System

Abstract

A system is provided.SOLUTION: The system includes a means for receiving a question related to assignment setting, information collection, data arrangement, and presentation input by a student in a learning process, a means for generating an appropriate prompt by a generation engine corresponding to question content, a means for transmitting the generated prompt to a natural language processing model and receiving an answer, and a means for shaping the received answer, transmitting the shaped answer to a terminal of the student, and displaying the shaped answer.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] While inquiry-based learning will be promoted in high schools from 2022, there is an overwhelming shortage of teaching resources, as each student will be working on different themes and challenges. Furthermore, while students need support with specialized knowledge in the various learning processes they face, it is difficult to secure such support due to human, time, and financial constraints. The objective of this invention is to solve these problems and provide individually optimized learning support. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for accepting questions entered by students in the course of their studies regarding task setting, information gathering, data organization, and presentations, a means for generating appropriate prompts using a generation engine corresponding to the content of the questions, a means for sending the generated prompts to a natural language processing model and receiving answers, and a means for formatting the received answers and sending them to the student's terminal for display. Furthermore, the prompt generation engine generates prompts according to preset templates for each learning process, and the natural language processing model provides answers based on the student's individual learning progress, thereby enabling individually optimized learning support.

[0006] "Student" refers to a person engaged in learning activities, and in particular to a student at a secondary education institution engaged in inquiry-based learning.

[0007] The "learning process" refers to the multiple phases that students go through as they progress through their learning activities, including setting goals, gathering information, organizing data, and making presentations.

[0008] "Problem setting" refers to the process of determining the theme or goal to be explored in the early stages of learning.

[0009] "Information gathering" refers to the process of researching relevant information for the set task.

[0010] "Data organization" refers to the process of systematically organizing collected information and data.

[0011] "Presentation" refers to the process of summarizing and presenting the results of learning.

[0012] "Means for accepting questions" refers to a mechanism for importing questions entered by students into the system and sending them to a central processing unit such as a server.

[0013] A "generation engine" refers to a program or algorithm that generates appropriate prompts based on questions received from students.

[0014] A "prompt" refers to an instruction statement that instructs a natural language processing model to perform a specific process.

[0015] A "natural language processing model" refers to a machine learning model that understands and generates human language, and in the present invention in particular has the role of answering questions.

[0016] "Means for receiving answers" refers to the mechanism by which the answer obtained from the natural language processing model is received within the system and passed on to the next required processing.

[0017] "Formatting" refers to arranging the received responses into an appropriate format and content, and processing them into a form that is easy to display and save.

[0018] "Means for displaying" refers to the mechanism for visually presenting the formatted answers on the student's device.

[0019] "Template" refers to a pre-defined format or framework that serves as the basis for the prompt generation engine to generate prompts.

[0020] "Learning progress" refers to the stage or achievement of a student's current learning process. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0023] First, the terms used in the following description will be explained.

[0024] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0025] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0026] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0027] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0034] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0035] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0042] This invention is a system that provides effective, individually optimized learning support for students as they progress through inquiry-based learning. The system accepts questions entered by students during the learning process regarding task setting, information gathering, data organization, and presentations, generates appropriate prompts corresponding to the questions, and provides answers using a natural language processing model.

[0043] composition

[0044] The system mainly consists of the following components:

[0045] 1. Method of accepting questions

[0046] The terminal accepts questions from students. Specifically, it provides a chat box-style user interface, allowing students to input questions about setting assignments, gathering information, etc.

[0047] 2. Prompt Generation Engine

[0048] The server generates appropriate prompts based on the questions received from students. The prompt generation engine dynamically generates prompts using templates tailored to each learning process.

[0049] 3. Natural Language Processing Model

[0050] The server generates prompts and sends them to a natural language processing model, which uses the most state-of-the-art model available today (e.g., GPT-3 or equivalent), and receives responses.

[0051] 4. Answer formatting means

[0052] The server formats the answers received from the natural language processing model, specifically by making the answers easier to understand and converting them into a format that is useful to the student.

[0053] 5. Display means

[0054] The device displays the formatted answer to the student, allowing them to quickly get the information they need and take action to move forward to the next step in their learning.

[0055] A natural language description of the program's operation

[0056] Question acceptance method

[0057] The user inputs a question during the learning process. For example, they input a question such as "I would like to set a research topic about environmental issues" into the chat box.

[0058] Prompt Generation Engine

[0059] The server receives questions from users and generates corresponding prompts based on templates for each process, such as problem setting, information gathering, data organization, and presentation.

[0060] Natural Language Processing Model

[0061] The server sends the generated prompt to a natural language processing model to obtain an answer. For example, if the prompt is "Which aspects of environmental issues are you concerned about?", the natural language processing model generates an answer such as "Air pollution, ocean pollution, deforestation, etc."

[0062] Answer formatting means

[0063] The server formats the answer it receives from the natural language processing model, for example by turning the answer into a bulleted list or adding specific examples.

[0064] Display means

[0065] The device displays the formatted answer in a user interface, allowing the user to proceed to the next learning step based on the displayed information.

[0066] Specific examples

[0067] For example, if a student types in a question like "I want to find the latest research on air pollution. Where can I find it?", the following happens:

[0068] 1. A user types a question: "I want to find the latest research on air pollution. Where can I find it?"

[0069] 2. The device sends a question to the server.

[0070] 3. The server uses a prompt generation engine to generate the prompt: "What are some reliable sources for finding the latest research materials?"

[0071] 4. The server sends the generated prompt to the natural language processing model.

[0072] 5. A natural language processing model generates the answer: "You can use a scholarly search engine such as Google Scholar or PubMed."

[0073] 6. The server receives and formats the response.

[0074] 7. The server sends the formatted response to the device.

[0075] 8. The device displays the answer in the user interface: "You might want to use a scholarly search engine such as Google Scholar or PubMed."

[0076] In this way, the system helps students to effectively engage in inquiry-based learning, allowing them to advance their learning by asking questions and obtaining answers on their own, without the need for a specialist escort.

[0077] The processing flow will be explained below.

[0078] Detailed steps in the assignment process

[0079] Step 1:

[0080] The user enters a question about setting a research topic into the chat box on the device. For example, the user might enter, "I would like to set a research topic about environmental issues. What perspective should I take?"

[0081] Step 2:

[0082] The terminal transmits the user's question to the server in real time. The transmitted data includes the question content and user information.

[0083] Step 3:

[0084] The server receives the question and passes it to a prompt generation engine, which identifies which process the question belongs to.

[0085] Step 4:

[0086] A prompt generation engine uses the challenge template to generate appropriate prompts, such as "What aspects of environmental issues interest you?"

[0087] Step 5:

[0088] The server sends the generated prompt to the natural language processing model (ChatGPT), along with the prompt and related information in the form of an API request.

[0089] Step 6:

[0090] A natural language processing model generates an answer based on the prompt, such as "Air pollution, marine pollution, deforestation, etc. Please choose the area that you are particularly interested in."

[0091] Step 7:

[0092] The server receives the answer from the natural language processing model, which is then formatted as needed.

[0093] Step 8:

[0094] The server then sends the formatted response to the terminal, which includes the response content and instructions for display.

[0095] Step 9:

[0096] The device displays the received answers in the user interface, and the user decides whether to ask further questions or proceed to the next step based on the information presented.

[0097] Detailed processing steps of the information gathering process

[0098] Step 1:

[0099] A user types a question about information gathering into a chat box on a terminal, for example, "I'd like to find the latest research materials on air pollution. Where can I find them?"

[0100] Step 2:

[0101] The terminal transmits the user's question to the server in real time.

[0102] Step 3:

[0103] The server receives the question and passes it to the prompt generation engine.

[0104] Step 4:

[0105] A prompt generation engine uses information-gathering templates to generate appropriate prompts, such as "What are some reliable sources for finding the latest research materials?"

[0106] Step 5:

[0107] The server sends the generated prompt to the natural language processing model (ChatGPT).

[0108] Step 6:

[0109] A natural language processing model generates an answer based on the prompt, such as "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[0110] Step 7:

[0111] The server receives the answer from the natural language processing model, which is then formatted as needed.

[0112] Step 8:

[0113] The server formats the response and sends it to the device.

[0114] Step 9:

[0115] The terminal displays the received answers on the user interface, allowing the user to begin searching for materials based on the presented information.

[0116] Detailed processing steps of the data reduction process

[0117] Step 1:

[0118] A user types a question about data organization into a chat box on the device, for example, "How should I organize the data for...?"

[0119] Step 2:

[0120] The terminal transmits the user's question to the server in real time.

[0121] Step 3:

[0122] The server receives the question and passes it to the prompt generation engine.

[0123] Step 4:

[0124] The prompt generation engine uses templates for data organization to generate appropriate prompts, such as "What are the basic techniques for data analysis?"

[0125] Step 5:

[0126] The server sends the generated prompt to the natural language processing model (ChatGPT).

[0127] Step 6:

[0128] A natural language processing model generates an answer based on the prompt, such as "Basic techniques for data analysis include graphing, statistical analysis, and regression analysis."

[0129] Step 7:

[0130] The server receives the answer from the natural language processing model, which is then formatted as needed.

[0131] Step 8:

[0132] The server formats the response and sends it to the device.

[0133] Step 9:

[0134] The device displays the received answers in a user interface, allowing the user to organize the data based on the presented information.

[0135] Detailed processing steps of the presentation process

[0136] Step 1:

[0137] A user types a question about the presentation into the chat box of the device, for example, "How should I structure my presentation?"

[0138] Step 2:

[0139] The terminal transmits the user's question to the server in real time.

[0140] Step 3:

[0141] The server receives the question and passes it to the prompt generation engine.

[0142] Step 4:

[0143] The prompt generation engine uses the presentation template to generate appropriate prompts, such as "How do I structure an effective presentation?"

[0144] Step 5:

[0145] The server sends the generated prompt to the natural language processing model (ChatGPT).

[0146] Step 6:

[0147] The natural language processing model generates an answer based on the prompt sent, for example, "The basic structure of a presentation has three parts: introduction, main body, and conclusion. The introduction explains the purpose and background, the main body provides details using data and examples, and the conclusion introduces the results and next steps."

[0148] Step 7:

[0149] The server receives the answer from the natural language processing model, which is then formatted as needed.

[0150] Step 8:

[0151] The server formats the response and sends it to the device.

[0152] Step 9:

[0153] The device displays the received answers on a user interface, allowing the user to prepare a presentation based on the information presented.

[0154] Example 1

[0155] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0156] In today's educational environment, there is a lack of appropriate support tailored to each student's individual learning progress and level of understanding, and students often find it difficult to engage in independent inquiry-based learning. Furthermore, limited teacher and instructor resources mean that individualized instruction is difficult to provide. Furthermore, there are few ways for students to receive appropriate learning support in real time, which can result in a decline in learning efficiency.

[0157] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0158] In this invention, the server includes means for accepting questions entered by students in the course of their studies regarding task setting, information gathering, data organization, and presentations, means for generating appropriate prompts using a generation engine corresponding to the content of the questions, means for sending the generated prompts to a natural language processing model and receiving answers, and means for formatting the received answers and sending them to the student's terminal for display. This allows students to receive individual learning support in real time, enabling them to effectively advance independent inquiry-based learning.

[0159] "Student" means a person who belongs to an educational institution and engages in learning activities.

[0160] "Learning process" refers to the steps of learning activities such as setting a task, gathering information, organizing data, and making a presentation.

[0161] "Questions" are content related to doubts or issues that students have while studying.

[0162] A "prompt generation engine" is a system that automatically generates appropriate prompts based on the questions it receives.

[0163] A "prompt" is a sentence that is sent to a natural language processing model to get an answer to a question.

[0164] A "natural language processing model" refers to an algorithm that understands natural language and generates an answer based on input text.

[0165] An "answer" is a response sentence that a natural language processing model generates based on a prompt.

[0166] "Formatting" is the process of converting the answers received into a format that is easy to read and understand.

[0167] "Device" refers to devices used by students, such as computers, tablets, and smartphones.

[0168] "Educational support system" refers to the entire system designed to enable students to receive individually optimized learning support.

[0169] MODE FOR CARRYING OUT THE INVENTION

[0170] The present invention is an educational support system that provides individually optimized learning support to students as they progress through inquiry-based learning. This system accepts questions entered by students during the learning process regarding task setting, information gathering, data organization, and presentations, generates appropriate prompts based on the content of the questions, and provides answers using a natural language processing model. Specific embodiments of this system are described below.

[0171] Hardware and Software Configuration

[0172] The system mainly consists of the following components:

[0173] 1. Device: A device used by a student, such as a computer, tablet, or smartphone. The device provides a chat box-style input field as a user interface.

[0174] 2. Server: A backend system for implementing the prompt generation engine and natural language processing model. The server is responsible for receiving questions, parsing them, generating prompts, sending them to the natural language processing model, formatting answers, and sending the formatted answers.

[0175] 3. Natural language processing models: For example, generative AI models like GPT-3, which are used to generate answers to students' questions.

[0176] Data processing and calculation

[0177] 1. Acceptance and submission:

[0178] The user (student) inputs questions they have during their studies into the terminal. For example, a student might input, "I want to find the latest research materials on air pollution."

[0179] The device sends the question to the server in real time, using JSON data or other formats.

[0180] 2. Prompt generation:

[0181] The server analyzes the question received from the user and generates an appropriate prompt using a prompt generation engine.

[0182] If the question is "I want to find the latest research on air pollution," the generated prompt will be "What are some reliable sources for finding the latest research?"

[0183] 3. Sending prompts and generating answers:

[0184] The server sends the generated prompt to a natural language processing model (such as GPT-3) using an API request.

[0185] A natural language processing model generates an appropriate answer based on the prompt and returns it to the server, such as "You might want to use a scholarly article search engine such as Google Scholar or PubMed."

[0186] 4. Formatting the answer:

[0187] The server formats the answers received from the natural language processing model, specifically converting the answers into an easy-to-read format (such as bullet points or adding specific examples).

[0188] The formatted content is converted into JSON or another appropriate data format and sent to the terminal.

[0189] 5. Show Answer:

[0190] The device receives a formatted answer from the server and displays it to the student in an easy-to-understand manner. For example, it might say, "You might want to use a scholarly paper search engine such as Google Scholar or PubMed."

[0191] Specific examples

[0192] For example, if a student types a question like "What are some tips for giving a successful presentation?", the process would go something like this:

[0193] 1. User types question: "What are some tips for giving a successful presentation?"

[0194] 2. The device sends the question to the server.

[0195] 3. The server parses the question and generates an appropriate prompt: "What specific tips can I use to give a successful presentation?"

[0196] 4. The server sends the generated prompt to the natural language processing model.

[0197] 5. The natural language processing model generates answers such as "set clear goals, practice, and use visual aids."

[0198] 6. The server formats the response and sends it to the device.

[0199] 7. The device displays formatted answers to students: "Successful presentations require clear goals, practice, and the use of visual aids."

[0200] In this way, the present invention enables students to receive individually optimized learning support, and provides support for effectively promoting inquiry-based learning.

[0201] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0202] Step 1:

[0203] Enter and submit your question

[0204] The user inputs questions they have during their learning process into the device, for example, "I want to find the latest research materials on air pollution."

[0205] The device converts the entered question into JSON data format and sends it to the server in real time using WebSocket or HTTP requests.

[0206] Input: A text question: "I would like to find the latest research on air pollution."

[0207] Output: The question data sent to the server is converted to JSON format.

[0208] Step 2:

[0209] Question Analysis

[0210] The server receives the question sent from the device and analyzes the question, extracting important keywords and context from the question.

[0211] The server analyzes the question data and prepares it to generate appropriate prompts, for example by extracting keywords such as "air pollution" and "latest research materials."

[0212] Input: A JSON question: "I want to find the latest research on air pollution."

[0213] Output: Analysis results (e.g. keywords and contextual information) for use by the prompt generation engine.

[0214] Step 3:

[0215] Prompt Generation

[0216] The server uses a prompt generation engine to generate an appropriate prompt based on the analysis results, for example, "What are some reliable sources for finding the latest research materials?"

[0217] Input: Analysis results (e.g., keywords and context information).

[0218] Output: The generated prompt (the text reads "What reliable sources can I use to find the latest research materials?").

[0219] Step 4:

[0220] Sending a prompt

[0221] The server sends the generated prompt to the natural language processing model (generative AI model), passing the prompt to the model in the form of an API request.

[0222] Input: Generated prompt (e.g., "What reliable sources can I use to find the latest research materials?").

[0223] Output: The prompt data sent to the natural language processing model.

[0224] Step 5:

[0225] Generating and receiving answers

[0226] A natural language processing model generates an answer based on the prompt it receives, such as "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[0227] The natural language processing model returns the generated answer to the server.

[0228] Input: Submitted prompt ("What reliable sources can I use to find the latest research materials?").

[0229] Output: The generated answer (e.g., "You may find it helpful to use a scholarly search engine such as Google Scholar or PubMed").

[0230] Step 6:

[0231] Formatting answers

[0232] The server formats the answer received from the natural language processing model, converting the answer into an easy-to-read format and adding bullet points and specific examples as needed.

[0233] Input: A generated answer (e.g., "You might want to use a scholarly search engine such as Google Scholar or PubMed").

[0234] Output: A formatted answer (e.g., "You may find it helpful to use a scholarly search engine such as Google Scholar or PubMed." "Examples: Google Scholar, PubMed").

[0235] Step 7:

[0236] Show Answers

[0237] The terminal displays the formatted response received from the server in a user interface, for example, in a chat box.

[0238] Input: A formatted answer (e.g., "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed.").

[0239] Output: User-visible display of answers.

[0240] (Application example 1)

[0241] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0242] Conventional learning support systems have had the problem of being unable to provide appropriate information and support in a timely manner for the challenges that students face individually.In addition, when students independently engage in inquiry-based learning, it is difficult for them to know how to access reliable information sources or how to gather appropriate information, which can slow down their learning progress.

[0243] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0244] In this invention, the server includes means for accepting questions related to task setting, information gathering, data organization, and presentations entered by students in the course of their studies, means for generating appropriate prompts using a generation engine corresponding to the content of the questions, means for sending the generated prompts to a natural language processing model and receiving answers, means for formatting the received answers and sending them to the student's terminal for display, and means for providing learning support through a content distribution service. This enables students to quickly and effectively obtain appropriate information related to the content of their studies.

[0245] "Problem setting" is the process by which students decide on a specific theme or question to be solved during the learning process.

[0246] "Information gathering" is the activity of gathering relevant data and knowledge based on the problem setting.

[0247] "Data organization" is the process of classifying, analyzing, and organizing collected information into an easy-to-understand format.

[0248] A "presentation" is the act of organizing the results of learning and presenting them to others in an easy-to-understand manner.

[0249] A "generation engine" is a system component that generates appropriate prompts based on the input question.

[0250] A "prompt" is an input sentence that gives instructions to a natural language processing model.

[0251] A "natural language processing model" is an AI technology that understands and generates human language.

[0252] "Answer formatting" is the process of organizing the answers received from a natural language processing model in an easy-to-read format.

[0253] A "terminal" is an electronic device that allows a user to input information and display results.

[0254] A "content distribution service" is a platform for providing information to users via the Internet.

[0255] This invention is a system that provides optimal individualized learning support to students as they progress through inquiry-based learning. The system accepts questions about task setting, information gathering, data organization, and presentations, and provides appropriate answers to those questions.

[0256] Hardware and software used

[0257] The hardware required to implement this system includes a smartphone, tablet, or personal computer. It also requires connection to a server, terminal, and user interface. The software used is Python, the OpenAI API, and a front-end framework (React, Flutter, etc.).

[0258] System Components

[0259] 1. How to contact us:

[0260] The device (e.g., a smartphone or PC) accepts questions from students through a chat box-style user interface. For example, a student might type in a question like, "I want to find the latest research materials on air pollution. Where should I look for them?"

[0261] 2. Prompt generation engine:

[0262] The server generates an appropriate prompt based on the question it receives. For example, after receiving a question, the server generates a prompt like, "Please explain in detail the following question that interests you: I'd like to find the latest research on air pollution. Where can I find it?"

[0263] 3. Natural Language Processing Models:

[0264] The server sends the generated prompt to a natural language processing model (e.g., OpenAI's GPT-3) and receives an answer from the model, such as, "You can use academic paper search engines such as Google Scholar or PubMed. You can use the filter function when searching for papers to find the latest research."

[0265] 4. Answer formatting method:

[0266] The server formats the answers it receives from the natural language processing model to make them easier to read, for example by editing the answers to make them easier to understand, bulleting important information, and adding examples.

[0267] 5. Display means:

[0268] The device will then display the formatted answer in a user interface. For example, the student's device might say, "You can use academic paper search engines such as Google Scholar or PubMed. Use the filter function when searching for papers to find the latest research."

[0269] By providing learning support through a content delivery service, students can quickly and effectively acquire the right information related to their learning. The system utilizes cutting-edge generative AI models and prompting technology to ensure optimal learning support is always provided to students.

[0270] Specific examples

[0271] For example, if a student types a question like this:

[0272] "I want to find the latest research on air pollution. Where can I find it?"

[0273] The system responds to this question in the following way:

[0274] 1. The device accepts the question.

[0275] 2. The server uses the prompt generation engine to generate the following prompt:

[0276] "Please explain in detail the following question that interests you: I would like to find the latest research materials on air pollution. Where can I find them?"

[0277] 3. The server sends the generated prompt to a natural language processing model and receives a response such as:

[0278] "You can use academic search engines like Google Scholar and PubMed, which have filters to help you find the latest research."

[0279] 4. The server formats the response it receives and sends it to the terminal for display.

[0280] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0281] Step 1:

[0282] During the learning process, the user enters questions or concerns into a chat box-style user interface. For example, the user might enter a question like, "I want to find the latest research materials on air pollution. Where should I look for them?" This input is recorded on the terminal as a string of characters.

[0283] Step 2:

[0284] The terminal sends the input question data to the server, where it is received and analyzed.

[0285] Step 3:

[0286] The server starts a prompt generation engine based on the received question. The question data received as input is passed to the prompt generation engine, which generates an appropriate prompt based on that. For example, this prompt might be in the form of "Please explain in detail the following question that interests you: I want to find the latest research materials on air pollution. Where can I find them?" The generated prompt is recorded as a string.

[0287] Step 4:

[0288] The server sends the generated prompt string to a natural language processing model, such as a generative AI model like GPT-3, which generates an answer based on the received prompt. The model uses the prompt data as input and generates an appropriate answer as output.

[0289] Step 5:

[0290] The server receives the answer output from the natural language processing model and passes it to the answer formatting engine. The answer formatting engine formats the received answer into an easy-to-understand format, for example by turning sentences into bullet points or adding specific examples. This formatting process generates an answer that is easy to understand and organized.

[0291] Step 6:

[0292] The server sends the formatted answers to the device, which then displays the received answer data on its user interface. For example, the student's screen might read, "We recommend using academic paper search engines such as Google Scholar or PubMed. Use the filter function when searching for papers to find the latest research."

[0293] Step 7:

[0294] The user reviews the displayed answers and decides on the next action to take, such as actually searching for the latest research materials using an academic paper search engine.

[0295] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0296] This invention is a system that provides effective, individually optimized learning support for students as they progress through inquiry-based learning. In particular, by combining it with an emotion engine that recognizes students' emotions and optimizes the learning process, it achieves more advanced support.

[0297] composition

[0298] The system mainly consists of the following components:

[0299] 1. Method of accepting questions

[0300] The terminal accepts questions from students. Specifically, it provides a chat box-style user interface, allowing students to input questions about setting assignments, gathering information, etc.

[0301] 2. Prompt Generation Engine

[0302] The server generates appropriate prompts based on the questions received from students. The prompt generation engine dynamically generates prompts using templates tailored to each learning process.

[0303] 3. Natural Language Processing Model

[0304] The server generates prompts and sends them to a natural language processing model, which uses the most advanced models available today, to receive responses.

[0305] 4. Answer formatting means

[0306] The server formats the answers received from the natural language processing model, specifically by making the answers easier to understand and converting them into a format that is useful to the student.

[0307] 5. Display means

[0308] The device displays the formatted answer to the student, allowing them to quickly get the information they need and move on to the next step in their learning.

[0309] 6. Emotion Engine

[0310] The server recognizes emotions from the user's input text and voice. The emotion engine uses emotion analysis algorithms to understand the student's emotional state.

[0311] 7. Emotion-linked prompt generation

[0312] The server uses the emotion engine to generate prompts based on the emotion data it receives. For example, if a negative emotion is detected, it generates an encouraging prompt.

[0313] A natural language description of the program's operation

[0314] Question acceptance method

[0315] The user inputs a question during the learning process. For example, they input a question such as "I would like to set a research topic about environmental issues" into the chat box.

[0316] Prompt Generation Engine

[0317] The server receives questions from users and generates corresponding prompts based on templates for each process, such as problem setting, information gathering, data organization, and presentation.

[0318] Natural Language Processing Model

[0319] The server sends the generated prompt to a natural language processing model to obtain an answer. For example, if the prompt is "Which aspects of environmental issues are you interested in?", the natural language processing model generates an answer such as "Air pollution, marine pollution, deforestation, etc."

[0320] Answer formatting means

[0321] The server formats the answer it receives from the natural language processing model, for example by turning the answer into a bulleted list or adding specific examples.

[0322] Display means

[0323] The device displays the formatted answer in a user interface, and the user decides based on the displayed information whether to ask further questions or proceed to the next step.

[0324] Adding emotion engine processing

[0325] emotion recognition

[0326] The server sends the user's input text and voice to the emotion engine, which then analyzes the text and voice to determine the user's emotional state (stress, joy, excitement, anxiety, etc.).

[0327] Emotion-linked prompt generation

[0328] The server uses the emotion data obtained from the emotion engine to generate emotion-linked prompts. For example, if a user enters "I'm having trouble finding research materials on air pollution" and the emotion engine detects "anxiety," the prompt generation engine will provide support such as, "First, try some reliable sources of information. If necessary, please refer to this guide."

[0329] Specific examples

[0330] For example, if a student types a question like "I'd like to find the latest research on air pollution, but I don't know where to start," the following happens:

[0331] 1. A user types a question: "I'm looking for the latest research on air pollution, but I don't know where to start."

[0332] 2. The device sends a question to the server.

[0333] 3. The server receives the question and passes it to the prompt generation engine.

[0334] 4. The emotion engine analyzes emotions from the question text and detects "anxiety."

[0335] 5. The prompt generation engine takes sentiment data into account to generate an appropriate prompt: "Let's start by trying some trusted sources, such as Google Scholar and PubMed."

[0336] 6. The server sends the prompt to the natural language processing model.

[0337] 7. Natural language processing models generate relevant answers: "You can use a scholarly search engine such as Google Scholar or PubMed."

[0338] 8. The server receives and formats the response.

[0339] 9. The server sends the formatted response to the device.

[0340] 10. The device displays the answer it receives in the user interface: "You may find it helpful to use a scholarly paper search engine such as Google Scholar or PubMed."

[0341] In this way, the system helps students to effectively engage in inquiry-based learning and provides special support based on emotion recognition, making students feel more at ease and empowering them to ask and answer their own questions.

[0342] The processing flow will be explained below.

[0343] Detailed steps in the question acceptance and prompt generation process

[0344] Step 1:

[0345] During the learning process, the user can input a question, for example, "I want to find the latest research on air pollution, but I don't know where to start" into the chat box.

[0346] Step 2:

[0347] The device sends the user's question to the server in real time, including the question content and the user ID.

[0348] Step 3:

[0349] The server receives the user's question and sends the text data to the emotion engine.

[0350] Step 4:

[0351] The emotion engine analyzes the received text data and recognizes the user's emotional state, for example, detecting "anxiety."

[0352] Step 5:

[0353] The server passes the emotion data obtained from the emotion engine to the prompt generation engine, along with the question content and the emotional state.

[0354] Step 6:

[0355] The prompt generation engine generates appropriate prompts based on sentiment data and the question itself, such as "Let's start by trying some trusted sources, such as Google Scholar and PubMed."

[0356] Step 7:

[0357] The server sends the generated prompt to the natural language processing model in the form of an API request.

[0358] Step 8:

[0359] A natural language processing model generates an answer based on the prompt received, such as "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[0360] Step 9:

[0361] The server formats the answers it receives from the natural language processing model, for example by adding bullet points to the answer or highlighting important information.

[0362] Step 10:

[0363] The server then sends the formatted response to the user's terminal, where the formatted response data is sent.

[0364] Step 11:

[0365] The device displays the received answer on the user interface, and the user can decide whether to ask further questions or proceed to the next step based on the displayed information.

[0366] Specific examples

[0367] As a specific example, the following describes in detail how a student would respond if they typed in a question such as, "I want to find the latest research materials on air pollution, but I don't know where to look."

[0368] Step 1:

[0369] A user types a question: "I'm looking for the latest research on air pollution, but I don't know where to start."

[0370] Step 2:

[0371] The device sends the user's question to the server. The sent data includes the user ID and the question.

[0372] Step 3:

[0373] The server receives the question and sends the text data to the emotion engine.

[0374] Step 4:

[0375] The emotion engine analyzes emotions from the question text and detects "anxiety."

[0376] Step 5:

[0377] The server passes the emotional data and question content to the prompt generation engine. The data includes the question content, "I want to find the latest research materials on air pollution, but I don't know where to look," and the emotional state, "anxiety."

[0378] Step 6:

[0379] The prompt generation engine generates appropriate prompts based on the sentiment and question content, such as "Let's start by trying some reliable sources, such as Google Scholar and PubMed."

[0380] Step 7:

[0381] The server sends the generated prompt to the natural language processing model (ChatGPT), which sends the prompt in the form of an API request.

[0382] Step 8:

[0383] A natural language processing model generates an answer based on the prompt, for example, "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[0384] Step 9:

[0385] The server formats the answer received from the natural language processing model, for example by turning the answer into a list of items.

[0386] Step 10:

[0387] The server then sends the formatted response to the user's terminal. The transmitted data includes the formatted response.

[0388] Step 11:

[0389] The device displays the received answer on the user interface. For example, it may say, "We recommend using academic paper search engines such as Google Scholar or PubMed." The user can then begin searching for materials based on the information provided.

[0390] In this way, the system helps students to effectively engage in inquiry-based learning. In particular, by providing special support based on emotion recognition, students can feel more at ease while studying.

[0391] Example 2

[0392] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0393] Conventional learning support systems lacked adequate support for each student's learning situation and emotional state, making it difficult for students to effectively engage in inquiry-based learning. Furthermore, because they did not provide individually optimized learning support, they were unable to reduce the anxiety and stress students felt during the learning process.

[0394] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0395] In this invention, the server includes means for generating appropriate prompts using a generation engine corresponding to the content of the question, means for sending the generated prompts to a natural language processing model and receiving answers, means for formatting the received answers and sending them to the student's terminal for display, and means for recognizing emotions from the student's input text or voice and generating prompts based on that emotion data, thereby enabling individually optimal support according to the learning situation and emotional state of each student.

[0396] "Student" refers to a learner who uses this system to engage in inquiry-based learning.

[0397] The "question acceptance means" is a component for accepting questions from students regarding assignment setting, information gathering, data organization, and presentations.

[0398] The "generation engine" is a component that generates an appropriate prompt based on the content of the received question.

[0399] A "prompt" is an instruction or question generated by a generation engine and sent to a natural language processing model.

[0400] A "natural language processing model" is an AI model that generates answers based on generated prompts.

[0401] The "answer formatting means" is a component for organizing and formatting the answers received from the natural language processing model in an easy-to-understand manner.

[0402] The "emotion engine" is an algorithm that recognizes emotions from text and voice input by students and extracts that emotional data.

[0403] The "emotion-linked prompt generation means" is a means for generating a prompt based on emotion data obtained from the emotion engine.

[0404] "Terminal" means the device used by a student to enter questions and view answers from the system.

[0405] "Display means" refers to the functionality for visually presenting formatted answers to students.

[0406] This invention relates to a learning support system that effectively supports students' inquiry-based learning by accepting questions about task setting, information gathering, data organization, and presentations entered by students during the learning process and providing appropriate answers. In particular, it uses an emotion engine to analyze students' emotions and generates prompts based on those emotions to provide individually optimized learning support.

[0407] component

[0408] The system includes the following main components:

[0409] 1. Method of accepting questions

[0410] 2. Prompt Generation Engine

[0411] 3. Natural Language Processing Models (NLP Models)

[0412] 4. Answer formatting means

[0413] 5. Emotion Engine

[0414] 6. Emotion-linked prompt generation method

[0415] 7. Display means

[0416] Question acceptance method

[0417] While studying, students enter questions and challenges using a chat box-style user interface, which is provided by a software application running on a PC, tablet, smartphone, or other device. For example, a student might enter, "Tell me about the types of renewable energy."

[0418] Prompt Generation Engine

[0419] The server receives a question from the user and generates an appropriate prompt. The engine uses a template that corresponds to the question, generating prompts such as "What aspects of environmental issues are you interested in?" or "What are some reliable sources of information on environmental issues?"

[0420] Natural Language Processing Model

[0421] The generated prompt is sent from the server to a natural language processing model (e.g., GPT-4), which generates an appropriate answer based on the prompt. For example, it generates an answer such as, "There are solar power, wind power, hydroelectric power, and biomass power generation."

[0422] Answer formatting means

[0423] The server formats the answers it receives from the NLP model, which may include bulleting the answer, adding specific examples, and highlighting important information, such as "The following are the types of renewable energy:\n1. Solar power\n2. Wind power\n3. Hydroelectric power\n4. Biomass power."

[0424] Emotion Engine

[0425] The emotion engine analyzes user-supplied text and voice input to recognize emotional states (e.g., stress, joy, anxiety), for example using the Emotion API or similar algorithms.

[0426] Emotion-linked prompt generation method

[0427] Based on the emotional data obtained from the emotion engine, the prompt generation engine generates prompts according to the user's emotional state. For example, if a user types, "I'm having trouble finding research materials on air pollution," and anxiety is detected, the prompt will be adjusted to provide support such as, "Let's start by trying some reliable sources."

[0428] Display means

[0429] The formatted answer is sent from the server to the device and displayed on the user interface. The user can confirm the displayed answer and then enter further questions or proceed to the next step. For example, it might say, "The following are the types of renewable energy:\n1. Solar power generation\n2. Wind power generation\n3. Hydroelectric power generation\n4. Biomass power generation."

[0430] By combining the above components and their interaction, this invention can effectively support students' inquiry-based learning and provide individually optimized learning support.

[0431] Examples of prompt statements

[0432] 1. "What aspects of environmental issues interest you?"

[0433] 2. "What are some reliable sources of information on environmental issues?"

[0434] 3. "What are the main types of renewable energy?"

[0435] These prompts can be used to effectively obtain useful information from generative AI models.

[0436] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0437] Step 1: Enter your question

[0438] While studying, users input questions or problems using a chat box-style user interface. Specifically, they input text such as "Please tell me about the types of renewable energy" into an application running on a device such as a PC or smartphone. This input triggers the processing of the entire system.

[0439] Step 2: Submit your question

[0440] The terminal sends the user's question to the server. An HTTP POST request is often used here. Specifically, a data packet containing the question text entered by the user is sent to the server. The input is the user's question text, and the output is a response indicating that the data transfer to the server is complete.

[0441] Step 3: Prompt generation

[0442] The server passes the received question to the prompt generation engine, which generates an appropriate prompt based on a pre-configured template. For example, it generates a prompt such as "Please provide more information about renewable energy." The input is the question data received by the server, and the output is the generated prompt.

[0443] Step 4: Sentiment analysis

[0444] The server sends the question text to the emotion engine, which then analyzes it. The emotion engine uses a text analysis algorithm to recognize the user's emotions. For example, it can detect emotions such as "troubled" or "anxious." The input is the question text sent from the server, and the output is the emotion data resulting from the analysis.

[0445] Step 5: Emotion-linked prompt generation

[0446] Based on the emotion data received by the server from the emotion engine, the prompt generation engine generates a prompt according to the emotion. For example, if the server detects that the user is "in trouble," it creates a prompt such as "Let's start with some basic information." The input is emotion data and the original question, and the output is an emotion-linked prompt.

[0447] Step 6: Send prompts

[0448] The server sends the generated prompt to the natural language processing model (NLP model). Specifically, the prompt is sent to the natural language processing API via an HTTP request. The input is the generated prompt, and the output is a confirmation that the request was sent to the NLP model.

[0449] Step 7: Get the answer

[0450] The server receives the answer generated by the natural language processing model. For example, the NLP model might answer, "There are solar power, wind power, hydroelectric power, and biomass power generation." The input is the data returned by the NLP model, and the output is the answer data.

[0451] Step 8: Formatting your answers

[0452] The server then formats the answer it receives, making it easier for the user to understand. Specifically, it may do things like bullet points or insert additional information. For example, it may format the answer into something like "The following are the types of renewable energy:\n1. Solar power\n2. Wind power\n3. Hydroelectric power\n4. Biomass power." The input is the answer received from the NLP, and the output is the formatted answer.

[0453] Step 9: Submit your response

[0454] The server sends the formatted answer to the terminal as an HTTP response. The input is the formatted answer data, and the output is a response indicating that data transfer to the terminal is complete.

[0455] Step 10: Display answers

[0456] The terminal displays the received answer in the user interface. Specifically, the formatted answer is displayed in a chat box so that the user can see it. For example, it displays "The following are the types of renewable energy:\n1. Solar power generation\n2. Wind power generation\n3. Hydroelectric power generation\n4. Biomass power generation." The input is the answer data sent from the server, and the output is the visualized state provided to the user.

[0457] (Application example 2)

[0458] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0459] Conventional learning support systems have difficulty addressing students' psychological burdens and emotional needs, resulting in insufficient optimization of learning. Furthermore, they are unable to provide prompts and answers tailored to each student's learning progress and emotional state, and can only provide uniform support. This makes it difficult for students to progress effectively in their studies.

[0460] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for accepting questions related to task setting, information gathering, data organization, and presentations entered by students in the course of their studies; means for generating appropriate prompts using a generation engine corresponding to the content of the questions; means for sending the generated prompts to a natural language processing model and receiving answers; means for formatting the received answers and sending them to the student's terminal for display; means for recognizing emotions from the input text; and means including a generation engine for adjusting the prompts according to the recognized emotions. This enables optimal support to be provided according to each student's individual learning progress and emotional state.

[0461] "Problem setting" refers to the specific learning goals or problems that students set at the beginning of the learning process.

[0462] "Information gathering" refers to the act of collecting data and materials necessary for the learning process.

[0463] "Data organization" refers to the act of classifying and organizing collected information and processing it into a format that is easy to use.

[0464] A "presentation" is a means of communicating information to explain and announce the results of learning to others.

[0465] "Means for accepting questions" refers to the interface that allows the system to accept questions entered by students.

[0466] A "generation engine" is a program that generates appropriate prompts based on the student's question.

[0467] "Prompts" are instructions or questions generated by the system in response to students' questions or learning progress.

[0468] A "natural language processing model" is a machine learning algorithm for processing and understanding human language.

[0469] The "means for receiving an answer" refers to an interface for receiving an answer generated from a natural language processing model.

[0470] A "response formatter" is a program that converts the received responses into a format that is easy for students to understand.

[0471] A "terminal" is a device used by students to operate the learning support system.

[0472] An "emotion recognition means" is a program that analyzes a student's emotional state from input text.

[0473] A "prompt-adjusting generation engine" is a program that adjusts the content and expression of the prompt depending on the recognized emotion.

[0474] This invention is a system for providing learning support services in a physical store. The system is mainly composed of three entities: a server, a terminal, and a user. The roles and processing contents of each entity are explained below.

[0475] What the server does:

[0476] The server is the central processing unit and contains the following components:

[0477] A means of accepting questions: Receives and records questions entered by students. A chat box-style user interface is used in this section.

[0478] Generation engine: Generates appropriate prompts based on the question content. When generating prompts, templates corresponding to each learning process are used.

[0479] Natural Language Processing Model: The generated prompt is sent to a natural language processing model that uses the latest machine learning algorithms to receive an answer.

[0480] Formatting responses: Format the responses you receive in a way that is easier for students to understand. For example, add bullet points or examples.

[0481] Emotion recognition: Emotions are analyzed from the student's input text using a sentiment analysis algorithm.

[0482] Prompt-adjusting generation engine: Adjusts prompts based on emotion recognition results, generating prompts that provide encouragement or specific instructions as needed.

[0483] What the device does:

[0484] The terminal acts as the student interface and performs the following tasks:

[0485] Question input: Provide a chat box where students can enter questions about setting assignments, gathering information, etc.

[0486] Displaying formatted answers: Displaying formatted answers received from the server to students, allowing them to quickly move on to the next learning step.

[0487] What the user does:

[0488] The user (student) uses the above system to carry out the following learning process:

[0489] Entering questions: Enter any questions or issues that arise during the learning process into the chat box on your device.

[0490] Check the answer: Check the formatted answer from the server and use it as a reference for the next learning step.

[0491] Examples:

[0492] For example, if a student types a question like "I'm worried because I can't find any resources about environmental issues," the system will process it as follows:

[0493] 1. Accept Question: The server receives the student's input.

[0494] 2. Recognizing emotions: The server uses an emotion engine to recognize the emotion "anxiety."

[0495] 3. Generate a prompt: The generation engine takes this sentiment data into account to generate a prompt, such as "Please refer to the following steps. We will show you how to find resources related to environmental issues."

[0496] 4. Send to Natural Language Processing Model: The generated prompt is sent to a natural language processing model and an appropriate answer is received.

[0497] 5. Formatting the answer: For example, format the answer "Google Scholar and PubMed are useful" into a more relevant and understandable format for the question.

[0498] 6. Display on device: The formatted answer is displayed on the student's device, and a message is displayed saying, "Google Scholar and PubMed are useful."

[0499] Example prompt sentence:

[0500] Typed question: "I'm worried because I can't find any materials on environmental issues."

[0501] Generated prompt: "Let's use the following steps to help you find resources on environmental issues."

[0502] The natural language processing model answers: "Google Scholar and PubMed are useful."

[0503] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0504] Step 1:

[0505] Input: Students type their question into the chat box on their devices. Example: "I'm worried because I can't find any resources on environmental issues."

[0506] Action: The device sends this question to the server.

[0507] Output: The server receives the query.

[0508] Step 2:

[0509] Input: The query data received by the server.

[0510] How it works: The server sends the question text to the emotion engine, which recognizes the emotion.

[0511] Output: The emotion engine generates emotion data such as "anxiety" and sends it back to the server.

[0512] Step 3:

[0513] Input: Question data and sentiment data.

[0514] How it works: The server uses a generation engine to generate prompts based on the question and sentiment. Example: "Try these steps to help you find resources on environmental issues."

[0515] Output: The generated prompt.

[0516] Step 4:

[0517] Input: The generated prompt.

[0518] How it works: The server sends a prompt to the natural language processing model.

[0519] Output: Answer data from the natural language processing model. Example: "Google Scholar and PubMed are useful."

[0520] Step 5:

[0521] Input: Response data from a natural language processing model.

[0522] What it does: The server formats the answer data, for example by adding bullet points or specific examples. Example of a formatted answer: "Google Scholar and PubMed are useful."

[0523] Output: Formatted response data.

[0524] Step 6:

[0525] Input: Formatted response data.

[0526] What it does: The server sends a formatted response to the device.

[0527] Output: The formatted answer data is displayed on the terminal. Example: "Google Scholar and PubMed are useful."

[0528] Step 7:

[0529] Input: Formatted response data.

[0530] Action: The device displays the formatted answer data to the student.

[0531] Output: Helps students check their answers and guides them to the next step in their learning.

[0532] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0533] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0534] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0535] [Second embodiment]

[0536] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0537] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0538] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0539] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0540] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0541] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0542] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0543] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0544] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0545] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0546] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0547] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0548] This invention is a system that provides effective, individually optimized learning support for students as they progress through inquiry-based learning. The system accepts questions entered by students during the learning process regarding task setting, information gathering, data organization, and presentations, generates appropriate prompts corresponding to the questions, and provides answers using a natural language processing model.

[0549] composition

[0550] The system mainly consists of the following components:

[0551] 1. Method of accepting questions

[0552] The terminal accepts questions from students. Specifically, it provides a chat box-style user interface, allowing students to input questions about setting assignments, gathering information, etc.

[0553] 2. Prompt Generation Engine

[0554] The server generates appropriate prompts based on the questions received from students. The prompt generation engine dynamically generates prompts using templates tailored to each learning process.

[0555] 3. Natural Language Processing Model

[0556] The server generates prompts and sends them to a natural language processing model, which uses the most state-of-the-art model available today (e.g., GPT-3 or equivalent), and receives responses.

[0557] 4. Answer formatting means

[0558] The server formats the answers received from the natural language processing model, specifically by making the answers easier to understand and converting them into a format that is useful to the student.

[0559] 5. Display means

[0560] The device displays the formatted answer to the student, allowing them to quickly get the information they need and take action to move forward to the next step in their learning.

[0561] A natural language description of the program's operation

[0562] Question acceptance method

[0563] The user inputs a question during the learning process. For example, they input a question such as "I would like to set a research topic about environmental issues" into the chat box.

[0564] Prompt Generation Engine

[0565] The server receives questions from users and generates corresponding prompts based on templates for each process, such as problem setting, information gathering, data organization, and presentation.

[0566] Natural Language Processing Model

[0567] The server sends the generated prompt to a natural language processing model to obtain an answer. For example, if the prompt is "Which aspects of environmental issues are you concerned about?", the natural language processing model generates an answer such as "Air pollution, ocean pollution, deforestation, etc."

[0568] Answer formatting means

[0569] The server formats the answer it receives from the natural language processing model, for example by turning the answer into a bulleted list or adding specific examples.

[0570] Display means

[0571] The device displays the formatted answer in a user interface, allowing the user to proceed to the next learning step based on the displayed information.

[0572] Specific examples

[0573] For example, if a student types in a question like "I want to find the latest research on air pollution. Where can I find it?", the following happens:

[0574] 1. A user types a question: "I want to find the latest research on air pollution. Where can I find it?"

[0575] 2. The device sends a question to the server.

[0576] 3. The server uses a prompt generation engine to generate the prompt: "What are some reliable sources for finding the latest research materials?"

[0577] 4. The server sends the generated prompt to the natural language processing model.

[0578] 5. A natural language processing model generates the answer: "You can use a scholarly search engine such as Google Scholar or PubMed."

[0579] 6. The server receives and formats the response.

[0580] 7. The server sends the formatted response to the device.

[0581] 8. The device displays the answer in the user interface: "You might want to use a scholarly search engine such as Google Scholar or PubMed."

[0582] In this way, the system helps students to effectively engage in inquiry-based learning, allowing them to advance their learning by asking questions and obtaining answers on their own, without the need for a specialist escort.

[0583] The processing flow will be explained below.

[0584] Detailed steps in the assignment process

[0585] Step 1:

[0586] The user enters a question about setting a research topic into the chat box on the device. For example, the user might enter, "I would like to set a research topic about environmental issues. What perspective should I take?"

[0587] Step 2:

[0588] The terminal transmits the user's question to the server in real time. The transmitted data includes the question content and user information.

[0589] Step 3:

[0590] The server receives the question and passes it to a prompt generation engine, which identifies which process the question belongs to.

[0591] Step 4:

[0592] A prompt generation engine uses the challenge template to generate appropriate prompts, such as "What aspects of environmental issues interest you?"

[0593] Step 5:

[0594] The server sends the generated prompt to the natural language processing model (ChatGPT), along with the prompt and related information in the form of an API request.

[0595] Step 6:

[0596] A natural language processing model generates an answer based on the prompt, such as "Air pollution, marine pollution, deforestation, etc. Please choose the area that you are particularly interested in."

[0597] Step 7:

[0598] The server receives the answer from the natural language processing model, which is then formatted as needed.

[0599] Step 8:

[0600] The server then sends the formatted response to the terminal, which includes the response content and instructions for display.

[0601] Step 9:

[0602] The device displays the received answers in the user interface, and the user decides whether to ask further questions or proceed to the next step based on the information presented.

[0603] Detailed processing steps of the information gathering process

[0604] Step 1:

[0605] A user types a question about information gathering into a chat box on a terminal, for example, "I'd like to find the latest research materials on air pollution. Where can I find them?"

[0606] Step 2:

[0607] The terminal transmits the user's question to the server in real time.

[0608] Step 3:

[0609] The server receives the question and passes it to the prompt generation engine.

[0610] Step 4:

[0611] A prompt generation engine uses information-gathering templates to generate appropriate prompts, such as "What are some reliable sources for finding the latest research materials?"

[0612] Step 5:

[0613] The server sends the generated prompt to the natural language processing model (ChatGPT).

[0614] Step 6:

[0615] A natural language processing model generates an answer based on the prompt, such as "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[0616] Step 7:

[0617] The server receives the answer from the natural language processing model, which is then formatted as needed.

[0618] Step 8:

[0619] The server formats the response and sends it to the device.

[0620] Step 9:

[0621] The terminal displays the received answers on the user interface, allowing the user to begin searching for materials based on the presented information.

[0622] Detailed processing steps of the data reduction process

[0623] Step 1:

[0624] A user types a question about data organization into a chat box on the device, for example, "How should I organize the data for...?"

[0625] Step 2:

[0626] The terminal transmits the user's question to the server in real time.

[0627] Step 3:

[0628] The server receives the question and passes it to the prompt generation engine.

[0629] Step 4:

[0630] The prompt generation engine uses templates for data organization to generate appropriate prompts, such as "What are the basic techniques for data analysis?"

[0631] Step 5:

[0632] The server sends the generated prompt to the natural language processing model (ChatGPT).

[0633] Step 6:

[0634] A natural language processing model generates an answer based on the prompt, such as "Basic techniques for data analysis include graphing, statistical analysis, and regression analysis."

[0635] Step 7:

[0636] The server receives the answer from the natural language processing model, which is then formatted as needed.

[0637] Step 8:

[0638] The server formats the response and sends it to the device.

[0639] Step 9:

[0640] The device displays the received answers in a user interface, allowing the user to organize the data based on the presented information.

[0641] Detailed processing steps of the presentation process

[0642] Step 1:

[0643] A user types a question about the presentation into the chat box of the device, for example, "How should I structure my presentation?"

[0644] Step 2:

[0645] The terminal transmits the user's question to the server in real time.

[0646] Step 3:

[0647] The server receives the question and passes it to the prompt generation engine.

[0648] Step 4:

[0649] The prompt generation engine uses the presentation template to generate appropriate prompts, such as "How do I structure an effective presentation?"

[0650] Step 5:

[0651] The server sends the generated prompt to the natural language processing model (ChatGPT).

[0652] Step 6:

[0653] The natural language processing model generates an answer based on the prompt sent, for example, "The basic structure of a presentation has three parts: introduction, main body, and conclusion. The introduction explains the purpose and background, the main body provides details using data and examples, and the conclusion introduces the results and next steps."

[0654] Step 7:

[0655] The server receives the answer from the natural language processing model, which is then formatted as needed.

[0656] Step 8:

[0657] The server formats the response and sends it to the device.

[0658] Step 9:

[0659] The device displays the received answers on a user interface, allowing the user to prepare a presentation based on the information presented.

[0660] Example 1

[0661] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0662] In today's educational environment, there is a lack of appropriate support tailored to each student's individual learning progress and level of understanding, and students often find it difficult to engage in independent inquiry-based learning. Furthermore, limited teacher and instructor resources mean that individualized instruction is difficult to provide. Furthermore, there are few ways for students to receive appropriate learning support in real time, which can result in a decline in learning efficiency.

[0663] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0664] In this invention, the server includes means for accepting questions entered by students in the course of their studies regarding task setting, information gathering, data organization, and presentations, means for generating appropriate prompts using a generation engine corresponding to the content of the questions, means for sending the generated prompts to a natural language processing model and receiving answers, and means for formatting the received answers and sending them to the student's terminal for display. This allows students to receive individual learning support in real time, enabling them to effectively advance independent inquiry-based learning.

[0665] "Student" means a person who belongs to an educational institution and engages in learning activities.

[0666] "Learning process" refers to the steps of learning activities such as setting a task, gathering information, organizing data, and making a presentation.

[0667] "Questions" are content related to doubts or issues that students have while studying.

[0668] A "prompt generation engine" is a system that automatically generates appropriate prompts based on the questions it receives.

[0669] A "prompt" is a sentence that is sent to a natural language processing model to get an answer to a question.

[0670] A "natural language processing model" refers to an algorithm that understands natural language and generates an answer based on input text.

[0671] An "answer" is a response sentence that a natural language processing model generates based on a prompt.

[0672] "Formatting" is the process of converting the answers received into a format that is easy to read and understand.

[0673] "Device" refers to devices used by students, such as computers, tablets, and smartphones.

[0674] "Educational support system" refers to the entire system designed to enable students to receive individually optimized learning support.

[0675] MODE FOR CARRYING OUT THE INVENTION

[0676] The present invention is an educational support system that provides individually optimized learning support to students as they progress through inquiry-based learning. This system accepts questions entered by students during the learning process regarding task setting, information gathering, data organization, and presentations, generates appropriate prompts based on the content of the questions, and provides answers using a natural language processing model. Specific embodiments of this system are described below.

[0677] Hardware and Software Configuration

[0678] The system mainly consists of the following components:

[0679] 1. Device: A device used by a student, such as a computer, tablet, or smartphone. The device provides a chat box-style input field as a user interface.

[0680] 2. Server: A backend system for implementing the prompt generation engine and natural language processing model. The server is responsible for receiving questions, parsing them, generating prompts, sending them to the natural language processing model, formatting answers, and sending the formatted answers.

[0681] 3. Natural language processing models: For example, generative AI models like GPT-3, which are used to generate answers to students' questions.

[0682] Data processing and calculation

[0683] 1. Acceptance and submission:

[0684] The user (student) inputs questions they have during their studies into the terminal. For example, a student might input, "I want to find the latest research materials on air pollution."

[0685] The device sends the question to the server in real time, using JSON data or other formats.

[0686] 2. Prompt generation:

[0687] The server analyzes the question received from the user and generates an appropriate prompt using a prompt generation engine.

[0688] If the question is "I want to find the latest research on air pollution," the generated prompt will be "What are some reliable sources for finding the latest research?"

[0689] 3. Sending prompts and generating answers:

[0690] The server sends the generated prompt to a natural language processing model (such as GPT-3) using an API request.

[0691] A natural language processing model generates an appropriate answer based on the prompt and returns it to the server, such as "You might want to use a scholarly article search engine such as Google Scholar or PubMed."

[0692] 4. Formatting the answer:

[0693] The server formats the answers received from the natural language processing model, specifically converting the answers into an easy-to-read format (such as bullet points or adding specific examples).

[0694] The formatted content is converted into JSON or another appropriate data format and sent to the terminal.

[0695] 5. Show Answer:

[0696] The device receives a formatted answer from the server and displays it to the student in an easy-to-understand manner. For example, it might say, "You might want to use a scholarly paper search engine such as Google Scholar or PubMed."

[0697] Specific examples

[0698] For example, if a student types a question like "What are some tips for giving a successful presentation?", the process would go something like this:

[0699] 1. User types question: "What are some tips for giving a successful presentation?"

[0700] 2. The device sends the question to the server.

[0701] 3. The server parses the question and generates an appropriate prompt: "What specific tips can I use to give a successful presentation?"

[0702] 4. The server sends the generated prompt to the natural language processing model.

[0703] 5. The natural language processing model generates answers such as "set clear goals, practice, and use visual aids."

[0704] 6. The server formats the response and sends it to the device.

[0705] 7. The device displays formatted answers to students: "Successful presentations require clear goals, practice, and the use of visual aids."

[0706] In this way, the present invention enables students to receive individually optimized learning support, and provides support for effectively promoting inquiry-based learning.

[0707] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0708] Step 1:

[0709] Enter and submit your question

[0710] The user inputs questions they have during their learning process into the device, for example, "I want to find the latest research materials on air pollution."

[0711] The device converts the entered question into JSON data format and sends it to the server in real time using WebSocket or HTTP requests.

[0712] Input: A text question: "I would like to find the latest research on air pollution."

[0713] Output: The question data sent to the server is converted to JSON format.

[0714] Step 2:

[0715] Question Analysis

[0716] The server receives the question sent from the device and analyzes the question, extracting important keywords and context from the question.

[0717] The server analyzes the question data and prepares it to generate appropriate prompts, for example by extracting keywords such as "air pollution" and "latest research materials."

[0718] Input: A JSON question: "I want to find the latest research on air pollution."

[0719] Output: Analysis results (e.g. keywords and contextual information) for use by the prompt generation engine.

[0720] Step 3:

[0721] Prompt Generation

[0722] The server uses a prompt generation engine to generate an appropriate prompt based on the analysis results, for example, "What are some reliable sources for finding the latest research materials?"

[0723] Input: Analysis results (e.g., keywords and context information).

[0724] Output: The generated prompt (the text reads "What reliable sources can I use to find the latest research materials?").

[0725] Step 4:

[0726] Sending a prompt

[0727] The server sends the generated prompt to the natural language processing model (generative AI model), passing the prompt to the model in the form of an API request.

[0728] Input: Generated prompt (e.g., "What reliable sources can I use to find the latest research materials?").

[0729] Output: The prompt data sent to the natural language processing model.

[0730] Step 5:

[0731] Generating and receiving answers

[0732] A natural language processing model generates an answer based on the prompt it receives, such as "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[0733] The natural language processing model returns the generated answer to the server.

[0734] Input: Submitted prompt ("What reliable sources can I use to find the latest research materials?").

[0735] Output: The generated answer (e.g., "You may find it helpful to use a scholarly search engine such as Google Scholar or PubMed").

[0736] Step 6:

[0737] Formatting answers

[0738] The server formats the answer received from the natural language processing model, converting the answer into an easy-to-read format and adding bullet points and specific examples as needed.

[0739] Input: A generated answer (e.g., "You might want to use a scholarly search engine such as Google Scholar or PubMed").

[0740] Output: A formatted answer (e.g., "You may find it helpful to use a scholarly search engine such as Google Scholar or PubMed." "Examples: Google Scholar, PubMed").

[0741] Step 7:

[0742] Show Answers

[0743] The terminal displays the formatted response received from the server in a user interface, for example, in a chat box.

[0744] Input: A formatted answer (e.g., "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed.").

[0745] Output: User-visible display of answers.

[0746] (Application example 1)

[0747] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0748] Conventional learning support systems have had the problem of being unable to provide appropriate information and support in a timely manner for the challenges that students face individually.In addition, when students independently engage in inquiry-based learning, it is difficult for them to know how to access reliable information sources or how to gather appropriate information, which can slow down their learning progress.

[0749] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0750] In this invention, the server includes means for accepting questions related to task setting, information gathering, data organization, and presentations entered by students in the course of their studies, means for generating appropriate prompts using a generation engine corresponding to the content of the questions, means for sending the generated prompts to a natural language processing model and receiving answers, means for formatting the received answers and sending them to the student's terminal for display, and means for providing learning support through a content distribution service. This enables students to quickly and effectively obtain appropriate information related to the content of their studies.

[0751] "Problem setting" is the process by which students decide on a specific theme or question to be solved during the learning process.

[0752] "Information gathering" is the activity of gathering relevant data and knowledge based on the problem setting.

[0753] "Data organization" is the process of classifying, analyzing, and organizing collected information into an easy-to-understand format.

[0754] A "presentation" is the act of organizing the results of learning and presenting them to others in an easy-to-understand manner.

[0755] A "generation engine" is a system component that generates appropriate prompts based on the input question.

[0756] A "prompt" is an input sentence that gives instructions to a natural language processing model.

[0757] A "natural language processing model" is an AI technology that understands and generates human language.

[0758] "Answer formatting" is the process of organizing the answers received from a natural language processing model in an easy-to-read format.

[0759] A "terminal" is an electronic device that allows a user to input information and display results.

[0760] A "content distribution service" is a platform for providing information to users via the Internet.

[0761] This invention is a system that provides optimal individualized learning support to students as they progress through inquiry-based learning. The system accepts questions about task setting, information gathering, data organization, and presentations, and provides appropriate answers to those questions.

[0762] Hardware and software used

[0763] The hardware required to implement this system includes a smartphone, tablet, or personal computer. It also requires connection to a server, terminal, and user interface. The software used is Python, the OpenAI API, and a front-end framework (React, Flutter, etc.).

[0764] System Components

[0765] 1. How to contact us:

[0766] The device (e.g., a smartphone or PC) accepts questions from students through a chat box-style user interface. For example, a student might type in a question like, "I want to find the latest research materials on air pollution. Where should I look for them?"

[0767] 2. Prompt generation engine:

[0768] The server generates an appropriate prompt based on the question it receives. For example, after receiving a question, the server generates a prompt like, "Please explain in detail the following question that interests you: I'd like to find the latest research on air pollution. Where can I find it?"

[0769] 3. Natural Language Processing Models:

[0770] The server sends the generated prompt to a natural language processing model (e.g., OpenAI's GPT-3) and receives an answer from the model, such as, "You can use academic paper search engines such as Google Scholar or PubMed. You can use the filter function when searching for papers to find the latest research."

[0771] 4. Answer formatting method:

[0772] The server formats the answers it receives from the natural language processing model to make them easier to read, for example by editing the answers to make them easier to understand, bulleting important information, and adding examples.

[0773] 5. Display means:

[0774] The device will then display the formatted answer in a user interface. For example, the student's device might say, "You can use academic paper search engines such as Google Scholar or PubMed. Use the filter function when searching for papers to find the latest research."

[0775] By providing learning support through a content delivery service, students can quickly and effectively acquire the right information related to their learning. The system utilizes cutting-edge generative AI models and prompting technology to ensure optimal learning support is always provided to students.

[0776] Specific examples

[0777] For example, if a student types a question like this:

[0778] "I want to find the latest research on air pollution. Where can I find it?"

[0779] The system responds to this question in the following way:

[0780] 1. The device accepts the question.

[0781] 2. The server uses the prompt generation engine to generate the following prompt:

[0782] "Please explain in detail the following question that interests you: I would like to find the latest research materials on air pollution. Where can I find them?"

[0783] 3. The server sends the generated prompt to a natural language processing model and receives a response such as:

[0784] "You can use academic search engines like Google Scholar and PubMed, which have filters to help you find the latest research."

[0785] 4. The server formats the response it receives and sends it to the terminal for display.

[0786] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0787] Step 1:

[0788] During the learning process, the user enters questions or concerns into a chat box-style user interface. For example, the user might enter a question like, "I want to find the latest research materials on air pollution. Where should I look for them?" This input is recorded on the terminal as a string of characters.

[0789] Step 2:

[0790] The terminal sends the input question data to the server, where it is received and analyzed.

[0791] Step 3:

[0792] The server starts a prompt generation engine based on the received question. The question data received as input is passed to the prompt generation engine, which generates an appropriate prompt based on that. For example, this prompt might be in the form of "Please explain in detail the following question that interests you: I want to find the latest research materials on air pollution. Where can I find them?" The generated prompt is recorded as a string.

[0793] Step 4:

[0794] The server sends the generated prompt string to a natural language processing model, such as a generative AI model like GPT-3, which generates an answer based on the received prompt. The model uses the prompt data as input and generates an appropriate answer as output.

[0795] Step 5:

[0796] The server receives the answer output from the natural language processing model and passes it to the answer formatting engine. The answer formatting engine formats the received answer into an easy-to-understand format, for example by turning sentences into bullet points or adding specific examples. This formatting process generates an answer that is easy to understand and organized.

[0797] Step 6:

[0798] The server sends the formatted answers to the device, which then displays the received answer data on its user interface. For example, the student's screen might read, "We recommend using academic paper search engines such as Google Scholar or PubMed. Use the filter function when searching for papers to find the latest research."

[0799] Step 7:

[0800] The user reviews the displayed answers and decides on the next action to take, such as actually searching for the latest research materials using an academic paper search engine.

[0801] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0802] This invention is a system that provides effective, individually optimized learning support for students as they progress through inquiry-based learning. In particular, by combining it with an emotion engine that recognizes students' emotions and optimizes the learning process, it achieves more advanced support.

[0803] composition

[0804] The system mainly consists of the following components:

[0805] 1. Method of accepting questions

[0806] The terminal accepts questions from students. Specifically, it provides a chat box-style user interface, allowing students to input questions about setting assignments, gathering information, etc.

[0807] 2. Prompt Generation Engine

[0808] The server generates appropriate prompts based on the questions received from students. The prompt generation engine dynamically generates prompts using templates tailored to each learning process.

[0809] 3. Natural Language Processing Model

[0810] The server generates prompts and sends them to a natural language processing model, which uses the most advanced models available today, to receive responses.

[0811] 4. Answer formatting means

[0812] The server formats the answers received from the natural language processing model, specifically by making the answers easier to understand and converting them into a format that is useful to the student.

[0813] 5. Display means

[0814] The device displays the formatted answer to the student, allowing them to quickly get the information they need and move on to the next step in their learning.

[0815] 6. Emotion Engine

[0816] The server recognizes emotions from the user's input text and voice. The emotion engine uses emotion analysis algorithms to understand the student's emotional state.

[0817] 7. Emotion-linked prompt generation

[0818] The server uses the emotion engine to generate prompts based on the emotion data it receives. For example, if a negative emotion is detected, it generates an encouraging prompt.

[0819] A natural language description of the program's operation

[0820] Question acceptance method

[0821] The user inputs a question during the learning process. For example, they input a question such as "I would like to set a research topic about environmental issues" into the chat box.

[0822] Prompt Generation Engine

[0823] The server receives questions from users and generates corresponding prompts based on templates for each process, such as problem setting, information gathering, data organization, and presentation.

[0824] Natural Language Processing Model

[0825] The server sends the generated prompt to a natural language processing model to obtain an answer. For example, if the prompt is "Which aspects of environmental issues are you interested in?", the natural language processing model generates an answer such as "Air pollution, marine pollution, deforestation, etc."

[0826] Answer formatting means

[0827] The server formats the answer it receives from the natural language processing model, for example by turning the answer into a bulleted list or adding specific examples.

[0828] Display means

[0829] The device displays the formatted answer in a user interface, and the user decides based on the displayed information whether to ask further questions or proceed to the next step.

[0830] Adding emotion engine processing

[0831] emotion recognition

[0832] The server sends the user's input text and voice to the emotion engine, which then analyzes the text and voice to determine the user's emotional state (stress, joy, excitement, anxiety, etc.).

[0833] Emotion-linked prompt generation

[0834] The server uses the emotion data obtained from the emotion engine to generate emotion-linked prompts. For example, if a user enters "I'm having trouble finding research materials on air pollution" and the emotion engine detects "anxiety," the prompt generation engine will provide support such as, "First, try some reliable sources of information. If necessary, please refer to this guide."

[0835] Specific examples

[0836] For example, if a student types a question like "I'd like to find the latest research on air pollution, but I don't know where to start," the following happens:

[0837] 1. A user types a question: "I'm looking for the latest research on air pollution, but I don't know where to start."

[0838] 2. The device sends a question to the server.

[0839] 3. The server receives the question and passes it to the prompt generation engine.

[0840] 4. The emotion engine analyzes emotions from the question text and detects "anxiety."

[0841] 5. The prompt generation engine takes sentiment data into account to generate an appropriate prompt: "Let's start by trying some trusted sources, such as Google Scholar and PubMed."

[0842] 6. The server sends the prompt to the natural language processing model.

[0843] 7. Natural language processing models generate relevant answers: "You can use a scholarly search engine such as Google Scholar or PubMed."

[0844] 8. The server receives and formats the response.

[0845] 9. The server sends the formatted response to the device.

[0846] 10. The device displays the answer it receives in the user interface: "You may find it helpful to use a scholarly paper search engine such as Google Scholar or PubMed."

[0847] In this way, the system helps students to effectively engage in inquiry-based learning and provides special support based on emotion recognition, making students feel more at ease and empowering them to ask and answer their own questions.

[0848] The processing flow will be explained below.

[0849] Detailed steps in the question acceptance and prompt generation process

[0850] Step 1:

[0851] During the learning process, the user can input a question, for example, "I want to find the latest research on air pollution, but I don't know where to start" into the chat box.

[0852] Step 2:

[0853] The device sends the user's question to the server in real time, including the question content and the user ID.

[0854] Step 3:

[0855] The server receives the user's question and sends the text data to the emotion engine.

[0856] Step 4:

[0857] The emotion engine analyzes the received text data and recognizes the user's emotional state, for example, detecting "anxiety."

[0858] Step 5:

[0859] The server passes the emotion data obtained from the emotion engine to the prompt generation engine, along with the question content and the emotional state.

[0860] Step 6:

[0861] The prompt generation engine generates appropriate prompts based on sentiment data and the question itself, such as "Let's start by trying some trusted sources, such as Google Scholar and PubMed."

[0862] Step 7:

[0863] The server sends the generated prompt to the natural language processing model in the form of an API request.

[0864] Step 8:

[0865] A natural language processing model generates an answer based on the prompt received, such as "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[0866] Step 9:

[0867] The server formats the answers it receives from the natural language processing model, for example by adding bullet points to the answer or highlighting important information.

[0868] Step 10:

[0869] The server then sends the formatted response to the user's terminal, where the formatted response data is sent.

[0870] Step 11:

[0871] The device displays the received answer on the user interface, and the user can decide whether to ask further questions or proceed to the next step based on the displayed information.

[0872] Specific examples

[0873] As a specific example, the following describes in detail how a student would respond if they typed in a question such as, "I want to find the latest research materials on air pollution, but I don't know where to look."

[0874] Step 1:

[0875] A user types a question: "I'm looking for the latest research on air pollution, but I don't know where to start."

[0876] Step 2:

[0877] The device sends the user's question to the server. The sent data includes the user ID and the question.

[0878] Step 3:

[0879] The server receives the question and sends the text data to the emotion engine.

[0880] Step 4:

[0881] The emotion engine analyzes emotions from the question text and detects "anxiety."

[0882] Step 5:

[0883] The server passes the emotional data and question content to the prompt generation engine. The data includes the question content, "I want to find the latest research materials on air pollution, but I don't know where to look," and the emotional state, "anxiety."

[0884] Step 6:

[0885] The prompt generation engine generates appropriate prompts based on the sentiment and question content, such as "Let's start by trying some reliable sources, such as Google Scholar and PubMed."

[0886] Step 7:

[0887] The server sends the generated prompt to the natural language processing model (ChatGPT), which sends the prompt in the form of an API request.

[0888] Step 8:

[0889] A natural language processing model generates an answer based on the prompt, for example, "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[0890] Step 9:

[0891] The server formats the answer received from the natural language processing model, for example by turning the answer into a list of items.

[0892] Step 10:

[0893] The server then sends the formatted response to the user's terminal. The transmitted data includes the formatted response.

[0894] Step 11:

[0895] The device displays the received answer on the user interface. For example, it may say, "We recommend using academic paper search engines such as Google Scholar or PubMed." The user can then begin searching for materials based on the information provided.

[0896] In this way, the system helps students to effectively engage in inquiry-based learning. In particular, by providing special support based on emotion recognition, students can feel more at ease while studying.

[0897] Example 2

[0898] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0899] Conventional learning support systems lacked adequate support for each student's learning situation and emotional state, making it difficult for students to effectively engage in inquiry-based learning. Furthermore, because they did not provide individually optimized learning support, they were unable to reduce the anxiety and stress students felt during the learning process.

[0900] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0901] In this invention, the server includes means for generating appropriate prompts using a generation engine corresponding to the content of the question, means for sending the generated prompts to a natural language processing model and receiving answers, means for formatting the received answers and sending them to the student's terminal for display, and means for recognizing emotions from the student's input text or voice and generating prompts based on that emotion data, thereby enabling individually optimal support according to the learning situation and emotional state of each student.

[0902] "Student" refers to a learner who uses this system to engage in inquiry-based learning.

[0903] The "question acceptance means" is a component for accepting questions from students regarding assignment setting, information gathering, data organization, and presentations.

[0904] The "generation engine" is a component that generates an appropriate prompt based on the content of the received question.

[0905] A "prompt" is an instruction or question generated by a generation engine and sent to a natural language processing model.

[0906] A "natural language processing model" is an AI model that generates answers based on generated prompts.

[0907] The "answer formatting means" is a component for organizing and formatting the answers received from the natural language processing model in an easy-to-understand manner.

[0908] The "emotion engine" is an algorithm that recognizes emotions from text and voice input by students and extracts that emotional data.

[0909] The "emotion-linked prompt generation means" is a means for generating a prompt based on emotion data obtained from the emotion engine.

[0910] "Terminal" means the device used by a student to enter questions and view answers from the system.

[0911] "Display means" refers to the functionality for visually presenting formatted answers to students.

[0912] This invention relates to a learning support system that effectively supports students' inquiry-based learning by accepting questions about task setting, information gathering, data organization, and presentations entered by students during the learning process and providing appropriate answers. In particular, it uses an emotion engine to analyze students' emotions and generates prompts based on those emotions to provide individually optimized learning support.

[0913] component

[0914] The system includes the following main components:

[0915] 1. Method of accepting questions

[0916] 2. Prompt Generation Engine

[0917] 3. Natural Language Processing Models (NLP Models)

[0918] 4. Answer formatting means

[0919] 5. Emotion Engine

[0920] 6. Emotion-linked prompt generation method

[0921] 7. Display means

[0922] Question acceptance method

[0923] While studying, students enter questions and challenges using a chat box-style user interface, which is provided by a software application running on a PC, tablet, smartphone, or other device. For example, a student might enter, "Tell me about the types of renewable energy."

[0924] Prompt Generation Engine

[0925] The server receives a question from the user and generates an appropriate prompt. The engine uses a template that corresponds to the question, generating prompts such as "What aspects of environmental issues are you interested in?" or "What are some reliable sources of information on environmental issues?"

[0926] Natural Language Processing Model

[0927] The generated prompt is sent from the server to a natural language processing model (e.g., GPT-4), which generates an appropriate answer based on the prompt. For example, it generates an answer such as, "There are solar power, wind power, hydroelectric power, and biomass power generation."

[0928] Answer formatting means

[0929] The server formats the answers it receives from the NLP model, which may include bulleting the answer, adding specific examples, and highlighting important information, such as "The following are the types of renewable energy:\n1. Solar power\n2. Wind power\n3. Hydroelectric power\n4. Biomass power."

[0930] Emotion Engine

[0931] The emotion engine analyzes user-supplied text and voice input to recognize emotional states (e.g., stress, joy, anxiety), for example using the Emotion API or similar algorithms.

[0932] Emotion-linked prompt generation method

[0933] Based on the emotional data obtained from the emotion engine, the prompt generation engine generates prompts according to the user's emotional state. For example, if a user types, "I'm having trouble finding research materials on air pollution," and anxiety is detected, the prompt will be adjusted to provide support such as, "Let's start by trying some reliable sources."

[0934] Display means

[0935] The formatted answer is sent from the server to the device and displayed on the user interface. The user can confirm the displayed answer and then enter further questions or proceed to the next step. For example, it might say, "The following are the types of renewable energy:\n1. Solar power generation\n2. Wind power generation\n3. Hydroelectric power generation\n4. Biomass power generation."

[0936] By combining the above components and their interaction, this invention can effectively support students' inquiry-based learning and provide individually optimized learning support.

[0937] Examples of prompt statements

[0938] 1. "What aspects of environmental issues interest you?"

[0939] 2. "What are some reliable sources of information on environmental issues?"

[0940] 3. "What are the main types of renewable energy?"

[0941] These prompts can be used to effectively obtain useful information from generative AI models.

[0942] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0943] Step 1: Enter your question

[0944] While studying, users input questions or problems using a chat box-style user interface. Specifically, they input text such as "Please tell me about the types of renewable energy" into an application running on a device such as a PC or smartphone. This input triggers the processing of the entire system.

[0945] Step 2: Submit your question

[0946] The terminal sends the user's question to the server. An HTTP POST request is often used here. Specifically, a data packet containing the question text entered by the user is sent to the server. The input is the user's question text, and the output is a response indicating that the data transfer to the server is complete.

[0947] Step 3: Prompt generation

[0948] The server passes the received question to the prompt generation engine, which generates an appropriate prompt based on a pre-configured template. For example, it generates a prompt such as "Please provide more information about renewable energy." The input is the question data received by the server, and the output is the generated prompt.

[0949] Step 4: Sentiment analysis

[0950] The server sends the question text to the emotion engine, which then analyzes it. The emotion engine uses a text analysis algorithm to recognize the user's emotions. For example, it can detect emotions such as "troubled" or "anxious." The input is the question text sent from the server, and the output is the emotion data resulting from the analysis.

[0951] Step 5: Emotion-linked prompt generation

[0952] Based on the emotion data received by the server from the emotion engine, the prompt generation engine generates a prompt according to the emotion. For example, if the server detects that the user is "in trouble," it creates a prompt such as "Let's start with some basic information." The input is emotion data and the original question, and the output is an emotion-linked prompt.

[0953] Step 6: Send prompts

[0954] The server sends the generated prompt to the natural language processing model (NLP model). Specifically, the prompt is sent to the natural language processing API via an HTTP request. The input is the generated prompt, and the output is a confirmation that the request was sent to the NLP model.

[0955] Step 7: Get the answer

[0956] The server receives the answer generated by the natural language processing model. For example, the NLP model might answer, "There are solar power, wind power, hydroelectric power, and biomass power generation." The input is the data returned by the NLP model, and the output is the answer data.

[0957] Step 8: Formatting your answers

[0958] The server then formats the answer it receives, making it easier for the user to understand. Specifically, it may do things like bullet points or insert additional information. For example, it may format the answer into something like "The following are the types of renewable energy:\n1. Solar power\n2. Wind power\n3. Hydroelectric power\n4. Biomass power." The input is the answer received from the NLP, and the output is the formatted answer.

[0959] Step 9: Submit your response

[0960] The server sends the formatted answer to the terminal as an HTTP response. The input is the formatted answer data, and the output is a response indicating that data transfer to the terminal is complete.

[0961] Step 10: Display answers

[0962] The terminal displays the received answer in the user interface. Specifically, the formatted answer is displayed in a chat box so that the user can see it. For example, it displays "The following are the types of renewable energy:\n1. Solar power generation\n2. Wind power generation\n3. Hydroelectric power generation\n4. Biomass power generation." The input is the answer data sent from the server, and the output is the visualized state provided to the user.

[0963] (Application example 2)

[0964] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0965] Conventional learning support systems have difficulty addressing students' psychological burdens and emotional needs, resulting in insufficient optimization of learning. Furthermore, they are unable to provide prompts and answers tailored to each student's learning progress and emotional state, and can only provide uniform support. This makes it difficult for students to progress effectively in their studies.

[0966] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for accepting questions related to task setting, information gathering, data organization, and presentations entered by students in the course of their studies; means for generating appropriate prompts using a generation engine corresponding to the content of the questions; means for sending the generated prompts to a natural language processing model and receiving answers; means for formatting the received answers and sending them to the student's terminal for display; means for recognizing emotions from the input text; and means including a generation engine for adjusting the prompts according to the recognized emotions. This enables optimal support to be provided according to each student's individual learning progress and emotional state.

[0967] "Problem setting" refers to the specific learning goals or problems that students set at the beginning of the learning process.

[0968] "Information gathering" refers to the act of collecting data and materials necessary for the learning process.

[0969] "Data organization" refers to the act of classifying and organizing collected information and processing it into a format that is easy to use.

[0970] A "presentation" is a means of communicating information to explain and announce the results of learning to others.

[0971] "Means for accepting questions" refers to the interface that allows the system to accept questions entered by students.

[0972] A "generation engine" is a program that generates appropriate prompts based on the student's question.

[0973] "Prompts" are instructions or questions generated by the system in response to students' questions or learning progress.

[0974] A "natural language processing model" is a machine learning algorithm for processing and understanding human language.

[0975] The "means for receiving an answer" refers to an interface for receiving an answer generated from a natural language processing model.

[0976] A "response formatter" is a program that converts the received responses into a format that is easy for students to understand.

[0977] A "terminal" is a device used by students to operate the learning support system.

[0978] An "emotion recognition means" is a program that analyzes a student's emotional state from input text.

[0979] A "prompt-adjusting generation engine" is a program that adjusts the content and expression of the prompt depending on the recognized emotion.

[0980] This invention is a system for providing learning support services in a physical store. The system is mainly composed of three entities: a server, a terminal, and a user. The roles and processing contents of each entity are explained below.

[0981] What the server does:

[0982] The server is the central processing unit and contains the following components:

[0983] A means of accepting questions: Receives and records questions entered by students. A chat box-style user interface is used in this section.

[0984] Generation engine: Generates appropriate prompts based on the question content. When generating prompts, templates corresponding to each learning process are used.

[0985] Natural Language Processing Model: The generated prompt is sent to a natural language processing model that uses the latest machine learning algorithms to receive an answer.

[0986] Formatting responses: Format the responses you receive in a way that is easier for students to understand. For example, add bullet points or examples.

[0987] Emotion recognition: Emotions are analyzed from the student's input text using a sentiment analysis algorithm.

[0988] Prompt-adjusting generation engine: Adjusts prompts based on emotion recognition results, generating prompts that provide encouragement or specific instructions as needed.

[0989] What the device does:

[0990] The terminal acts as the student interface and performs the following tasks:

[0991] Question input: Provide a chat box where students can enter questions about setting assignments, gathering information, etc.

[0992] Displaying formatted answers: Displaying formatted answers received from the server to students, allowing them to quickly move on to the next learning step.

[0993] What the user does:

[0994] The user (student) uses the above system to carry out the following learning process:

[0995] Entering questions: Enter any questions or issues that arise during the learning process into the chat box on your device.

[0996] Check the answer: Check the formatted answer from the server and use it as a reference for the next learning step.

[0997] Examples:

[0998] For example, if a student types a question like "I'm worried because I can't find any resources about environmental issues," the system will process it as follows:

[0999] 1. Accept Question: The server receives the student's input.

[1000] 2. Recognizing emotions: The server uses an emotion engine to recognize the emotion "anxiety."

[1001] 3. Generate a prompt: The generation engine takes this sentiment data into account to generate a prompt, such as "Please refer to the following steps. We will show you how to find resources related to environmental issues."

[1002] 4. Send to Natural Language Processing Model: The generated prompt is sent to a natural language processing model and an appropriate answer is received.

[1003] 5. Formatting the answer: For example, format the answer "Google Scholar and PubMed are useful" into a more relevant and understandable format for the question.

[1004] 6. Display on device: The formatted answer is displayed on the student's device, and a message is displayed saying, "Google Scholar and PubMed are useful."

[1005] Example prompt sentence:

[1006] Typed question: "I'm worried because I can't find any materials on environmental issues."

[1007] Generated prompt: "Let's use the following steps to help you find resources on environmental issues."

[1008] The natural language processing model answers: "Google Scholar and PubMed are useful."

[1009] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1010] Step 1:

[1011] Input: Students type their question into the chat box on their devices. Example: "I'm worried because I can't find any resources on environmental issues."

[1012] Action: The device sends this question to the server.

[1013] Output: The server receives the query.

[1014] Step 2:

[1015] Input: The query data received by the server.

[1016] How it works: The server sends the question text to the emotion engine, which recognizes the emotion.

[1017] Output: The emotion engine generates emotion data such as "anxiety" and sends it back to the server.

[1018] Step 3:

[1019] Input: Question data and sentiment data.

[1020] How it works: The server uses a generation engine to generate prompts based on the question and sentiment. Example: "Try these steps to help you find resources on environmental issues."

[1021] Output: The generated prompt.

[1022] Step 4:

[1023] Input: The generated prompt.

[1024] How it works: The server sends a prompt to the natural language processing model.

[1025] Output: Answer data from the natural language processing model. Example: "Google Scholar and PubMed are useful."

[1026] Step 5:

[1027] Input: Response data from a natural language processing model.

[1028] What it does: The server formats the answer data, for example by adding bullet points or specific examples. Example of a formatted answer: "Google Scholar and PubMed are useful."

[1029] Output: Formatted response data.

[1030] Step 6:

[1031] Input: Formatted response data.

[1032] What it does: The server sends a formatted response to the device.

[1033] Output: The formatted answer data is displayed on the terminal. Example: "Google Scholar and PubMed are useful."

[1034] Step 7:

[1035] Input: Formatted response data.

[1036] Action: The device displays the formatted answer data to the student.

[1037] Output: Helps students check their answers and guides them to the next step in their learning.

[1038] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1039] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1040] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1041] [Third embodiment]

[1042] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1043] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1044] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1045] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1046] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1047] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1048] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1049] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1050] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1051] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1052] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1053] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1054] This invention is a system that provides effective, individually optimized learning support for students as they progress through inquiry-based learning. The system accepts questions entered by students during the learning process regarding task setting, information gathering, data organization, and presentations, generates appropriate prompts corresponding to the questions, and provides answers using a natural language processing model.

[1055] composition

[1056] The system mainly consists of the following components:

[1057] 1. Method of accepting questions

[1058] The terminal accepts questions from students. Specifically, it provides a chat box-style user interface, allowing students to input questions about setting assignments, gathering information, etc.

[1059] 2. Prompt Generation Engine

[1060] The server generates appropriate prompts based on the questions received from students. The prompt generation engine dynamically generates prompts using templates tailored to each learning process.

[1061] 3. Natural Language Processing Model

[1062] The server generates prompts and sends them to a natural language processing model, which uses the most state-of-the-art model available today (e.g., GPT-3 or equivalent), and receives responses.

[1063] 4. Answer formatting means

[1064] The server formats the answers received from the natural language processing model, specifically by making the answers easier to understand and converting them into a format that is useful to the student.

[1065] 5. Display means

[1066] The device displays the formatted answer to the student, allowing them to quickly get the information they need and take action to move forward to the next step in their learning.

[1067] A natural language description of the program's operation

[1068] Question acceptance method

[1069] The user inputs a question during the learning process. For example, they input a question such as "I would like to set a research topic about environmental issues" into the chat box.

[1070] Prompt Generation Engine

[1071] The server receives questions from users and generates corresponding prompts based on templates for each process, such as problem setting, information gathering, data organization, and presentation.

[1072] Natural Language Processing Model

[1073] The server sends the generated prompt to a natural language processing model to obtain an answer. For example, if the prompt is "Which aspects of environmental issues are you concerned about?", the natural language processing model generates an answer such as "Air pollution, ocean pollution, deforestation, etc."

[1074] Answer formatting means

[1075] The server formats the answer it receives from the natural language processing model, for example by turning the answer into a bulleted list or adding specific examples.

[1076] Display means

[1077] The device displays the formatted answer in a user interface, allowing the user to proceed to the next learning step based on the displayed information.

[1078] Specific examples

[1079] For example, if a student types in a question like "I want to find the latest research on air pollution. Where can I find it?", the following happens:

[1080] 1. A user types a question: "I want to find the latest research on air pollution. Where can I find it?"

[1081] 2. The device sends a question to the server.

[1082] 3. The server uses a prompt generation engine to generate the prompt: "What are some reliable sources for finding the latest research materials?"

[1083] 4. The server sends the generated prompt to the natural language processing model.

[1084] 5. A natural language processing model generates the answer: "You can use a scholarly search engine such as Google Scholar or PubMed."

[1085] 6. The server receives and formats the response.

[1086] 7. The server sends the formatted response to the device.

[1087] 8. The device displays the answer in the user interface: "You might want to use a scholarly search engine such as Google Scholar or PubMed."

[1088] In this way, the system helps students to effectively engage in inquiry-based learning, allowing them to advance their learning by asking questions and obtaining answers on their own, without the need for a specialist escort.

[1089] The processing flow will be explained below.

[1090] Detailed steps in the assignment process

[1091] Step 1:

[1092] The user enters a question about setting a research topic into the chat box on the device. For example, the user might enter, "I would like to set a research topic about environmental issues. What perspective should I take?"

[1093] Step 2:

[1094] The terminal transmits the user's question to the server in real time. The transmitted data includes the question content and user information.

[1095] Step 3:

[1096] The server receives the question and passes it to a prompt generation engine, which identifies which process the question belongs to.

[1097] Step 4:

[1098] A prompt generation engine uses the challenge template to generate appropriate prompts, such as "What aspects of environmental issues interest you?"

[1099] Step 5:

[1100] The server sends the generated prompt to the natural language processing model (ChatGPT), along with the prompt and related information in the form of an API request.

[1101] Step 6:

[1102] A natural language processing model generates an answer based on the prompt, such as "Air pollution, marine pollution, deforestation, etc. Please choose the area that you are particularly interested in."

[1103] Step 7:

[1104] The server receives the answer from the natural language processing model, which is then formatted as needed.

[1105] Step 8:

[1106] The server then sends the formatted response to the terminal, which includes the response content and instructions for display.

[1107] Step 9:

[1108] The device displays the received answers in the user interface, and the user decides whether to ask further questions or proceed to the next step based on the information presented.

[1109] Detailed processing steps of the information gathering process

[1110] Step 1:

[1111] A user types a question about information gathering into a chat box on a terminal, for example, "I'd like to find the latest research materials on air pollution. Where can I find them?"

[1112] Step 2:

[1113] The terminal transmits the user's question to the server in real time.

[1114] Step 3:

[1115] The server receives the question and passes it to the prompt generation engine.

[1116] Step 4:

[1117] A prompt generation engine uses information-gathering templates to generate appropriate prompts, such as "What are some reliable sources for finding the latest research materials?"

[1118] Step 5:

[1119] The server sends the generated prompt to the natural language processing model (ChatGPT).

[1120] Step 6:

[1121] A natural language processing model generates an answer based on the prompt, such as "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[1122] Step 7:

[1123] The server receives the answer from the natural language processing model, which is then formatted as needed.

[1124] Step 8:

[1125] The server formats the response and sends it to the device.

[1126] Step 9:

[1127] The terminal displays the received answers on the user interface, allowing the user to begin searching for materials based on the presented information.

[1128] Detailed processing steps of the data reduction process

[1129] Step 1:

[1130] A user types a question about data organization into a chat box on the device, for example, "How should I organize the data for...?"

[1131] Step 2:

[1132] The terminal transmits the user's question to the server in real time.

[1133] Step 3:

[1134] The server receives the question and passes it to the prompt generation engine.

[1135] Step 4:

[1136] The prompt generation engine uses templates for data organization to generate appropriate prompts, such as "What are the basic techniques for data analysis?"

[1137] Step 5:

[1138] The server sends the generated prompt to the natural language processing model (ChatGPT).

[1139] Step 6:

[1140] A natural language processing model generates an answer based on the prompt, such as "Basic techniques for data analysis include graphing, statistical analysis, and regression analysis."

[1141] Step 7:

[1142] The server receives the answer from the natural language processing model, which is then formatted as needed.

[1143] Step 8:

[1144] The server formats the response and sends it to the device.

[1145] Step 9:

[1146] The device displays the received answers in a user interface, allowing the user to organize the data based on the presented information.

[1147] Detailed processing steps of the presentation process

[1148] Step 1:

[1149] A user types a question about the presentation into the chat box of the device, for example, "How should I structure my presentation?"

[1150] Step 2:

[1151] The terminal transmits the user's question to the server in real time.

[1152] Step 3:

[1153] The server receives the question and passes it to the prompt generation engine.

[1154] Step 4:

[1155] The prompt generation engine uses the presentation template to generate appropriate prompts, such as "How do I structure an effective presentation?"

[1156] Step 5:

[1157] The server sends the generated prompt to the natural language processing model (ChatGPT).

[1158] Step 6:

[1159] The natural language processing model generates an answer based on the prompt sent, for example, "The basic structure of a presentation has three parts: introduction, main body, and conclusion. The introduction explains the purpose and background, the main body provides details using data and examples, and the conclusion introduces the results and next steps."

[1160] Step 7:

[1161] The server receives the answer from the natural language processing model, which is then formatted as needed.

[1162] Step 8:

[1163] The server formats the response and sends it to the device.

[1164] Step 9:

[1165] The device displays the received answers on a user interface, allowing the user to prepare a presentation based on the information presented.

[1166] Example 1

[1167] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1168] In today's educational environment, there is a lack of appropriate support tailored to each student's individual learning progress and level of understanding, and students often find it difficult to engage in independent inquiry-based learning. Furthermore, limited teacher and instructor resources mean that individualized instruction is difficult to provide. Furthermore, there are few ways for students to receive appropriate learning support in real time, which can result in a decline in learning efficiency.

[1169] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1170] In this invention, the server includes means for accepting questions entered by students in the course of their studies regarding task setting, information gathering, data organization, and presentations, means for generating appropriate prompts using a generation engine corresponding to the content of the questions, means for sending the generated prompts to a natural language processing model and receiving answers, and means for formatting the received answers and sending them to the student's terminal for display. This allows students to receive individual learning support in real time, enabling them to effectively advance independent inquiry-based learning.

[1171] "Student" means a person who belongs to an educational institution and engages in learning activities.

[1172] "Learning process" refers to the steps of learning activities such as setting a task, gathering information, organizing data, and making a presentation.

[1173] "Questions" are content related to doubts or issues that students have while studying.

[1174] A "prompt generation engine" is a system that automatically generates appropriate prompts based on the questions it receives.

[1175] A "prompt" is a sentence that is sent to a natural language processing model to get an answer to a question.

[1176] A "natural language processing model" refers to an algorithm that understands natural language and generates an answer based on input text.

[1177] An "answer" is a response sentence that a natural language processing model generates based on a prompt.

[1178] "Formatting" is the process of converting the answers received into a format that is easy to read and understand.

[1179] "Device" refers to devices used by students, such as computers, tablets, and smartphones.

[1180] "Educational support system" refers to the entire system designed to enable students to receive individually optimized learning support.

[1181] MODE FOR CARRYING OUT THE INVENTION

[1182] The present invention is an educational support system that provides individually optimized learning support to students as they progress through inquiry-based learning. This system accepts questions entered by students during the learning process regarding task setting, information gathering, data organization, and presentations, generates appropriate prompts based on the content of the questions, and provides answers using a natural language processing model. Specific embodiments of this system are described below.

[1183] Hardware and Software Configuration

[1184] The system mainly consists of the following components:

[1185] 1. Device: A device used by a student, such as a computer, tablet, or smartphone. The device provides a chat box-style input field as a user interface.

[1186] 2. Server: A backend system for implementing the prompt generation engine and natural language processing model. The server is responsible for receiving questions, parsing them, generating prompts, sending them to the natural language processing model, formatting answers, and sending the formatted answers.

[1187] 3. Natural language processing models: For example, generative AI models like GPT-3, which are used to generate answers to students' questions.

[1188] Data processing and calculation

[1189] 1. Acceptance and submission:

[1190] The user (student) inputs questions they have during their studies into the terminal. For example, a student might input, "I want to find the latest research materials on air pollution."

[1191] The device sends the question to the server in real time, using JSON data or other formats.

[1192] 2. Prompt generation:

[1193] The server analyzes the question received from the user and generates an appropriate prompt using a prompt generation engine.

[1194] If the question is "I want to find the latest research on air pollution," the generated prompt will be "What are some reliable sources for finding the latest research?"

[1195] 3. Sending prompts and generating answers:

[1196] The server sends the generated prompt to a natural language processing model (such as GPT-3) using an API request.

[1197] A natural language processing model generates an appropriate answer based on the prompt and returns it to the server, such as "You might want to use a scholarly article search engine such as Google Scholar or PubMed."

[1198] 4. Formatting the answer:

[1199] The server formats the answers received from the natural language processing model, specifically converting the answers into an easy-to-read format (such as bullet points or adding specific examples).

[1200] The formatted content is converted into JSON or another appropriate data format and sent to the terminal.

[1201] 5. Show Answer:

[1202] The device receives a formatted answer from the server and displays it to the student in an easy-to-understand manner. For example, it might say, "You might want to use a scholarly paper search engine such as Google Scholar or PubMed."

[1203] Specific examples

[1204] For example, if a student types a question like "What are some tips for giving a successful presentation?", the process would go something like this:

[1205] 1. User types question: "What are some tips for giving a successful presentation?"

[1206] 2. The device sends the question to the server.

[1207] 3. The server parses the question and generates an appropriate prompt: "What specific tips can I use to give a successful presentation?"

[1208] 4. The server sends the generated prompt to the natural language processing model.

[1209] 5. The natural language processing model generates answers such as "set clear goals, practice, and use visual aids."

[1210] 6. The server formats the response and sends it to the device.

[1211] 7. The device displays formatted answers to students: "Successful presentations require clear goals, practice, and the use of visual aids."

[1212] In this way, the present invention enables students to receive individually optimized learning support, and provides support for effectively promoting inquiry-based learning.

[1213] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1214] Step 1:

[1215] Enter and submit your question

[1216] The user inputs questions they have during their learning process into the device, for example, "I want to find the latest research materials on air pollution."

[1217] The device converts the entered question into JSON data format and sends it to the server in real time using WebSocket or HTTP requests.

[1218] Input: A text question: "I would like to find the latest research on air pollution."

[1219] Output: The question data sent to the server is converted to JSON format.

[1220] Step 2:

[1221] Question Analysis

[1222] The server receives the question sent from the device and analyzes the question, extracting important keywords and context from the question.

[1223] The server analyzes the question data and prepares it to generate appropriate prompts, for example by extracting keywords such as "air pollution" and "latest research materials."

[1224] Input: A JSON question: "I want to find the latest research on air pollution."

[1225] Output: Analysis results (e.g. keywords and contextual information) for use by the prompt generation engine.

[1226] Step 3:

[1227] Prompt Generation

[1228] The server uses a prompt generation engine to generate an appropriate prompt based on the analysis results, for example, "What are some reliable sources for finding the latest research materials?"

[1229] Input: Analysis results (e.g., keywords and context information).

[1230] Output: The generated prompt (the text reads "What reliable sources can I use to find the latest research materials?").

[1231] Step 4:

[1232] Sending a prompt

[1233] The server sends the generated prompt to the natural language processing model (generative AI model), passing the prompt to the model in the form of an API request.

[1234] Input: Generated prompt (e.g., "What reliable sources can I use to find the latest research materials?").

[1235] Output: The prompt data sent to the natural language processing model.

[1236] Step 5:

[1237] Generating and receiving answers

[1238] A natural language processing model generates an answer based on the prompt it receives, such as "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[1239] The natural language processing model returns the generated answer to the server.

[1240] Input: Submitted prompt ("What reliable sources can I use to find the latest research materials?").

[1241] Output: The generated answer (e.g., "You may find it helpful to use a scholarly search engine such as Google Scholar or PubMed").

[1242] Step 6:

[1243] Formatting answers

[1244] The server formats the answer received from the natural language processing model, converting the answer into an easy-to-read format and adding bullet points and specific examples as needed.

[1245] Input: A generated answer (e.g., "You might want to use a scholarly search engine such as Google Scholar or PubMed").

[1246] Output: A formatted answer (e.g., "You may find it helpful to use a scholarly search engine such as Google Scholar or PubMed." "Examples: Google Scholar, PubMed").

[1247] Step 7:

[1248] Show Answers

[1249] The terminal displays the formatted response received from the server in a user interface, for example, in a chat box.

[1250] Input: A formatted answer (e.g., "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed.").

[1251] Output: User-visible display of answers.

[1252] (Application example 1)

[1253] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1254] Conventional learning support systems have had the problem of being unable to provide appropriate information and support in a timely manner for the challenges that students face individually.In addition, when students independently engage in inquiry-based learning, it is difficult for them to know how to access reliable information sources or how to gather appropriate information, which can slow down their learning progress.

[1255] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1256] In this invention, the server includes means for accepting questions related to task setting, information gathering, data organization, and presentations entered by students in the course of their studies, means for generating appropriate prompts using a generation engine corresponding to the content of the questions, means for sending the generated prompts to a natural language processing model and receiving answers, means for formatting the received answers and sending them to the student's terminal for display, and means for providing learning support through a content distribution service. This enables students to quickly and effectively obtain appropriate information related to the content of their studies.

[1257] "Problem setting" is the process by which students decide on a specific theme or question to be solved during the learning process.

[1258] "Information gathering" is the activity of gathering relevant data and knowledge based on the problem setting.

[1259] "Data organization" is the process of classifying, analyzing, and organizing collected information into an easy-to-understand format.

[1260] A "presentation" is the act of organizing the results of learning and presenting them to others in an easy-to-understand manner.

[1261] A "generation engine" is a system component that generates appropriate prompts based on the input question.

[1262] A "prompt" is an input sentence that gives instructions to a natural language processing model.

[1263] A "natural language processing model" is an AI technology that understands and generates human language.

[1264] "Answer formatting" is the process of organizing the answers received from a natural language processing model in an easy-to-read format.

[1265] A "terminal" is an electronic device that allows a user to input information and display results.

[1266] A "content distribution service" is a platform for providing information to users via the Internet.

[1267] This invention is a system that provides optimal individualized learning support to students as they progress through inquiry-based learning. The system accepts questions about task setting, information gathering, data organization, and presentations, and provides appropriate answers to those questions.

[1268] Hardware and software used

[1269] The hardware required to implement this system includes a smartphone, tablet, or personal computer. It also requires connection to a server, terminal, and user interface. The software used is Python, the OpenAI API, and a front-end framework (React, Flutter, etc.).

[1270] System Components

[1271] 1. How to contact us:

[1272] The device (e.g., a smartphone or PC) accepts questions from students through a chat box-style user interface. For example, a student might type in a question like, "I want to find the latest research materials on air pollution. Where should I look for them?"

[1273] 2. Prompt generation engine:

[1274] The server generates an appropriate prompt based on the question it receives. For example, after receiving a question, the server generates a prompt like, "Please explain in detail the following question that interests you: I'd like to find the latest research on air pollution. Where can I find it?"

[1275] 3. Natural Language Processing Models:

[1276] The server sends the generated prompt to a natural language processing model (e.g., OpenAI's GPT-3) and receives an answer from the model, such as, "You can use academic paper search engines such as Google Scholar or PubMed. You can use the filter function when searching for papers to find the latest research."

[1277] 4. Answer formatting method:

[1278] The server formats the answers it receives from the natural language processing model to make them easier to read, for example by editing the answers to make them easier to understand, bulleting important information, and adding examples.

[1279] 5. Display means:

[1280] The device will then display the formatted answer in a user interface. For example, the student's device might say, "You can use academic paper search engines such as Google Scholar or PubMed. Use the filter function when searching for papers to find the latest research."

[1281] By providing learning support through a content delivery service, students can quickly and effectively acquire the right information related to their learning. The system utilizes cutting-edge generative AI models and prompting technology to ensure optimal learning support is always provided to students.

[1282] Specific examples

[1283] For example, if a student types a question like this:

[1284] "I want to find the latest research on air pollution. Where can I find it?"

[1285] The system responds to this question in the following way:

[1286] 1. The device accepts the question.

[1287] 2. The server uses the prompt generation engine to generate the following prompt:

[1288] "Please explain in detail the following question that interests you: I would like to find the latest research materials on air pollution. Where can I find them?"

[1289] 3. The server sends the generated prompt to a natural language processing model and receives a response such as:

[1290] "You can use academic search engines like Google Scholar and PubMed, which have filters to help you find the latest research."

[1291] 4. The server formats the response it receives and sends it to the terminal for display.

[1292] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1293] Step 1:

[1294] During the learning process, the user enters questions or concerns into a chat box-style user interface. For example, the user might enter a question like, "I want to find the latest research materials on air pollution. Where should I look for them?" This input is recorded on the terminal as a string of characters.

[1295] Step 2:

[1296] The terminal sends the input question data to the server, where it is received and analyzed.

[1297] Step 3:

[1298] The server starts a prompt generation engine based on the received question. The question data received as input is passed to the prompt generation engine, which generates an appropriate prompt based on that. For example, this prompt might be in the form of "Please explain in detail the following question that interests you: I want to find the latest research materials on air pollution. Where can I find them?" The generated prompt is recorded as a string.

[1299] Step 4:

[1300] The server sends the generated prompt string to a natural language processing model, such as a generative AI model like GPT-3, which generates an answer based on the received prompt. The model uses the prompt data as input and generates an appropriate answer as output.

[1301] Step 5:

[1302] The server receives the answer output from the natural language processing model and passes it to the answer formatting engine. The answer formatting engine formats the received answer into an easy-to-understand format, for example by turning sentences into bullet points or adding specific examples. This formatting process generates an answer that is easy to understand and organized.

[1303] Step 6:

[1304] The server sends the formatted answers to the device, which then displays the received answer data on its user interface. For example, the student's screen might read, "We recommend using academic paper search engines such as Google Scholar or PubMed. Use the filter function when searching for papers to find the latest research."

[1305] Step 7:

[1306] The user reviews the displayed answers and decides on the next action to take, such as actually searching for the latest research materials using an academic paper search engine.

[1307] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1308] This invention is a system that provides effective, individually optimized learning support for students as they progress through inquiry-based learning. In particular, by combining it with an emotion engine that recognizes students' emotions and optimizes the learning process, it achieves more advanced support.

[1309] composition

[1310] The system mainly consists of the following components:

[1311] 1. Method of accepting questions

[1312] The terminal accepts questions from students. Specifically, it provides a chat box-style user interface, allowing students to input questions about setting assignments, gathering information, etc.

[1313] 2. Prompt Generation Engine

[1314] The server generates appropriate prompts based on the questions received from students. The prompt generation engine dynamically generates prompts using templates tailored to each learning process.

[1315] 3. Natural Language Processing Model

[1316] The server generates prompts and sends them to a natural language processing model, which uses the most advanced models available today, to receive responses.

[1317] 4. Answer formatting means

[1318] The server formats the answers received from the natural language processing model, specifically by making the answers easier to understand and converting them into a format that is useful to the student.

[1319] 5. Display means

[1320] The device displays the formatted answer to the student, allowing them to quickly get the information they need and move on to the next step in their learning.

[1321] 6. Emotion Engine

[1322] The server recognizes emotions from the user's input text and voice. The emotion engine uses emotion analysis algorithms to understand the student's emotional state.

[1323] 7. Emotion-linked prompt generation

[1324] The server uses the emotion engine to generate prompts based on the emotion data it receives. For example, if a negative emotion is detected, it generates an encouraging prompt.

[1325] A natural language description of the program's operation

[1326] Question acceptance method

[1327] The user inputs a question during the learning process. For example, they input a question such as "I would like to set a research topic about environmental issues" into the chat box.

[1328] Prompt Generation Engine

[1329] The server receives questions from users and generates corresponding prompts based on templates for each process, such as problem setting, information gathering, data organization, and presentation.

[1330] Natural Language Processing Model

[1331] The server sends the generated prompt to a natural language processing model to obtain an answer. For example, if the prompt is "Which aspects of environmental issues are you interested in?", the natural language processing model generates an answer such as "Air pollution, marine pollution, deforestation, etc."

[1332] Answer formatting means

[1333] The server formats the answer it receives from the natural language processing model, for example by turning the answer into a bulleted list or adding specific examples.

[1334] Display means

[1335] The device displays the formatted answer in a user interface, and the user decides based on the displayed information whether to ask further questions or proceed to the next step.

[1336] Adding emotion engine processing

[1337] emotion recognition

[1338] The server sends the user's input text and voice to the emotion engine, which then analyzes the text and voice to determine the user's emotional state (stress, joy, excitement, anxiety, etc.).

[1339] Emotion-linked prompt generation

[1340] The server uses the emotion data obtained from the emotion engine to generate emotion-linked prompts. For example, if a user enters "I'm having trouble finding research materials on air pollution" and the emotion engine detects "anxiety," the prompt generation engine will provide support such as, "First, try some reliable sources of information. If necessary, please refer to this guide."

[1341] Specific examples

[1342] For example, if a student types a question like "I'd like to find the latest research on air pollution, but I don't know where to start," the following happens:

[1343] 1. A user types a question: "I'm looking for the latest research on air pollution, but I don't know where to start."

[1344] 2. The device sends a question to the server.

[1345] 3. The server receives the question and passes it to the prompt generation engine.

[1346] 4. The emotion engine analyzes emotions from the question text and detects "anxiety."

[1347] 5. The prompt generation engine takes sentiment data into account to generate an appropriate prompt: "Let's start by trying some trusted sources, such as Google Scholar and PubMed."

[1348] 6. The server sends the prompt to the natural language processing model.

[1349] 7. Natural language processing models generate relevant answers: "You can use a scholarly search engine such as Google Scholar or PubMed."

[1350] 8. The server receives and formats the response.

[1351] 9. The server sends the formatted response to the device.

[1352] 10. The device displays the answer it receives in the user interface: "You may find it helpful to use a scholarly paper search engine such as Google Scholar or PubMed."

[1353] In this way, the system helps students to effectively engage in inquiry-based learning and provides special support based on emotion recognition, making students feel more at ease and empowering them to ask and answer their own questions.

[1354] The processing flow will be explained below.

[1355] Detailed steps in the question acceptance and prompt generation process

[1356] Step 1:

[1357] During the learning process, the user can input a question, for example, "I want to find the latest research on air pollution, but I don't know where to start" into the chat box.

[1358] Step 2:

[1359] The device sends the user's question to the server in real time, including the question content and the user ID.

[1360] Step 3:

[1361] The server receives the user's question and sends the text data to the emotion engine.

[1362] Step 4:

[1363] The emotion engine analyzes the received text data and recognizes the user's emotional state, for example, detecting "anxiety."

[1364] Step 5:

[1365] The server passes the emotion data obtained from the emotion engine to the prompt generation engine, along with the question content and the emotional state.

[1366] Step 6:

[1367] The prompt generation engine generates appropriate prompts based on sentiment data and the question itself, such as "Let's start by trying some trusted sources, such as Google Scholar and PubMed."

[1368] Step 7:

[1369] The server sends the generated prompt to the natural language processing model in the form of an API request.

[1370] Step 8:

[1371] A natural language processing model generates an answer based on the prompt received, such as "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[1372] Step 9:

[1373] The server formats the answers it receives from the natural language processing model, for example by adding bullet points to the answer or highlighting important information.

[1374] Step 10:

[1375] The server then sends the formatted response to the user's terminal, where the formatted response data is sent.

[1376] Step 11:

[1377] The device displays the received answer on the user interface, and the user can decide whether to ask further questions or proceed to the next step based on the displayed information.

[1378] Specific examples

[1379] As a specific example, the following describes in detail how a student would respond if they typed in a question such as, "I want to find the latest research materials on air pollution, but I don't know where to look."

[1380] Step 1:

[1381] A user types a question: "I'm looking for the latest research on air pollution, but I don't know where to start."

[1382] Step 2:

[1383] The device sends the user's question to the server. The sent data includes the user ID and the question.

[1384] Step 3:

[1385] The server receives the question and sends the text data to the emotion engine.

[1386] Step 4:

[1387] The emotion engine analyzes emotions from the question text and detects "anxiety."

[1388] Step 5:

[1389] The server passes the emotional data and question content to the prompt generation engine. The data includes the question content, "I want to find the latest research materials on air pollution, but I don't know where to look," and the emotional state, "anxiety."

[1390] Step 6:

[1391] The prompt generation engine generates appropriate prompts based on the sentiment and question content, such as "Let's start by trying some reliable sources, such as Google Scholar and PubMed."

[1392] Step 7:

[1393] The server sends the generated prompt to the natural language processing model (ChatGPT), which sends the prompt in the form of an API request.

[1394] Step 8:

[1395] A natural language processing model generates an answer based on the prompt, for example, "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[1396] Step 9:

[1397] The server formats the answer received from the natural language processing model, for example by turning the answer into a list of items.

[1398] Step 10:

[1399] The server then sends the formatted response to the user's terminal. The transmitted data includes the formatted response.

[1400] Step 11:

[1401] The device displays the received answer on the user interface. For example, it may say, "We recommend using academic paper search engines such as Google Scholar or PubMed." The user can then begin searching for materials based on the information provided.

[1402] In this way, the system helps students to effectively engage in inquiry-based learning. In particular, by providing special support based on emotion recognition, students can feel more at ease while studying.

[1403] Example 2

[1404] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1405] Conventional learning support systems lacked adequate support for each student's learning situation and emotional state, making it difficult for students to effectively engage in inquiry-based learning. Furthermore, because they did not provide individually optimized learning support, they were unable to reduce the anxiety and stress students felt during the learning process.

[1406] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1407] In this invention, the server includes means for generating appropriate prompts using a generation engine corresponding to the content of the question, means for sending the generated prompts to a natural language processing model and receiving answers, means for formatting the received answers and sending them to the student's terminal for display, and means for recognizing emotions from the student's input text or voice and generating prompts based on that emotion data, thereby enabling individually optimal support according to the learning situation and emotional state of each student.

[1408] "Student" refers to a learner who uses this system to engage in inquiry-based learning.

[1409] The "question acceptance means" is a component for accepting questions from students regarding assignment setting, information gathering, data organization, and presentations.

[1410] The "generation engine" is a component that generates an appropriate prompt based on the content of the received question.

[1411] A "prompt" is an instruction or question generated by a generation engine and sent to a natural language processing model.

[1412] A "natural language processing model" is an AI model that generates answers based on generated prompts.

[1413] The "answer formatting means" is a component for organizing and formatting the answers received from the natural language processing model in an easy-to-understand manner.

[1414] The "emotion engine" is an algorithm that recognizes emotions from text and voice input by students and extracts that emotional data.

[1415] The "emotion-linked prompt generation means" is a means for generating a prompt based on emotion data obtained from the emotion engine.

[1416] "Terminal" means the device used by a student to enter questions and view answers from the system.

[1417] "Display means" refers to the functionality for visually presenting formatted answers to students.

[1418] This invention relates to a learning support system that effectively supports students' inquiry-based learning by accepting questions about task setting, information gathering, data organization, and presentations entered by students during the learning process and providing appropriate answers. In particular, it uses an emotion engine to analyze students' emotions and generates prompts based on those emotions to provide individually optimized learning support.

[1419] component

[1420] The system includes the following main components:

[1421] 1. Method of accepting questions

[1422] 2. Prompt Generation Engine

[1423] 3. Natural Language Processing Models (NLP Models)

[1424] 4. Answer formatting means

[1425] 5. Emotion Engine

[1426] 6. Emotion-linked prompt generation method

[1427] 7. Display means

[1428] Question acceptance method

[1429] While studying, students enter questions and challenges using a chat box-style user interface, which is provided by a software application running on a PC, tablet, smartphone, or other device. For example, a student might enter, "Tell me about the types of renewable energy."

[1430] Prompt Generation Engine

[1431] The server receives a question from the user and generates an appropriate prompt. The engine uses a template that corresponds to the question, generating prompts such as "What aspects of environmental issues are you interested in?" or "What are some reliable sources of information on environmental issues?"

[1432] Natural Language Processing Model

[1433] The generated prompt is sent from the server to a natural language processing model (e.g., GPT-4), which generates an appropriate answer based on the prompt. For example, it generates an answer such as, "There are solar power, wind power, hydroelectric power, and biomass power generation."

[1434] Answer formatting means

[1435] The server formats the answers it receives from the NLP model, which may include bulleting the answer, adding specific examples, and highlighting important information, such as "The following are the types of renewable energy:\n1. Solar power\n2. Wind power\n3. Hydroelectric power\n4. Biomass power."

[1436] Emotion Engine

[1437] The emotion engine analyzes user-supplied text and voice input to recognize emotional states (e.g., stress, joy, anxiety), for example using the Emotion API or similar algorithms.

[1438] Emotion-linked prompt generation method

[1439] Based on the emotional data obtained from the emotion engine, the prompt generation engine generates prompts according to the user's emotional state. For example, if a user types, "I'm having trouble finding research materials on air pollution," and anxiety is detected, the prompt will be adjusted to provide support such as, "Let's start by trying some reliable sources."

[1440] Display means

[1441] The formatted answer is sent from the server to the device and displayed on the user interface. The user can confirm the displayed answer and then enter further questions or proceed to the next step. For example, it might say, "The following are the types of renewable energy:\n1. Solar power generation\n2. Wind power generation\n3. Hydroelectric power generation\n4. Biomass power generation."

[1442] By combining the above components and their interaction, this invention can effectively support students' inquiry-based learning and provide individually optimized learning support.

[1443] Examples of prompt statements

[1444] 1. "What aspects of environmental issues interest you?"

[1445] 2. "What are some reliable sources of information on environmental issues?"

[1446] 3. "What are the main types of renewable energy?"

[1447] These prompts can be used to effectively obtain useful information from generative AI models.

[1448] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1449] Step 1: Enter your question

[1450] While studying, users input questions or problems using a chat box-style user interface. Specifically, they input text such as "Please tell me about the types of renewable energy" into an application running on a device such as a PC or smartphone. This input triggers the processing of the entire system.

[1451] Step 2: Submit your question

[1452] The terminal sends the user's question to the server. An HTTP POST request is often used here. Specifically, a data packet containing the question text entered by the user is sent to the server. The input is the user's question text, and the output is a response indicating that the data transfer to the server is complete.

[1453] Step 3: Prompt generation

[1454] The server passes the received question to the prompt generation engine, which generates an appropriate prompt based on a pre-configured template. For example, it generates a prompt such as "Please provide more information about renewable energy." The input is the question data received by the server, and the output is the generated prompt.

[1455] Step 4: Sentiment analysis

[1456] The server sends the question text to the emotion engine, which then analyzes it. The emotion engine uses a text analysis algorithm to recognize the user's emotions. For example, it can detect emotions such as "troubled" or "anxious." The input is the question text sent from the server, and the output is the emotion data resulting from the analysis.

[1457] Step 5: Emotion-linked prompt generation

[1458] Based on the emotion data received by the server from the emotion engine, the prompt generation engine generates a prompt according to the emotion. For example, if the server detects that the user is "in trouble," it creates a prompt such as "Let's start with some basic information." The input is emotion data and the original question, and the output is an emotion-linked prompt.

[1459] Step 6: Send prompts

[1460] The server sends the generated prompt to the natural language processing model (NLP model). Specifically, the prompt is sent to the natural language processing API via an HTTP request. The input is the generated prompt, and the output is a confirmation that the request was sent to the NLP model.

[1461] Step 7: Get the answer

[1462] The server receives the answer generated by the natural language processing model. For example, the NLP model might answer, "There are solar power, wind power, hydroelectric power, and biomass power generation." The input is the data returned by the NLP model, and the output is the answer data.

[1463] Step 8: Formatting your answers

[1464] The server then formats the answer it receives, making it easier for the user to understand. Specifically, it may do things like bullet points or insert additional information. For example, it may format the answer into something like "The following are the types of renewable energy:\n1. Solar power\n2. Wind power\n3. Hydroelectric power\n4. Biomass power." The input is the answer received from the NLP, and the output is the formatted answer.

[1465] Step 9: Submit your response

[1466] The server sends the formatted answer to the terminal as an HTTP response. The input is the formatted answer data, and the output is a response indicating that data transfer to the terminal is complete.

[1467] Step 10: Display answers

[1468] The terminal displays the received answer in the user interface. Specifically, the formatted answer is displayed in a chat box so that the user can see it. For example, it displays "The following are the types of renewable energy:\n1. Solar power generation\n2. Wind power generation\n3. Hydroelectric power generation\n4. Biomass power generation." The input is the answer data sent from the server, and the output is the visualized state provided to the user.

[1469] (Application example 2)

[1470] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1471] Conventional learning support systems have difficulty addressing students' psychological burdens and emotional needs, resulting in insufficient optimization of learning. Furthermore, they are unable to provide prompts and answers tailored to each student's learning progress and emotional state, and can only provide uniform support. This makes it difficult for students to progress effectively in their studies.

[1472] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for accepting questions related to task setting, information gathering, data organization, and presentations entered by students in the course of their studies; means for generating appropriate prompts using a generation engine corresponding to the content of the questions; means for sending the generated prompts to a natural language processing model and receiving answers; means for formatting the received answers and sending them to the student's terminal for display; means for recognizing emotions from the input text; and means including a generation engine for adjusting the prompts according to the recognized emotions. This enables optimal support to be provided according to each student's individual learning progress and emotional state.

[1473] "Problem setting" refers to the specific learning goals or problems that students set at the beginning of the learning process.

[1474] "Information gathering" refers to the act of collecting data and materials necessary for the learning process.

[1475] "Data organization" refers to the act of classifying and organizing collected information and processing it into a format that is easy to use.

[1476] A "presentation" is a means of communicating information to explain and announce the results of learning to others.

[1477] "Means for accepting questions" refers to the interface that allows the system to accept questions entered by students.

[1478] A "generation engine" is a program that generates appropriate prompts based on the student's question.

[1479] "Prompts" are instructions or questions generated by the system in response to students' questions or learning progress.

[1480] A "natural language processing model" is a machine learning algorithm for processing and understanding human language.

[1481] The "means for receiving an answer" refers to an interface for receiving an answer generated from a natural language processing model.

[1482] A "response formatter" is a program that converts the received responses into a format that is easy for students to understand.

[1483] A "terminal" is a device used by students to operate the learning support system.

[1484] An "emotion recognition means" is a program that analyzes a student's emotional state from input text.

[1485] A "prompt-adjusting generation engine" is a program that adjusts the content and expression of the prompt depending on the recognized emotion.

[1486] This invention is a system for providing learning support services in a physical store. The system is mainly composed of three entities: a server, a terminal, and a user. The roles and processing contents of each entity are explained below.

[1487] What the server does:

[1488] The server is the central processing unit and contains the following components:

[1489] A means of accepting questions: Receives and records questions entered by students. A chat box-style user interface is used in this section.

[1490] Generation engine: Generates appropriate prompts based on the question content. When generating prompts, templates corresponding to each learning process are used.

[1491] Natural Language Processing Model: The generated prompt is sent to a natural language processing model that uses the latest machine learning algorithms to receive an answer.

[1492] Formatting responses: Format the responses you receive in a way that is easier for students to understand. For example, add bullet points or examples.

[1493] Emotion recognition: Emotions are analyzed from the student's input text using a sentiment analysis algorithm.

[1494] Prompt-adjusting generation engine: Adjusts prompts based on emotion recognition results, generating prompts that provide encouragement or specific instructions as needed.

[1495] What the device does:

[1496] The terminal acts as the student interface and performs the following tasks:

[1497] Question input: Provide a chat box where students can enter questions about setting assignments, gathering information, etc.

[1498] Displaying formatted answers: Displaying formatted answers received from the server to students, allowing them to quickly move on to the next learning step.

[1499] What the user does:

[1500] The user (student) uses the above system to carry out the following learning process:

[1501] Entering questions: Enter any questions or issues that arise during the learning process into the chat box on your device.

[1502] Check the answer: Check the formatted answer from the server and use it as a reference for the next learning step.

[1503] Examples:

[1504] For example, if a student types a question like "I'm worried because I can't find any resources about environmental issues," the system will process it as follows:

[1505] 1. Accept Question: The server receives the student's input.

[1506] 2. Recognizing emotions: The server uses an emotion engine to recognize the emotion "anxiety."

[1507] 3. Generate a prompt: The generation engine takes this sentiment data into account to generate a prompt, such as "Please refer to the following steps. We will show you how to find resources related to environmental issues."

[1508] 4. Send to Natural Language Processing Model: The generated prompt is sent to a natural language processing model and an appropriate answer is received.

[1509] 5. Formatting the answer: For example, format the answer "Google Scholar and PubMed are useful" into a more relevant and understandable format for the question.

[1510] 6. Display on device: The formatted answer is displayed on the student's device, and a message is displayed saying, "Google Scholar and PubMed are useful."

[1511] Example prompt sentence:

[1512] Typed question: "I'm worried because I can't find any materials on environmental issues."

[1513] Generated prompt: "Let's use the following steps to help you find resources on environmental issues."

[1514] The natural language processing model answers: "Google Scholar and PubMed are useful."

[1515] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1516] Step 1:

[1517] Input: Students type their question into the chat box on their devices. Example: "I'm worried because I can't find any resources on environmental issues."

[1518] Action: The device sends this question to the server.

[1519] Output: The server receives the query.

[1520] Step 2:

[1521] Input: The query data received by the server.

[1522] How it works: The server sends the question text to the emotion engine, which recognizes the emotion.

[1523] Output: The emotion engine generates emotion data such as "anxiety" and sends it back to the server.

[1524] Step 3:

[1525] Input: Question data and sentiment data.

[1526] How it works: The server uses a generation engine to generate prompts based on the question and sentiment. Example: "Try these steps to help you find resources on environmental issues."

[1527] Output: The generated prompt.

[1528] Step 4:

[1529] Input: The generated prompt.

[1530] How it works: The server sends a prompt to the natural language processing model.

[1531] Output: Answer data from the natural language processing model. Example: "Google Scholar and PubMed are useful."

[1532] Step 5:

[1533] Input: Response data from a natural language processing model.

[1534] What it does: The server formats the answer data, for example by adding bullet points or specific examples. Example of a formatted answer: "Google Scholar and PubMed are useful."

[1535] Output: Formatted response data.

[1536] Step 6:

[1537] Input: Formatted response data.

[1538] What it does: The server sends a formatted response to the device.

[1539] Output: The formatted answer data is displayed on the terminal. Example: "Google Scholar and PubMed are useful."

[1540] Step 7:

[1541] Input: Formatted response data.

[1542] Action: The device displays the formatted answer data to the student.

[1543] Output: Helps students check their answers and guides them to the next step in their learning.

[1544] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1545] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1546] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1547] [Fourth embodiment]

[1548] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1549] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1550] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1551] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1552] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1553] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1554] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1555] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1556] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1557] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1558] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1559] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1560] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1561] This invention is a system that provides effective, individually optimized learning support for students as they progress through inquiry-based learning. The system accepts questions entered by students during the learning process regarding task setting, information gathering, data organization, and presentations, generates appropriate prompts corresponding to the questions, and provides answers using a natural language processing model.

[1562] composition

[1563] The system mainly consists of the following components:

[1564] 1. Method of accepting questions

[1565] The terminal accepts questions from students. Specifically, it provides a chat box-style user interface, allowing students to input questions about setting assignments, gathering information, etc.

[1566] 2. Prompt Generation Engine

[1567] The server generates appropriate prompts based on the questions received from students. The prompt generation engine dynamically generates prompts using templates tailored to each learning process.

[1568] 3. Natural Language Processing Model

[1569] The server generates prompts and sends them to a natural language processing model, which uses the most state-of-the-art model available today (e.g., GPT-3 or equivalent), and receives responses.

[1570] 4. Answer formatting means

[1571] The server formats the answers received from the natural language processing model, specifically by making the answers easier to understand and converting them into a format that is useful to the student.

[1572] 5. Display means

[1573] The device displays the formatted answer to the student, allowing them to quickly get the information they need and take action to move forward to the next step in their learning.

[1574] A natural language description of the program's operation

[1575] Question acceptance method

[1576] The user inputs a question during the learning process. For example, they input a question such as "I would like to set a research topic about environmental issues" into the chat box.

[1577] Prompt Generation Engine

[1578] The server receives questions from users and generates corresponding prompts based on templates for each process, such as problem setting, information gathering, data organization, and presentation.

[1579] Natural Language Processing Model

[1580] The server sends the generated prompt to a natural language processing model to obtain an answer. For example, if the prompt is "Which aspects of environmental issues are you concerned about?", the natural language processing model generates an answer such as "Air pollution, ocean pollution, deforestation, etc."

[1581] Answer formatting means

[1582] The server formats the answer it receives from the natural language processing model, for example by turning the answer into a bulleted list or adding specific examples.

[1583] Display means

[1584] The device displays the formatted answer in a user interface, allowing the user to proceed to the next learning step based on the displayed information.

[1585] Specific examples

[1586] For example, if a student types in a question like "I want to find the latest research on air pollution. Where can I find it?", the following happens:

[1587] 1. A user types a question: "I want to find the latest research on air pollution. Where can I find it?"

[1588] 2. The device sends a question to the server.

[1589] 3. The server uses a prompt generation engine to generate the prompt: "What are some reliable sources for finding the latest research materials?"

[1590] 4. The server sends the generated prompt to the natural language processing model.

[1591] 5. A natural language processing model generates the answer: "You can use a scholarly search engine such as Google Scholar or PubMed."

[1592] 6. The server receives and formats the response.

[1593] 7. The server sends the formatted response to the device.

[1594] 8. The device displays the answer in the user interface: "You might want to use a scholarly search engine such as Google Scholar or PubMed."

[1595] In this way, the system helps students to effectively engage in inquiry-based learning, allowing them to advance their learning by asking questions and obtaining answers on their own, without the need for a specialist escort.

[1596] The processing flow will be explained below.

[1597] Detailed steps in the assignment process

[1598] Step 1:

[1599] The user enters a question about setting a research topic into the chat box on the device. For example, the user might enter, "I would like to set a research topic about environmental issues. What perspective should I take?"

[1600] Step 2:

[1601] The terminal transmits the user's question to the server in real time. The transmitted data includes the question content and user information.

[1602] Step 3:

[1603] The server receives the question and passes it to a prompt generation engine, which identifies which process the question belongs to.

[1604] Step 4:

[1605] A prompt generation engine uses the challenge template to generate appropriate prompts, such as "What aspects of environmental issues interest you?"

[1606] Step 5:

[1607] The server sends the generated prompt to the natural language processing model (ChatGPT), along with the prompt and related information in the form of an API request.

[1608] Step 6:

[1609] A natural language processing model generates an answer based on the prompt, such as "Air pollution, marine pollution, deforestation, etc. Please choose the area that you are particularly interested in."

[1610] Step 7:

[1611] The server receives the answer from the natural language processing model, which is then formatted as needed.

[1612] Step 8:

[1613] The server then sends the formatted response to the terminal, which includes the response content and instructions for display.

[1614] Step 9:

[1615] The device displays the received answers in the user interface, and the user decides whether to ask further questions or proceed to the next step based on the information presented.

[1616] Detailed processing steps of the information gathering process

[1617] Step 1:

[1618] A user types a question about information gathering into a chat box on a terminal, for example, "I'd like to find the latest research materials on air pollution. Where can I find them?"

[1619] Step 2:

[1620] The terminal transmits the user's question to the server in real time.

[1621] Step 3:

[1622] The server receives the question and passes it to the prompt generation engine.

[1623] Step 4:

[1624] A prompt generation engine uses information-gathering templates to generate appropriate prompts, such as "What are some reliable sources for finding the latest research materials?"

[1625] Step 5:

[1626] The server sends the generated prompt to the natural language processing model (ChatGPT).

[1627] Step 6:

[1628] A natural language processing model generates an answer based on the prompt, such as "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[1629] Step 7:

[1630] The server receives the answer from the natural language processing model, which is then formatted as needed.

[1631] Step 8:

[1632] The server formats the response and sends it to the device.

[1633] Step 9:

[1634] The terminal displays the received answers on the user interface, allowing the user to begin searching for materials based on the presented information.

[1635] Detailed processing steps of the data reduction process

[1636] Step 1:

[1637] A user types a question about data organization into a chat box on the device, for example, "How should I organize the data for...?"

[1638] Step 2:

[1639] The terminal transmits the user's question to the server in real time.

[1640] Step 3:

[1641] The server receives the question and passes it to the prompt generation engine.

[1642] Step 4:

[1643] The prompt generation engine uses templates for data organization to generate appropriate prompts, such as "What are the basic techniques for data analysis?"

[1644] Step 5:

[1645] The server sends the generated prompt to the natural language processing model (ChatGPT).

[1646] Step 6:

[1647] A natural language processing model generates an answer based on the prompt, such as "Basic techniques for data analysis include graphing, statistical analysis, and regression analysis."

[1648] Step 7:

[1649] The server receives the answer from the natural language processing model, which is then formatted as needed.

[1650] Step 8:

[1651] The server formats the response and sends it to the device.

[1652] Step 9:

[1653] The device displays the received answers in a user interface, allowing the user to organize the data based on the presented information.

[1654] Detailed processing steps of the presentation process

[1655] Step 1:

[1656] A user types a question about the presentation into the chat box of the device, for example, "How should I structure my presentation?"

[1657] Step 2:

[1658] The terminal transmits the user's question to the server in real time.

[1659] Step 3:

[1660] The server receives the question and passes it to the prompt generation engine.

[1661] Step 4:

[1662] The prompt generation engine uses the presentation template to generate appropriate prompts, such as "How do I structure an effective presentation?"

[1663] Step 5:

[1664] The server sends the generated prompt to the natural language processing model (ChatGPT).

[1665] Step 6:

[1666] The natural language processing model generates an answer based on the prompt sent, for example, "The basic structure of a presentation has three parts: introduction, main body, and conclusion. The introduction explains the purpose and background, the main body provides details using data and examples, and the conclusion introduces the results and next steps."

[1667] Step 7:

[1668] The server receives the answer from the natural language processing model, which is then formatted as needed.

[1669] Step 8:

[1670] The server formats the response and sends it to the device.

[1671] Step 9:

[1672] The device displays the received answers on a user interface, allowing the user to prepare a presentation based on the information presented.

[1673] Example 1

[1674] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1675] In today's educational environment, there is a lack of appropriate support tailored to each student's individual learning progress and level of understanding, and students often find it difficult to engage in independent inquiry-based learning. Furthermore, limited teacher and instructor resources mean that individualized instruction is difficult to provide. Furthermore, there are few ways for students to receive appropriate learning support in real time, which can result in a decline in learning efficiency.

[1676] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1677] In this invention, the server includes means for accepting questions entered by students in the course of their studies regarding task setting, information gathering, data organization, and presentations, means for generating appropriate prompts using a generation engine corresponding to the content of the questions, means for sending the generated prompts to a natural language processing model and receiving answers, and means for formatting the received answers and sending them to the student's terminal for display. This allows students to receive individual learning support in real time, enabling them to effectively advance independent inquiry-based learning.

[1678] "Student" means a person who belongs to an educational institution and engages in learning activities.

[1679] "Learning process" refers to the steps of learning activities such as setting a task, gathering information, organizing data, and making a presentation.

[1680] "Questions" are content related to doubts or issues that students have while studying.

[1681] A "prompt generation engine" is a system that automatically generates appropriate prompts based on the questions it receives.

[1682] A "prompt" is a sentence that is sent to a natural language processing model to get an answer to a question.

[1683] A "natural language processing model" refers to an algorithm that understands natural language and generates an answer based on input text.

[1684] An "answer" is a response sentence that a natural language processing model generates based on a prompt.

[1685] "Formatting" is the process of converting the answers received into a format that is easy to read and understand.

[1686] "Device" refers to devices used by students, such as computers, tablets, and smartphones.

[1687] "Educational support system" refers to the entire system designed to enable students to receive individually optimized learning support.

[1688] MODE FOR CARRYING OUT THE INVENTION

[1689] The present invention is an educational support system that provides individually optimized learning support to students as they progress through inquiry-based learning. This system accepts questions entered by students during the learning process regarding task setting, information gathering, data organization, and presentations, generates appropriate prompts based on the content of the questions, and provides answers using a natural language processing model. Specific embodiments of this system are described below.

[1690] Hardware and Software Configuration

[1691] The system mainly consists of the following components:

[1692] 1. Device: A device used by a student, such as a computer, tablet, or smartphone. The device provides a chat box-style input field as a user interface.

[1693] 2. Server: A backend system for implementing the prompt generation engine and natural language processing model. The server is responsible for receiving questions, parsing them, generating prompts, sending them to the natural language processing model, formatting answers, and sending the formatted answers.

[1694] 3. Natural language processing models: For example, generative AI models like GPT-3, which are used to generate answers to students' questions.

[1695] Data processing and calculation

[1696] 1. Acceptance and submission:

[1697] The user (student) inputs questions they have during their studies into the terminal. For example, a student might input, "I want to find the latest research materials on air pollution."

[1698] The device sends the question to the server in real time, using JSON data or other formats.

[1699] 2. Prompt generation:

[1700] The server analyzes the question received from the user and generates an appropriate prompt using a prompt generation engine.

[1701] If the question is "I want to find the latest research on air pollution," the generated prompt will be "What are some reliable sources for finding the latest research?"

[1702] 3. Sending prompts and generating answers:

[1703] The server sends the generated prompt to a natural language processing model (such as GPT-3) using an API request.

[1704] A natural language processing model generates an appropriate answer based on the prompt and returns it to the server, such as "You might want to use a scholarly article search engine such as Google Scholar or PubMed."

[1705] 4. Formatting the answer:

[1706] The server formats the answers received from the natural language processing model, specifically converting the answers into an easy-to-read format (such as bullet points or adding specific examples).

[1707] The formatted content is converted into JSON or another appropriate data format and sent to the terminal.

[1708] 5. Show Answer:

[1709] The device receives a formatted answer from the server and displays it to the student in an easy-to-understand manner. For example, it might say, "You might want to use a scholarly paper search engine such as Google Scholar or PubMed."

[1710] Specific examples

[1711] For example, if a student types a question like "What are some tips for giving a successful presentation?", the process would go something like this:

[1712] 1. User types question: "What are some tips for giving a successful presentation?"

[1713] 2. The device sends the question to the server.

[1714] 3. The server parses the question and generates an appropriate prompt: "What specific tips can I use to give a successful presentation?"

[1715] 4. The server sends the generated prompt to the natural language processing model.

[1716] 5. The natural language processing model generates answers such as "set clear goals, practice, and use visual aids."

[1717] 6. The server formats the response and sends it to the device.

[1718] 7. The device displays formatted answers to students: "Successful presentations require clear goals, practice, and the use of visual aids."

[1719] In this way, the present invention enables students to receive individually optimized learning support, and provides support for effectively promoting inquiry-based learning.

[1720] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1721] Step 1:

[1722] Enter and submit your question

[1723] The user inputs questions they have during their learning process into the device, for example, "I want to find the latest research materials on air pollution."

[1724] The device converts the entered question into JSON data format and sends it to the server in real time using WebSocket or HTTP requests.

[1725] Input: A text question: "I would like to find the latest research on air pollution."

[1726] Output: The question data sent to the server is converted to JSON format.

[1727] Step 2:

[1728] Question Analysis

[1729] The server receives the question sent from the device and analyzes the question, extracting important keywords and context from the question.

[1730] The server analyzes the question data and prepares it to generate appropriate prompts, for example by extracting keywords such as "air pollution" and "latest research materials."

[1731] Input: A JSON question: "I want to find the latest research on air pollution."

[1732] Output: Analysis results (e.g. keywords and contextual information) for use by the prompt generation engine.

[1733] Step 3:

[1734] Prompt Generation

[1735] The server uses a prompt generation engine to generate an appropriate prompt based on the analysis results, for example, "What are some reliable sources for finding the latest research materials?"

[1736] Input: Analysis results (e.g., keywords and context information).

[1737] Output: The generated prompt (the text reads "What reliable sources can I use to find the latest research materials?").

[1738] Step 4:

[1739] Sending a prompt

[1740] The server sends the generated prompt to the natural language processing model (generative AI model), passing the prompt to the model in the form of an API request.

[1741] Input: Generated prompt (e.g., "What reliable sources can I use to find the latest research materials?").

[1742] Output: The prompt data sent to the natural language processing model.

[1743] Step 5:

[1744] Generating and receiving answers

[1745] A natural language processing model generates an answer based on the prompt it receives, such as "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[1746] The natural language processing model returns the generated answer to the server.

[1747] Input: Submitted prompt ("What reliable sources can I use to find the latest research materials?").

[1748] Output: The generated answer (e.g., "You may find it helpful to use a scholarly search engine such as Google Scholar or PubMed").

[1749] Step 6:

[1750] Formatting answers

[1751] The server formats the answer received from the natural language processing model, converting the answer into an easy-to-read format and adding bullet points and specific examples as needed.

[1752] Input: A generated answer (e.g., "You might want to use a scholarly search engine such as Google Scholar or PubMed").

[1753] Output: A formatted answer (e.g., "You may find it helpful to use a scholarly search engine such as Google Scholar or PubMed." "Examples: Google Scholar, PubMed").

[1754] Step 7:

[1755] Show Answers

[1756] The terminal displays the formatted response received from the server in a user interface, for example, in a chat box.

[1757] Input: A formatted answer (e.g., "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed.").

[1758] Output: User-visible display of answers.

[1759] (Application example 1)

[1760] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1761] Conventional learning support systems have had the problem of being unable to provide appropriate information and support in a timely manner for the challenges that students face individually.In addition, when students independently engage in inquiry-based learning, it is difficult for them to know how to access reliable information sources or how to gather appropriate information, which can slow down their learning progress.

[1762] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1763] In this invention, the server includes means for accepting questions related to task setting, information gathering, data organization, and presentations entered by students in the course of their studies, means for generating appropriate prompts using a generation engine corresponding to the content of the questions, means for sending the generated prompts to a natural language processing model and receiving answers, means for formatting the received answers and sending them to the student's terminal for display, and means for providing learning support through a content distribution service. This enables students to quickly and effectively obtain appropriate information related to the content of their studies.

[1764] "Problem setting" is the process by which students decide on a specific theme or question to be solved during the learning process.

[1765] "Information gathering" is the activity of gathering relevant data and knowledge based on the problem setting.

[1766] "Data organization" is the process of classifying, analyzing, and organizing collected information into an easy-to-understand format.

[1767] A "presentation" is the act of organizing the results of learning and presenting them to others in an easy-to-understand manner.

[1768] A "generation engine" is a system component that generates appropriate prompts based on the input question.

[1769] A "prompt" is an input sentence that gives instructions to a natural language processing model.

[1770] A "natural language processing model" is an AI technology that understands and generates human language.

[1771] "Answer formatting" is the process of organizing the answers received from a natural language processing model in an easy-to-read format.

[1772] A "terminal" is an electronic device that allows a user to input information and display results.

[1773] A "content distribution service" is a platform for providing information to users via the Internet.

[1774] This invention is a system that provides optimal individualized learning support to students as they progress through inquiry-based learning. The system accepts questions about task setting, information gathering, data organization, and presentations, and provides appropriate answers to those questions.

[1775] Hardware and software used

[1776] The hardware required to implement this system includes a smartphone, tablet, or personal computer. It also requires connection to a server, terminal, and user interface. The software used is Python, the OpenAI API, and a front-end framework (React, Flutter, etc.).

[1777] System Components

[1778] 1. How to contact us:

[1779] The device (e.g., a smartphone or PC) accepts questions from students through a chat box-style user interface. For example, a student might type in a question like, "I want to find the latest research materials on air pollution. Where should I look for them?"

[1780] 2. Prompt generation engine:

[1781] The server generates an appropriate prompt based on the question it receives. For example, after receiving a question, the server generates a prompt like, "Please explain in detail the following question that interests you: I'd like to find the latest research on air pollution. Where can I find it?"

[1782] 3. Natural Language Processing Models:

[1783] The server sends the generated prompt to a natural language processing model (e.g., OpenAI's GPT-3) and receives an answer from the model, such as, "You can use academic paper search engines such as Google Scholar or PubMed. You can use the filter function when searching for papers to find the latest research."

[1784] 4. Answer formatting method:

[1785] The server formats the answers it receives from the natural language processing model to make them easier to read, for example by editing the answers to make them easier to understand, bulleting important information, and adding examples.

[1786] 5. Display means:

[1787] The device will then display the formatted answer in a user interface. For example, the student's device might say, "You can use academic paper search engines such as Google Scholar or PubMed. Use the filter function when searching for papers to find the latest research."

[1788] By providing learning support through a content delivery service, students can quickly and effectively acquire the right information related to their learning. The system utilizes cutting-edge generative AI models and prompting technology to ensure optimal learning support is always provided to students.

[1789] Specific examples

[1790] For example, if a student types a question like this:

[1791] "I want to find the latest research on air pollution. Where can I find it?"

[1792] The system responds to this question in the following way:

[1793] 1. The device accepts the question.

[1794] 2. The server uses the prompt generation engine to generate the following prompt:

[1795] "Please explain in detail the following question that interests you: I would like to find the latest research materials on air pollution. Where can I find them?"

[1796] 3. The server sends the generated prompt to a natural language processing model and receives a response such as:

[1797] "You can use academic search engines like Google Scholar and PubMed, which have filters to help you find the latest research."

[1798] 4. The server formats the response it receives and sends it to the terminal for display.

[1799] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1800] Step 1:

[1801] During the learning process, the user enters questions or concerns into a chat box-style user interface. For example, the user might enter a question like, "I want to find the latest research materials on air pollution. Where should I look for them?" This input is recorded on the terminal as a string of characters.

[1802] Step 2:

[1803] The terminal sends the input question data to the server, where it is received and analyzed.

[1804] Step 3:

[1805] The server starts a prompt generation engine based on the received question. The question data received as input is passed to the prompt generation engine, which generates an appropriate prompt based on that. For example, this prompt might be in the form of "Please explain in detail the following question that interests you: I want to find the latest research materials on air pollution. Where can I find them?" The generated prompt is recorded as a string.

[1806] Step 4:

[1807] The server sends the generated prompt string to a natural language processing model, such as a generative AI model like GPT-3, which generates an answer based on the received prompt. The model uses the prompt data as input and generates an appropriate answer as output.

[1808] Step 5:

[1809] The server receives the answer output from the natural language processing model and passes it to the answer formatting engine. The answer formatting engine formats the received answer into an easy-to-understand format, for example by turning sentences into bullet points or adding specific examples. This formatting process generates an answer that is easy to understand and organized.

[1810] Step 6:

[1811] The server sends the formatted answers to the device, which then displays the received answer data on its user interface. For example, the student's screen might read, "We recommend using academic paper search engines such as Google Scholar or PubMed. Use the filter function when searching for papers to find the latest research."

[1812] Step 7:

[1813] The user reviews the displayed answers and decides on the next action to take, such as actually searching for the latest research materials using an academic paper search engine.

[1814] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1815] This invention is a system that provides effective, individually optimized learning support for students as they progress through inquiry-based learning. In particular, by combining it with an emotion engine that recognizes students' emotions and optimizes the learning process, it achieves more advanced support.

[1816] composition

[1817] The system mainly consists of the following components:

[1818] 1. Method of accepting questions

[1819] The terminal accepts questions from students. Specifically, it provides a chat box-style user interface, allowing students to input questions about setting assignments, gathering information, etc.

[1820] 2. Prompt Generation Engine

[1821] The server generates appropriate prompts based on the questions received from students. The prompt generation engine dynamically generates prompts using templates tailored to each learning process.

[1822] 3. Natural Language Processing Model

[1823] The server generates prompts and sends them to a natural language processing model, which uses the most advanced models available today, to receive responses.

[1824] 4. Answer formatting means

[1825] The server formats the answers received from the natural language processing model, specifically by making the answers easier to understand and converting them into a format that is useful to the student.

[1826] 5. Display means

[1827] The device displays the formatted answer to the student, allowing them to quickly get the information they need and move on to the next step in their learning.

[1828] 6. Emotion Engine

[1829] The server recognizes emotions from the user's input text and voice. The emotion engine uses emotion analysis algorithms to understand the student's emotional state.

[1830] 7. Emotion-linked prompt generation

[1831] The server uses the emotion engine to generate prompts based on the emotion data it receives. For example, if a negative emotion is detected, it generates an encouraging prompt.

[1832] A natural language description of the program's operation

[1833] Question acceptance method

[1834] The user inputs a question during the learning process. For example, they input a question such as "I would like to set a research topic about environmental issues" into the chat box.

[1835] Prompt Generation Engine

[1836] The server receives questions from users and generates corresponding prompts based on templates for each process, such as problem setting, information gathering, data organization, and presentation.

[1837] Natural Language Processing Model

[1838] The server sends the generated prompt to a natural language processing model to obtain an answer. For example, if the prompt is "Which aspects of environmental issues are you interested in?", the natural language processing model generates an answer such as "Air pollution, marine pollution, deforestation, etc."

[1839] Answer formatting means

[1840] The server formats the answer it receives from the natural language processing model, for example by turning the answer into a bulleted list or adding specific examples.

[1841] Display means

[1842] The device displays the formatted answer in a user interface, and the user decides based on the displayed information whether to ask further questions or proceed to the next step.

[1843] Adding emotion engine processing

[1844] emotion recognition

[1845] The server sends the user's input text and voice to the emotion engine, which then analyzes the text and voice to determine the user's emotional state (stress, joy, excitement, anxiety, etc.).

[1846] Emotion-linked prompt generation

[1847] The server uses the emotion data obtained from the emotion engine to generate emotion-linked prompts. For example, if a user enters "I'm having trouble finding research materials on air pollution" and the emotion engine detects "anxiety," the prompt generation engine will provide support such as, "First, try some reliable sources of information. If necessary, please refer to this guide."

[1848] Specific examples

[1849] For example, if a student types a question like "I'd like to find the latest research on air pollution, but I don't know where to start," the following happens:

[1850] 1. A user types a question: "I'm looking for the latest research on air pollution, but I don't know where to start."

[1851] 2. The device sends a question to the server.

[1852] 3. The server receives the question and passes it to the prompt generation engine.

[1853] 4. The emotion engine analyzes emotions from the question text and detects "anxiety."

[1854] 5. The prompt generation engine takes sentiment data into account to generate an appropriate prompt: "Let's start by trying some trusted sources, such as Google Scholar and PubMed."

[1855] 6. The server sends the prompt to the natural language processing model.

[1856] 7. Natural language processing models generate relevant answers: "You can use a scholarly search engine such as Google Scholar or PubMed."

[1857] 8. The server receives and formats the response.

[1858] 9. The server sends the formatted response to the device.

[1859] 10. The device displays the answer it receives in the user interface: "You may find it helpful to use a scholarly paper search engine such as Google Scholar or PubMed."

[1860] In this way, the system helps students to effectively engage in inquiry-based learning and provides special support based on emotion recognition, making students feel more at ease and empowering them to ask and answer their own questions.

[1861] The processing flow will be explained below.

[1862] Detailed steps in the question acceptance and prompt generation process

[1863] Step 1:

[1864] During the learning process, the user can input a question, for example, "I want to find the latest research on air pollution, but I don't know where to start" into the chat box.

[1865] Step 2:

[1866] The device sends the user's question to the server in real time, including the question content and the user ID.

[1867] Step 3:

[1868] The server receives the user's question and sends the text data to the emotion engine.

[1869] Step 4:

[1870] The emotion engine analyzes the received text data and recognizes the user's emotional state, for example, detecting "anxiety."

[1871] Step 5:

[1872] The server passes the emotion data obtained from the emotion engine to the prompt generation engine, along with the question content and the emotional state.

[1873] Step 6:

[1874] The prompt generation engine generates appropriate prompts based on sentiment data and the question itself, such as "Let's start by trying some trusted sources, such as Google Scholar and PubMed."

[1875] Step 7:

[1876] The server sends the generated prompt to the natural language processing model in the form of an API request.

[1877] Step 8:

[1878] A natural language processing model generates an answer based on the prompt received, such as "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[1879] Step 9:

[1880] The server formats the answers it receives from the natural language processing model, for example by adding bullet points to the answer or highlighting important information.

[1881] Step 10:

[1882] The server then sends the formatted response to the user's terminal, where the formatted response data is sent.

[1883] Step 11:

[1884] The device displays the received answer on the user interface, and the user can decide whether to ask further questions or proceed to the next step based on the displayed information.

[1885] Specific examples

[1886] As a specific example, the following describes in detail how a student would respond if they typed in a question such as, "I want to find the latest research materials on air pollution, but I don't know where to look."

[1887] Step 1:

[1888] A user types a question: "I'm looking for the latest research on air pollution, but I don't know where to start."

[1889] Step 2:

[1890] The device sends the user's question to the server. The sent data includes the user ID and the question.

[1891] Step 3:

[1892] The server receives the question and sends the text data to the emotion engine.

[1893] Step 4:

[1894] The emotion engine analyzes emotions from the question text and detects "anxiety."

[1895] Step 5:

[1896] The server passes the emotional data and question content to the prompt generation engine. The data includes the question content, "I want to find the latest research materials on air pollution, but I don't know where to look," and the emotional state, "anxiety."

[1897] Step 6:

[1898] The prompt generation engine generates appropriate prompts based on the sentiment and question content, such as "Let's start by trying some reliable sources, such as Google Scholar and PubMed."

[1899] Step 7:

[1900] The server sends the generated prompt to the natural language processing model (ChatGPT), which sends the prompt in the form of an API request.

[1901] Step 8:

[1902] A natural language processing model generates an answer based on the prompt, for example, "You might find it helpful to use a scholarly search engine such as Google Scholar or PubMed."

[1903] Step 9:

[1904] The server formats the answer received from the natural language processing model, for example by turning the answer into a list of items.

[1905] Step 10:

[1906] The server then sends the formatted response to the user's terminal. The transmitted data includes the formatted response.

[1907] Step 11:

[1908] The device displays the received answer on the user interface. For example, it may say, "We recommend using academic paper search engines such as Google Scholar or PubMed." The user can then begin searching for materials based on the information provided.

[1909] In this way, the system helps students to effectively engage in inquiry-based learning. In particular, by providing special support based on emotion recognition, students can feel more at ease while studying.

[1910] Example 2

[1911] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1912] Conventional learning support systems lacked adequate support for each student's learning situation and emotional state, making it difficult for students to effectively engage in inquiry-based learning. Furthermore, because they did not provide individually optimized learning support, they were unable to reduce the anxiety and stress students felt during the learning process.

[1913] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1914] In this invention, the server includes means for generating appropriate prompts using a generation engine corresponding to the content of the question, means for sending the generated prompts to a natural language processing model and receiving answers, means for formatting the received answers and sending them to the student's terminal for display, and means for recognizing emotions from the student's input text or voice and generating prompts based on that emotion data, thereby enabling individually optimal support according to the learning situation and emotional state of each student.

[1915] "Student" refers to a learner who uses this system to engage in inquiry-based learning.

[1916] The "question acceptance means" is a component for accepting questions from students regarding assignment setting, information gathering, data organization, and presentations.

[1917] The "generation engine" is a component that generates an appropriate prompt based on the content of the received question.

[1918] A "prompt" is an instruction or question generated by a generation engine and sent to a natural language processing model.

[1919] A "natural language processing model" is an AI model that generates answers based on generated prompts.

[1920] The "answer formatting means" is a component for organizing and formatting the answers received from the natural language processing model in an easy-to-understand manner.

[1921] The "emotion engine" is an algorithm that recognizes emotions from text and voice input by students and extracts that emotional data.

[1922] The "emotion-linked prompt generation means" is a means for generating a prompt based on emotion data obtained from the emotion engine.

[1923] "Terminal" means the device used by a student to enter questions and view answers from the system.

[1924] "Display means" refers to the functionality for visually presenting formatted answers to students.

[1925] This invention relates to a learning support system that effectively supports students' inquiry-based learning by accepting questions about task setting, information gathering, data organization, and presentations entered by students during the learning process and providing appropriate answers. In particular, it uses an emotion engine to analyze students' emotions and generates prompts based on those emotions to provide individually optimized learning support.

[1926] component

[1927] The system includes the following main components:

[1928] 1. Method of accepting questions

[1929] 2. Prompt Generation Engine

[1930] 3. Natural Language Processing Models (NLP Models)

[1931] 4. Answer formatting means

[1932] 5. Emotion Engine

[1933] 6. Emotion-linked prompt generation method

[1934] 7. Display means

[1935] Question acceptance method

[1936] While studying, students enter questions and challenges using a chat box-style user interface, which is provided by a software application running on a PC, tablet, smartphone, or other device. For example, a student might enter, "Tell me about the types of renewable energy."

[1937] Prompt Generation Engine

[1938] The server receives a question from the user and generates an appropriate prompt. The engine uses a template that corresponds to the question, generating prompts such as "What aspects of environmental issues are you interested in?" or "What are some reliable sources of information on environmental issues?"

[1939] Natural Language Processing Model

[1940] The generated prompt is sent from the server to a natural language processing model (e.g., GPT-4), which generates an appropriate answer based on the prompt. For example, it generates an answer such as, "There are solar power, wind power, hydroelectric power, and biomass power generation."

[1941] Answer formatting means

[1942] The server formats the answers it receives from the NLP model, which may include bulleting the answer, adding specific examples, and highlighting important information, such as "The following are the types of renewable energy:\n1. Solar power\n2. Wind power\n3. Hydroelectric power\n4. Biomass power."

[1943] Emotion Engine

[1944] The emotion engine analyzes user-supplied text and voice input to recognize emotional states (e.g., stress, joy, anxiety), for example using the Emotion API or similar algorithms.

[1945] Emotion-linked prompt generation method

[1946] Based on the emotional data obtained from the emotion engine, the prompt generation engine generates prompts according to the user's emotional state. For example, if a user types, "I'm having trouble finding research materials on air pollution," and anxiety is detected, the prompt will be adjusted to provide support such as, "Let's start by trying some reliable sources."

[1947] Display means

[1948] The formatted answer is sent from the server to the device and displayed on the user interface. The user can confirm the displayed answer and then enter further questions or proceed to the next step. For example, it might say, "The following are the types of renewable energy:\n1. Solar power generation\n2. Wind power generation\n3. Hydroelectric power generation\n4. Biomass power generation."

[1949] By combining the above components and their interaction, this invention can effectively support students' inquiry-based learning and provide individually optimized learning support.

[1950] Examples of prompt statements

[1951] 1. "What aspects of environmental issues interest you?"

[1952] 2. "What are some reliable sources of information on environmental issues?"

[1953] 3. "What are the main types of renewable energy?"

[1954] These prompts can be used to effectively obtain useful information from generative AI models.

[1955] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1956] Step 1: Enter your question

[1957] While studying, users input questions or problems using a chat box-style user interface. Specifically, they input text such as "Please tell me about the types of renewable energy" into an application running on a device such as a PC or smartphone. This input triggers the processing of the entire system.

[1958] Step 2: Submit your question

[1959] The terminal sends the user's question to the server. An HTTP POST request is often used here. Specifically, a data packet containing the question text entered by the user is sent to the server. The input is the user's question text, and the output is a response indicating that the data transfer to the server is complete.

[1960] Step 3: Prompt generation

[1961] The server passes the received question to the prompt generation engine, which generates an appropriate prompt based on a pre-configured template. For example, it generates a prompt such as "Please provide more information about renewable energy." The input is the question data received by the server, and the output is the generated prompt.

[1962] Step 4: Sentiment analysis

[1963] The server sends the question text to the emotion engine, which then analyzes it. The emotion engine uses a text analysis algorithm to recognize the user's emotions. For example, it can detect emotions such as "troubled" or "anxious." The input is the question text sent from the server, and the output is the emotion data resulting from the analysis.

[1964] Step 5: Emotion-linked prompt generation

[1965] Based on the emotion data received by the server from the emotion engine, the prompt generation engine generates a prompt according to the emotion. For example, if the server detects that the user is "in trouble," it creates a prompt such as "Let's start with some basic information." The input is emotion data and the original question, and the output is an emotion-linked prompt.

[1966] Step 6: Send prompts

[1967] The server sends the generated prompt to the natural language processing model (NLP model). Specifically, the prompt is sent to the natural language processing API via an HTTP request. The input is the generated prompt, and the output is a confirmation that the request was sent to the NLP model.

[1968] Step 7: Get the answer

[1969] The server receives the answer generated by the natural language processing model. For example, the NLP model might answer, "There are solar power, wind power, hydroelectric power, and biomass power generation." The input is the data returned by the NLP model, and the output is the answer data.

[1970] Step 8: Formatting your answers

[1971] The server then formats the answer it receives, making it easier for the user to understand. Specifically, it may do things like bullet points or insert additional information. For example, it may format the answer into something like "The following are the types of renewable energy:\n1. Solar power\n2. Wind power\n3. Hydroelectric power\n4. Biomass power." The input is the answer received from the NLP, and the output is the formatted answer.

[1972] Step 9: Submit your response

[1973] The server sends the formatted answer to the terminal as an HTTP response. The input is the formatted answer data, and the output is a response indicating that data transfer to the terminal is complete.

[1974] Step 10: Display answers

[1975] The terminal displays the received answer in the user interface. Specifically, the formatted answer is displayed in a chat box so that the user can see it. For example, it displays "The following are the types of renewable energy:\n1. Solar power generation\n2. Wind power generation\n3. Hydroelectric power generation\n4. Biomass power generation." The input is the answer data sent from the server, and the output is the visualized state provided to the user.

[1976] (Application example 2)

[1977] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1978] Conventional learning support systems have difficulty addressing students' psychological burdens and emotional needs, resulting in insufficient optimization of learning. Furthermore, they are unable to provide prompts and answers tailored to each student's learning progress and emotional state, and can only provide uniform support. This makes it difficult for students to progress effectively in their studies.

[1979] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for accepting questions related to task setting, information gathering, data organization, and presentations entered by students in the course of their studies; means for generating appropriate prompts using a generation engine corresponding to the content of the questions; means for sending the generated prompts to a natural language processing model and receiving answers; means for formatting the received answers and sending them to the student's terminal for display; means for recognizing emotions from the input text; and means including a generation engine for adjusting the prompts according to the recognized emotions. This enables optimal support to be provided according to each student's individual learning progress and emotional state.

[1980] "Problem setting" refers to the specific learning goals or problems that students set at the beginning of the learning process.

[1981] "Information gathering" refers to the act of collecting data and materials necessary for the learning process.

[1982] "Data organization" refers to the act of classifying and organizing collected information and processing it into a format that is easy to use.

[1983] A "presentation" is a means of communicating information to explain and announce the results of learning to others.

[1984] "Means for accepting questions" refers to the interface that allows the system to accept questions entered by students.

[1985] A "generation engine" is a program that generates appropriate prompts based on the student's question.

[1986] "Prompts" are instructions or questions generated by the system in response to students' questions or learning progress.

[1987] A "natural language processing model" is a machine learning algorithm for processing and understanding human language.

[1988] The "means for receiving an answer" refers to an interface for receiving an answer generated from a natural language processing model.

[1989] A "response formatter" is a program that converts the received responses into a format that is easy for students to understand.

[1990] A "terminal" is a device used by students to operate the learning support system.

[1991] An "emotion recognition means" is a program that analyzes a student's emotional state from input text.

[1992] A "prompt-adjusting generation engine" is a program that adjusts the content and expression of the prompt depending on the recognized emotion.

[1993] This invention is a system for providing learning support services in a physical store. The system is mainly composed of three entities: a server, a terminal, and a user. The roles and processing contents of each entity are explained below.

[1994] What the server does:

[1995] The server is the central processing unit and contains the following components:

[1996] A means of accepting questions: Receives and records questions entered by students. A chat box-style user interface is used in this section.

[1997] Generation engine: Generates appropriate prompts based on the question content. When generating prompts, templates corresponding to each learning process are used.

[1998] Natural Language Processing Model: The generated prompt is sent to a natural language processing model that uses the latest machine learning algorithms to receive an answer.

[1999] Formatting responses: Format the responses you receive in a way that is easier for students to understand. For example, add bullet points or examples.

[2000] Emotion recognition: Emotions are analyzed from the student's input text using a sentiment analysis algorithm.

[2001] Prompt-adjusting generation engine: Adjusts prompts based on emotion recognition results, generating prompts that provide encouragement or specific instructions as needed.

[2002] What the device does:

[2003] The terminal acts as the student interface and performs the following tasks:

[2004] Question input: Provide a chat box where students can enter questions about setting assignments, gathering information, etc.

[2005] Displaying formatted answers: Displaying formatted answers received from the server to students, allowing them to quickly move on to the next learning step.

[2006] What the user does:

[2007] The user (student) uses the above system to carry out the following learning process:

[2008] Entering questions: Enter any questions or issues that arise during the learning process into the chat box on your device.

[2009] Check the answer: Check the formatted answer from the server and use it as a reference for the next learning step.

[2010] Examples:

[2011] For example, if a student types a question like "I'm worried because I can't find any resources about environmental issues," the system will process it as follows:

[2012] 1. Accept Question: The server receives the student's input.

[2013] 2. Recognizing emotions: The server uses an emotion engine to recognize the emotion "anxiety."

[2014] 3. Generate a prompt: The generation engine takes this sentiment data into account to generate a prompt, such as "Please refer to the following steps. We will show you how to find resources related to environmental issues."

[2015] 4. Send to Natural Language Processing Model: The generated prompt is sent to a natural language processing model and an appropriate answer is received.

[2016] 5. Formatting the answer: For example, format the answer "Google Scholar and PubMed are useful" into a more relevant and understandable format for the question.

[2017] 6. Display on device: The formatted answer is displayed on the student's device, and a message is displayed saying, "Google Scholar and PubMed are useful."

[2018] Example prompt sentence:

[2019] Typed question: "I'm worried because I can't find any materials on environmental issues."

[2020] Generated prompt: "Let's use the following steps to help you find resources on environmental issues."

[2021] The natural language processing model answers: "Google Scholar and PubMed are useful."

[2022] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2023] Step 1:

[2024] Input: Students type their question into the chat box on their devices. Example: "I'm worried because I can't find any resources on environmental issues."

[2025] Action: The device sends this question to the server.

[2026] Output: The server receives the query.

[2027] Step 2:

[2028] Input: The query data received by the server.

[2029] How it works: The server sends the question text to the emotion engine, which recognizes the emotion.

[2030] Output: The emotion engine generates emotion data such as "anxiety" and sends it back to the server.

[2031] Step 3:

[2032] Input: Question data and sentiment data.

[2033] How it works: The server uses a generation engine to generate prompts based on the question and sentiment. Example: "Try these steps to help you find resources on environmental issues."

[2034] Output: The generated prompt.

[2035] Step 4:

[2036] Input: The generated prompt.

[2037] How it works: The server sends a prompt to the natural language processing model.

[2038] Output: Answer data from the natural language processing model. Example: "Google Scholar and PubMed are useful."

[2039] Step 5:

[2040] Input: Response data from a natural language processing model.

[2041] What it does: The server formats the answer data, for example by adding bullet points or specific examples. Example of a formatted answer: "Google Scholar and PubMed are useful."

[2042] Output: Formatted response data.

[2043] Step 6:

[2044] Input: Formatted response data.

[2045] What it does: The server sends a formatted response to the device.

[2046] Output: The formatted answer data is displayed on the terminal. Example: "Google Scholar and PubMed are useful."

[2047] Step 7:

[2048] Input: Formatted response data.

[2049] Action: The device displays the formatted answer data to the student.

[2050] Output: Helps students check their answers and guides them to the next step in their learning.

[2051] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2052] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2053] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2054] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2055] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2056] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2057] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2058] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2059] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2060] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2061] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2062] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2063] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2064] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[2065] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2066] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2067] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[2068] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2069] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2070] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2071] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2072] The following is further disclosed regarding the above embodiment.

[2073] (Claim 1)

[2074] A means to receive questions about the assignments, information gathering, data organization, and presentations that students input during the learning process;

[2075] a means for generating an appropriate prompt using a generation engine corresponding to the question content;

[2076] a means for sending the generated prompt to a natural language processing model and receiving a response;

[2077] A means to format the received answers, send them to the students' terminals and display them;

[2078] A system including:

[2079] (Claim 2)

[2080] 2. The system according to claim 1, wherein the prompt generation engine generates prompts according to preset templates for each learning process.

[2081] (Claim 3)

[2082] 10. The system of claim 1, wherein the natural language processing model provides answers based on a student's individual learning progress.

[2083] "Example 1"

[2084] (Claim 1)

[2085] A means to receive questions about the assignments, information gathering, data organization, and presentations that students input during the learning process;

[2086] a means for generating an appropriate prompt using a generation engine corresponding to the question content;

[2087] a means for sending the generated prompt to a natural language processing model and receiving a response;

[2088] A means to format the received answers, send them to the students' terminals and display them;

[2089] Educational support system including.

[2090] (Claim 2)

[2091] 2. The education support system according to claim 1, wherein the prompt generation engine generates prompts for each learning process according to a preset template.

[2092] (Claim 3)

[2093] 2. The educational support system according to claim 1, wherein the natural language processing model provides answers based on the student's individual learning progress.

[2094] (Claim 4)

[2095] 2. The education support system according to claim 1, wherein the means for accepting questions provides a user interface in the form of a chat box and transmits questions to the server in real time.

[2096] (Claim 5)

[2097] The educational support system described in claim 1, characterized in that the prompt generation engine dynamically generates a prompt based on a template from the received question, and sends the generated prompt to the natural language processing model in the form of an API request.

[2098] (Claim 6)

[2099] 2. The education support system according to claim 1, wherein the answer formatting means converts the answer received from the natural language processing model into an easy-to-read format and adds specific additional input and reference information.

[2100] "Application Example 1"

[2101] (Claim 1)

[2102] A means to receive questions about the assignments, information gathering, data organization, and presentations that students input during the learning process;

[2103] a means for generating an appropriate prompt using a generation engine corresponding to the question content;

[2104] a means for sending the generated prompt to a natural language processing model and receiving a response;

[2105] A means to format the received answers, send them to the students' terminals and display them;

[2106] A means of providing learning support through content distribution services;

[2107] A system including:

[2108] (Claim 2)

[2109] 2. The system according to claim 1, wherein the prompt generation engine generates prompts according to preset templates for each learning process.

[2110] (Claim 3)

[2111] 10. The system of claim 1, wherein the natural language processing model provides answers based on a student's individual learning progress.

[2112] "Example 2: Combining Emotion Engines"

[2113] (Claim 1)

[2114] A means to receive questions about the assignments, information gathering, data organization, and presentations that students input during the learning process;

[2115] a means for generating an appropriate prompt using a generation engine corresponding to the question content;

[2116] a means for sending the generated prompt to a natural language processing model and receiving a response;

[2117] A means to format the received answers, send them to the students' terminals and display them;

[2118] A means of recognizing emotions from students' input text and speech and generating prompts based on the emotion data;

[2119] A system including:

[2120] (Claim 2)

[2121] 2. The system according to claim 1, wherein the prompt generation engine generates prompts according to preset templates for each learning process.

[2122] (Claim 3)

[2123] 10. The system of claim 1, wherein the natural language processing model provides answers based on a student's individual learning progress.

[2124] "Application example 2 when combining emotion engines"

[2125] (Claim 1)

[2126] A means to receive questions about the assignments, information gathering, data organization, and presentations that students input during the learning process;

[2127] a means for generating an appropriate prompt using a generation engine corresponding to the question content;

[2128] a means for sending the generated prompt to a natural language processing model and receiving a response;

[2129] A means to format the received answers, send them to the students' terminals and display them;

[2130] a means for recognizing emotions from input text;

[2131] a generation engine for adjusting the prompt in response to the recognized emotion;

[2132] A system including:

[2133] (Claim 2)

[2134] 2. The system according to claim 1, wherein the prompt generation engine generates prompts according to preset templates for each learning process.

[2135] (Claim 3)

[2136] 10. The system of claim 1, wherein the natural language processing model provides answers based on a student's individual learning progress and emotional state. [Explanation of symbols]

[2137] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means to receive questions about the assignments, information gathering, data organization, and presentations that students input during the learning process; a means for generating an appropriate prompt using a generation engine corresponding to the question content; a means for sending the generated prompt to a natural language processing model and receiving a response; A means to format the received answers, send them to the students' terminals and display them; A system including:

2. 2. The system of claim 1, wherein the prompt generation engine generates prompts according to preset templates for each learning process.

3. The system of claim 1 , wherein the natural language processing model provides answers based on a student's individual learning progress.

Images