Prompt generation device and method

Abstract

A prompt generation device 30 according to the present disclosure comprises: a child information acquisition unit 31 that acquires child information including an inquiry objective of inquiry-based learning performed by a child; a determination unit 32 that determines an inquiry theme for the inquiry-based learning; and a generation unit 33 that generates, on the basis of the inquiry objective and the inquiry theme, a first prompt for instructing a generative AI model 21 to create content for prompting the child to perform the inquiry-based learning.

Description

Prompt generating apparatus and method

[0001] The present disclosure relates to an apparatus and a method.

[0002] Patent Document 1 discloses a voice dialogue device that includes a topic estimation unit configured to generate a topic of interest to a speaker based on a recognized utterance and an identified speaker, and a voice output unit configured to output the topic as voice.

[0003] JP 2016-71050 A

[0004] In the device described in Patent Document 1, when the speaker is a child, the topics provided to the child may be biased toward the content of the child's speech, which may make it difficult for the child to acquire new information and to encourage inquiry-based learning in the child.

[0005] The present disclosure aims to provide an apparatus and method capable of instructing the creation of content suitable for encouraging inquiry-based learning in children.

[0006] An apparatus according to one aspect of the present disclosure includes a child information acquisition unit that acquires child information including an inquiry purpose for inquiry-based learning conducted by the child, a determination unit that determines an inquiry theme for the inquiry-based learning, and a generation unit that generates a first prompt based on the inquiry purpose and the inquiry theme to instruct a generative AI model to create content to encourage the child to engage in inquiry-based learning.

[0007] A method according to another aspect of the present disclosure includes steps of obtaining child information including an inquiry objective for inquiry-based learning to be performed by the child, determining an inquiry theme for the inquiry-based learning, and generating a first prompt based on the inquiry objective and the inquiry theme, the first prompt instructing a generative AI model to create content to encourage the child to engage in inquiry-based learning.

[0008] According to the present disclosure, it is possible to instruct the creation of content suitable for encouraging children to engage in inquiry-based learning.

[0009] FIG. 1 is a schematic configuration diagram of an inquiry-based learning system including a prompt generation device according to an embodiment of the present disclosure. FIG. 2 is a diagram illustrating an example of data stored in a persona database. FIG. 3 is a diagram illustrating an example of data stored in a theme information database. FIG. 4 is a flowchart of a content creation method performed by the inquiry-based learning system shown in FIG. 1. FIG. 5 is a diagram illustrating an example of child information. FIG. 6 is a diagram illustrating an example of a first prompt. FIG. 7 is a diagram illustrating an example of the hardware configuration of a prompt generation device according to an embodiment of the present disclosure.

[0010] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the description of the drawings, the same elements are designated by the same reference numerals, and duplicated descriptions will be omitted.

[0011] An inquiry-based learning system including a prompt generation device according to an embodiment of the present disclosure will be described with reference to Figures 1, 2, and 3. Figure 1 is a schematic configuration diagram of an inquiry-based learning system including a prompt generation device according to an embodiment of the present disclosure. Figure 2 is a diagram showing an example of data stored in a persona database. Figure 3 is a diagram showing an example of data stored in a theme information database.

[0012] The inquiry-based learning system 1 shown in FIG. 1 is a computer system that creates content that encourages inquiry-based learning in children. Inquiry-based learning is learning in which children independently explore the essence of things and seek to ascertain their true nature. The inquiry-based learning system 1 encourages children to engage in proactive, interactive, and deep learning through content generated by a generative AI model 21 (described below). This allows children to acquire new knowledge. Hereinafter, "content that encourages inquiry-based learning in children" may be simply referred to as "content." The inquiry-based learning system 1 includes a user terminal 10, a generative AI server 20, and a prompt generation device 30. The generative AI server 20 includes the generative AI model 21 and is a device that creates and provides content using the generative AI model 21. The prompt generation device 30 is configured to be able to communicate with each of the user terminal 10 and the generative AI server 20 via any communication network.

[0013] The user terminal 10 is a device used by a child who is engaged in inquiry-based learning using the inquiry-based learning system 1. The user terminal 10 is, for example, a personal computer, a smartphone, a tablet terminal, a feature phone, a server device, or a game device.

[0014] The generative AI model 21 is a model that can generate content in response to a prompt input including input information output by the prompt generation device 30, according to any one or a combination of instructions, context, questions, and output formats indicated by the prompt, and return the content as response information. A prompt is information indicating instructions or questions input to the generative AI model 21 in an interactive system such as a dialogue with the generative AI model 21 or a command line interface (CLI). The prompt can include various types of input information (e.g., user responses) in addition to the input information output by the prompt generation device 30. In this case, the generative AI model 21 generates response information targeted at the various types of input information. The type and format of the input information are not particularly limited, and the input information can include, for example, data files with file names including a predetermined extension, such as text data, image data, application-related data, audio data, video data, and still image data. Application-related data is data such as document data, table data, and graph data that can be processed by a default application program.

[0015] The generative AI model 21 may be configured to include, for example, a large-scale language model (LLM) and a user interface (UI) for interacting with the user. The generative AI model 21 may be an interactive AI model capable of text-based or voice-based chat with the user. Examples of such generative AI models 21 include ChatGPT, GPT (registered trademark)-3.5, GPT-4V, and PaLM2. The generative AI model 21 may also be an AI model other than the large-scale language models described above. As shown in FIG. 1, the generative AI model 21 may be located on a generative AI server 20 separate from the prompt generation device 30, or it may be located on the prompt generation device 30. The generative AI model 21 may also be located on the user terminal 10. In this case, the functions of the prompt generation device 30 may also be located on the user terminal 10. In other words, the user terminal 10 itself may function as the prompt generation device 30 of this embodiment.

[0016] The prompt generation device 30 is a device that generates a prompt that instructs the generation AI model 21 to create content. The prompt generation device 30 is, for example, a Retrieval-Augmented Generation (RAG) system. The prompt generation device 30 includes, as functional elements, a child information acquisition unit 31, a determination unit 32, a generation unit 33, a presentation unit 34, an answer acquisition unit 35, a judgment unit 36, a memory unit 37, a persona database 38, and a theme information database 39. Hereinafter, the persona database 38 and the theme information database 39 may be referred to as a persona database (DB) 38 and a theme information DB 39, respectively. In this embodiment, the memory unit 37, the persona DB 38, and the theme information DB 39 are implemented on the prompt generation device 30, but they may also be implemented outside the prompt generation device 30 (e.g., on a network).

[0017] The child information acquisition unit 31 acquires child information. For example, the child information acquisition unit 31 acquires the child information by acquiring various data from the user terminal 10. The child information includes, for example, basic child information about the child, the inquiry purpose of the inquiry-based learning, and the inquiry level of the inquiry-based learning.

[0018] The child's basic information includes at least one item of the child's attribute information, the child's grade information, and the child's preference information. The attribute information includes, for example, at least one item of name, nickname, age, gender, and family composition. The grade information is information about the child's grades at the school or cram school that the child attends. The grade information includes, for example, at least one item of strong subjects and weak subjects. The preference information is information about the child's tastes. The preference information may include at least one item of the child's likes and dislikes, or may include trivia topics in which the child is interested or curious.

[0019] The purpose of inquiry is what a child aims to achieve through inquiry learning. Examples of the purpose of inquiry are discovering a subject that the child is interested in, strengthening a weak subject, strengthening a strong subject, or studying for an exam. Examples of studying for an exam are studying for a kindergarten or elementary school entrance exam.

[0020] The inquiry level is an indicator of the depth or difficulty of inquiry-based learning. Examples of inquiry level categories include beginner, intermediate, and advanced. For example, a child who is using the inquiry-based learning system 1 for the first time corresponds to a "beginner," and a child whose progress in inquiry-based learning using the inquiry-based learning system 1 has reached a predetermined level (e.g., has completed the beginner's content) corresponds to an "intermediate" or "advanced." The inquiry level may also be an indicator of a child's knowledge level (the amount of knowledge the child has).

[0021] The determination unit 32 determines an inquiry theme for inquiry-based learning. The inquiry theme is a subject (material) that a child will study in depth. The inquiry theme is, for example, natural science, society, or language. The inquiry theme may be a more detailed theme. Examples of more detailed themes include animals and space. The determination unit 32 may determine one inquiry theme or multiple inquiry themes.

[0022] The determination unit 32 acquires theme information. The theme information is information for encouraging a child to acquire new knowledge about a certain theme. The theme information includes, for example, at least one of trivia and questions about the theme.

[0023] The generation unit 33 generates a prompt that instructs the generation AI model 21 to create content. The generation unit 33 inputs the prompt to the generation AI model 21 and acquires the content created by the generation AI model 21. The presentation unit 34 presents the created content to the user terminal 10. The answer acquisition unit 35 acquires the child's answer to the content. The determination unit 36 ​​determines whether to change the content of the prompt input to the generation AI model 21 (content creation policy) based on the content and the child's answer. The memory unit 37 stores a plurality of exploration purposes and a plurality of exploration levels that are presented as options to the user terminal 10 in step S1, which will be described later.

[0024] The persona DB 38 stores data records that associate persona basic information about a virtual child with a virtual research theme in which the virtual child is interested. The virtual child is set to represent a typical child who uses the inquiry-based learning system 1. The persona basic information includes items similar to the child basic information described above. Specifically, the persona basic information includes at least one item of attribute information of the virtual child, grade information of the virtual child, and preference information of the virtual child. The virtual research theme is a research theme in which the virtual child is interested.

[0025] As shown in Figure 2, the persona DB 38 includes, for example, a persona image, a name, a nickname, an age, a gender, a family structure, a good subject, a bad subject, a favorite thing, and one or more virtual research themes. The persona image indicates the characteristics of a virtual child. In Figure 2, two virtual research themes, "animals" and "space," are set for a virtual child named "A-kun." Each virtual research theme is associated with the interest level of the virtual child. The higher the interest level, the greater the degree to which the virtual child is interested in the virtual research theme.

[0026] The theme information DB 39 stores data records that associate the purpose of inquiry-based learning, the theme of inquiry-based learning, and theme information related to the theme. As shown in FIG. 3 , the theme information DB 39 includes a trivia table 39A and a question table 39B. The trivia table 39A includes, for example, the purpose of inquiry-based learning, an inquiry level appropriate for the trivia, the theme of the inquiry-based learning, trivia related to the theme, a persona (a type of virtual child), and the virtual child's interest level. The question table 39B includes trivia related to the theme, a question related to the trivia, an inquiry level appropriate for the question, and the difficulty level of the question. The theme information DB 39 (trivia table 39A) associates multiple pairs of the purpose of inquiry-based learning, an inquiry level appropriate for the trivia, the theme of the inquiry-based learning, and trivia related to the theme with a persona and a virtual child's interest level.

[0027] The purpose of the inquiry-based learning is set to, for example, one of the options for the inquiry purpose stored in the memory unit 37. The inquiry level suitable for trivia and the inquiry level suitable for a question are each set to, for example, one of the options for the inquiry level stored in the memory unit 37. The inquiry level suitable for a question may be set to "beginner" if the difficulty level of the question is 0 to 30, to "intermediate" if the difficulty level of the question is 30 to 70, or to "advanced" if the difficulty level of the question is 70 to 100. The interest level of the virtual child is the persona's interest level in trivia. In FIG. 3, the interest level of the virtual child "Jiro" for the trivia that "male lions have manes but female lions do not" is "62."

[0028] 3, one piece of trivia, "Male lions have manes but female lions do not," is associated with two questions, "Do you know why male lions have long manes?" and "Do you know whether males or females have manes?" In other words, in the theme information DB 39, questions are associated with themes via trivia.

[0029] A content creation method performed by the inquiry-based learning system 1 will be described with reference to Fig. 4. Fig. 4 is a flowchart of the content creation method performed by the inquiry-based learning system shown in Fig. 1. The following processing may be started when the prompt generation device 30 (e.g., the child information acquisition unit 31) receives a content creation request from the user terminal 10. The request may include child information.

[0030] First, the child information acquisition unit 31 acquires child information (step S1). The child information acquisition unit 31 acquires the child basic information from, for example, the user terminal 10. A user (e.g., a child or the child's parent) inputs the child basic information into the user terminal 10, and the child information acquisition unit 31 acquires the child basic information. The child information acquisition unit 31 may acquire a child ID that can uniquely identify the child from the user terminal 10, and acquire the child basic information corresponding to the child ID from the storage unit 37. In this case, the storage unit 37 stores the child ID and the child basic information in association with each other.

[0031] The child information acquisition unit 31 acquires multiple exploration goals and multiple exploration levels from the storage unit 37 and presents these as options to the user terminal 10. The user selects an exploration goal and an exploration level on the user terminal 10, and the child information acquisition unit 31 acquires the selected exploration goal and exploration level. The child information acquisition unit 31 may acquire from the user terminal 10 an exploration goal and an exploration level that the user directly inputs to the user terminal 10, without presenting options to the user terminal 10.

[0032] The child information acquisition unit 31 acquires child information including the child basic information, the inquiry purpose, and the inquiry level by integrating the child basic information, the inquiry purpose, and the inquiry level. FIG. 5 is a diagram showing an example of child information. The child information shown in FIG. 5 includes "child's name," "child's age," and "child's gender" as attribute information. The child information includes "child's interests or concerns" as preference information. The child information includes "grades at school, cram school, etc." as grade information.

[0033] Next, the determination unit 32 determines an inquiry theme for the inquiry-based learning (step S2). The determination unit 32 may determine the inquiry theme based on the child information. The determination unit 32 may determine information included in the child basic information as the inquiry theme. Specifically, if "animals" is set as the preference information (e.g., "child's interests or concerns"), the determination unit 32 may determine "animals" as the inquiry theme.

[0034] The determination unit 32 may determine the exploration theme by converting information included in the child basic information based on a predetermined rule. The rule may include a correspondence between certain information and other information. For example, the determination unit 32 may determine "Japanese" as the exploration theme by converting "animals" into "Japanese" based on the rule. In this case, the prompt generation device 30 (e.g., the storage unit 37) may store the rule.

[0035] The determination unit 32 may determine the investigation theme based on both the child's basic information and the investigation purpose. The determination unit 32 may determine, as the investigation theme, information related to the investigation purpose from among the information included in the child's basic information. For example, if "strengthening weak subjects" is set as the investigation purpose and "Japanese" is set as the child's weak subject, the determination unit 32 may determine "Japanese" as the investigation theme.

[0036] The determination unit 32 may compare the persona DB 38 with the child basic information and determine a virtual exploration theme acquired from the persona DB 38 as the exploration theme. When a combination of one or more items included in the child basic information matches a combination of one or more items included in the persona basic information, the determination unit 32 may determine a virtual exploration theme corresponding to the combination in the persona basic information as the exploration theme. For example, because the combination of "child's age" and "child's gender" shown in FIG. 5 matches the combination of "age" and "gender" of "A-kun" shown in FIG. 2, the determination unit 32 may determine two virtual exploration themes, "animals" and "space," associated with "A-kun" as the two exploration themes.

[0037] As described above, the determination unit 32 may determine multiple investigation themes. In this case, the determination unit 32 may determine the child's level of interest in each of the multiple investigation themes. When the virtual child's level of interest is associated with the virtual investigation theme in the persona DB 38, the determination unit 32 may determine the acquired virtual investigation theme as the investigation theme and determine the virtual child's level of interest in the virtual investigation theme as the child's level of interest in the investigation theme. In FIG. 2 , the determination unit 32 determines the level of interest in "animals" to be "62" and the level of interest in "space" to be "43." The determination unit 32 may predict the child's level of interest in the investigation theme by inputting the child's basic information and the investigation theme into a scoring model.

[0038] The determination unit 32 may determine the research theme randomly. The determination unit 32 may determine the research theme as an research theme that is directly input by the user to the user terminal 10.

[0039] Next, the determination unit 32 acquires theme information related to the research theme (step S3). The determination unit 32 may compare the combination of the research purpose and the research theme with the theme information DB 39 to acquire the theme information from the theme information DB 39. If the combination of the research purpose and the research theme matches a combination of purpose and theme included in the theme information DB 39, the determination unit 32 may acquire the theme information corresponding to that combination from the theme information DB 39.

[0040] For example, if the purpose of the exploration is "discovering something that interests children" and the theme of the exploration is "animals," the determination unit 32 acquires two pieces of trivia, "male lions have manes but female lions do not" and "male and female lions have different roles; males protect the pack and females hunt," as shown in Fig. 3. The determination unit 32 may acquire an exploration level appropriate for the acquired piece of trivia from the theme information DB 39.

[0041] The determination unit 32 may acquire the degree of interest in trivia from the theme information DB 39. When a combination of one or more items included in the child basic information matches a combination of one or more items included in the persona basic information stored in the persona DB 38, the determination unit 32 may acquire the degree of interest of a virtual child having the persona basic information as the degree of interest in trivia. For example, when the child basic information matches the persona basic information of the "Jiro type" shown in FIG. 3 , the determination unit 32 acquires "62" as the child's degree of interest in the statement "Male lions have manes but female lions do not." By acquiring the interest degree of a virtual child in this way, it is possible to estimate the child's level of interest even when the child's level of interest using the inquiry-based learning system 1 is unknown.

[0042] The determination unit 32 may further acquire questions related to trivia from the theme information DB 39. In FIG. 3 , if the acquired trivia is "male lions have manes but female lions do not," the determination unit 32 acquires two questions corresponding to the acquired trivia, "do you know why male lions have long manes?" and "do you know whether males or females have manes?" The determination unit 32 may acquire, from the theme information DB 39, an inquiry level and difficulty level appropriate for the question corresponding to the acquired question.

[0043] Next, the generation unit 33 generates a first prompt (step S4). The generation unit 33 generates the first prompt based on at least the research purpose and the research theme. The generation unit 33 may generate the first prompt based on the child's basic information, the research level, and the theme information in addition to the research purpose and the research theme. The generation unit 33 may generate the first prompt in which an interest level is associated with each of a plurality of research themes. The generation unit 33 may generate the first prompt in which at least one of a research level and an interest level appropriate for each of a plurality of trivia facts is associated with each of a plurality of trivia facts. The generation unit 33 may generate the first prompt in which at least one of a research level and a question difficulty appropriate for each of a plurality of questions is associated with each of a plurality of questions. The generation unit 33 may generate the first prompt by adding necessary information to a first prompt template prepared in advance.

[0044] 6 is a diagram showing an example of a first prompt. In FIG. 6, child basic information is entered in area R1 of the first prompt, the exploration level is entered in area R2 of the first prompt, the exploration theme is entered in area R3 of the first prompt, the exploration purpose is entered in area R4 of the first prompt, and thematic information is entered in area R5 of the first prompt. The content entered in advance in the template of the first prompt is, for example, the content entered in areas other than areas R1 to R5.

[0045] As shown in area R5, in addition to the theme information, the generation unit 33 may add a sentence to instruct the generative AI model 21 to provide the theme information to the child. This sentence may be written in advance in the template. While area R5 contains trivia and questions related to the research theme "animals," area R5 may contain trivia and questions related to the research theme "space." As a result, the generation unit 33 generates a first prompt that instructs the generative AI model 21 to create content for providing at least one of trivia and questions to the child.

[0046] Next, the generation unit 33 creates content using the generation AI model 21 (step S5). Specifically, the generation unit 33 creates the content by inputting the first prompt into the generation AI model 21 and acquiring the content created by the generation AI model 21. Then, the presentation unit 34 presents the content to the user terminal 10.

[0047] When the first prompt shown in FIG. 6 is input to the generative AI model 21, the generative AI model 21 creates content including trivia or questions related to the inquiry themes "animals" or "space," for example. When a level of interest is associated with each of a plurality of inquiry themes, as in the first prompt shown in FIG. 6, the generative AI model 21 attempts to provide trivia or questions related to the inquiry theme with the highest level of interest preferentially. When a level of interest is associated with each of a plurality of trivia, the generative AI model 21 attempts to provide trivia with the highest level of interest preferentially. When a level of difficulty of the question (or an inquiry level appropriate for the question) is associated with each of a plurality of questions, the generative AI model 21 attempts to provide questions with a difficulty level appropriate for the child's inquiry level (or an inquiry level appropriate for the question) preferentially.

[0048] Next, the answer acquisition unit 35 acquires the child's answer to the content (step S6). The child inputs an answer to the content into the user terminal 10, and the answer acquisition unit 35 acquires the answer. If trivia is provided to the child, the answer is the child's interest in the trivia. If a question is presented to the child, the answer is the child's answer to the question.

[0049] Next, the determination unit 36 ​​determines whether to change the content (content creation policy) instructed to the generation AI model 21 by the first prompt (step S7). In the following processing, a second prompt is generated to change the content creation policy. Therefore, step S7 can also be considered as processing in which the determination unit 36 ​​determines whether to generate a second prompt.

[0050] In step S7, the determination unit 36 ​​determines whether to generate a second prompt based on the content created in step S5 and the child's answer acquired in step S6. If steps S5 and S6 are performed multiple times, the determination unit 36 ​​determines whether to generate a second prompt based on the content created each time and the answer acquired each time. In other words, the determination unit 36 ​​determines whether to generate a second prompt based on one or more pieces of content and one or more answers stored in the prompt generation device 30 through use of the inquiry-based learning system 1.

[0051] For example, the determination unit 36 ​​determines whether the child's answer satisfies a predetermined condition, and determines to generate a second prompt if the child's answer satisfies the predetermined condition. If the content includes trivia, the predetermined condition may be, for example, that the number of answers indicating that the child is not interested in the content is equal to or greater than a threshold. If the content includes a question, the determination unit 36 ​​may obtain the child's correct answer rate for the question based on one or more answers. In this case, the predetermined condition is that the correct answer rate is less than a threshold (or equal to or greater than a threshold).

[0052] If it is determined in step S7 that the second prompt will not be generated (step S7: No), the generation unit 33 generates content using the generation AI model 21 without changing the content creation policy (step S8). Specifically, the generation unit 33 generates content by inputting the child's answer into the generation AI model 21 and obtaining content created by the generation AI model 21. Then, the presentation unit 34 presents the content on the user terminal 10. Then, steps S6 and S7 are executed again.

[0053] On the other hand, in step S7, if the determination unit 36 ​​determines that a second prompt should be generated (step S7: Yes), it outputs a determination result including a change policy for the instruction content (content creation policy) provided by the first prompt. The change policy includes a method for changing the instruction content based on the child's reaction to the content presented to the child. The change policy may be, for example, "providing trivia or questions related to a different research topic," "lowering (raising) the child's research level," "providing a question with a low (high) research level (difficulty) appropriate for the question," or "providing hints (options) related to the question."

[0054] Next, the generation unit 33 generates a second prompt based on the determination result (step S9). The generation unit 33 may generate the second prompt in which the change policy included in the determination result (or a policy equivalent to the change policy) is described. For example, if the change policy is "provide trivia or a question related to a different research topic," "provide hints (options) related to the question," or "provide a question with a low (high) research level (question difficulty) appropriate for the question," the generation unit 33 generates the second prompt in which the change policy (or a policy equivalent to the change policy) is described. In this way, for example, if an intermediate-level child makes two consecutive mistakes on questions rated 30 to 70, content can be created in which the difficulty level is changed to 0 to 30.

[0055] The generation unit 33 may generate a second prompt to change the item described in the first prompt based on the change policy. For example, if the change policy is to "lower (raise) the child's exploration level," the generation unit 33 may generate a second prompt to change the exploration level described in the first prompt (changing intermediate to advanced or beginner).

[0056] The generation unit 33 may generate a second prompt for adding new theme information to the theme information described in the first prompt based on the change policy. For example, if the change policy is "provide a question with a low (high) inquiry level (question difficulty) appropriate for the question," the generation unit 33 may obtain, from the theme information DB 39, a question with a low (high) inquiry level (question difficulty) appropriate for the question compared to the question described in the first prompt, and generate a second prompt for providing the question to the child. In this case, the determination unit 32 may obtain the question.

[0057] Next, the generation unit 33 creates content using the generation AI model 21 (step S10). Specifically, the generation unit 33 creates the content by inputting the child's answer and the second prompt into the generation AI model 21 and obtaining the content created by the generation AI model 21. The generation unit 33 may input the child's answer and the second prompt into the generation AI model 21 as a single prompt, or may input the child's answer and the second prompt into the generation AI model 21 as separate prompts. Then, the presentation unit 34 presents the content to the user terminal 10. Then, steps S6 and S7 are executed again.

[0058] Although not shown in FIG. 4, the process of the content creation method ends when the prompt generation device 30 receives an end instruction from the user, for example.

[0059] In the prompt generation device 30 and content creation method described above, a first prompt is generated that instructs the generation AI model 21 to create content to encourage children to engage in inquiry-based learning, based on the inquiry purpose and inquiry theme of the child's inquiry-based learning. By inputting the generated first prompt into the generation AI model 21 to create content, it is possible to create content that reflects the inquiry purpose and inquiry theme of the inquiry-based learning. This makes it possible to provide children with new knowledge that is in line with the inquiry purpose and inquiry theme. Therefore, it is possible to instruct the creation of content that is suitable for encouraging children to engage in inquiry-based learning.

[0060] In step S4, the generation unit 33 may generate the first prompt based on the inquiry level in addition to the inquiry purpose and inquiry theme. With this configuration, content can be created by inputting the generated first prompt into the generative AI model 21, thereby creating content that reflects the inquiry level of inquiry-based learning. This makes it possible to provide the child with new knowledge that is in line with their inquiry level.

[0061] In step S2, the determination unit 32 may determine the research theme based on the child information. With this configuration, it is possible to determine an appropriate research theme that will interest the child.

[0062] In step S2, the determination unit 32 may determine the child's level of interest in each of the multiple research themes, and in step S4, the generation unit 33 may generate a first prompt in which the level of interest is associated with each of the multiple research themes. This configuration makes it possible to create content that reflects the child's level of interest. For example, new knowledge can be provided to the child in order of the child's level of interest.

[0063] In step S2, the determination unit 32 may compare the persona DB 38 with the child basic information and determine the virtual investigation theme obtained from the persona DB 38 as the investigation theme. This configuration makes it possible to easily determine an appropriate investigation theme. For example, even if it is difficult to uniquely determine an investigation theme from the child information, the investigation theme can be easily determined by referring to the persona DB 38.

[0064] In step S3, the determination unit 32 may compare the combination of the research purpose and research theme with the theme information DB 39 to obtain theme information from the theme information DB 39. In step S4, the generation unit 33 may generate a first prompt based on the theme information in addition to the research purpose and research theme. This configuration makes it possible to create content that reflects the theme information obtained from the theme information DB 39. This can encourage the child to acquire new knowledge.

[0065] In step S4, the generation unit 33 may generate a first prompt that instructs the generative AI model 21 to create content for providing the child with at least one of trivia and questions. With this configuration, providing the child with at least one of trivia and questions as new knowledge can further encourage the child to engage in inquiry-based learning.

[0066] In step S7, the determination unit 36 ​​determines whether to generate a second prompt based on the content created in step S5 and the child's answer acquired in step S6, and in step S9, the generation unit 33 generates a second prompt based on the determination result of the determination unit 36. This allows the content created by the generation AI model 21 to be changed based on the child's answer. For example, if the content is difficult for a child, the difficulty level of the content can be lowered to make it more likely to attract the child's interest.

[0067] Although one embodiment of the present disclosure has been described in detail above, the present disclosure is not limited to the above embodiment. The device and method according to the present disclosure can be modified in various ways without departing from the spirit and scope of the present disclosure.

[0068] For example, the determination unit 32 may determine the inquiry theme using a learning model. The learning model may be implemented on the prompt generation device 30 or may be implemented outside the prompt generation device 30 (e.g., on a network). The learning model is a learning model that is machine-learned using training data consisting of pairs of persona basic information about a virtual child and virtual inquiry themes that interest the virtual child. The determination unit 32 may input the child basic information into the learning model and determine the inquiry theme as the child's inquiry theme based on the estimated result of the child's inquiry theme output from the learning model. This configuration makes it possible to easily determine an appropriate inquiry theme. For example, even if it is difficult to uniquely determine an inquiry theme from the child information, the inquiry theme can be easily determined by using the learning model.

[0069] The child information may include at least the inquiry purpose of the inquiry-based learning, or may include only the inquiry purpose. The generation unit 33 may generate the first prompt based only on the inquiry purpose and the inquiry theme.

[0070] In the theme information DB 39 shown in Fig. 3, questions are associated with themes via trivia, but questions may be associated directly with themes without via trivia. In the theme information DB 39 shown in Fig. 3, both trivia and questions are stored, but only either trivia or questions may be stored in the theme information DB 39.

[0071] 6, the research theme is described in region R3, but the description of the research theme may be omitted from the first prompt. For example, if the theme information is described in the first prompt, the description of the research theme may be omitted. In other words, the generation unit 33 does not need to describe the research theme in the first prompt.

[0072] The device and method of the present disclosure have the following configuration.

[0073] [1] An apparatus comprising: a child information acquisition unit that acquires child information including an inquiry purpose for inquiry-based learning conducted by the child; a determination unit that determines an inquiry theme for the inquiry-based learning; and a generation unit that generates a first prompt based on the inquiry purpose and the inquiry theme, the first prompt instructing a generative AI model to create content to encourage the child to engage in the inquiry-based learning.

[0074] [2] The device described in [1], wherein the child information further includes an inquiry level of the inquiry-based learning, and the generation unit generates the first prompt further based on the inquiry level.

[0075] [3] The device according to [1] or [2], wherein the determination unit determines the research theme based on the child information.

[0076] [4] The device described in any of [1] to [3], wherein the determination unit determines a plurality of inquiry themes including the inquiry theme and the child's level of interest in each of the plurality of inquiry themes, and the generation unit generates the first prompt in which the level of interest is associated with each of the plurality of inquiry themes.

[0077] [5] The device described in any of [1] to [4], wherein the child information further includes basic child information about the child, and the determination unit compares the child basic information with a persona database that stores data records that associate persona basic information about a virtual child with virtual exploration themes in which the virtual child is interested, and determines the virtual exploration theme obtained from the persona database as the exploration theme.

[0078] [6] The device described in any of [1] to [4], wherein the child information further includes basic child information about the child, and the determination unit inputs the basic child information into a learning model that has been machine-learned using teacher data consisting of a pair of persona basic information about a virtual child and a virtual inquiry theme in which the virtual child is interested, and determines the estimated result of the child's inquiry theme output from the learning model as the inquiry theme.

[0079] [7] The device described in any of [1] to [6], wherein the determination unit compares the combination of the inquiry purpose and the inquiry theme with a theme information database that stores data records that associate the purpose of the inquiry learning, the theme of the inquiry learning, and theme information for encouraging the child to acquire new knowledge related to the theme, and obtains the theme information from the theme information database, and the generation unit generates the first prompt further based on the theme information.

[0080] [8] The device described in [7], wherein the theme information includes at least one of trivia and questions related to the theme, and the first prompt instructs the generative AI model to create the content for providing at least one of the trivia and the questions to the child.

[0081] [9] The device described in any of [1] to [8], further comprising a judgment unit that judges whether to generate a second prompt based on the content and the child's response to the content, and the generation unit generates the second prompt to change the content instructed to the generative AI model by the first prompt based on the judgment result by the judgment unit.

[0082]

[10] A method comprising the steps of: acquiring child information including an inquiry purpose for inquiry-based learning performed by the child; determining an inquiry theme for the inquiry-based learning; and generating a first prompt based on the inquiry purpose and the inquiry theme, the first prompt instructing a generative AI model to create content to encourage the child to engage in the inquiry-based learning.

[0083] The block diagrams used to explain the above embodiments show functional blocks. These functional blocks (components) are realized by any combination of at least one of hardware and software. The method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are connected directly or indirectly (e.g., via wire, wirelessly, etc.) and these multiple devices. The functional block may also be realized by combining software with the single device or multiple devices.

[0084] Functions include, but are not limited to, judgment, determination, judgment, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, resolution, selection, election, establishment, comparison, assumption, expectation, regard, broadcasting, notifying, communicating, forwarding, configuring, reconfiguring, allocating, mapping, and assignment. For example, a functional block (component) that performs a transmission function is called a transmitting unit or transmitter. As mentioned above, there are no particular limitations on how the functions are implemented.

[0085] For example, the prompt generation device 30 according to an embodiment of the present disclosure may function as a computer that performs processing of the method of the present disclosure. Fig. 7 is a diagram illustrating an example of a hardware configuration of a device according to an embodiment of the present disclosure. The prompt generation device 30 may be physically configured as a computer including a processor 1001, a memory 1002, a storage device 1003, a communication device 1004, an input device 1005, an output device 1006, and a bus 1007.

[0086] In the following description, the term "device" may be interpreted as a circuit, a device, a unit, etc. The hardware configuration of the prompt generation device 30 may be configured to include one or more of the devices shown in the figure, or may be configured to exclude some of the devices.

[0087] Each function in the prompt generating device 30 is realized by loading specified software (programs) onto hardware such as the processor 1001 and memory 1002, causing the processor 1001 to perform calculations, control communication via the communication device 1004, and control at least one of reading and writing data in the memory 1002 and storage 1003.

[0088] The processor 1001, for example, runs an operating system to control the entire computer. The processor 1001 may be configured as a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic unit, a register, etc. For example, at least one of the functional units of the inquiry-based learning system 1 described above may be realized by the processor 1001.

[0089] The processor 1001 reads programs (program codes), software modules, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002 and executes various processes in accordance with the programs. The programs used are those that cause a computer to execute at least some of the operations described in the above-described embodiments. For example, at least one of the functional units of the inquiry-based learning system 1 described above may be implemented by a control program stored in the memory 1002 and running on the processor 1001, and similar implementations may be made for other functional blocks. While the above-described various processes have been described as being executed by one processor 1001, they may also be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. The programs may also be transmitted from a network via a telecommunications line.

[0090] The memory 1002 is a computer-readable recording medium and may be configured, for example, by at least one of a read-only memory (ROM), an erasable programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), and a random access memory (RAM). The memory 1002 may also be referred to as a register, a cache, or a main memory. The memory 1002 may store executable programs (program codes) and software modules for implementing a prompt generation method according to an embodiment of the present disclosure.

[0091] Storage 1003 is a computer-readable recording medium, and may be composed of at least one of, for example, an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory (e.g., a card, a stick, a key drive), a floppy (registered trademark) disk, and a magnetic strip. Storage 1003 may also be referred to as an auxiliary storage device. The above-mentioned storage medium may be, for example, a database, a server, or other appropriate medium including at least one of memory 1002 and storage 1003.

[0092] The communication device 1004 is hardware (transmitting / receiving device) for communicating between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, or a communication module. The communication device 1004 may include, for example, a high-frequency switch, a duplexer, a filter, and a frequency synthesizer to realize at least one of frequency division duplex (FDD) and time division duplex (TDD). For example, at least one of the functional units of the inquiry-based learning system 1 described above may be realized by the communication device 1004. The communication device 1004 may be implemented with a transmitting unit and a receiving unit that are physically or logically separated.

[0093] The input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) that receives input from the outside. The output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) that outputs to the outside. Note that the input device 1005 and the output device 1006 may be integrated (e.g., a touch panel).

[0094] The processor 1001, memory 1002, and other devices are connected by a bus 1007 for communicating information. The bus 1007 may be configured using a single bus, or may be configured using different buses for each device.

[0095] The prompt generation device 30 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), and a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these pieces of hardware.

[0096] The notification of information is not limited to the aspects / embodiments described in the present disclosure and may be performed using other methods. For example, the notification of information may be performed by physical layer signaling (e.g., Downlink Control Information (DCI) and Uplink Control Information (UCI)), higher layer signaling (e.g., Radio Resource Control (RRC) signaling, Medium Access Control (MAC) signaling, broadcast information (Master Information Block (MIB) and System Information Block (SIB))), other signals, or a combination thereof. The RRC signaling may be referred to as an RRC message, and may be, for example, an RRC Connection Setup message, an RRC Connection Reconfiguration message, or the like.

[0097] In the processing procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure, the order of processing may be changed unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order and are not limited to the particular order presented.

[0098] Input and output information may be stored in a specific location (for example, memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0099] The determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0100] The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to explicit notification, but may be implicit (e.g., by not notifying the predetermined information).

[0101] Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure.

[0102] Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., whether referred to as software, firmware, middleware, microcode, hardware description language, or otherwise.

[0103] Software, instructions, information, etc. may be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), these wired and / or wireless technologies are included within the definition of transmission media.

[0104] The information, signals, etc. described in this disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0105] Note that terms described in the present disclosure and terms necessary for understanding the present disclosure may be replaced with terms having the same or similar meanings. For example, at least one of a channel and a symbol may be a signal (signaling). A signal may be a message. A component carrier (CC) may be called a carrier frequency, a cell, a frequency carrier, or the like.

[0106] The information, parameters, etc. described in the present disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or other corresponding information. For example, a radio resource may be indicated by an index.

[0107] The names used for the above-described parameters are not intended to be limiting in any way. Furthermore, the formulas using these parameters may differ from those explicitly disclosed in this disclosure. The various channels (e.g., PUCCH, PDCCH, etc.) and information elements may be identified by any suitable names, and therefore the various names assigned to these various channels and information elements are not intended to be limiting in any way.

[0108] In this disclosure, terms such as "Mobile Station (MS)," "user terminal," "User Equipment (UE)," and "terminal" may be used interchangeably.

[0109] A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable terminology.

[0110] The terms "determining" and "determining" as used in this disclosure may encompass a wide variety of actions. "Determining" and "determining" may be considered, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., looking up in a table, database, or another data structure), ascertaining, etc. "Determining" and "determining" may also be considered, for example, receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, or accessing (e.g., accessing data in memory). "Determining" and "determining" may also be considered, for example, resolving, selecting, choosing, establishing, comparing, etc. That is, "determining" and "determining" may include considering any action related to "determining." The word "judgment (decision)" may be read as "assuming," "expecting," or "considering," etc.

[0111] The terms "connected," "coupled," or any variation thereof, refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." When "connected" or "coupled" is used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using at least one of an electrical wire, cable, and printed electrical connection, or may be considered to be "connected" or "coupled" to each other using electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0112] As used in this disclosure, the phrase "based on" does not mean "based only on," unless expressly stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0113] As used in this disclosure, any reference to an element using designations such as "first" and "second" does not generally limit the quantity or order of those elements. These designations may be used in this disclosure as a convenient method of distinguishing between two or more elements. Thus, a reference to a first and a second element does not imply that only two elements may be employed or that the first element must in some way precede the second element.

[0114] When the terms "include," "including," and variations thereof are used in this disclosure, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, when the term "or" is used in this disclosure, it is not intended to be an exclusive or.

[0115] In this disclosure, where articles are added by translation, such as "a," "an," and "the" in English, the disclosure may include that the nouns following these articles are plural.

[0116] In the present disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "coupled" may also be interpreted in the same way as "different."

[0117] 21...generative AI model, 30...prompt generation device, 31...child information acquisition unit, 32...decision unit, 33...generation unit, 36...judgment unit, 38...persona database, 39...theme information database.

Claims

a child information acquisition unit that acquires child information including an inquiry purpose of inquiry-based learning conducted by the child; a determination unit that determines an inquiry theme for the inquiry-based learning; The device comprises a generation unit that generates a first prompt based on the inquiry purpose and the inquiry theme, the first prompt instructing a generative AI model to create content to encourage the child to engage in inquiry-based learning. 　 The child information further includes an inquiry level of the inquiry-based learning; the generator generates the first prompt further based on the exploration level.

10. The apparatus of claim 1. 　 the determination unit determines the research theme based on the child information.

10. The apparatus of claim 1. 　 the determination unit determines a plurality of inquiry themes including the inquiry theme and a degree of interest of the child in each of the plurality of inquiry themes; the generation unit generates the first prompt in which the interest level is associated with each of the plurality of research themes.

10. The apparatus of claim 1. 　 The child information further includes basic child information about the child; the determination unit compares the child basic information with a persona database that stores data records associating persona basic information about a virtual child with virtual exploration themes that the virtual child is interested in, and determines the virtual exploration theme acquired from the persona database as the exploration theme; 10. The apparatus of claim 1. 　 The child information further includes basic child information about the child; the determination unit inputs the child basic information into a learning model that has been machine-learned using teacher data consisting of a pair of persona basic information about a virtual child and a virtual inquiry theme in which the virtual child is interested, and determines the inquiry theme as an estimated result of the child's inquiry theme output from the learning model.

10. The apparatus of claim 1. 　 the determination unit compares the combination of the inquiry purpose and the inquiry theme with a theme information database that stores data records that associate the purpose of the inquiry learning, the theme of the inquiry learning, and theme information for encouraging the child to acquire new knowledge related to the theme, and acquires the theme information from the theme information database; the generating unit generates the first prompt further based on the theme information.

10. The apparatus of claim 1. 　 the theme information includes at least one of trivia and questions related to the theme; the first prompt instructs the generative AI model to create the content to provide at least one of the trivia and the question to the child; 8. The apparatus of claim 7. 　 a determination unit that determines whether to generate a second prompt based on the content and the child's response to the content; The generation unit generates the second prompt for changing the content instructed to the generated AI model by the first prompt based on the determination result by the determination unit.

10. The apparatus of claim 1. 　 acquiring child information including an inquiry purpose for inquiry learning to be performed by the child; A step of determining an inquiry theme for the inquiry-based learning; generating a first prompt based on the inquiry purpose and the inquiry theme, the first prompt instructing a generative AI model to create content to encourage the child to engage in inquiry-based learning.

Images