of the learning schedule," and "generating text to communicate the learning plan to the user."

[0067] "#Functions usable for learning" refers to information indicating the functions related to learning that a user can use when learning using the services realized by the support device 100, and is used as a constraint condition when the large-scale language model generates a learning plan. For example, as shown in (1-3) of Figure 8, "#Functions usable for learning" includes information that identifies various functions used for learning, such as "e-book / video viewing function," "problem practice function," "question function," "person-to-person coaching function," and "remote lab function."

[0068] "#Personal Assignment Data" contains information about the user's learning objectives. The information included in "#Personal Assignment Data" may be user learning information stored in the user learning information DB122. For example, as shown in (1-4) of Figure 8, "#Personal Assignment Data" may include information such as "Learning start date," "Learning completion deadline," and "Learning objectives using ebooks (ebook objectives), learning objectives using videos (video objectives), and learning objectives using problems (problem objectives)."

[0069] The "#Learning Progress Data" field contains information about the user's learning progress. The information included in "#Learning Progress Data" may be user learning information stored in the User Learning Information DB122. For example, as shown in (1-5) of Figure 8, "#Learning Progress Data" may include information such as "Current Date," "Progress of learning using ebooks (ebook progress), progress of learning using videos (video progress), and progress of learning using problems (problem progress)."

[0070] The support device 100 (output unit) then outputs learning support messages generated based on the prompts shown in Figure 8(1), as shown in Figure 8(2). For example, the messages shown in Figure 8(2) include "current situation analysis," "necessary actions," "short-term goals," "suggestions for support functions," and "suggestions for schedule revision" (Figure 8(2-1)), based on a comparison between "#personal assignment data" and "#learning progress data," as well as a message to the user (Figure 8(2-2)).

[0071] For example, the "Current Situation Analysis" section might include messages such as, "As of [Date], there are [number] months remaining until the deadline. Progress on learning using ebooks is [percentage]%, progress on learning using videos is [percentage]%, and progress on learning using problems is [percentage]%." The "Required Actions" section might include messages such as, "You have [percentage]% remaining to reach your target. You need to progress by [percentage]% each day. A recommended approach is to make full use of the ebook reading function and set a goal to read at least [number] chapters each day."

[0072] "Short-term goals" include things like "advance learning using ebooks to X%", "advance learning using videos to X%", and "advance learning using problems to X%". "Suggestions for support features" include things like "If you have any questions, use the question function to clarify them. Furthermore, if you face individual challenges, you should also consider using the person-to-person coaching function to receive direct advice." "Suggestions for schedule revision" include things like "Considering the current pace and estimated progress pace, it is highly likely that it will be difficult to meet the deadline, especially for the ebooks. Therefore, please consider extending the deadline to Month Day."

[0073] Furthermore, the message to the user (Figure 8 (2-2)) includes phrases such as, "Follow this plan to continue your daily learning, regularly evaluate your progress, and make adjustments as needed."

[0074] Here, we will explain the "example of output in chat format" described in Figures 7 and 8 using Figure 9. Figure 9 shows an example of output of learning support information in chat format related to the first example.

[0075] Figure 9 shows a chat-style screen for outputting learning support messages and learning plans generated by a large-scale language model. For example, the support device 100 (output unit) can display learning support messages and learning plans generated by the large-scale language model to the user, as shown in (1) of Figure 9.

[0076] Furthermore, the support device 100 (reception unit) can receive replies and questions regarding learning support messages and learning plans entered by the user (Figure 9 (2)). Then, the support device 100 (generation unit) can generate further learning support messages and learning plans in response to the received replies and questions.

[0077] (Second example: Answering a user's question) Next, we will describe an example in which the support device 100 generates "answers to user questions" as learning support information and outputs them to the user. In the second example, the support device 100 generates answers to questions according to the user's learning status and the user's questions, and outputs them to the user.

[0078] Specifically, the support device 100 (reception unit) receives questions from the user in a chat format. The support device 100 (generation unit) then inputs the received questions and commands to generate answers to those questions into a large-scale language model, generating answers to the questions as learning support information for the user.

[0079] Here, we will explain the input prompt examples and output examples in the processing related to the second example using Figure 10. Figure 10 is a diagram showing an example of prompts related to the second example. Figure 10 shows several examples of prompts (Figure 10(1) and (2)) for generating answers in response to the large-scale language model in accordance with the user's learning status and questions from the user, and an example of an answer generated and output based on the prompt (Figure 10(3)).

[0080] The first prompt shown in Figure 10 (1) includes "#Background Information", "#Instruction (Figure 10 (1-1))", and "#Constraints (Figure 10 (1-2))". Note that "#Background Information" is processed in the same way as in Figure 7 based on the instructions described in Figure 10, so its explanation is omitted.

[0081] "#command" is a directive that causes the large-scale language model to perform a predetermined process, similar to the example in Figure 7. For example, the directive shown in (1-1) of Figure 10 allows the support device 100 (generation unit) to cause the large-scale language model to perform tasks such as "generating an answer to a question from a user regarding predetermined content (teaching materials / themes), while strictly adhering to the set constraints."

[0082] "#Constraints" are instructions that define (restrict) the execution method of processing by the large-scale language model, similar to the example in Figure 8. For example, the instruction shown in (1-2) of Figure 10 allows the support device 100 (generation unit) to impose constraints on the large-scale language model when generating an answer, such as "character limit" or "suggest an alternative learning function if an answer is not possible."

[0083] Furthermore, the second prompt shown in Figure 10 (2) includes "# command (Figure 10 (2-1))". For example, the command shown in Figure 10 (2-1) causes the large-scale language model to "generate a message summarizing the learning theme and confirming whether there are any questions about that learning theme on the first attempt," and "generate a message based on the message entered by the user and the message generated immediately before on subsequent attempts," etc.

[0084] The support device 100 (output unit) then outputs the initial message generated based on the prompts shown in Figure 10 (1) and (2), as well as the answers to the user's questions, as shown in Figure 10 (3). For example, the support device 100 (output unit) outputs text such as "...(summary of learning theme)...Do you have any questions? (Figure 10 (3-1))" as the initial message.

[0085] Next, the user inputs a question to (3-1) in Figure 10, such as, "I've completely forgotten about XX. Could you explain it to me? (Figure 10 (3-2))." The support device 100 (output unit) then outputs a message such as "...(detailed answer)...(Figure 10 (3-3))" in response to the question input by the user.

[0086] Here, we will explain the "example of output in chat format" described in Figure 10 using Figure 11. Figure 11 is a diagram showing an example of output of learning support information in chat format related to the second example. Figure 11 shows a chat-format screen for outputting the initial message and answers to questions generated by a large-scale language model.

[0087] For example, the support device 100 (output unit) can display an initial message generated by a large-scale language model to the user, as shown in Figure 11 (1). The support device 100 (reception unit) can receive questions and other inputs from the user (Figure 11 (2)). The support device 100 (generation unit) can then display the generated answers to the user in response to the received questions and other inputs (Figure 11 (3)). In this way, the support device 100 can output interactive answers to questions from the user.

[0088] Furthermore, the support device 100 can perform coaching using information contained in the teaching materials. Here, an example of optimizing coaching using information contained in the teaching materials will be explained using Figure 12. Figure 12 is a diagram showing an example of a prompt used for coaching optimization in the second example.

[0089] First, the support device 100 (reception unit) receives a question from the user. Next, the support device 100 (generation unit) searches for text data related to the user's question based on vector data, etc. Subsequently, the support device 100 (generation unit) inputs the user's question and the retrieved text data into the large-scale language model using the first prompt shown in (1) of Figure 12 and the second prompt shown in (2) of Figure 12.

[0090] The support device 100 (generation unit) searches for different text data based on the generation results output from the large-scale language model and the user's question. The support device 100 (generation unit) then inputs the generation results output from the large-scale language model, the user's question, and the searched different text data back into the large-scale language model using the first prompt shown in (1) of Figure 12 and the third prompt shown in (3) of Figure 12. This process is repeated until predetermined conditions such as the number of iterations and generation accuracy are met.

[0091] The support device 100 (output unit) then outputs the generated message to the user. Based on the above processing, the support device 100 can provide the user with optimized coaching using the information contained in the teaching materials.

[0092] (Example 3: Generation and output of practice problems and solution information) Next, we will describe an example in which the support device 100 generates "practice problems" as learning support information and outputs them to the user. In the third example, the support device 100 generates practice problems according to the user's learning progress and outputs them to the user.

[0093] Furthermore, the support device 100 generates scoring results and explanatory information based on the scoring results for the user's answers to the practice problems presented, and outputs them to the user. The "explanatory information" here includes whether the user's answer is correct or incorrect, a detailed explanation of the content of the correct answer, and information on transitions to educational data related to the correct answer.

[0094] In terms of specific processing, the support device 100 (generation unit) inputs a command to a large-scale language model to generate practice problems (predetermined tasks) based on constraints such as the number of questions, answer choices, difficulty level, not generating the same question twice, and character limits, according to the user's learning progress, thereby generating the practice problems as learning support information for the user.

[0095] Furthermore, the support device 100 (reception unit) receives answers to practice problems from the user. Next, the support device 100 (generation unit) inputs the received answers and commands to generate scoring results and explanatory information for the answers into a large-scale language model, and generates the scoring results and explanatory information as learning support information for the user.

[0096] Here, we will explain the input prompt examples and output examples in the processing related to the third example. Figure 13 is a diagram showing an example of prompts related to the third example. Figure 13 shows an example of multiple prompts (Figure 13(1) and (2)) for generating practice problems for a large-scale language model according to the user's learning progress, an example of practice problems generated and output based on the prompts, and an example of the scoring results and explanatory information for the practice problems (Figure 13(3)).

[0097] The first prompt shown in Figure 13 (1) includes "#Background Information", "#Instruction (Figure 13 (1-1))", and "#Constraints (Figure 13 (1-2))". Note that "#Background Information" is processed in the same way as in Figure 7 based on the instructions described in Figure 13, so its explanation is omitted.

[0098] "#command" is a directive that causes the large-scale language model to perform a predetermined process, similar to the example in Figure 7. For example, the directive shown in (1-1) of Figure 13 allows the support device 100 (generation unit) to perform tasks such as "generating practice problems of a predetermined format, such as multiple-choice questions, according to the user's learning progress, while strictly adhering to the set constraints."

[0099] "#Constraints" are instructions that define (restrict) the execution method of processing by the large-scale language model, similar to the example in Figure 8. For example, the instructions shown in (1-2) of Figure 13 allow the support device 100 (generation unit) to impose constraints on the large-scale language model when generating practice problems, such as "limiting the number of problems," "limiting the answer choices," "adjusting the difficulty level," "presenting different problems," and "limiting the number of characters."

[0100] Furthermore, the second prompt shown in Figure 13 (2) includes "# command (Figure 13 (2-1))". Note that the second prompt shown in Figure 13 (2) is the same as the prompt shown in Figure 10 (2-1), so no explanation is provided.

[0101] The support device 100 (output unit) then outputs practice problems generated based on the prompts shown in (1) and (2) of Figure 13, as well as scoring results and explanatory information for the practice problems, as shown in (3) of Figure 13.

[0102] For example, the support device 100 (output unit) outputs text such as "...(summary of learning theme)...Now, let's try solving the following problem." and "Problem: What is the role of XX?...(omitted)...Which do you think is the correct answer?" as messages displayed when a practice problem is presented (Figure 13 (3-1)).

[0103] The user inputs an answer to (3-1) in Figure 13, such as "I think 'A' is the correct answer" (Figure 13 (3-2)). The support device 100 (output unit) then outputs text in response to the user's answer, such as "That's correct!... (explanation)...", "Let's move on to the next question. The next one is a little more difficult..." (Figure 13 (3-3)).

[0104] Here, we will explain the "example of output in chat format" described in Figure 13 using Figure 14. Figure 14 is a diagram showing an example of output of learning support information in chat format related to the third example. Figure 14 shows a chat-format screen for outputting practice problems generated by a large-scale language model, scoring results and explanatory information for answers to the practice problems, etc., in natural language.

[0105] For example, the support device 100 (output unit) can display a message to the user regarding the presentation of practice problems generated by a large-scale language model, as shown in Figure 14 (1). The support device 100 (reception unit) can also receive answers to the practice problems entered by the user (Figure 14 (2)).

[0106] The support device 100 (output unit) can then display to the user the scoring results and explanatory information generated according to the received answers (Figure 14 (3)). Furthermore, the support device 100 (output unit) can then present practice problems, which have been generated with adjusted difficulty levels according to the user's answers, as the next problem (Figure 14 (3)).

[0107] Furthermore, as shown in (4) and (5) of Figure 14, the support device 100 can receive answers from the user and output scoring results and explanatory information generated according to the received answers. In addition, by repeatedly executing the above processes, the support device 100 effectively supports the user in performing practice problems and reviewing the explanations.

[0108] (Processing procedure according to the first embodiment) From here, a series of processing procedures implemented by the support device 100 according to the first embodiment will be described. Figure 15 is a flowchart of the processing performed by the support device 100 according to the first embodiment.

[0109] The support device 100 waits to start processing until the conditions for starting the generation of learning support information are met (No in S101). Then, when the conditions for starting the generation of learning support information are met, the support device 100 starts processing (Yes in S101). The conditions for starting the generation referred to here are arbitrary conditions and include, for example, input from the user, the elapsed time of a predetermined period, the arrival of a set schedule, instructions from an administrator, etc.

[0110] The generation unit 132 inputs user learning information into a large-scale language model to generate learning support information according to the user's learning status (S102). Next, the output unit 133 outputs learning support information according to the user's learning status (S103).

[0111] Here, if the processing termination condition is not met (No in S104), the support device 100 returns to the previous step and continues processing. On the other hand, if the processing termination condition is met (Yes in S104), the support device 100 terminates the process. The processing termination condition referred to here is an arbitrary condition and includes, for example, input from the user, elapsed time, arrival of a set schedule, instructions from an administrator, etc.

[0112] (effect) Next, we will explain the effects of the support device 100 according to the first embodiment. Conventionally, there have been challenges in providing learning support tailored to the learning status of the user when learning online.

[0113] Therefore, the generation unit 132 of the support device 100 according to the first embodiment inputs user learning information, which is used for learning from ebooks, into a large-scale language model to generate user learning support information according to the user's learning status. The output unit 133 of the support device 100 outputs the generated user learning support information.

[0114] Therefore, the support device 100 has the effect of enabling appropriate learning support according to the user's learning progress. Furthermore, the support device 100 achieves predetermined effects by executing the processes described below.

[0115] The generation unit 132 inputs a command to the large-scale language model to generate a user learning support message that includes at least one of the following: words of encouragement for the user according to the user's learning progress, a summary of the user's learning content, and a message confirming whether or not there are any questions, and generates the user learning support message as user learning support information.

[0116] Through the processing described above, for example, if the user's learning progress is behind, the support device 100 can display encouraging words (words of support) to the user, such as "Your learning is behind, is there anything wrong? It's tough, but let's do our best!" Furthermore, to support the user's learning, the support device 100 can display a "summary of the learning content up to the last lesson" to the user, and then display questions such as "Do you have any questions about the learning content up to the last lesson?" to resolve any points of confusion the user may have and deepen their understanding of the learning content. As a result, the support device 100 has the effect of enabling the user to progress in their learning efficiently and effectively, according to the user's learning progress.

[0117] The reception unit 131 receives questions from users in a chat format. The generation unit 132 inputs the received questions and commands to generate answers to those questions into a large-scale language model, and generates answers to the questions as learning support information for the user.

[0118] Through the process described above, the support device 100 can, for example, display an explanation of "XX" as an answer to a question from a user, such as "What is XX?". As a result, the user can appropriately engage in self-study based on the answers provided by the support device 100 to their questions. Therefore, the support device 100 has the effect of enabling more efficient and effective self-study for users than before.

[0119] The generation unit 132 inputs a command to the large-scale language model to generate practice problems (predetermined tasks) based on constraints regarding the format of the practice problems (predetermined tasks) according to the user's learning progress, and generates the practice problems (predetermined tasks) as learning support information for the user.

[0120] Through the process described above, the support device 100 can generate and provide to the user appropriate practice problems based on the user's learning progress and the e-books the user uses for learning. As a result, the user can perform appropriate self-study, such as solving practice problems, based on the practice problems provided by the support device 100 that are tailored to the user's learning status. Therefore, the support device 100 has the effect of enabling more efficient and effective self-study for the user than before.

[0121] The reception unit 131 receives answers from the user to practice problems (predetermined tasks). The generation unit 132 inputs the received answers and commands to generate scoring results and explanatory information for the answers into a large-scale language model, and generates the scoring results and explanatory information as learning support information for the user.

[0122] Through the processing described above, the support device 100 can provide scoring results, such as correctness, for the user's answers to the practice problems generated by the support device 100. In addition, the support device 100 can provide explanatory information, such as chapters, sections, or individual descriptions of ebooks related to the user's answers and scoring results, as well as explanatory videos, in association with the user's answers.

[0123] As a result, users can engage in appropriate self-study, such as reviewing the results of their practice exercises and reviewing content they do not fully understand, based on the scoring results and explanatory information provided by the support device 100. Therefore, the support device 100 has the effect of enabling more efficient and effective self-study for users than before.

[0124] The output unit 133 outputs the generated user learning support information to the user in chat format. Through the above processing, the support device 100 realizes natural interaction in a conversational format using natural language for coaching, teaching, receiving and answering questions from the user. As a result, the support device 100 has the effect of providing an environment in which the user can naturally consult with or ask questions of the support device 100.

[0125] The generation unit 132 inputs information about the user's learning, including at least one of the user's learning history, the user's learning goals, and past conversation data, into a large-scale language model to generate learning support information that corresponds to the user's learning status using the task.

[0126] Through the processes described above, for example, the support device 100 can provide teaching, coaching, and answer questions to the user according to the user's learning status and learning goals. As a result, the user can receive educational support from the support device 100 that is tailored to their learning situation, enabling them to resolve points of confusion and deepen their understanding of the learning content more effectively than before. Therefore, the support device 100 has the effect of enabling the user to progress in their learning efficiently and effectively.

[0127] <Second Embodiment> Next, a second embodiment will be described in which the support device 100, in addition to teaching and coaching the user as described in the first embodiment, further supports the implementation of hacking exercises. The support device 100 according to the second embodiment performs tasks such as dividing participants into teams for the hacking exercise, constructing the environment for conducting the hacking exercise, and generating and outputting feedback information on the results of the hacking exercise.

[0128] The hacking exercise described above involves users being divided into an "attack team" and a "defense team." The attack team carries out a virtual hacking (cracking, etc.) attack, while the defense team tries to prevent the attack team's virtual hacking attack.

[0129] (Support device 100) Next, the support device 100 according to the second embodiment will be described in detail. Figure 16 is a diagram showing an example of the configuration of the support device 100 according to the second embodiment. As shown in Figure 16, the support device 100 according to the second embodiment has a communication unit 110, a storage unit 120, and a control unit 130, similar to the first embodiment. Note that the support device 100 according to the second embodiment and the support device 100 according to the first embodiment have common functions. Therefore, in the following sections, the functions common to the first and second embodiments will be omitted as appropriate.

[0130] (Storage unit 120) The memory unit 120 includes a teaching material information DB 121, a user learning information DB 122, a generation model DB 123, and a result information DB 124.

[0131] (Results Information DB124) The Results Information DB124 is a database that stores information (results information) regarding the results of hacking exercises conducted by each team. Specifically, the Results Information DB124 stores information identifying the teams that participated in the hacking exercises (teams) and the results of the hacking exercises as results information.

[0132] Here, we will explain an example of result information stored in the result information DB124. Figure 17 is a table diagram showing an example of result information according to the second embodiment. As shown in Figure 17, the result information DB124 stores the items "Team" and "Exercise Result" and the information related to those items in a table format, etc., associated with "No," which is information that identifies individual result information.

[0133] For example, as shown in Figure 17, the results information DB124 stores the team "Attack," identified by No. "1," and the exercise result "K" in association with each other. Note that the letters "K" and "L" included in the table diagram shown in Figure 17 are legends for each item of individual result information stored in the results information DB124, and the actual information stored is not particularly limited.

[0134] The "team" mentioned above refers to the team conducting the hacking exercise, and includes information identifying the "attack team" that attempts to hack and the "defense team" that prevents hacking. The "exercise results" refer to information about the results of the hacking exercise, and for example, for the attack team, this includes information such as "score, number of anomalies, final number of anomalies, and time of anomaly occurrence," while for the defense team, it includes information such as "score, number of resolved anomalies, final number of normal occurrences, time of anomaly resolution, and normal operating time."

[0135] (Control unit 130) Now, let's return to Figure 16 and continue the explanation. The control unit 130 has a reception unit 131, a generation unit 132, and an output unit 133, as well as a team design unit 134 and a construction unit 135.

[0136] (Generation unit 132) The generation unit 132 inputs the results of exercises performed using the constructed execution environment and commands to generate feedback information regarding the exercise results into a large-scale language model, thereby generating feedback information regarding the exercise results as user learning support information. For example, the generation unit 132 inputs prompts including "#background information", "#command", and "#exercise results" into the large-scale language model to generate feedback information regarding the exercise results.

[0137] The above "#Background Information" includes information that defines your role, such as, "You are an AI instructor who will grade hacking exercises. Follow the #Instructions to generate feedback information regarding the results of the hacking exercises." The "#Instructions" include commands such as, "Score the exercise results using the number of anomalies, the final number of anomalies, and the duration of the anomalies in the attacking team," or "Score the exercise results using the number of anomaly resolutions, the final number of normal operations, the duration of anomaly resolution, and the normal operating time in the defending team." The above prompts may also include "#Constraints."

[0138] (Output section 133) The output unit 133 outputs feedback information regarding the results of the generated exercise. For example, the output unit 133 outputs feedback information to users who participated in the hacking exercise, including exercise results for the attacking team such as "score, number of anomalies, final number of anomalies, and time of anomaly occurrence," and exercise results for the defending team such as "score, number of anomaly resolutions, final number of normal occurrences, time of anomaly resolution, and normal operating time."

[0139] (Team Design Department 134) The team design unit 134 assigns users to either the first team, which is the attacking team, or the second team, which is the defending team, depending on the user's learning status. For example, the team design unit 134 assigns users whose learning progress falls within the top XX to the "defensive team" and users whose learning progress falls within the bottom XX to the "attacking team," based on the user's learning status as determined by the user's learning information stored in the user learning information DB 122.

[0140] (Construction Section 135) The construction unit 135 constructs an execution environment for the first team (attack team) and second team (defense team) to carry out hacking exercises, according to the user's learning progress. Specifically, the construction unit 135 uses RPA (Robotic Process Automation) tools and other means to execute registered scripts according to the user's learning progress based on the user's learning information stored in the user learning information DB 122, thereby automatically and periodically performing operations such as email, chat, file sharing, and website browsing.

[0141] For example, in the case of a hacking exercise conducted by multiple users whose learning progress falls within the top XX category, the construction unit 135 automatically performs operations such as "browsing a website." On the other hand, in the case of a hacking exercise conducted by multiple users whose learning progress falls within the bottom XX category, the construction unit 135 automatically performs operations such as "sending email, chatting, and sharing files."

[0142] (Example of a hacking exercise screen) From here, an example of team division, environment setup, and generation and output of feedback information regarding the results of a hacking exercise, as implemented by the support device 100 according to the second embodiment, will be explained using Figure 18. Figure 18 is a diagram showing an example of the processing of the support device 100 according to the second embodiment.

[0143] First, the support device 100 begins preparations for conducting the hacking exercise. If the conditions for starting the hacking exercise are not met, the device waits until the exercise can begin.

[0144] The support device 100 (team design unit) assigns the user to either an "attack team" or a "defense team" according to the user's learning progress and designs the "attack team" and "defense team" (Figure 18 (1)). Next, the support device 100 (construction unit) constructs a hacking exercise environment in which email, chat, file sharing, website browsing, etc. are automatically executed according to the user's learning progress (Figure 18 (2)).

[0145] Users assigned to either the "attack team" or the "defense team" then participate in hacking exercises conducted by the support device 100 (Figures 18 (3-1) and (3-2)).

[0146] When a hacking exercise is performed, the support device 100 (generation unit) inputs the results of the hacking exercise (exercise results) into a large-scale language model (Figure 18 (4-1)) and generates feedback information about the results of the hacking exercise (Figure 18 (4-2)).

[0147] The support device 100 (output unit) outputs the generated feedback information to the terminal device 200 (Figure 18 (5-1)). As a result, the terminal device 200 can display information such as "summary of exercise results" and "explanatory information about the results of the hacking exercise" to the user as learning support information (Figure 18 (5-2)).

[0148] Here, an example of feedback information output by the support device 100 (output unit) will be explained using Figure 19. Figure 19 is a diagram showing an example of a hacking exercise screen according to the second embodiment. Figure 19 shows the hacking exercise environment (Figure 19(1)) and the hacking exercise results (Figure 19(2)).

[0149] The exercise environment shown in Figure 19(1) is an environment where emails are automatically sent to a specified recipient. The attack team will hack into this automated email sending environment. Note that the automated email sending environment shown in Figure 19(1) is just one example; other environments that automatically perform operations such as chat, file sharing, and website browsing may also be used.

[0150] In the area shown in (2) of Figure 19, information such as "score, number of anomalies, final number of anomalies, and duration of anomalies" is displayed for the attacking team, and "score, number of anomalies resolved, final number of normal events, duration of anomaly resolution, and normal operating time" is displayed for the defending team. The results of the hacking exercise shown in (2) of Figure 19 may be displayed in real time during the hacking exercise, or they may be displayed as a comprehensive result after the exercise is completed.

[0151] (Processing procedure according to the second embodiment) Next, a series of processing steps implemented by the support device 100 according to the second embodiment will be described. Figure 20 is a flowchart of the processing performed by the support device 100 according to the second embodiment.

[0152] The support device 100 waits to process until the hacking exercise begins (No in S201). Then, when the hacking exercise begins (Yes in S201), the team design unit 134 divides the users into teams according to their learning progress (S202). Next, the construction unit 135 constructs the execution environment for the hacking exercise according to the users' learning progress (S203).

[0153] If the exercise is not yet complete (No in S204), the support device 100 waits to proceed to the next step. On the other hand, if the exercise is complete (Yes in S204), the generation unit 132 generates feedback information (S205). Next, the output unit 133 outputs the feedback information (S206). Then, the support device 100 completes the process.

[0154] (effect) In the second embodiment, the team design unit 134 of the support device 100 assigns the user to either a first team or a second team according to the user's learning progress and designs the teams. The construction unit 135 of the support device 100 constructs an execution environment for the designed first team and second team to perform hacking exercises, according to the user's learning progress. The generation unit 132 then inputs the results of the exercises performed using the constructed execution environment and commands to generate feedback information regarding the exercise results into a large-scale language model, and generates feedback information regarding the exercise results as learning support information for the user.

[0155] Therefore, the support device 100 enables the implementation of appropriate hacking exercises tailored to each user's level of understanding, technical skill, and learning progress.

[0156] Specifically, the support device 100 enables appropriate team design, taking into account the skill and knowledge levels of the users to ensure that the balance of abilities among teams during hacking exercises is not skewed. As a result, the support device 100 enables more effective hacking exercises than before.

[0157] Furthermore, when conducting hacking exercises, the environment in which the exercises are conducted is taken into consideration. For example, if an execution environment is built that is too high or too low compared to the users' technical level or knowledge level, users will not be able to perform appropriate hacking exercises, and thus effective hacking exercises that improve users' skills cannot be conducted. Therefore, the support device 100 takes into consideration the balance of skills among teams when building an execution environment for hacking exercises that matches the technical level and knowledge level of the users, and enables appropriate team design. As a result, the support device 100 enables the conduct of more effective hacking exercises than before.

[0158] Furthermore, the support device 100 generates feedback information, including scoring results, summaries, and explanatory information regarding the hacking exercises, based on a large-scale language model. As a result, the support device 100 enables the generation of feedback information in real time and the generation of feedback information with a larger amount of information than before. Consequently, the support device 100 has the effect of enabling more effective hacking exercises than before. The above-mentioned "larger amount of information" means that it includes, for example, "scores for each team," "good or bad points for each team," "areas for improvement," and "related ebooks or information collected from external sources."

[0159] <Variation> The following describes modifications that can be implemented by the support device 100 according to this embodiment.

[0160] (Another form of generating and grading practice problems) The support device 100 according to the first embodiment described above generates practice problems and scores practice problems based on a large-scale language model, but is not limited to this.

[0161] For example, the support device 100 presents the user with practice problems entered by an administrator or the like. Next, the support device 100 receives the user's answers to the practice problems. Then, the support device 100 compares the received answers with pre-registered correct answers and scores them.

[0162] Through the above process, the support device 100 can, for example, present the user with practice problems for remotely configuring actual equipment such as communication devices, and the user configures the communication devices based on remote operation in response to the practice problems. The support device 100 can then compare the configuration state of the communication devices configured by the user based on remote operation with the configuration state of communication devices that has been registered as the correct answer in advance, and score the user's performance.

[0163] (Data, etc.) The names of the functional parts of the support device 100, such as ebooks, coaching, teaching, practice problems (predetermined assignments), learning support messages, etc., as well as the names of steps, processes, and steps or processes used in the description of the above embodiment, are merely examples and can be changed at will.

[0164] For example, while it was explained that the teaching material information DB121 stores items such as "title," "link," "order," "number of content items," "assignment," and "type," as well as information related to those items, in a table format, etc., associated with "No," which is information that identifies individual teaching material information, the items, content, and storage format are not limited. While it was explained that the user learning information DB122 stores items such as "user identification information," "teaching materials used," "learning history," "learning objectives," and "conversation history," as well as information related to those items, in a table format, etc., associated with "No," which is information that identifies individual user learning information, the items, content, and storage format are not limited. While it was explained that the results information DB124 stores items such as "team" and "exercise results," as well as information related to those items, in a table format, etc., associated with "No," which is information that identifies individual results information, the items, content, and storage format are not limited.

[0165] (Regarding the use of generative models) In this embodiment, the model (large-scale language model) used by the support device 100 is described as being stored in the generated model DB 123 of the storage unit 120, but this is not limited to this. For example, the support device 100 can access an external information processing device (server, etc.) and use a predetermined model.

[0166] (Flowcharts, etc.) In flowcharts, each step may be rearranged as long as it does not create inconsistencies, and some steps may be omitted. Furthermore, conjunctions such as "next," "continue," "in addition," "at this time," and "on this occasion" in flowchart descriptions do not limit the order or timing of the processes in the flowchart.

[0167] (Systems, etc.) Of the processes described in the embodiments and modifications described above, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0168] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily have to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0169] The aforementioned components include those that are easily conceivable by those skilled in the art, those that are substantially identical, and those that fall within the so-called equivalent range. Furthermore, the embodiments and modifications described above can be combined as appropriate, as long as the processing content is not contradictory.

[0170] Furthermore, the terms "section," "module," and "unit" mentioned above can be replaced with "means" or "circuit," etc. For example, a control unit can be replaced with a control means or a control circuit.

[0171] Although several embodiments have been described in detail above with reference to the drawings, these are merely examples, and it is possible to implement these embodiments in various modified and improved forms based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

[0172] <Hardware Configuration> The device included in the support device 100 according to this embodiment is implemented by a computer 1000 having a configuration as shown in Figure 21. Figure 21 is a diagram showing an example of the hardware configuration of a computer that implements the support device 100 according to this embodiment.

[0173] The computer 1000 has a configuration in which a CPU 1100, memory 1200, auxiliary storage device 1300, input interface 1400, output interface 1500, and communication interface 1600 are connected by a bus 1700.

[0174] The CPU 1100 operates based on programs stored in the memory 1200 or auxiliary storage device 1300, and controls each functional unit. The memory 1200 consists of, for example, RAM (Random Access Memory) or ROM (Read Only Memory), and stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

[0175] For example, when the computer 1000 functions as the support device 100 according to this embodiment, the CPU 1100 of the computer 1000 can realize the functions of the control unit 130 by executing a program loaded on the memory 1200.

[0176] The auxiliary storage device 1300 stores programs executed by the CPU 1100, as well as data used by such programs. The CPU 1100 controls input devices 1410, such as keyboards and mice, via the input interface 1400. The CPU 1100 also acquires data from the input devices 1410 via the input interface 1400.

[0177] The CPU 1100 controls output devices 1510, such as displays and printers, via the output interface 1500. The CPU 1100 also outputs generated data to the output devices 1510 via the output interface 1500.

[0178] The communication interface 1600 receives data from other devices via a predetermined network NW and sends it to the CPU 1100, and the CPU 1100 transmits the generated data to other devices via the predetermined network NW. [Explanation of Symbols]

[0179] 100 Support equipment 110 Communications Department 120 Storage section 121 Teaching material information DB 122 User Learning Information Database 123 Generative Model DB 124 Results information DB 130 Control Unit 131 Reception Department 132 Generation part 133 Output section 134 Team Design Department 135 Construction Department

Claims

1. A team design department that assigns a user to a first team or a second team and designs the teams based on the user's learning status, which is determined by information relating to the user's learning, including learning materials used by the user for learning, learning history, learning goals, and conversation history, relating to the user who uses the ebook for learning. A construction unit that constructs an execution environment for the first team and the second team to perform hacking exercises according to the user's learning status, A support device characterized by having the following features.

2. The system further includes an output unit that outputs feedback information to users who participated in the hacking exercise, including the exercise results for the first team, which is a team that attempts hacking, and the exercise results for the second team, which is a team that prevents hacking. The support device according to feature 1.

3. The system further includes a generation unit that inputs the results of the hacking exercise performed using the constructed execution environment and a command to generate feedback information regarding the results of the hacking exercise into a large-scale language model, and generates the feedback information regarding the results of the hacking exercise as information to support the user's learning. The support device according to feature 1 or 2.

4. The aforementioned team design department, As for the learning status of the users, users whose learning progress falls within a predetermined rank in descending order are assigned to the second team, and users whose learning progress falls within a predetermined rank in descending order are assigned to the second team, thereby designing the teams. The support device according to feature 1 or 2.

5. The aforementioned construction unit is Depending on the user's learning progress, an environment is created in which at least one of the following operations—email, chat, file sharing, and website browsing—is automatically and periodically performed by executing a predetermined script. The support device according to feature 1 or 2.

6. A support method to be executed by a support device, A team design process that assigns a user to a first team or a second team and designs the team, based on the user's learning status, which is determined by information relating to the user's learning, including learning materials used by the user for learning, learning history, learning goals, and conversation history, relating to the user who uses the ebook for learning. A construction process for constructing an execution environment for the first team and the second team to perform hacking exercises, according to the learning status of the users, A support method characterized by including

7. A team design step that assigns a user to a first team or a second team and designs the team, based on the user's learning status, which is determined by information relating to the user's learning, including learning materials used for learning, learning history, learning goals, and conversation history, relating to the user who uses the ebook for learning. A construction step to build an execution environment for the first team and the second team to perform hacking exercises, according to the learning status of the users, A support program characterized by having a computer execute a command.

Images