Support device, support method, and support program

Abstract

This makes it possible to appropriately support user education within an organization. [Solution] The support device 100 processes data related to organizational education, which is data used for educating users belonging to an organization and stored in a storage unit for each organization, into practice questions to be completed by the user for learning about the organization based on a large-scale language model, or processes the data into educational videos to be used by the user for learning about the organization based on text data included in the data related to organizational education. The support device 100 outputs the processed practice questions or educational videos to the user.

Description

[Technical Field]

[0001] The present invention relates to an assistance device, an assistance method, and an assistance program. [Background technology]

[0002] Training may be provided to personnel belonging to an organization (hereinafter referred to as "users") to enable them to behave appropriately within the organization. Materials used for such training are managed by educational purpose and content, and are used when users receive training related to the organization. Users then use the materials and content to learn on their own.

[0003] In recent years, data management technologies using on-premise or cloud-based server devices have been used to manage educational materials and content. For example, a conventional technology is known in which an application for managing data is built using no-code and the built application is used to manage materials and content (see, for example, Non-Patent Document 1). [Prior art documents] [Non-patent literature]

[0004] [Non-Patent Document 1] Kintone,<URL:https: / / kintone.cybozu.co.jp / > ,<Search date: September 3, 2020> Summary of the Invention [Problem to be solved by the invention]

[0005] However, conventional technologies have problems in providing appropriate support for user education within an organization. For example, while conventional technologies can create applications for workflow and data management, they have problems in processing educational materials and content for each organization to generate assignments to be used in user education and thereby support user education. [Means for solving the problem]

[0006] Therefore, in order to solve the above problems and achieve the objectives, the support device of the present invention is characterized by comprising a processing unit that processes data related to organizational education, which is data used for educating users belonging to an organization and is stored in a memory unit for each organization, into practice problems to be carried out by the users to be used in their learning about the organization based on a large-scale language model, or into educational videos to be used by the users to be used in their learning about the organization based on text data included in the data related to the organization's education, depending on the learning status of the users belonging to the organization, and an output unit that outputs the processed practice problems or educational videos to the users. [Effects of the Invention]

[0007] The present invention has an effect of enabling appropriate support for user education in an organization. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram showing an outline of educational support for a user according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of the support device according to the embodiment. [Figure 3] FIG. 3 is a table diagram illustrating an example of the teaching material information according to the embodiment. [Figure 4] FIG. 4 is a table diagram illustrating an example of user learning information according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a reception screen according to the embodiment. [Figure 6] FIG. 6 is a diagram showing an example of a screen for accepting training data according to the embodiment. [Figure 7] FIG. 7 is a diagram showing a series of flows of the generation process and output process according to the embodiment. [Figure 8] FIG. 8 is a diagram illustrating an example of a prompt according to the first example. [Figure 9] FIG. 9 is a diagram showing an example of output of learning support information in a chat format according to the first example. [Figure 10] FIG. 10 is a diagram illustrating an example of a prompt according to the second example. [Figure 11] FIG. 11 is a diagram illustrating an example of a prompt according to the second example. [Figure 12] FIG. 12 is a diagram showing an example of output of learning support information in a chat format according to the second example. [Figure 13] FIG. 13 is a diagram illustrating an example of a prompt according to the third example. [Figure 14] FIG. 14 is a diagram showing an example of learning support information output in a chat format according to the third example. [Figure 15] FIG. 15 is a flowchart of the processing of the support device according to the embodiment. [Figure 16] FIG. 16 is a diagram illustrating an example of a hardware configuration of a computer that realizes the support device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention (hereinafter referred to as "embodiments") will be described with reference to the drawings. Note that the embodiments are not limited to the following description.

[0010] <Introduction> (background) Traditionally, users belonging to an organization may be trained to behave appropriately within the organization. Training may be conducted in the form of classroom lectures by educators in the organization or on-the-job training (OJT) by business instructors. In addition, users may learn by themselves using educational materials for the organization's education, which are managed by educational purpose and content.

[0011] As a technology for enabling users to learn by themselves, there is known a technology for managing educational materials for each educational purpose and content. For example, there is known a reference technology for managing materials and content used in the education of users belonging to an organization using an on-premise or cloud-based server device. The reference technology allows various applications to be created without coding and the target data to be managed using the applications.

[0012] However, it is difficult to process data of educational materials managed by each organization and generate predetermined assignments (hereinafter simply referred to as "assignments") such as educational videos and practice questions to be used in user education. Therefore, it may be difficult for the reference technology to appropriately support user education.

[0013] (Processing by the support device 100) Therefore, the support device 100 of this embodiment provides appropriate support for the user's education related to the organization by outputting to the user being educated "assignments" generated using data related to the education of the organization (hereinafter, sometimes referred to as "educational data"), which is data used for educating users belonging to the organization and is managed by each organization.

[0014] Here, an overview of the processing by the assistance device 100 will be described. Fig. 1 is a diagram showing an overview of educational assistance for a user according to an embodiment. The assistance device 100 shown in Fig. 1 is an example of a computer that provides technology for realizing the information processing described below.

[0015] First, the support device 100 receives training data for each organization input by a trainer or the like in each organization and stores the data in the storage unit 120, as shown in (1-1) to (1-3) in FIG.

[0016] The support device 100 processes the educational data for each organization stored in the storage unit 120 into "tasks" to be used by the user 10 for learning about the organization ((2-1) in FIG. 1). For example, the support device 100 processes the educational data for each organization to generate educational videos ((2-2) in FIG. 1), exercises (not shown in FIG. 1), etc.

[0017] The support device 100 outputs the generated assignment to the user 10. Then, the user 10 watches videos, practices problems, etc. in response to the assignments such as educational videos and practice problems output from the support device 100.

[0018] Next, the support device 100 inputs the learning situation of the user 10 using the assignment ((3-1) in FIG. 1) into the large-scale language model as prior knowledge ((3-2) in FIG. 1). Then, based on the learning situation of the user 10 input as prior knowledge, the support device 100 provides teaching and coaching to the user 10, answers questions from the user 10, asks questions, etc.

[0019] For example, the support device 100 prepares a study plan for the user 10 to efficiently advance their studies, manages the progress of their studies based on the study plan, and provides encouragement or reprimand to the user 10, depending on the user's learning situation ("Coaching" shown in (4-1) of FIG. 1). Furthermore, the support device 100 presents practice questions based on the user's learning situation, depending on the user's academic ability level and learning progress, and follows up on the answers given by the user 10 to the practice questions ("Teaching" shown in (4-2) of FIG. 1). Furthermore, the support device 100 outputs answers to "Questions ((4-3) of FIG. 1)" input by the user 10, depending on educational data for each organization and the learning situation of the user 10 ("Answer" shown in (4-4) of FIG. 1).

[0020] The support device 100 can realize the above-mentioned "coaching ((4-1) in FIG. 1)," "teaching ((4-2) in FIG. 1)," and "answering ((4-4) in FIG. 1)" in a natural language dialogue format (chat format), as shown in (5) in FIG. 1, for example.

[0021] In this way, the support device 100 according to this embodiment has the effect of enabling appropriate support for user education in an organization by generating assignments based on educational data for each organization, teaching and coaching to support user learning using the assignments, answering questions from users, and so on.

[0022] <Explanation of the support device 100> (Support device 100) Next, the support device 100 according to this embodiment will be described in detail. Fig. 2 is a diagram showing an example of the configuration of the support device 100 according to the embodiment. As shown in Fig. 2, the support device 100 according to the first embodiment has a communication unit 110, a storage unit 120, and a control unit 130.

[0023] 2, the assistance device 100 may include an input unit such as a keyboard or a mouse for receiving input of operations by an administrator, etc. The assistance device 100 may also include a display unit such as a display for displaying the teaching material information, user learning information, etc. stored in the storage unit 120 to the administrator.

[0024] (Communication unit 110) The communication unit 110 performs data communication related to input of information related to user learning, including educational data for each organization, information on the learning status of users who use the educational data, etc. (hereinafter, this may be referred to as "user learning information"), information related to conversations regarding coaching and teaching entered by users, answers to assignments, questions, etc., and output of generated information to support users' learning (hereinafter, this may be referred to as "learning support information") to terminal devices, etc.

[0025] The communication unit 110 is realized by, for example, a network interface card (NIC) or a network interface controller. The communication unit 110 is connected to a network (for example, the Internet) by wire or wirelessly. The communication unit 110 transmits and receives information to and from external devices via the network.

[0026] Note that the communication unit 110 may 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).

[0027] (Storage unit 120) The storage unit 120 stores data and programs used for various processes by the control unit 130, and various data acquired by the operation of the control unit 130. The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 2 , the storage unit 120 has a learning material information DB 121, a user learning information DB 122, and a generative model DB 123.

[0028] (Teaching material information DB121) The learning material information DB 121 is a database that stores educational data for each organization and assignments, etc. (learning material information) generated using the educational data. Specifically, the learning material information DB 121 stores, as learning material information, information that identifies an organization (organization identification information), titles of educational data, etc. managed for each organization (titles), link information (links) for accessing educational data stored in a predetermined storage device, information (order) indicating the display order when displaying a list of educational data, information (number of contents) indicating the number of contents of a predetermined granularity in the educational data, information (assignments) related to assignments associated with the educational data, information (types) indicating the release type of the learning material, etc.

[0029] Here, an example of the teaching material information stored in the teaching material information DB 121 will be described. Fig. 3 is a table diagram showing an example of the teaching material information according to the embodiment. The teaching material information DB 121 stores items such as "organization identification information," "title," "link," "order," "number of contents," "assignment," and "type" and information related to the items in a table format or the like, in association with "No.", which is information identifying individual teaching material information.

[0030] 3, the learning material information DB 121 stores organization identification information "1 (information identifying "organization 1")" identified by No. "1", a title "A", a link "B", an order "C", the number of contents "D", an assignment "E", and a type "F" in association with each other. Note that the above alphabets "A to F" are information showing a legend for each item of individual learning material information stored in the learning material information DB 121, and the information actually stored is not particularly limited.

[0031] Furthermore, using the learning material information stored in the learning material information DB 121, the support device 100 can display learning material information for each organization to a user, administrator, etc. in a list format including items such as "type," "thumbnail," "title," "order," "chapter," "section," and "task," as shown in (1) of Fig. 3. For example, the support device 100 can display learning material information at the granularity of "Company A," "Company B," etc., or at the granularity of "sales organization," "research and development organization," etc., which are included in "company."

[0032] The above "title" is information that identifies the educational data used by the user for learning, and includes, for example, information such as the title, volume number, and issue number of the educational data, expressed in natural language such as text, numbers, and symbols. "Link" is information for accessing the storage medium that stores the educational data itself or thumbnail information of the educational data, and includes, for example, information such as a URL (Uniform Resource Locator) associated with each educational data. "Order" is information used to specify the display order of the educational data when it is displayed in a list.

[0033] "Number of contents" is the number of contents organized at a predetermined granularity contained in the educational data, and includes, for example, the "number of chapters (chapters)" and the "number of sections (sections)." "Assignments" is information about assignments such as educational videos processed from educational data and practice questions given to users, and includes information such as the content and correct answers of the practice questions, the number of practice questions, etc. "Type" is a status that indicates the public status of the educational data, and includes, for example, "public," which is available to all registered users, and "limited," which is available only to specific users.

[0034] (User learning information DB122) The user learning information DB 122 is a database that stores information (user learning information) related to user learning, including information such as the learning status of the user who is learning using assignments. Specifically, the user learning information DB 122 stores, as user learning information, information for identifying the user (user identification information), assignments (teaching materials used) generated from educational data that the user uses for learning, the user's learning history (learning history), the user's learning goals (learning objectives), and the history of conversations between the user and the assistance device 100 (conversation history).

[0035] Here, an example of user learning information stored in the user learning information DB 122 will be described. Fig. 4 is a table diagram showing an example of user learning information according to an embodiment. The user learning information DB 122 stores items such as "user identification information," "teaching materials used," "learning history," "learning goals," and "conversation history" and information related to the items in a table format or the like, in association with "No.", which is information identifying individual user learning information.

[0036] 4, the user learning information DB 122 stores the user identification information "User 10" identified by No. "1," the learning material used "G," the learning history "H," the learning goal "I," and the conversation history "J," each associated with the other. Note that the above alphabets "G to J" are information indicating a legend for each item of individual user learning information stored in the user learning information DB 122, and the information actually stored is not particularly limited.

[0037] Furthermore, using the user learning information stored in the user learning information DB 122, the support device 100 can display to the user, administrator, etc., in a list format including items such as "chapter," "section," "task," "type," "correct answer rate," and "result," as shown in (1) of Figure 4.

[0038] The above-mentioned "user identification information" refers to information that identifies an individual user who uses a task to learn about an organization, and includes, for example, user-specific identification information such as the name or nickname of the user who belongs to the organization, a telephone number, a membership number for a service, etc. The user learning information DB 122 can store user identification information while protecting personal information by deleting or replacing information that could identify an individual user with obscured characters, etc., based on known technology.

[0039] "Teaching materials used" is information for identifying the assignments used by the user for studying, and includes, for example, information for identifying the "title" of the teaching material information stored in the teaching material information DB 121. "Study history" is historical information on the user's study using the assignments, and includes, for example, information on the study date, study time, and study progress. "Study goals" is information on the study objectives set by the user who studies using educational data and assignments generated based on the educational data, and includes, for example, goals such as "complete study of content XX by XX month XX" or "study XX hours per week." "Conversation history" is historical information (past conversation data) of conversations in natural language between the user who is studying and the assistance device 100.

[0040] (Generated model DB123) The generative model DB 123 is a database that stores predetermined generative models used for generating learning support information by the generation unit 134 (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, as the large-scale language model, "ChatGPT (registered trademark)," which is a large-scale language model having general-purpose knowledge (see, for example, Reference 1).

[0041] (Reference 1):ChatGPT(OpenAI),<URL:https: / / openai.com / chatgpt> ,<Searched on September 3, 2020>

[0042] (control unit 130) Here, the explanation will be continued by returning to Fig. 2. The control unit 130 is realized by a processor, an MPU (Micro Processing Unit), a CPU (Central Processing Unit), or the like executing various programs stored in the storage unit 120 using the RAM as a working area.

[0043] The control unit 130 is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array), and as shown in FIG. 2, the control unit 130 includes a receiving unit 131, a storage unit 132, a processing unit 133, a generating unit 134, and an output unit 135.

[0044] (Reception Department 131) The receiving unit 131 receives information such as conversations related to teaching or coaching, answers to practice questions, questions, etc., input by the user in a chat format, etc. The receiving unit 131 also receives information used by the processing unit 133, which will be described later, to generate (process) practice questions.

[0045] Here, an example of a reception screen for information used to generate practice questions and answers to the generated practice questions by the reception unit 131 will be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of a reception screen according to the embodiment.

[0046] As shown in Fig. 5, the receiving unit 131 receives conditions for generating practice questions from an administrator or the like via a screen for receiving conditions for generating practice questions shown in (1) of Fig. 5. For example, the receiving unit 131 receives conditions for which content of the teaching materials, such as "teaching material," "chapter," or "section," practice questions are to be generated for ((1-1) of Fig. 5). The receiving unit 131 can also display a preview screen of the content identified based on the conditions shown in (1-1) of Fig. 5 ((1-2) of Fig. 5). Furthermore, the receiving unit 131 receives conditions such as "number of options," "number of questions to be created," etc. ((1-3) of Fig. 5).

[0047] The receiving unit 131 can then receive answers from the user to the practice questions posed via the practice question screen shown in (2) of Fig. 5. Note that the receiving unit 131 can also receive answers to the practice questions in a chat format, in addition to the practice question screen ((2) of Fig. 5).

[0048] (storage section 132) The storage unit 132 stores, for each organization, training data used for training users belonging to the organization in the memory unit 120 (teaching material information DB 121). Specifically, the storage unit 132 stores the training data input by an educator or the like belonging to the organization in the teaching material information DB 121 in association with information identifying the organization (for example, the "organization identification information" shown in FIG. 3).

[0049] An example of a data reception screen for storing educational data will now be described with reference to FIG. 6. FIG. 6 is a diagram showing an example of an educational data reception screen according to an embodiment. FIG. 6 shows a registration screen ((1) in FIG. 6) that is used by an educational officer in an organization when registering educational data for that organization. The screen shown in (1) in FIG. 6 shows a "title ((1-1) in FIG. 6)," a "document registration screen ((1-2) in FIG. 6)," and a "video registration screen ((1-3) in FIG. 6)."

[0050] In the "Title" field shown in (1-1) of Fig. 6, information for identifying the educational data, such as the name of the educational data, is entered. Also, the document registration screen shown in (1-2) of Fig. 6 displays items for selecting the file format of the document data to be registered and the file to be registered, as well as a preview of the document to be registered. Also, the video registration screen shown in (1-3) of Fig. 6 displays items for selecting the file format of the video data to be registered and the file to be registered, a preview of the document to be registered, and an option for prohibiting video advancement.

[0051] (Processing section 133) Continuing the explanation by returning to Fig. 2, the processing unit 133 processes the educational data stored for each organization in the storage unit 120 (teaching material information DB 121) into tasks to be used by the user for learning about the organization.

[0052] Specifically, the processing unit 133 generates learning videos and practice questions based on constraints on the format of the tasks. Here, the constraints on the format of the tasks include the type of task, such as "video" or "practice questions."

[0053] For example, if the type of assignment is a "video for practice," the processing unit 133 generates a video file using text and graphics included in the educational data. For example, the processing unit 133 extracts text data included in the educational data. Next, the processing unit 133 generates audio data in which the extracted text data is read aloud. Then, the processing unit 133 generates a video file using the extracted text data and the generated audio data.

[0054] On the other hand, if the assignment type is "practice problem," the processing unit 133 uses text and graphics contained in the training data to generate practice problems that satisfy the above constraints based on a large-scale language model. Here, constraints on the format of the assignment include the number of practice problems, options, difficulty level, constraints on problem generation such as "not generating the same problem," and character limit. For example, the generation of practice problems by the processing unit 133 will be described below with an example.

[0055] (Generation unit 134) The generation unit 134 inputs information about the learning of users who are education targets in the organization into the large-scale language model, and generates learning support information according to the user's learning situation. Specifically, the generation unit 134 inputs user learning information including at least one of the user's learning history, the user's learning goals, and past conversation data into the large-scale language model, and generates learning support information for the user.

[0056] As examples of the above-mentioned learning support information, the generation unit 134 generates messages to support the user in learning (hereinafter referred to as "learning support messages"), answers to questions, assignments to be given to the user, and information to follow up on the answers to the assignments, etc. The generation process by the generation unit 134 will be explained in the following sections using specific examples of prompts.

[0057] (output unit 135) The output unit 135 outputs to the user the assignments processed by the processing unit 133 and the learning support information generated by the generation unit 134. For example, the output unit 135 outputs the above-mentioned assignments and learning support information to the user in a chat format. The output process by the output unit 135 will be described in the following section.

[0058] (An example of the overall process flow) Hereinafter, an example of generation and output of learning support information by the support device 100 will be described. First, a flow of generation and output of assignments and learning support information by the support device 100 will be described with reference to Fig. 7. Fig. 7 is a diagram showing a series of flows of generation processing and output processing according to the embodiment.

[0059] The support device 100 (processing unit) performs processing ((1-1) in FIG. 7) using the educational data for each organization stored in the educational material information DB 121. Then, the support device 100 (processing unit) generates tasks such as educational videos and exercise questions ((1-2) in FIG. 7).

[0060] The support device 100 (output unit) outputs the generated assignment to the user. The user then studies using the assignment, such as an educational video or practice questions, output by the support device 100.

[0061] The terminal device 200 transmits input information about learning, such as "watching videos and practicing problems (working on assignments)" and "requests for coaching consultation," received from a user who is studying using assignments processed from educational data, to the support device 100 ((2) in Figure 7).

[0062] The assistance device 100 performs a process of generating learning support information for a user in response to input information related to learning received from the terminal device 200. First, the assistance device 100 (generation unit) generates a prompt including an instruction to assign a predetermined role to a large-scale language model, an instruction to input the user's learning information, and an instruction to generate learning support information for the user ((3-1) in FIG. 7). Next, the assistance device 100 (generation unit) inputs the generated prompt to the large-scale language model ((3-2) in FIG. 7). Then, the assistance device 100 (generation unit) generates learning support information for the user based on the generated prompt.

[0063] Specifically, the assistance device 100 (generation unit) inputs a prompt into the large-scale language model and sets a predetermined role such as "AI instructor who supports the user." In addition, the assistance device 100 (generation unit) causes the large-scale language model to acquire user learning information from the user learning information DB 122 ((4-1) in FIG. 7).

[0064] Then, the support device 100 (generation unit) uses the acquired user learning information to cause the large-scale language model to generate learning support information ((4-2) in FIG. 7). For example, the support device 100 (generation unit) causes the large-scale language model to generate a "learning support message ((4-3) in FIG. 7)" or an "answer to a question ((4-4) in FIG. 7)" as learning support information related to coaching. In addition, the support device 100 (generation unit) causes the large-scale language model to generate "scoring and follow-up of answers ((4-5) in FIG. 7)" as learning support information related to teaching.

[0065] The support device 100 (output unit) outputs the generated learning support information to the terminal device 200 ((5) in FIG. 7). As a result, the terminal device 200 can display information related to "assignment and explanation information," "learning support messages," "answers to questions from users," etc. as learning support information to the user ((6) in FIG. 7).

[0066] Next, an example of the generation process and output process of learning support information by the support device 100 will be described with reference to FIGS. 8 to 14, taking more specific prompts and output screens as examples.

[0067] (First example: generating and outputting assignment and explanation information) First, an example will be described in which the support device 100 processes educational data to generate an "assignment (practice problem)" as learning support information and outputs the assignment to the user. In the first example, the support device 100 generates an assignment according to the learning situation of a user belonging to an organization using educational data for each organization and outputs the assignment to the user.

[0068] Furthermore, the support device 100 generates a grading result and commentary information based on the grading result for the user's answer to the given task, and outputs the result to the user. Note that the "commentary information" here includes information such as whether the user's answer is correct or incorrect, a detailed explanation of the content of the correct answer, and transition information to educational data related to the correct answer.

[0069] In specific processing, the support device 100 (processing unit) inputs commands to process the educational data of the organization into tasks based on constraints regarding the format of the tasks, such as learning videos and practice problems, into a large-scale language model, and processes the educational data of the organization stored in the memory unit 120 for each organization into tasks.

[0070] Furthermore, the support device 100 (receiving unit) receives an answer to the assignment from the user. The support device 100 (generating unit) inputs the received answer and a command to generate a marking result and commentary information for the answer into a large-scale language model, and generates the marking result and commentary information as learning support information.

[0071] Here, examples of input prompts and output examples in the processing according to the first example will be described. Fig. 8 is a diagram showing an example of a prompt according to the first example. Fig. 8 shows an example of a plurality of prompts ((1) and (2) in Fig. 8) for processing assignments (practice questions) into a large-scale language model using educational data for each organization, an assignment that is processed and output based on the prompts, and an example of the assignment's grading results and explanation information ((3) in Fig. 8).

[0072] The first prompt shown in (1) of Figure 8 includes "#Background information ((1-1) of Figure 8)", "#Instructions ((1-2) of Figure 8)", and "#Constraints ((1-3) of Figure 8)".

[0073] By using the command shown in (1-1) of Figure 8, the support device 100 (processing unit) can assign the large-scale language model the role of "being an AI instructor who issues tasks to users who are learning about educational data" and "processing educational data into practice questions (#command)."

[0074] The "# command" is a command to make the large-scale language model execute a predetermined process. For example, the command shown in (1-2) of Fig. 8 allows the assistance device 100 (processing unit) to make the large-scale language model execute a process such as "processing the training data into a predetermined format question such as a multiple-choice question while strictly following the set constraint conditions."

[0075] "#Constraints" is a command for specifying (limiting) the execution method of processing by a large-scale language model. For example, by the command shown in (1-3) of Fig. 8, the support device 100 (processing unit) can impose constraints on the large-scale language model, such as "limiting the number of questions," "limiting answer choices," "asking different questions," and "limiting the number of characters," when processing training data into practice questions.

[0076] Also, the second prompt shown in (2) of Fig. 8 includes a "# command." For example, the command shown in (2-1) of Fig. 8 allows the assistance device 100 (processing unit) to cause the large-scale language model to execute operations such as "generating a message summarizing the learning topic and asking whether there are any questions about the learning topic for the first time," and "generating a message based on the message entered by the user and the message generated immediately before that for the second time and thereafter."

[0077] The support device 100 (output unit) then outputs the assignment generated based on the prompts shown in (1) and (2) of Fig. 8 as shown in (3) of Fig. 8. For example, the support device 100 (output unit) outputs text such as "...(Summary of the learning theme)...Now, let's try solving the following problem" or "Question: What is the role of XX?...(omitted)...Which do you think is the correct answer?" as a message to be displayed when the assignment is issued ((3-1) of Fig. 8).

[0078] Here, the "example of output in chat format" explained in Fig. 8 will be explained using Fig. 9. Fig. 9 is a diagram showing an example of output in chat format of learning support information according to the first example. Fig. 9 shows a chat format screen for outputting, in natural language, practice questions generated by a large-scale language model, the results of scoring the answers to the practice questions, explanatory information, etc.

[0079] For example, the support device 100 (output unit) can display a message regarding a task generated by a large-scale language model to the user as shown in (1) of Fig. 9. Also, the support device 100 (receiving unit) can receive answers and the like input by the user ((2) of Fig. 9).

[0080] Here, the support device 100 (generation unit) inputs a prompt including an instruction such as "After receiving the answer from the user, please grade and explain the answer. After grading and explaining the answer, please pose a new multiple-choice question" into the large-scale language model in the "#command", and generates scoring results and explanation information based on the large-scale language model in accordance with the accepted answers, etc.

[0081] The support device 100 (output unit) can display to the user the scoring results and explanation information generated according to the accepted answers, etc. ((3) in FIG. 9). Furthermore, the support device 100 (output unit) can present the next question, which is generated by adjusting the difficulty level according to the user's answer ((3) in FIG. 9).

[0082] 9(4) and (5), the support device 100 can receive answers from the user and output scoring results and explanation information generated in accordance with the received answers. Furthermore, the support device 100 supports the user in effectively practicing problems and checking explanations by repeatedly executing the above processes.

[0083] (Second example: generating and outputting learning support messages) Next, an example will be described in which the assistance device 100 generates a "learning assistance message" as learning assistance information and outputs it to the user. In the second example, the assistance device 100 generates a "learning assistance message" that is a message to support the user in effectively progressing with their learning, depending on the user's learning situation, and outputs it to the user.

[0084] In specific processing, the support device 100 (generation unit) inputs into the large-scale language model an instruction to generate a user's learning support message that includes at least one of words of encouragement for the user depending on the user's learning progress, a summary of the user's learning content, and a message confirming whether the user has any questions, and generates the user's learning support message as learning support information.

[0085] Here, examples of input prompts and output examples in the processing according to the second example will be described with reference to Fig. 10 and Fig. 11. Fig. 10 and Fig. 11 are diagrams showing examples of prompts according to the second example.

[0086] Figure 10 shows an example of a prompt ((1) in Figure 10) for causing a large-scale language model to generate a learning support message according to the user's learning situation, and an example of a learning support message ((2) in Figure 10) that is generated and output based on the prompt. The prompt shown in (1) in Figure 10 includes "#background information ((1-1) in Figure 10)," "#status ((1-2) in Figure 10)," and "#command ((1-3) in Figure 10)."

[0087] "#Background information" is a command for assigning a role desired by an educator or the like to a large-scale language model. For example, by the command shown in (1-1) of Fig. 10, the assistance device 100 (generation unit) can assign the large-scale language model the roles of "being an AI instructor who supports users who are learning," "having the role of increasing the user's motivation for continued learning," and "generating information (#command) according to the user's learning status (#status) described in the prompt."

[0088] "#Status" is information that expresses the user's learning status in natural language and is written based on the information stored in the user learning information DB 122. For example, the information shown in (1-2) of FIG. 10 indicates that "User A" has <1> This means that the

[0089] The "# command" is a command to make the large-scale language model execute a predetermined process. For example, by the command shown in (1-3) of Fig. 10, the assistance device 100 (generation unit) can make the large-scale language model execute the following: "Generate a message to encourage the user to continue studying similar to the previous day according to the user's study status," "Generate a message to encourage the user," "Summarize the content of the previous day's study," "Generate a message to check whether the user has any questions," etc.

[0090] Then, the assistance device 100 (output unit) outputs the learning assistance message generated based on the prompt shown in FIG. 10(1), as shown in FIG. 10(2).

[0091] Next, an example of generating a study plan in accordance with a user's study situation in a large-scale language model will be described with reference to Fig. 11. Fig. 11 shows an example of a prompt ((1) in Fig. 11) for causing a large-scale language model to generate a study plan in accordance with a user's study situation, and an example of a study plan generated and output based on the prompt ((2) in Fig. 11).

[0092] The prompt shown in (1) of Figure 11 includes "#background information," "#command ((1-1) of Figure 11)," "#constraint ((1-2) of Figure 11)," "#functions usable for learning ((1-3) of Figure 11)," "#individual assignment data ((1-4) of Figure 11)," and "#learning progress data ((1-5) of Figure 11)." Note that the "#background information" is processed in the same way as in Figure 10 based on the command described in Figure 11, so its explanation will be omitted.

[0093] The "# command" is a command to make the large-scale language model execute a predetermined process, similar to the example in Fig. 10. For example, the command shown in (1-1) in Fig. 11 allows the assistance device 100 (generation unit) to make the large-scale language model execute an operation such as "comparing the user's personal task data with the learning progress data in strict accordance with the set constraints, and generating advice for the user's learning progress."

[0094] "#Constraint" is a command for specifying (restricting) the method of executing processing by a large-scale language model. For example, by the command shown in (1-2) of Fig. 11, the assistance device 100 (generation unit) can impose constraints on the large-scale language model when generating a study plan, such as "generating a study plan using only functions that can be used for study," "limiting the number of characters," "modifying the study schedule," and "generating sentences to communicate the study plan to the user."

[0095] "#Functions usable for learning" is information indicating learning-related functions that can be used by a user when studying using the services realized by the assistance device 100, and is used as a constraint condition when the large-scale language model generates a study plan. For example, as shown in (1-3) of FIG. 11, "#Functions usable for learning" includes information identifying various functions used for learning, such as "document data viewing function / video viewing function," "problem practice function," "question function," "personal coaching function," and "remote lab function."

[0096] "#PersonalAssignmentData" includes information related to the user's learning goals. The information included in "#PersonalAssignmentData" may be user learning information stored in the user learning information DB 122. For example, as shown in (1-4) of FIG. 11, "#PersonalAssignmentData" includes information such as "study start date," "study completion deadline," "study goals using document data (document data goals), study goals using videos (video goals), and study goals using questions (question goals)."

[0097] "#StudyProgressData" includes information related to the user's learning progress. The information included in "#StudyProgressData" may be user learning information stored in the user learning information DB 122. For example, as shown in (1-5) of FIG. 11, "#StudyProgressData" includes information such as "current date," "study progress using document data (document data progress), study progress using videos (video progress), and study progress using questions (question progress)."

[0098] The support device 100 (output unit) then outputs a learning support message generated based on the prompt shown in (1) of Fig. 11, as shown in (2) of Fig. 11. For example, the message shown in (2) of Fig. 11 includes a message to the user ((2-2) of Fig. 11), such as "current situation analysis," "necessary actions," "short-term goals," "suggested support functions," and "suggested schedule review" ((2-1) of Fig. 11), based on a comparison between "#individual assignment data" and "#learning progress data."

[0099] For example, "Current situation analysis" includes messages such as "As of ____ / ____ / __, there are ____ months left until the deadline. Progress in learning using document data is ____%, progress in learning using videos is ____%, and progress in learning using questions is ____". "Necessary actions" includes messages such as "____% remains until the target progress. You need to advance ____% every day. A recommended method is to make full use of the document data viewing function and set a goal of reading at least ____ chapters every day".

[0100] "Short-term goals" include things like "Advance learning progress using document data to XX%, "Advance learning progress using videos to XX%, "Advance learning progress using quizzes to XX%, etc." "Support function suggestions" include things like, "If there's anything you don't understand, use the question function to clarify it. Furthermore, if you face individual challenges, it's a good idea to consider using the in-person coaching function to receive direct advice." "Schedule review suggestions" include things like, "Considering the current pace and estimated pace of progress, it's likely that it will be difficult to meet the deadline, especially with regard to the document data portion. Therefore, please consider postponing the deadline to XX month."

[0101] In addition, the message to the user ((2-2) in Figure 11) includes, for example, "Please proceed with your daily studies according to this plan, regularly evaluate your progress, and make adjustments as necessary."

[0102] Here, the "example of output in chat format" explained in Fig. 10 and Fig. 11 will be explained using Fig. 12. Fig. 12 is a diagram showing an example of output in chat format of learning support information according to the second example.

[0103] 12 shows a chat-style screen for outputting a learning support message, a learning plan, etc., generated by a large-scale language model. For example, the support device 100 (output unit) can display to the user a learning support message or a learning plan generated by a large-scale language model, as shown in (1) of FIG.

[0104] The support device 100 (reception unit) can also receive replies, questions, etc. to the learning support message and learning plan input by the user ((2) in FIG. 12). The support device 100 (generation unit) can then generate further learning support messages and learning plans in response to the received replies, questions, etc.

[0105] (Third example: Answering a user's question) Next, an example will be described in which the assistance device 100 generates an "answer to a question from a user" as learning assistance information and outputs it to the user. In a third example, the assistance device 100 generates an answer to a question in accordance with the user's learning situation and the question from the user, and outputs it to the user.

[0106] Specifically, the support device 100 (reception unit) receives a question input from a user in a chat format. The support device 100 (generation unit) inputs the received question and a command to generate an answer to the question into a large-scale language model, and generates the answer to the question as learning support information.

[0107] Here, examples of input prompts and output examples in the processing according to the third example will be described with reference to Fig. 13. Fig. 13 is a diagram showing an example of a prompt according to the third example. Fig. 13 shows an example of a plurality of prompts ((1) and (2) in Fig. 13) for causing a large-scale language model to generate answers according to the user's learning status and questions from the user, and an example of an answer ((3) in Fig. 13) generated and output based on the prompts.

[0108] The first prompt shown in (1) of Figure 13 includes "#background information," "#command ((1-1) of Figure 13)," and "#constraint ((1-2) of Figure 13)." Note that the "#background information" is processed in the same way as in Figure 8 based on the command shown in Figure 13, so its explanation is omitted here.

[0109] The "# command" is a command to make the large-scale language model execute a predetermined process, similar to the example in Fig. 8. For example, the command shown in (1-1) in Fig. 13 allows the assistance device 100 (generation unit) to make the large-scale language model execute an operation such as "when a user asks a question about a predetermined content (teaching material / theme), generate an answer to the question in strict accordance with the set constraints."

[0110] "#Constraints" is a command for specifying (restricting) the execution method of processing by a large-scale language model, as in the example of Fig. 8. For example, by the command shown in (1-2) of Fig. 13, the assistance device 100 (generation unit) can impose constraints on the large-scale language model when generating an answer, such as "limiting the number of characters" and "suggesting another learning function if the answer is not possible."

[0111] Furthermore, the second prompt shown in (2) of Fig. 13 includes a "# command ((2-1) of Fig. 13)." For example, the command shown in (2-1) of Fig. 13 allows the assistance device 100 (generation unit) to cause the large-scale language model to execute operations such as "generating, for the first time, a message summarizing the learning topic and asking whether there are any questions about the learning topic," and "generating, from the second time onwards, a message based on the message input by the user and the message generated immediately before."

[0112] Then, the support device 100 (output unit) outputs the initial message generated based on the prompts shown in (1) and (2) of Fig. 13 and the answer to the user's question as shown in (3) of Fig. 13. For example, the support device 100 (output unit) outputs text such as "...(Summary of the learning topic)...Do you have any questions? ((3-1) of Fig. 13)" as the initial message.

[0113] Next, the user inputs a question such as "I completely forgot about XX. Can you explain it to me? ((3-2) in Fig. 13)" to (3-1) in Fig. 13. Then, the support device 100 (output unit) outputs a message such as "...(detailed answer)...((3-3) in Fig. 13)" in response to the question input by the user.

[0114] Here, the "example of chat-style output" explained in Fig. 13 will be explained using Fig. 14. Fig. 14 is a diagram showing an example of chat-style output of learning support information according to the third example. Fig. 14 shows a chat-style screen for outputting an initial message generated by a large-scale language model, answers to questions, etc.

[0115] For example, the assistance device 100 (output unit) can display to the user an initial message generated by a large-scale language model as shown in (1) of FIG. 14. Furthermore, the assistance device 100 (reception unit) can receive a question or the like input by the user ((2) of FIG. 14). Then, the assistance device 100 (generation unit) can display to the user an answer generated in response to the received question or the like ((3) of FIG. 14). This allows the assistance device 100 to output an answer in an interactive format to a question from the user.

[0116] (Processing procedure of the support device 100) Next, a description will be given of a series of processing procedures realized by the support device 100 according to the first embodiment. Fig. 15 is a flowchart of the processing of the support device 100 according to the embodiment.

[0117] The storage unit 132 stores the educational data for each organization input by the educational staff of the organization or the like in the educational material information DB 121 (S101). Here, if the support device 100 does not process the educational data into an assignment (No in S102), the support device 100 waits for processing.

[0118] On the other hand, if the training data is to be processed into an assignment (Yes in S102), the processing unit 133 processes the training data into an assignment (S103). Next, the output unit 135 outputs the assignment processed by the processing unit 133 to the user (S104).

[0119] Next, if learning support is to be provided to a user who is studying about an organization (Yes in S105), educational support information is generated in accordance with the user's input (S106). Next, the output unit 135 outputs the educational support information (S107). On the other hand, if learning support is not to be provided to the user (No in S105), the support device 100 ends the process.

[0120] Here, if the processing termination condition is not satisfied (No in S108), the support device 100 returns to the previous step and continues the processing. On the other hand, if the processing termination condition is satisfied (Yes in S108), the support device 100 terminates the processing. Note that the processing termination condition here is a condition that can be set arbitrarily, and includes, for example, an input from a user, the passage of a predetermined time, the arrival of a set schedule, an instruction from an administrator, etc.

[0121] (effect) Hereinafter, a description will be given of the effects achieved by the support device 100 according to this embodiment. Conventionally, it has been impossible to process educational data managed by each organization to generate assignments to be used in user education, and it has sometimes been difficult to appropriately support user education.

[0122] Therefore, the storage unit 132 of the support device 100 according to this embodiment stores, for each organization, training data used for training users belonging to the organization in the memory unit 120. The processing unit 133 of the support device 100 processes the training data stored in the memory unit 120 for each organization into assignments to be used by users for learning about the organization. The output unit 135 of the support device 100 outputs the processed assignments to the user.

[0123] Therefore, the assistance device 100 has the effect of enabling appropriate learning assistance according to the user's learning situation. Furthermore, the assistance device 100 achieves predetermined effects by executing the processes described below.

[0124] The processing unit 133 inputs a command to process the training data into a task based on constraints related to the format of the task into the large-scale language model, and processes the training data stored in the storage unit 120 for each organization into a task.

[0125] Through the above-described processing, the assistance device 100 can generate appropriate educational videos and practice questions corresponding to the educational data for each organization and provide them to the user. As a result, the user can appropriately perform self-study on education related to the organization based on the educational videos and practice questions corresponding to the educational data for each organization provided by the assistance device 100. Therefore, the assistance device 100 has the effect of enabling the user to self-study more efficiently and effectively than before.

[0126] The generation unit 134 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, and generates learning support information according to the user's learning situation using tasks.

[0127] By the above-described processing, for example, the assistance device 100 can provide teaching, coaching, and answers to questions to the user according to the user's learning situation and learning goals. As a result, the user can receive educational support from the assistance device 100 according to his / her learning situation, and can more appropriately resolve problems and deepen understanding of the learning content than before. Therefore, the assistance device 100 has the effect of being able to support the user to progress in learning efficiently / effectively.

[0128] The receiving unit 131 receives answers to exercises such as practice questions from a user. The generating unit 134 inputs the received answers and a command to generate a marking result and commentary information for the answers into a large-scale language model, and generates the marking result and commentary information as learning support information.

[0129] Through the above-described processing, the support device 100 can provide a scoring result such as correct or incorrect for the user's answer to the practice questions generated by the support device 100. In addition, the support device 100 can provide a chapter or section of the educational data related to the user's answer or the scoring result, or an individual description, or commentary information such as other commentary videos, in association with the user's answer.

[0130] As a result, the user can carry out appropriate self-study, such as reviewing the results of his / her own practice problems and reviewing content that he / she has a low level of understanding, based on the scoring results and explanation information provided by the support device 100. Therefore, the support device 100 has the effect of enabling the user to carry out self-study more efficiently / effectively than before.

[0131] The generation unit 134 inputs into the large-scale language model an instruction to generate a user learning support message that includes at least one of words of encouragement for the user depending on the user's learning progress, a summary of the user's learning content, and a message confirming whether the user has any questions, and generates the user's learning support message as learning support information.

[0132] Through the above-described processing, for example, when the user's learning progress is behind, the assistance device 100 can display words of encouragement (words of support) to the user, such as "You're behind in your studies. Is there something wrong? It's tough, but let's do our best!". Furthermore, the assistance device 100 can display a "summary of what you've learned up to the last time" to the user to support the user's learning, and then display a message such as "Do you have any questions about what you've learned up to the last time?" to resolve any points the user is unsure of and deepen the user's understanding of the learning content. As a result, the assistance device 100 has the effect of being able to support the user in efficiently / effectively progressing in their learning, according to the user's learning.

[0133] The receiving unit 131 receives a question input from a user in a chat format. The generating unit 134 inputs the received question and a command to generate an answer to the question into a large-scale language model, and generates the answer to the question as learning support information.

[0134] By the above-described process, when a user asks a question such as "What is XX?", the assistance device 100 can display an explanation about "XX" to the user as a response to the question. As a result, the user can appropriately carry out self-study based on the response to the user's question returned from the assistance device 100. Therefore, the assistance device 100 has the effect of enabling the user to self-study more efficiently and effectively than before.

[0135] The output unit 135 outputs the generated learning support information to the user in a chat format. Through the above-described processing, the support device 100 realizes natural conversational exchanges using natural language for coaching and teaching the user, accepting and answering questions from the user, etc. As a result, the support device 100 has the effect of providing an environment in which the user can easily ask the support device 100 for advice or ask questions in a natural manner.

[0136] <Modification> Below, modifications realized by the assistance device 100 according to this embodiment will be described.

[0137] (Another form of assignment generation and grading) The above-described assistance device 100 processes training data based on a large-scale language model to generate assignments and to grade the assignments, but the present invention is not limited to this.

[0138] For example, the support device 100 presents a task input by an administrator or the like to the user. Next, the support device 100 receives an answer to the task from the user. Then, the support device 100 compares the received answer with a correct answer registered in advance and performs scoring.

[0139] By the above process, the support device 100 can present the user with questions that the educator or the like desires to present, instead of practice questions processed from educational data, for example. As a result, the support device 100 can present the user with practice questions that are focused on learning subjects that the educator or the like considers particularly important.

[0140] (Data, etc.) The educational data, assignments, coaching, teaching, learning support messages, etc. for each organization, as well as the names of the functional parts, steps, processes, names of steps or processes, etc. of the support device 100 used in the description of the above embodiment are merely examples and can be changed as desired.

[0141] For example, it has been explained that the learning material information DB121 stores items such as "organization identification information," "title," "link," "order," "number of contents," "assignment," and "type" and information related to these items in a table format or the like, in association with "No.", which is information identifying individual learning material information, but the items, content, storage format, etc. to be stored are not limited. It has been explained that the user learning information DB122 stores items such as "user identification information," "teaching material used," "learning history," "learning goal," and "conversation history" and information related to these items in a table format or the like, in association with "No.", which is information identifying individual user learning information, but the items, content, storage format, etc. to be stored are not limited.

[0142] (About the use of generative models) In the present embodiment, the model (large-scale language model) used by the assistance device 100 is described as being stored in the generative model DB 123 of the storage unit 120, but the present invention is not limited to this. For example, the assistance device 100 can access an external information processing device (such as a server) and use a predetermined model.

[0143] (Flowcharts, etc.) The steps in the flowcharts may be interchanged as long as there is no contradiction, and some steps may not be performed. In addition, conjunctions such as "next," "continue," "further," "at this time," and "on this occasion" used in the explanation of the flowcharts do not limit the order or timing of the execution of the processes in the flowcharts.

[0144] (Systems, etc.) Of the processes described in the above embodiments and variations, 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 using known methods. In addition, the information, including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings, can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown.

[0145] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0146] The above-described components include those that can be easily imagined by a person skilled in the art, those that are substantially the same, and those that fall within the so-called equivalent range. Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0147] Furthermore, the aforementioned "section, module, unit" can be read as "means" or "circuit," etc. For example, a control section can be read as control means or a control circuit.

[0148] Although some of the embodiments have been described in detail above with reference to the drawings, these are merely examples, and it is possible to implement the present embodiments in other forms that have undergone various modifications and improvements based on the knowledge of those skilled in the art, including the aspects described in the Disclosure of the Invention section.

[0149] <Hardware configuration> The devices included in the support device 100 according to this embodiment are realized, for example, by a computer 1000 configured as shown in Fig. 16. Fig. 16 is a diagram showing an example of the hardware configuration of a computer that realizes the support device 100 according to the embodiment.

[0150] The computer 1000 has a configuration in which a CPU 1100 , a memory 1200 , an auxiliary storage device 1300 , an input interface 1400 , an output interface 1500 , and a communication interface 1600 are connected by a bus 1700 .

[0151] The CPU 1100 operates and controls each functional unit based on a program stored in the memory 1200 or the auxiliary storage device 1300. The memory 1200 is configured, for example, with RAM (Random Access Memory) or ROM (Read Only Memory), and stores a boot program executed by the CPU 1100 when the computer 1000 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0152] For example, when the computer 1000 functions as the assistance device 100 according to this embodiment, the CPU 1100 of the computer 1000 executes a program loaded onto the memory 1200, thereby realizing the functions of the control unit .

[0153] The auxiliary storage device 1300 stores programs executed by the CPU 1100, data used by the programs, etc. The CPU 1100 controls an input device 1410 such as a keyboard or mouse via an input interface 1400. The CPU 1100 also acquires data from the input device 1410 via the input interface 1400.

[0154] The CPU 1100 controls an output device 1510 such as a display or a printer via an output interface 1500. The CPU 1100 also outputs generated data and the like to the output device 1510 via the output interface 1500.

[0155] The communication interface 1600 receives data from other devices via a predetermined network NW and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the predetermined network NW. [Explanation of symbols]

[0156] 100 Support equipment 110 Communications Department 120 Storage section 121 Teaching material information DB 122 User Learning Information DB 123 Generative Model DB 130 Control Unit 131 Reception 132 Storage area 133 Processing Department 134 Generation part 135 Output section

Claims

1. a processing unit that processes data related to organizational education, which is data used for educating users belonging to an organization and stored in a storage unit for each organization, into exercises for the users to use in their learning about the organization based on a large-scale language model, or processes data related to organizational education into educational videos to be used in their learning about the organization based on text data included in the data related to organizational education, according to the learning status of the users belonging to the organization; an output unit that outputs the modified practice questions or the modified educational videos to the user; The processing unit is When processing the data related to the education of the organization into the practice questions, a command to process the data related to the education of the organization into the practice questions is input to a large-scale language model based on constraints on the format of the practice questions, the constraint including at least one of a limit on the number of questions, a limit on answer options, a constraint on presenting different questions, and a limit on the number of characters, and the data related to the education of the organization stored in the storage unit for each organization is processed into the practice questions; When processing data related to the organization's education into the educational video, Extract text data contained in the educational data, generating voice data by reading out the extracted text data; generating a video file using the extracted text data and the generated audio data; 1. A support device comprising:

2. a generation unit that inputs information about the user's learning, including at least one of the user's learning history, the user's learning goal, and past conversation data, into a large-scale language model, and generates information to support the user's learning according to the user's learning situation using the practice questions or the educational videos; 2. The support device according to claim 1.

3. a receiving unit that receives answers to the practice questions from the user; The generation unit inputting the accepted answer and a command to generate a score and commentary information for the answer into the large-scale language model, and generating the score and commentary information as information to support the user's learning; 3. The support device according to claim 2.

4. The generation unit inputting into the large-scale language model a command to generate a message to support the user's learning, the message including at least one of words of encouragement to the user according to the user's learning progress, a summary of the learning content by the user, and a message to confirm whether the user has any questions, and thereby generating the message to support the user's learning as information to support the user's learning; 3. The support device according to claim 2.

5. a reception unit that receives input of questions about the practice questions or the educational videos from the user in a chat format; The generation unit inputting the received question and an instruction to generate an answer to the question into the large-scale language model, and generating the answer to the question as information to support the user's learning; 3. The support device according to claim 2.

6. A support method to be executed by a support device, a processing step of processing data related to organizational education, which is data used for educating users belonging to an organization and stored in a storage unit for each organization, into exercises for the users to use in their organization-related learning based on a large-scale language model, or into educational videos to be used in their organization-related learning based on text data included in the data related to organizational education, according to the learning status of the users belonging to the organization; an output step of outputting the modified practice questions or the modified educational video to the user; The processing step includes: When processing the data related to the education of the organization into the practice questions, a command to process the data related to the education of the organization into the practice questions is input to a large-scale language model based on constraints on the format of the practice questions, the constraint including at least one of a limit on the number of questions, a limit on answer options, a constraint on presenting different questions, and a limit on the number of characters, and the data related to the education of the organization stored in the storage unit for each organization is processed into the practice questions; When processing data related to the organization's education into the educational video, Extract text data contained in the educational data, generating voice data by reading out the extracted text data; generating a video file using the extracted text data and the generated audio data; A support method characterized by:

7. a processing step of processing the data on organizational education, which is data used for educating users belonging to the organization and stored in a storage unit for each organization, into exercises to be performed by the users to be used for learning about the organization based on a large-scale language model, or into educational videos to be used for learning about the organization by the users based on text data included in the data on organizational education, according to the learning status of the users belonging to the organization; an output step of outputting the modified practice questions or the modified educational videos to the user, The processing step includes: When processing the data related to the education of the organization into the practice questions, a command to process the data related to the education of the organization into the practice questions is input to a large-scale language model based on constraints on the format of the practice questions, the constraint including at least one of a limit on the number of questions, a limit on answer options, a constraint on presenting different questions, and a limit on the number of characters, and the data related to the education of the organization stored in the storage unit for each organization is processed into the practice questions; When processing data related to the organization's education into the educational video, Extract text data contained in the educational data, generating voice data by reading out the extracted text data; generating a video file using the extracted text data and the generated audio data; Support programs.

Images