System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving a question from a user; means for analyzing the received question; means for generating an answer using a generative AI model based on an analysis result; and means for transmitting the generated answer to the user.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] In online learning and remote training environments, learners often face difficulties in obtaining prompt and appropriate answers to their various doubts and questions. Furthermore, there is a risk of reduced learning efficiency due to insufficient personalized learning support based on each learner's progress and interests. Furthermore, learners may face time and location constraints when accessing necessary resources in online environments. The present invention aims to solve these problems. [Means for solving the problem]

[0005] The present invention provides a means for a user to input a question from a terminal, and a server to receive and analyze the question. The server is provided with a system including a means for quickly generating an answer using a generative AI model based on the analysis results and sending the generated answer to the user. The system further includes a means for referencing the user's learning progress data and providing personalized learning resources based on the referenced data. The system also includes a means for sending and receiving questions and answers between the terminal and the server, and for performing natural language processing using a generative AI model, thereby realizing a system that always provides optimal learning support.

[0006] "User" refers to any individual or entity who participates in online learning or remote training and seeks out questions or learning resources through the System.

[0007] A "terminal" is a device used by a user to access the online learning system, and includes a computer, tablet, smartphone, etc.

[0008] "Server" refers to a central management system that receives and analyzes questions sent by users, invokes a generative AI model, and generates and returns appropriate answers.

[0009] "Means for receiving a question" refers to the process or technology by which the server receives a question entered by a user from a terminal.

[0010] "Means for analyzing questions" refers to technologies, including natural language processing (NLP), necessary for the server to understand the content of the question received and generate an appropriate answer.

[0011] A "generative AI model" refers to an artificial intelligence algorithm that generates optimal answers and learning resources based on received questions and user progress data.

[0012] "Means of generating answers" refers to the process or technology that uses a generative AI model to create appropriate answers to questions.

[0013] "Means for referencing learning progress data" refers to the process or technology by which the server retrieves the user's learning history and progress from the database.

[0014] "Means for providing personalized learning resources" refers to the processes and technologies that use generative AI models to generate and provide individually optimized learning content and resources based on a user's learning history and progress.

[0015] "API" refers to the application programming interface for sending and receiving data between a terminal and a server.

[0016] "Natural language processing" refers to the technology that enables computers to understand and analyze human language, and is used when analyzing questions.

[0017] "Formatting methods" refers to the processes and techniques used to format the answers obtained from a generative AI model into a format that is easy for users to view. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] This invention is a system for supporting online learning and training, in which a server receives questions sent by users from their devices and provides quick answers using a generative AI model. It also includes a function to provide personalized learning support based on the user's learning progress and interests.

[0040] Explanation of program processing

[0041] Accepting user questions

[0042] A user logs in to the learning application using a device and inputs a question. For example, "Please tell me the basic definition of differential calculus." The device then sends this question to the server via an API. The server receives the question data and also retrieves metadata such as the user ID and timestamp.

[0043] Question Analysis

[0044] The server analyzes the received question using a natural language processing (NLP) module. Here, it identifies the intent and gist of the question and recognizes it as a "question about the definition of differential." Based on the results of this analysis, the server requests the generative AI model to generate an answer.

[0045] Generating answers

[0046] The server calls a generative AI model based on the analysis results. The generative AI model generates an appropriate answer based on its internal database and trained algorithms. Specifically, it generates an answer such as, "Differentiation is a method for determining the rate of change of a function, and represents the ratio of change in y to change in x." The server receives this answer, formats it in a user-friendly format, and sends it to the device. The device displays this answer to the user.

[0047] Personalized learning support

[0048] When a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Referring to the user's past courses and current progress, the server asks the generative AI model to generate personalized learning resources. Based on the user's weaknesses and interests, the generative AI model generates, for example, "a detailed explanation of vector spaces in linear algebra" or "a set of exercises." The server then sends these resources to the user to support their learning.

[0049] Specific examples

[0050] Example 1: Question about a math problem

[0051] 1. The user sends the question "Please tell me the basic definition of differentiation" to the server from their terminal.

[0052] 2. The server receives the question and parses it using NLP.

[0053] 3. The server calls the generative AI model and asks it to generate an appropriate answer to the question.

[0054] 4. The generative AI model generates the answer, "Differentiation is a method for finding the rate of change of a function, and represents the ratio of change in y to change in x."

[0055] 5. The server sends this response to the user, who then checks the response on their device.

[0056] Example 2: Personalized learning support

[0057] 1. The user sends a request to the server from their device saying, "I want to learn more about linear algebra."

[0058] 2. The server references the user's learning history and progress data and asks the generative AI model to generate personalized learning resources.

[0059] 3. The generative AI model generates a "detailed explanation of vector spaces in linear algebra" and a "set of exercises."

[0060] 4. The server sends these resources to the user, who then checks them on the device.

[0061] As described above, the system of the present invention can provide users with fast and appropriate answers to their questions and enhance their learning experience through personalized learning resources.

[0062] The processing flow will be explained below.

[0063] Step 1:

[0064] A user logs into a learning application using a terminal and types a question, for example, "What is the basic definition of differentiation?"

[0065] Step 2:

[0066] The user's device sends the entered question to the server via API, along with metadata such as the question text, user ID, and timestamp.

[0067] Step 3:

[0068] The server receives the question sent from the terminal and records the received data in a log, including the question text, user ID, and timestamp.

[0069] Step 4:

[0070] The server uses a natural language processing (NLP) module to analyze the intent of the question, for example, identifying that the question is about "definition of differential."

[0071] Step 5:

[0072] The server sends appropriate instructions to the generative AI model based on the analysis results. In this case, the instruction sent to the generative AI model is "Explain the definition of differentiation."

[0073] Step 6:

[0074] A generative AI model receives instructions and generates an optimal answer based on its internal database and trained algorithms, such as "Differentiation is a way to find the rate of change of a function..."

[0075] Step 7:

[0076] The server receives the generated response and formats it in a user-friendly format, for example, in HTML or plain text.

[0077] Step 8:

[0078] The server sends the formatted response to the user's terminal, including the response text.

[0079] Step 9:

[0080] The user's device will display the received answer on the screen, where the user can check the "basic definition of differentiation."

[0081] Step 10:

[0082] The server retrieves the user's learning progress data from the database and prepares to provide learning support based on the user's progress and interests.

[0083] Step 11:

[0084] The server references the user's progress data and asks the generative AI model to generate personalized learning resources, for example, in response to a request to "learn more about linear algebra."

[0085] Step 12:

[0086] The generative AI model generates optimal learning resources based on the user's progress and weaknesses, such as a detailed explanation of vector spaces in linear algebra or a set of exercises.

[0087] Step 13:

[0088] The server receives the generated learning resources, formats them in a user-friendly format, and organizes resource links, files, etc.

[0089] Step 14:

[0090] The server transmits the learning resources to the user's terminal so that the user can view them.

[0091] Step 15:

[0092] The user's terminal displays the received learning resource, and the user views the content.

[0093] Through the above steps, the system of the present invention can quickly and appropriately answer the user's questions and provide personalized assistance based on the user's learning progress.

[0094] Example 1

[0095] 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."

[0096] Conventional online learning support systems have difficulty providing prompt and appropriate answers to users' questions and requests, and have had issues with not providing sufficient personalized learning support based on the user's progress and interests. Furthermore, there is a lack of automated processing for generating answers and providing learning support resources, which requires a lot of time and effort.

[0097] 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.

[0098] In this invention, the server includes means for receiving input from a user, means for analyzing the received input, means for invoking a generative AI model based on the analysis result to generate an answer, and means for formatting the generated answer and sending it to the user, thereby enabling the provision of prompt and appropriate answers to user questions and personalized learning support.

[0099] "User" refers to an individual who uses the system to learn or search for information.

[0100] "Input" refers to information such as a question or request that a user provides to a system.

[0101] "Terminal" refers to the device a user uses to access the system, such as a PC or smartphone.

[0102] "Server" refers to a central computer system that receives input from users and performs processing such as analysis and response generation.

[0103] "Communication means" refers to the method or protocol for sending and receiving data between a terminal and a server. A typical example is the Internet Protocol (IP).

[0104] "Means for receiving" refers to the function by which the server receives input sent from the terminal.

[0105] "Means for analyzing" refers to the function of understanding the content of received input and performing processing to identify its intent and gist.

[0106] A "generative AI model" refers to an algorithm that uses machine learning and databases to automatically generate appropriate answers or resources from specific inputs.

[0107] "Means for generating answers" refers to the function of calling a generative AI model based on the analysis results and creating answers to users' questions.

[0108] "Means for formatting and sending" refers to a function for formatting generated answers and the like into a format that is easy for the user to view and sending it to the user's terminal.

[0109] "Progress data" refers to information about the progress of a user's learning, such as their learning status and past history.

[0110] "Personalized learning resources" refers to learning content and materials that are specifically customized based on a user's progress data and interests.

[0111] "Personalization" refers to providing services and content that are individualized according to each user's needs and past history.

[0112] This invention is a system for supporting online learning and training, in which a server receives questions sent by users from their devices and provides quick answers using a generative AI model. It also provides personalized learning support based on the user's learning progress and interests.

[0113] First, the user logs in to the learning application using their device. The learning application can be provided in various forms, such as a web browser or a dedicated application. When the user enters a question, the device sends this input to the server via an API. For example, if the user enters "Please tell me the basic definition of differentiation," the device sends this question data to the server.

[0114] The server receives the question data and acquires metadata such as the user ID and timestamp. The received question is analyzed by a natural language processing (NLP) module. The NLP module analyzes the input question and identifies its intent and gist. For example, it may recognize that the question is about the definition of differential. Based on the analysis results, the server invokes a generative AI model to generate an answer.

[0115] The generative AI model is equipped with an internal database and machine learning algorithms to generate appropriate answers. As a specific example of an answer, it might generate the following: "Differentiation is a method for determining the rate of change of a function, and represents the ratio of change in y to change in x." The server receives the generated answer and formats it in a format that is easy for the user to view. The formatted answer is then sent to the device, where the user can view it.

[0116] Furthermore, if a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Based on the user's past courses and current progress, the server asks the generative AI model to generate personalized learning resources. Based on the user's weaknesses and interests, the generative AI model generates, for example, "a detailed explanation of vector spaces in linear algebra" or "a set of exercises." The server formats these resources and sends them to the user's device. The user can view the resources on their device and use them for their studies.

[0117] As an example, the following prompt sentence is used for a generative AI model:

[0118] Question and Answer Generation

[0119] Generate a detailed answer to the user's question, "What is the basic definition of differentiation?"

[0120] Personalized learning resource generation

[0121] Based on a user's request to "learn more about linear algebra," suggest personalized learning resources based on the user's past learning history.

[0122] As described above, the present invention can quickly and appropriately answer user questions and provide personalized learning support according to the user's progress and interests, thereby enabling the user to study efficiently and effectively.

[0123] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0124] Step 1: Accepting user questions

[0125] 1. A user logs in to a learning application using a terminal. The input is the user's login information, and the output is a notification of login success or failure.

[0126] 2. The user inputs a question into the learning application. For example, "Please tell me the basic definition of differential calculus." The input is the user's question text, and the output is the transmission of the question data from the terminal to the server.

[0127] 3. The device uses the API to send the user's question data to the server. The input is the question text and metadata (user ID, timestamp), and the output is the status of successful submission.

[0128] Step 2: Parsing the Question

[0129] 1. The server receives the user's query data. The input is the query data sent from the device, and the output is the saving of the query data and metadata to the internal storage.

[0130] 2. The server's natural language processing (NLP) module analyzes the received question. The input is the question text, and the output is the analysis results that identify the intent and gist of the question.

[0131] 3. Based on the intent of the question, the server prepares data to be passed to the generative AI model. The input is the analysis result of the NLP module, and the output is the input data for the generative AI model.

[0132] Step 3: Generate the answer

[0133] 1. The server invokes the generative AI model based on the analysis results. The input is the analysis results, and the output is the success status of the generation request.

[0134] 2. Generative AI models generate answers using internal databases and machine learning algorithms. The input is the analysis result, and the output is the generated answer text.

[0135] 3. The server receives and formats the generated answer: the input is the generated answer text, and the output is the answer converted into a user-friendly format.

[0136] Step 4: Returning the Answer

[0137] 1. The server sends a formatted answer to the user's terminal. The input is the formatted answer, and the output is the success status of the answer transmission.

[0138] 2. The terminal displays the answer received from the server to the user. The input is the formatted answer and the output is the display of the answer to the user.

[0139] 3. The user checks the answers on the device and uses them to help them learn. The input is the displayed answer text, and the output is the user's learning progress.

[0140] Step 5: Personalized learning support

[0141] 1. A user requests, "I want to learn more about linear algebra." The input is the user's request text, and the output is the transmission of the request data from the terminal to the server.

[0142] 2. The device uses the API to send a request to the server. The input is the request text and metadata, and the output is a successful transmission status.

[0143] 3. The server retrieves the user's learning history and progress data from the database. The input is the user ID, and the output is the retrieved learning history and progress data.

[0144] 4. The server requests the generative AI model to generate personalized learning resources. The input is the learning history and progress data, and the output is the success status of the generation request.

[0145] 5. The generative AI model generates learning resources tailored to the user. For example, it generates a "detailed explanation of vector spaces in linear algebra" or a "set of exercises." The input is learning history and progress data, and the output is the generated learning resource.

[0146] 6. The server formats the generated learning resource and sends it to the user's terminal. The input is the generated learning resource, and the output is the successful transmission status of the formatted learning resource.

[0147] 7. The user checks the resources on the device and uses them for learning. The input is the formatted learning resource, and the output is the enrichment of the user's learning.

[0148] (Application example 1)

[0149] 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."

[0150] Conventional online learning systems have difficulty in providing quick and accurate answers to user questions, and they lack personalized learning support. They also have difficulty effectively utilizing users' learning history and progress information to provide optimal learning resources.

[0151] 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.

[0152] In this invention, the server includes means for receiving questions from users, means for analyzing the received questions, means for generating answers using a generative AI model based on the analysis results, means for sending the generated answers to the users, means for sending questions sent from the users' devices to the server via an API, means for formatting the generated answers and sending them to the users' devices, means for acquiring the users' learning history and progress information and providing personalized learning resources, and means for generating personalized learning content using the generative AI model. This makes it possible to quickly and accurately answer users' questions and provide optimal learning resources based on the users' learning progress and interests.

[0153] The "means for receiving a question from a user" refers to a device or system that has the function of receiving a question entered by a user through a terminal or interface.

[0154] The "means for analyzing the received question" refers to a device or system that has the function of analyzing the received question using natural language processing technology or the like and identifying the intent and content of the question.

[0155] "Means for generating answers using a generative AI model based on the analysis results" refers to devices or systems that have the functionality to utilize a generative AI model to generate appropriate answers based on the content of the analyzed question.

[0156] The "means for transmitting the generated answer to the user" refers to a device or system that has the function of formatting the generated answer and transmitting it to the terminal used by the user.

[0157] "Means for sending questions sent from a user's terminal to a server via an API" refers to a device or system that has the function of sending questions entered by a user to a server via an application programming interface.

[0158] "Means for formatting the generated answer and sending it to the user's device" refers to a device or system that has the function of converting the answer generated by the generative AI model into a format that is easy for the user to view and sending it to the user's device.

[0159] "Means for acquiring a user's learning history and progress information and providing personalized learning resources" refers to a device or system that has the function of acquiring a user's past learning data and current progress status and providing personalized learning resources based on that data.

[0160] "Means for generating personalized learning content using generative AI models" refers to devices or systems that utilize generative AI models to generate optimal learning content based on a user's learning history and interests.

[0161] The present invention is a system for supporting online learning and training, in which a server receives questions sent by a user from a terminal and provides quick answers using a generative AI model. It also provides personalized learning support based on the user's learning progress and interests. Specific embodiments of the system are described below.

[0162] Hardware and software used

[0163] To realize the system of the present invention, the following hardware and software are required.

[0164] Hardware: Smartphones, tablets, personal computers, etc.

[0165] Software: Python, Requests library, generative AI model (e.g., OpenAI (registered trademark) GPT-3 (registered trademark)), natural language processing module (e.g., SpaCy, NLTK)

[0166] System Configuration

[0167] Accepting user questions

[0168] Users log in to the learning application using a device such as a smartphone or tablet and enter a question. This question is sent to the server via an application programming interface (API). The server receives the question data and also acquires metadata such as the user ID and timestamp.

[0169] Question Analysis

[0170] The server analyzes the received question using a natural language processing module. Here, it identifies the intent and gist of the question and performs an appropriate analysis based on the content of the question. Based on the results of this analysis, it requests a generative AI model to generate an answer.

[0171] Generating answers

[0172] The server calls the generative AI model to generate an appropriate answer to the question. The generative AI model generates an answer based on its internal database and trained algorithms and returns it to the server. The server receives this answer, formats it in a user-friendly format, and sends it to the device. The device displays this answer to the user.

[0173] Personalized learning support

[0174] When a user inputs a learning request such as "I want to learn more," the server retrieves the user's learning history and progress data. Based on the user's past courses and current progress, the server requests the generative AI model to generate personalized learning resources. The generative AI model generates optimal learning content (for example, "A detailed explanation of vector spaces in linear algebra" or "Practice problems") based on the user's weaknesses and interests. The server then sends these resources to the user to support their learning.

[0175] Specific examples

[0176] Accepting questions and providing answers

[0177] 1. A user types a question into a smartphone app: "Please tell me the basic definition of differentiation."

[0178] 2. The server receives this question and parses it using the NLP module.

[0179] 3. The server calls the generative AI model, which generates an appropriate answer to the question, and obtains the answer, "Differentiation is a method for finding the rate of change of a function, and represents the ratio of change in y to change in x."

[0180] 4. This response is sent to the user's device and displayed.

[0181] Personalized learning support

[0182] 1. A user requests, "I want to learn more about linear algebra."

[0183] 2. The server obtains the user's learning history and progress.

[0184] 3. Using a generative AI model, we generate personalized resources such as "Detailed explanations of vector spaces in linear algebra" and "Practice problems" based on the user's learning history and interests.

[0185] 4. The generated resource is provided to the user.

[0186] Prompt Sentence Examples

[0187] "A user has entered the question 'What is the basic definition of derivative?' Use a generative AI model to generate the best answer to answer this question quickly and accurately."

[0188] The above is a specific embodiment and flow for carrying out the invention.

[0189] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0190] Step 1:

[0191] A user logs into the learning application on a terminal and enters a question.

[0192] Input: Username, password, question (e.g. "What is the basic definition of differentiation?")

[0193] Processing: After user authentication, obtain the question content

[0194] Output: Request data to send the question to the server via API

[0195] Step 2:

[0196] The server receives the question data via API and obtains the metadata (user ID, timestamp, etc.).

[0197] Input: Request data (question content, user ID, timestamp)

[0198] Processing: Parse the received question data and extract metadata

[0199] Output: Analysis data using the query and metadata

[0200] Step 3:

[0201] The server analyzes the received question using a natural language processing (NLP) module.

[0202] Input: Analysis data (question content, user ID, timestamp)

[0203] Processing: The NLP module identifies the intent and gist of the question (e.g., "Question about the definition of differential")

[0204] Output: NLP analysis results (analyzed question intent and summary)

[0205] Step 4:

[0206] The server requests the generation of an answer based on the analysis results and a generative AI model.

[0207] Input: NLP analysis results

[0208] Processing: Enter a prompt (e.g., "Please tell me the basic definition of differentiation") into the generative AI model and generate an answer.

[0209] Output: Generated answer (e.g., "Derivative is a way to find the rate of change of a function; it is the ratio of change in y to change in x.")

[0210] Step 5:

[0211] The server formats the generated answers in a user-friendly format and sends them to the device via an API.

[0212] Input: Generated Answer

[0213] Processing: Reformatting the response (e.g., converting it to JSON) and sending it

[0214] Output: The formatted answer sent to the user's terminal

[0215] Step 6:

[0216] The user checks the generated answer on the device.

[0217] Input: Formatted answer (e.g., "Derivative is a way to find the rate of change of a function; it is the ratio of change in y to change in x.")

[0218] Processing: Displayed by application

[0219] Output: User views displayed answer

[0220] Step 7:

[0221] When a user requests to "learn more," the server retrieves the user's learning history and progress data.

[0222] Input: User's new request (e.g., "I want to learn more about linear algebra"), User ID

[0223] Processing: Retrieve user learning history and progress information from the database

[0224] Output: Acquired learning history and progress data

[0225] Step 8:

[0226] The server generates personalized learning content using a generative AI model based on the acquired learning history.

[0227] Input: Acquired learning history and progress data, generative AI model

[0228] Processing: Generate personalized learning content (e.g., "Detailed explanation of vector spaces in linear algebra" or "Practice problems") using learning history and progress information

[0229] Output: Generated learning content

[0230] Step 9:

[0231] The server transmits the generated study content to the user terminal, and the user checks the study content.

[0232] Input: Generated learning content

[0233] Processing: Sending personalized learning content via API

[0234] Output: Learning content sent to the user's device, the user views the content

[0235] The above are the specific processing steps for carrying out the invention.

[0236] 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.

[0237] This invention is a system for supporting online learning and remote training, which analyzes user questions, recognizes the user's emotional state using an emotion engine, and provides fast and personalized answers using a generative AI model.The invention aims to improve the learning experience by referring to the user's learning progress data and providing answers and learning resources tailored by the emotion engine.

[0238] Explanation of program processing

[0239] Accepting user questions

[0240] A user logs into the learning application using their device and enters a question, for example, "What is the basic definition of differential calculus?" The user's device then sends the entered question to the server via an API, which receives metadata such as the question text, user ID, and timestamp.

[0241] Question Analysis

[0242] The server analyzes the received question using a natural language processing (NLP) module. Through the analysis, it identifies the intent of the question and recognizes it as a "question about the definition of differential." The emotion engine also analyzes the question text and recognizes the user's emotional state (e.g., excitement, stress, frustration, etc.).

[0243] Generating sentiment-based answers

[0244] The server sends appropriate instructions to the generative AI model based on the analysis results. At this time, the emotion engine adjusts the tone and content of the response based on the user's emotional state. For example, if the user is feeling stressed, the generative AI model will generate a response with a more polite and supportive tone. For example, in addition to the response "Differentiation is a way to find the rate of change of a function...", it will also include the advice "Take your time and learn slowly."

[0245] Formatting and Sending

[0246] The server receives the generated answer and formats it for the user to see (for example, by formatting the answer text in HTML or plain text), then sends the formatted answer to the user's device, where the user can view the answer.

[0247] Personalized learning support

[0248] When a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Referring to the user's past courses and current progress, the server asks the generative AI model to generate personalized learning resources. The emotion engine also references the user's emotional data and provides learning resources tailored to the user's specific emotional state. For example, if the user is interested, the server will include challenging content. Conversely, if the user is feeling stressed, the server will provide basic, easy-to-understand content.

[0249] Specific examples

[0250] Example 1: Math Question

[0251] 1. The user sends a question to the server from their terminal: "Please tell me the basic definition of differentiation."

[0252] 2. The server uses NLP to analyze the question and uses an emotion engine to recognize that the user is feeling stressed.

[0253] 3. The generative AI model generates a polite answer such as, "Differentiation is a way to find the rate of change of a function..." and adds the advice, "Take your time and learn."

[0254] 4. The server formats the answers and sends them to the user's device, where they review the answers and receive an emotionally supportive learning experience.

[0255] Example 2: Personalized learning support

[0256] 1. The user sends a request to the server from their device saying, "I want to learn more about linear algebra."

[0257] 2. The server references the user's learning history and progress data and uses an emotion engine to recognize the user's interests.

[0258] 3. The generative AI model generates a "detailed explanation of vector spaces in linear algebra" and a "set of applied problems."

[0259] 4. The server formats and sends these resources to the user's device, where the user can review the resources and receive a personalized learning experience based on their interests.

[0260] The system of the present invention can significantly enhance the learning experience by recognizing the user's emotional state and providing appropriate answers and learning resources based on that.

[0261] The processing flow will be explained below.

[0262] Step 1:

[0263] A user logs into a learning application using a terminal and types a question, for example, "What is the basic definition of differentiation?"

[0264] Step 2:

[0265] The user's device sends the entered question to the server via API, along with metadata such as the question text, user ID, and timestamp.

[0266] Step 3:

[0267] The server receives the question sent from the terminal and records the received data in a log, including the question text, user ID, and timestamp.

[0268] Step 4:

[0269] The server analyzes the received question using a natural language processing (NLP) module, identifying the intent of the question and recognizing it as a question about the definition of differential.

[0270] Step 5:

[0271] The emotion engine analyzes the question text and recognizes the user's emotional state, for example, determining whether the user is stressed or excited.

[0272] Step 6:

[0273] The server sends appropriate instructions to the generative AI model based on the analysis results and the emotion engine's recognition results, such as "Explain the definition of differentiation," and also instructs the model to adjust the tone and content of the response based on the user's emotional state.

[0274] Step 7:

[0275] Generative AI models receive instructions and generate optimal answers based on their internal database and trained algorithms, such as "Differentiation is a method for determining the rate of change of a function, and it represents the ratio of change in y to change in x."

[0276] Step 8:

[0277] The server receives the generated response and formats it in a user-friendly format, for example, in HTML or plain text.

[0278] Step 9:

[0279] The server sends the formatted response to the user's terminal, including the response text.

[0280] Step 10:

[0281] The user's device displays the received answers on the screen, allowing the user to review the answers and enjoy an emotionally supportive learning experience.

[0282] Step 11:

[0283] The server retrieves the user's learning progress data from the database and prepares to provide learning support based on the user's progress and interests.

[0284] Step 12:

[0285] The server references the user's progress data and asks the generative AI model to generate personalized learning resources, for example, in response to a request to "learn more about linear algebra."

[0286] Step 13:

[0287] The generative AI model generates optimal learning resources based on the user's progress and weaknesses, such as a detailed explanation of vector spaces in linear algebra or a set of exercises.

[0288] Step 14:

[0289] The server receives the generated learning resources, formats them in a user-friendly format, and organizes resource links, files, etc.

[0290] Step 15:

[0291] The server transmits the learning resources to the user's terminal so that the user can view them.

[0292] Step 16:

[0293] The user's device displays the received learning resources, and the user browses the content, resulting in a personalized learning experience based on their interests.

[0294] Through these steps, the system of the present invention can quickly and appropriately answer the user's questions and provide personalized assistance based on the user's learning progress and emotional state.

[0295] Example 2

[0296] 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."

[0297] Conventional online learning systems have the problem that they provide mechanical answers to user questions and do not provide personalized answers that reflect the user's emotions or learning progress. As a result, users may lose motivation to learn and feel stressed.

[0298] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving a question from a user, a means for performing natural language processing based on the received question, a means for analyzing the question and recognizing the emotional state, a means for generating an answer using a generative AI model based on the analysis and recognition results, and a means for sending the generated answer to the user. This makes it possible to provide personalized appropriate answers and learning resources based on the user's emotional state and learning progress.

[0299] A "user" is an individual or entity that utilizes the system to enter questions and receive answers.

[0300] A "question" is a text message that requests information that the user enters into the system.

[0301] "Terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[0302] A "server" is a computer system that receives and processes user questions, and generates and transmits answers.

[0303] "API" stands for Application Programming Interface, which provides rules and procedures for different software programs to communicate with each other.

[0304] "Natural language processing (NLP)" is a technology that allows computers to understand, analyze, and generate human language (natural language).

[0305] An "emotion engine" is a software module for analyzing and recognizing the emotional state from a user's text.

[0306] A "generative AI model" is an artificial intelligence model that generates appropriate answers based on analysis results.

[0307] "Metadata" refers to additional information related to the question text (e.g., user ID and timestamp).

[0308] "Personalization" means providing content that is customized according to the characteristics, emotional state, learning progress, etc. of each individual user.

[0309] "Formatting" refers to converting generated answers or resources into a user-friendly format (e.g., HTML or plain text).

[0310] "Learning resources" refers to educational materials and information provided to assist users in their learning.

[0311] This invention is a system for supporting online learning and remote training, which analyzes user questions, recognizes the user's emotional state using an emotion engine, and provides fast and personalized answers using a generative AI model.The invention aims to improve the learning experience by referring to the user's learning progress data and providing answers and learning resources tailored by the emotion engine.

[0312] Accepting user questions

[0313] A user logs in to the learning application using a device and enters a question, for example, "Please tell me the basic definition of differential calculus." The user's device sends the question text along with metadata including the user ID and timestamp to the server via an API. The server receives this data.

[0314] Question Analysis

[0315] The server analyzes the received question using a natural language processing (NLP) module. This analysis identifies the intent of the question and recognizes that it is a question about the definition of differential. The emotion engine also analyzes the question text and recognizes the user's emotional state (e.g., excitement, stress, frustration, etc.).

[0316] Generating sentiment-based answers

[0317] The server sends appropriate instructions to the generative AI model based on the analysis results and emotion recognition results, such as the following prompt:

[0318] Example prompt sentence:

[0319] "Explain the definition of differentiation in detail and respond in a gentle tone because the user is stressed."

[0320] Based on the instructions, the generative AI model generates a polite answer, such as "Differentiation is a way to find the rate of change of a function..." It also adds advice such as "Take your time and learn slowly."

[0321] Formatting and Sending

[0322] The server receives the generated answer, formats it into a user-friendly format (e.g., HTML or plain text), and sends the formatted answer back to the user's device via the API, where the user can view the answer.

[0323] Personalized learning support

[0324] When a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Based on this, it asks the generative AI model to generate personalized learning resources. At this time, the emotion engine also references the user's emotional data and provides learning resources tailored to the user's specific emotional state. For example, if the user is interested, it will include challenging content, and conversely, if the user is feeling stressed, it will provide basic, easy-to-understand content.

[0325] Specific examples

[0326] Example 1: Math Question

[0327] 1. The user sends a question to the server from their terminal: "Please tell me the basic definition of differentiation."

[0328] 2. The server uses NLP to analyze the question and uses an emotion engine to recognize that the user is feeling stressed.

[0329] 3. The generative AI model generates the answer, "Differentiation is a way to find the rate of change of a function..." and adds the advice, "Take your time and learn."

[0330] 4. The server formats the answers and sends them to the user's device, where they review the answers and receive an emotionally supportive learning experience.

[0331] Example 2: Personalized learning support

[0332] 1. The user sends a request to the server from their device saying, "I want to learn more about linear algebra."

[0333] 2. The server references the user's learning history and progress data and uses an emotion engine to recognize the user's interests.

[0334] 3. The generative AI model generates a "detailed explanation of vector spaces in linear algebra" and a "set of applied problems."

[0335] 4. The server formats and sends these resources to the user's device, where the user can review the resources and receive a personalized learning experience based on their interests.

[0336] The system of the present invention can significantly improve the learning experience by taking into account the user's emotional state and learning progress.

[0337] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0338] Step 1: Accepting user questions

[0339] A user uses a terminal to log in to a learning application and enter a question, for example, "What is the basic definition of differential calculus?"

[0340] The device sends the entered question text along with metadata including the user ID and timestamp to the server via API.

[0341] Input: The question text, user ID, and timestamp entered by the user on the terminal.

[0342] Output: Question data sent to the server (question text, user ID, timestamp).

[0343] Step 2: Parsing the Question

[0344] The server passes the received question data to a natural language processing (NLP) module, which analyzes the intent of the question. For example, it identifies the question as "a question about the definition of differential."

[0345] An emotion engine analyzes the question text and recognizes the user's emotional state (e.g., excitement, stress, frustration, etc.).

[0346] Input: Received question data (question text, user ID, timestamp).

[0347] Output: Parsed question content and user emotional state data.

[0348] Step 3: Generate sentiment-based answers

[0349] The server sends appropriate instructions to the generative AI model based on the analysis results (question content and emotional state), sending the following prompt to the generative AI model:

[0350] Example prompt: "Explain the definition of differentiation in detail and respond in a gentle tone as the user is stressed."

[0351] Based on the instructions, the generative AI model generates a polite answer, such as "Differentiation is a way to find the rate of change of a function..." It also adds advice such as "Take your time and learn slowly."

[0352] Input: The parsed question, the user's emotional state, and the prompt for the generative AI model.

[0353] Output: The generated answer text.

[0354] Step 4: Format and send

[0355] The server receives the generated response text and formats it into a user-friendly format (e.g., HTML or plain text).

[0356] The server then sends the formatted response back to the user's device via the API.

[0357] The user checks the answer on the terminal.

[0358] Input: The generated answer text.

[0359] Output: The formatted answer text and the answer sent to the user's device.

[0360] Step 5: Personalized learning support

[0361] If a user requests, "I want to learn more about linear algebra,"

[0362] The server retrieves the user's learning history and progress data from the database.

[0363] The server requests the generative AI model to generate personalized learning resources based on the referenced data and the user's emotional state as determined by the emotion engine.

[0364] For example, if a user is interested, include challenging content, but if they are stressed, provide basic, easy-to-understand content.

[0365] The generative AI model generates learning resources (e.g., a detailed explanation of vector spaces in linear algebra or a set of applied problems) based on instructions.

[0366] The server formats the generated learning resources and sends them to the user's terminal.

[0367] The user checks the learning resources on the device.

[0368] Input: User learning history, progress data, emotional state, and instructions to the generative AI model.

[0369] Output: The formatted learning resource and the learning resource sent to the user's device.

[0370] (Application example 2)

[0371] 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."

[0372] In modern manufacturing, operators and engineers working on factory floors need to receive technical information and training quickly and effectively. However, existing systems generally provide general learning content, making it difficult to provide personalized assistance based on individual users' emotional state and learning progress. Furthermore, there is a lack of means to provide appropriate support that takes emotions into account when users ask questions. This can reduce the effectiveness of operators and engineers' learning, negatively impacting on-site efficiency and quality.

[0373] The identification process by the identification 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 receiving a question from a user, means for analyzing the received question, means for generating an answer using a generative AI model based on the analysis result, means for sending the generated answer to the user, means for recognizing the user's emotional state, means for adjusting the tone and content of the answer based on the recognized emotional state, means for referencing the user's learning progress data, and means for providing personalized learning resources using a generative AI model based on the referenced data. This enables personalized support according to the user's emotional state and learning progress, thereby improving the effectiveness of technical information and training at the factory floor.

[0374] The "means for receiving a question from a user" is a function for transmitting a question entered by a user using a terminal to a server or related systems.

[0375] "Means for analyzing received questions" refers to a function that includes natural language processing (NLP) technology used to analyze questions received by the server and understand their content and intent.

[0376] "Means for generating answers using a generative AI model" refers to a function that utilizes an AI model to automatically generate appropriate answers based on the analysis results.

[0377] The "means for transmitting the generated answer to the user" is a function that formats the generated answer and transmits it to the user's terminal for display.

[0378] The "means for recognizing the user's emotional state" is a technology for analyzing the question text and the user's voice data to detect the user's emotional state (for example, excitement, stress, dissatisfaction, etc.).

[0379] The "means for adjusting the tone and content of the response based on the recognized emotional state" is a function that appropriately adjusts the expression method and content of the response according to the user's emotional state.

[0380] The "means for referencing user's learning progress data" is a function for retrieving and referencing the user's past learning history and progress status from a database.

[0381] "Means for providing personalized learning resources using a generative AI model based on referenced data" refers to a function that utilizes an AI model to generate individually optimized learning resources based on referenced learning progress data.

[0382] The "means for formatting and sending to the user's terminal" is a function for formatting the generated answers and learning resources into an appropriate format and sending them to the user's terminal.

[0383] The "means for displaying formatted answers to the user" is a function for displaying formatted answers and learning resources on the user's terminal.

[0384] "Means for viewing answers and learning resources using a head-mounted display" is a function for viewing answers and learning resources through the screen of a head-mounted display worn by the user.

[0385]

[0386] The system for realizing this invention provides a learning support application "SmartFactoryTutor" that is installed on a factory robot. A detailed embodiment of this system will be described below.

[0387] The server receives and analyzes input from the device used by the user (e.g., a tablet or head-mounted display). Specifically, the user enters a question in voice or text format. For example, the user might enter, "Please tell me the maintenance procedure for the machine."

[0388] The received question is sent to a server via an API, and the server receives metadata such as the question text, user ID, and timestamp. The server then analyzes the received question using a natural language processing (NLP) module (e.g., SpaCy or NLTK). This identifies the intent of the question and recognizes that it is a "question about maintenance procedures." An emotion engine (e.g., IBM Watson®) is then used to analyze the question text and recognize the user's emotional state (e.g., impatience, anxiety, excitement, etc.).

[0389] Based on the analysis results, the server sends instructions to a generative AI model (such as OpenAI GPT-3) to generate a response. The tone and content of the response are adjusted based on the user's emotional state as recognized by the emotion engine. For example, if the user is feeling impatient, the generative AI model will generate a polite and supportive response such as, "Machine maintenance is a very important process. Let's take it easy and check each step one by one."

[0390] The generated answers are formatted in HTML or plain text and sent from the server to the user's device, where they can view the answers via a tablet or head-mounted display.

[0391] Furthermore, when a user requests more detailed training materials or videos, the server retrieves the user's learning history and progress data from a database (e.g., PostgreSQL). If the emotion engine recognizes the user's interest, the generative AI model generates personalized training materials, such as "We've prepared new training videos based on what we learned during past maintenance work."

[0392] Specific examples

[0393] For example, if the user speaks, "Please tell me today's maintenance procedure," the server processes as follows:

[0394] 1. The tablet or HMD receives the user's question and sends it to the server via API.

[0395] 2. The server analyzes the question and uses its emotion engine to recognize that the user is anxious.

[0396] 3. Based on the analysis results, a prompt statement is sent to the generative AI model: "The user has asked about machine maintenance procedures. The user seems a little anxious. Please generate a polite and supportive answer.", and an answer is generated.

[0397] 4. Format the generated answers into HTML and send them to the tablet or HMD.

[0398] In this way, "SmartFactoryTutor" can efficiently support technical information and training on the factory floor.

[0399] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0400] Step 1: Accepting user questions

[0401] Users input questions in voice or text format using a tablet or head-mounted display. The input questions are sent to the server via an API. Inputs include specific technical questions such as "Please tell me the maintenance procedure for the machine." The output is metadata such as the question text, user ID, and timestamp.

[0402] Step 2: Parsing the Question

[0403] The server parses the received question using a natural language processing (NLP) module (e.g., SpaCy or NLTK). The input is the question text, which the NLP module parses to identify the intent of the question, recognizing it as a "question about maintenance procedures." The output is metadata about the question's category and intent.

[0404] Step 3: Recognizing your emotional state

[0405] The server uses an emotion engine (e.g., IBM Watson) to analyze the question text and recognize the user's emotional state (e.g., impatience, anxiety, excitement, etc.). The input is the question text, and the emotion engine analyzes the user's emotion based on this. The output is metadata that indicates the user's emotional state.

[0406] Step 4: Generate an answer

[0407] Based on the analysis results, the server sends instructions to a generative AI model (e.g., OpenAI GPT-3) to generate an answer. The tone and content of the answer are adjusted based on the user's emotional state as recognized by the emotion engine. The input is the question category, intent, and emotional state metadata, and the generative AI model generates an appropriate answer based on this. The output is the generated answer text.

[0408] Step 5: Format your response

[0409] The server formats the generated answer text into HTML or plain text. The input is the generated answer text, and the formatting engine formats it into the appropriate format. The output is the formatted answer text.

[0410] Step 6: Submit your response

[0411] The server sends the formatted answer to the user's device. The input is the formatted answer text, which the server sends via an API to the user's tablet or head-mounted display. The output is the answer text that is displayed to the user.

[0412] Step 7: Provide learning resources

[0413] When a user requests additional learning resources, the server retrieves the user's learning history and progress data from a database (e.g., PostgreSQL). The input is the user's request data, and the output is the user's learning history and progress data. The server then sends instructions to the generative AI model to generate personalized learning resources. The output is personalized learning resources (e.g., training videos and materials).

[0414] Step 8: Format and submit your learning resources

[0415] The server formats the generated learning resources into HTML or plain text format and sends them to the user's device. The input is the generated learning resources, which the formatting engine formats into an appropriate format. The output is the formatted learning resources displayed on the user's tablet or head-mounted display.

[0416] 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.

[0417] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0418] 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.

[0419] [Second embodiment]

[0420] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0421] 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.

[0422] 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).

[0423] 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.

[0424] 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.

[0425] 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).

[0426] 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.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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."

[0432] This invention is a system for supporting online learning and training, in which a server receives questions sent by users from their devices and provides quick answers using a generative AI model. It also includes a function to provide personalized learning support based on the user's learning progress and interests.

[0433] Explanation of program processing

[0434] Accepting user questions

[0435] A user logs in to the learning application using a device and inputs a question. For example, "Please tell me the basic definition of differential calculus." The device then sends this question to the server via an API. The server receives the question data and also retrieves metadata such as the user ID and timestamp.

[0436] Question Analysis

[0437] The server analyzes the received question using a natural language processing (NLP) module. Here, it identifies the intent and gist of the question and recognizes it as a "question about the definition of differential." Based on the results of this analysis, the server requests the generative AI model to generate an answer.

[0438] Generating answers

[0439] The server calls a generative AI model based on the analysis results. The generative AI model generates an appropriate answer based on its internal database and trained algorithms. Specifically, it generates an answer such as, "Differentiation is a method for determining the rate of change of a function, and represents the ratio of change in y to change in x." The server receives this answer, formats it in a user-friendly format, and sends it to the device. The device displays this answer to the user.

[0440] Personalized learning support

[0441] When a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Referring to the user's past courses and current progress, the server asks the generative AI model to generate personalized learning resources. Based on the user's weaknesses and interests, the generative AI model generates, for example, "a detailed explanation of vector spaces in linear algebra" or "a set of exercises." The server then sends these resources to the user to support their learning.

[0442] Specific examples

[0443] Example 1: Question about a math problem

[0444] 1. The user sends the question "Please tell me the basic definition of differentiation" to the server from their terminal.

[0445] 2. The server receives the question and parses it using NLP.

[0446] 3. The server calls the generative AI model and asks it to generate an appropriate answer to the question.

[0447] 4. The generative AI model generates the answer, "Differentiation is a method for finding the rate of change of a function, and represents the ratio of change in y to change in x."

[0448] 5. The server sends this response to the user, who then checks the response on their device.

[0449] Example 2: Personalized learning support

[0450] 1. The user sends a request to the server from their device saying, "I want to learn more about linear algebra."

[0451] 2. The server references the user's learning history and progress data and asks the generative AI model to generate personalized learning resources.

[0452] 3. The generative AI model generates a "detailed explanation of vector spaces in linear algebra" and a "set of exercises."

[0453] 4. The server sends these resources to the user, who then checks them on the device.

[0454] As described above, the system of the present invention can provide users with fast and appropriate answers to their questions and enhance their learning experience through personalized learning resources.

[0455] The processing flow will be explained below.

[0456] Step 1:

[0457] A user logs into a learning application using a terminal and types a question, for example, "What is the basic definition of differentiation?"

[0458] Step 2:

[0459] The user's device sends the entered question to the server via API, along with metadata such as the question text, user ID, and timestamp.

[0460] Step 3:

[0461] The server receives the question sent from the terminal and records the received data in a log, including the question text, user ID, and timestamp.

[0462] Step 4:

[0463] The server uses a natural language processing (NLP) module to analyze the intent of the question, for example, identifying that the question is about "definition of differential."

[0464] Step 5:

[0465] The server sends appropriate instructions to the generative AI model based on the analysis results. In this case, the instruction sent to the generative AI model is "Explain the definition of differentiation."

[0466] Step 6:

[0467] A generative AI model receives instructions and generates an optimal answer based on its internal database and trained algorithms, such as "Differentiation is a way to find the rate of change of a function..."

[0468] Step 7:

[0469] The server receives the generated response and formats it in a user-friendly format, for example, in HTML or plain text.

[0470] Step 8:

[0471] The server sends the formatted response to the user's terminal, including the response text.

[0472] Step 9:

[0473] The user's device will display the received answer on the screen, where the user can check the "basic definition of differentiation."

[0474] Step 10:

[0475] The server retrieves the user's learning progress data from the database and prepares to provide learning support based on the user's progress and interests.

[0476] Step 11:

[0477] The server references the user's progress data and asks the generative AI model to generate personalized learning resources, for example, in response to a request to "learn more about linear algebra."

[0478] Step 12:

[0479] The generative AI model generates optimal learning resources based on the user's progress and weaknesses, such as a detailed explanation of vector spaces in linear algebra or a set of exercises.

[0480] Step 13:

[0481] The server receives the generated learning resources, formats them in a user-friendly format, and organizes resource links, files, etc.

[0482] Step 14:

[0483] The server transmits the learning resources to the user's terminal so that the user can view them.

[0484] Step 15:

[0485] The user's terminal displays the received learning resource, and the user views the content.

[0486] Through the above steps, the system of the present invention can quickly and appropriately answer the user's questions and provide personalized assistance based on the user's learning progress.

[0487] Example 1

[0488] 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."

[0489] Conventional online learning support systems have difficulty providing prompt and appropriate answers to users' questions and requests, and have had issues with not providing sufficient personalized learning support based on the user's progress and interests. Furthermore, there is a lack of automated processing for generating answers and providing learning support resources, which requires a lot of time and effort.

[0490] 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.

[0491] In this invention, the server includes means for receiving input from a user, means for analyzing the received input, means for invoking a generative AI model based on the analysis result to generate an answer, and means for formatting the generated answer and sending it to the user, thereby enabling the provision of prompt and appropriate answers to user questions and personalized learning support.

[0492] "User" refers to an individual who uses the system to learn or search for information.

[0493] "Input" refers to information such as a question or request that a user provides to a system.

[0494] "Terminal" refers to the device a user uses to access the system, such as a PC or smartphone.

[0495] "Server" refers to a central computer system that receives input from users and performs processing such as analysis and response generation.

[0496] "Communication means" refers to the method or protocol for sending and receiving data between a terminal and a server. A typical example is the Internet Protocol (IP).

[0497] "Means for receiving" refers to the function by which the server receives input sent from the terminal.

[0498] "Means for analyzing" refers to the function of understanding the content of received input and performing processing to identify its intent and gist.

[0499] A "generative AI model" refers to an algorithm that uses machine learning and databases to automatically generate appropriate answers or resources from specific inputs.

[0500] "Means for generating answers" refers to the function of calling a generative AI model based on the analysis results and creating answers to users' questions.

[0501] "Means for formatting and sending" refers to a function for formatting generated answers and the like into a format that is easy for the user to view and sending it to the user's terminal.

[0502] "Progress data" refers to information about the progress of a user's learning, such as their learning status and past history.

[0503] "Personalized learning resources" refers to learning content and materials that are specifically customized based on a user's progress data and interests.

[0504] "Personalization" refers to providing services and content that are individualized according to each user's needs and past history.

[0505] This invention is a system for supporting online learning and training, in which a server receives questions sent by users from their devices and provides quick answers using a generative AI model. It also provides personalized learning support based on the user's learning progress and interests.

[0506] First, the user logs in to the learning application using their device. The learning application can be provided in various forms, such as a web browser or a dedicated application. When the user enters a question, the device sends this input to the server via an API. For example, if the user enters "Please tell me the basic definition of differentiation," the device sends this question data to the server.

[0507] The server receives the question data and acquires metadata such as the user ID and timestamp. The received question is analyzed by a natural language processing (NLP) module. The NLP module analyzes the input question and identifies its intent and gist. For example, it may recognize that the question is about the definition of differential. Based on the analysis results, the server invokes a generative AI model to generate an answer.

[0508] The generative AI model is equipped with an internal database and machine learning algorithms to generate appropriate answers. As a specific example of an answer, it might generate the following: "Differentiation is a method for determining the rate of change of a function, and represents the ratio of change in y to change in x." The server receives the generated answer and formats it in a format that is easy for the user to view. The formatted answer is then sent to the device, where the user can view it.

[0509] Furthermore, if a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Based on the user's past courses and current progress, the server asks the generative AI model to generate personalized learning resources. Based on the user's weaknesses and interests, the generative AI model generates, for example, "a detailed explanation of vector spaces in linear algebra" or "a set of exercises." The server formats these resources and sends them to the user's device. The user can view the resources on their device and use them for their studies.

[0510] As an example, the following prompt sentence is used for a generative AI model:

[0511] Question and Answer Generation

[0512] Generate a detailed answer to the user's question, "What is the basic definition of differentiation?"

[0513] Personalized learning resource generation

[0514] Based on a user's request to "learn more about linear algebra," suggest personalized learning resources based on the user's past learning history.

[0515] As described above, the present invention can quickly and appropriately answer user questions and provide personalized learning support according to the user's progress and interests, thereby enabling the user to study efficiently and effectively.

[0516] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0517] Step 1: Accepting user questions

[0518] 1. A user logs in to a learning application using a terminal. The input is the user's login information, and the output is a notification of login success or failure.

[0519] 2. The user inputs a question into the learning application. For example, "Please tell me the basic definition of differential calculus." The input is the user's question text, and the output is the transmission of the question data from the terminal to the server.

[0520] 3. The device uses the API to send the user's question data to the server. The input is the question text and metadata (user ID, timestamp), and the output is the status of successful submission.

[0521] Step 2: Parsing the Question

[0522] 1. The server receives the user's query data. The input is the query data sent from the device, and the output is the saving of the query data and metadata to the internal storage.

[0523] 2. The server's natural language processing (NLP) module analyzes the received question. The input is the question text, and the output is the analysis results that identify the intent and gist of the question.

[0524] 3. Based on the intent of the question, the server prepares data to be passed to the generative AI model. The input is the analysis result of the NLP module, and the output is the input data for the generative AI model.

[0525] Step 3: Generate the answer

[0526] 1. The server invokes the generative AI model based on the analysis results. The input is the analysis results, and the output is the success status of the generation request.

[0527] 2. Generative AI models generate answers using internal databases and machine learning algorithms. The input is the analysis result, and the output is the generated answer text.

[0528] 3. The server receives and formats the generated answer: the input is the generated answer text, and the output is the answer converted into a user-friendly format.

[0529] Step 4: Returning the Answer

[0530] 1. The server sends a formatted answer to the user's terminal. The input is the formatted answer, and the output is the success status of the answer transmission.

[0531] 2. The terminal displays the answer received from the server to the user. The input is the formatted answer and the output is the display of the answer to the user.

[0532] 3. The user checks the answers on the device and uses them to help them learn. The input is the displayed answer text, and the output is the user's learning progress.

[0533] Step 5: Personalized learning support

[0534] 1. A user requests, "I want to learn more about linear algebra." The input is the user's request text, and the output is the transmission of the request data from the terminal to the server.

[0535] 2. The device uses the API to send a request to the server. The input is the request text and metadata, and the output is a successful transmission status.

[0536] 3. The server retrieves the user's learning history and progress data from the database. The input is the user ID, and the output is the retrieved learning history and progress data.

[0537] 4. The server requests the generative AI model to generate personalized learning resources. The input is the learning history and progress data, and the output is the success status of the generation request.

[0538] 5. The generative AI model generates learning resources tailored to the user. For example, it generates a "detailed explanation of vector spaces in linear algebra" or a "set of exercises." The input is learning history and progress data, and the output is the generated learning resource.

[0539] 6. The server formats the generated learning resource and sends it to the user's terminal. The input is the generated learning resource, and the output is the successful transmission status of the formatted learning resource.

[0540] 7. The user checks the resources on the device and uses them for learning. The input is the formatted learning resource, and the output is the enrichment of the user's learning.

[0541] (Application example 1)

[0542] 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."

[0543] Conventional online learning systems have difficulty in providing quick and accurate answers to user questions, and they lack personalized learning support. They also have difficulty effectively utilizing users' learning history and progress information to provide optimal learning resources.

[0544] 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.

[0545] In this invention, the server includes means for receiving questions from users, means for analyzing the received questions, means for generating answers using a generative AI model based on the analysis results, means for sending the generated answers to the users, means for sending questions sent from the users' devices to the server via an API, means for formatting the generated answers and sending them to the users' devices, means for acquiring the users' learning history and progress information and providing personalized learning resources, and means for generating personalized learning content using the generative AI model. This makes it possible to quickly and accurately answer users' questions and provide optimal learning resources based on the users' learning progress and interests.

[0546] The "means for receiving a question from a user" refers to a device or system that has the function of receiving a question entered by a user through a terminal or interface.

[0547] The "means for analyzing the received question" refers to a device or system that has the function of analyzing the received question using natural language processing technology or the like and identifying the intent and content of the question.

[0548] "Means for generating answers using a generative AI model based on the analysis results" refers to devices or systems that have the functionality to utilize a generative AI model to generate appropriate answers based on the content of the analyzed question.

[0549] The "means for transmitting the generated answer to the user" refers to a device or system that has the function of formatting the generated answer and transmitting it to the terminal used by the user.

[0550] "Means for sending questions sent from a user's terminal to a server via an API" refers to a device or system that has the function of sending questions entered by a user to a server via an application programming interface.

[0551] "Means for formatting the generated answer and sending it to the user's device" refers to a device or system that has the function of converting the answer generated by the generative AI model into a format that is easy for the user to view and sending it to the user's device.

[0552] "Means for acquiring a user's learning history and progress information and providing personalized learning resources" refers to a device or system that has the function of acquiring a user's past learning data and current progress status and providing personalized learning resources based on that data.

[0553] "Means for generating personalized learning content using generative AI models" refers to devices or systems that utilize generative AI models to generate optimal learning content based on a user's learning history and interests.

[0554] The present invention is a system for supporting online learning and training, in which a server receives questions sent by a user from a terminal and provides quick answers using a generative AI model. It also provides personalized learning support based on the user's learning progress and interests. Specific embodiments of the system are described below.

[0555] Hardware and software used

[0556] To realize the system of the present invention, the following hardware and software are required.

[0557] Hardware: Smartphones, tablets, personal computers, etc.

[0558] Software: Python, Requests library, generative AI models (e.g., OpenAI GPT-3), natural language processing modules (e.g., SpaCy, NLTK)

[0559] System Configuration

[0560] Accepting user questions

[0561] Users log in to the learning application using a device such as a smartphone or tablet and enter a question. This question is sent to the server via an application programming interface (API). The server receives the question data and also acquires metadata such as the user ID and timestamp.

[0562] Question Analysis

[0563] The server analyzes the received question using a natural language processing module. Here, it identifies the intent and gist of the question and performs an appropriate analysis based on the content of the question. Based on the results of this analysis, it requests a generative AI model to generate an answer.

[0564] Generating answers

[0565] The server calls the generative AI model to generate an appropriate answer to the question. The generative AI model generates an answer based on its internal database and trained algorithms and returns it to the server. The server receives this answer, formats it in a user-friendly format, and sends it to the device. The device displays this answer to the user.

[0566] Personalized learning support

[0567] When a user inputs a learning request such as "I want to learn more," the server retrieves the user's learning history and progress data. Based on the user's past courses and current progress, the server requests the generative AI model to generate personalized learning resources. The generative AI model generates optimal learning content (for example, "A detailed explanation of vector spaces in linear algebra" or "Practice problems") based on the user's weaknesses and interests. The server then sends these resources to the user to support their learning.

[0568] Specific examples

[0569] Accepting questions and providing answers

[0570] 1. A user types a question into a smartphone app: "Please tell me the basic definition of differentiation."

[0571] 2. The server receives this question and parses it using the NLP module.

[0572] 3. The server calls the generative AI model, which generates an appropriate answer to the question, and obtains the answer, "Differentiation is a method for finding the rate of change of a function, and represents the ratio of change in y to change in x."

[0573] 4. This response is sent to the user's device and displayed.

[0574] Personalized learning support

[0575] 1. A user requests, "I want to learn more about linear algebra."

[0576] 2. The server obtains the user's learning history and progress.

[0577] 3. Using a generative AI model, we generate personalized resources such as "Detailed explanations of vector spaces in linear algebra" and "Practice problems" based on the user's learning history and interests.

[0578] 4. The generated resource is provided to the user.

[0579] Prompt Sentence Examples

[0580] "A user has entered the question 'What is the basic definition of derivative?' Use a generative AI model to generate the best answer to answer this question quickly and accurately."

[0581] The above is a specific embodiment and flow for carrying out the invention.

[0582] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0583] Step 1:

[0584] A user logs into the learning application on a terminal and enters a question.

[0585] Input: Username, password, question (e.g. "What is the basic definition of differentiation?")

[0586] Processing: After user authentication, obtain the question content

[0587] Output: Request data to send the question to the server via API

[0588] Step 2:

[0589] The server receives the question data via API and obtains the metadata (user ID, timestamp, etc.).

[0590] Input: Request data (question content, user ID, timestamp)

[0591] Processing: Parse the received question data and extract metadata

[0592] Output: Analysis data using the query and metadata

[0593] Step 3:

[0594] The server analyzes the received question using a natural language processing (NLP) module.

[0595] Input: Analysis data (question content, user ID, timestamp)

[0596] Processing: The NLP module identifies the intent and gist of the question (e.g., "Question about the definition of differential")

[0597] Output: NLP analysis results (analyzed question intent and summary)

[0598] Step 4:

[0599] The server requests the generation of an answer based on the analysis results and a generative AI model.

[0600] Input: NLP analysis results

[0601] Processing: Enter a prompt (e.g., "Please tell me the basic definition of differentiation") into the generative AI model and generate an answer.

[0602] Output: Generated answer (e.g., "Derivative is a way to find the rate of change of a function; it is the ratio of change in y to change in x.")

[0603] Step 5:

[0604] The server formats the generated answers in a user-friendly format and sends them to the device via an API.

[0605] Input: Generated Answer

[0606] Processing: Reformatting the response (e.g., converting it to JSON) and sending it

[0607] Output: The formatted answer sent to the user's terminal

[0608] Step 6:

[0609] The user checks the generated answer on the device.

[0610] Input: Formatted answer (e.g., "Derivative is a way to find the rate of change of a function; it is the ratio of change in y to change in x.")

[0611] Processing: Displayed by application

[0612] Output: User views displayed answer

[0613] Step 7:

[0614] When a user requests to "learn more," the server retrieves the user's learning history and progress data.

[0615] Input: User's new request (e.g., "I want to learn more about linear algebra"), User ID

[0616] Processing: Retrieve user learning history and progress information from the database

[0617] Output: Acquired learning history and progress data

[0618] Step 8:

[0619] The server generates personalized learning content using a generative AI model based on the acquired learning history.

[0620] Input: Acquired learning history and progress data, generative AI model

[0621] Processing: Generate personalized learning content (e.g., "Detailed explanation of vector spaces in linear algebra" or "Practice problems") using learning history and progress information

[0622] Output: Generated learning content

[0623] Step 9:

[0624] The server transmits the generated study content to the user terminal, and the user checks the study content.

[0625] Input: Generated learning content

[0626] Processing: Sending personalized learning content via API

[0627] Output: Learning content sent to the user's device, the user views the content

[0628] The above are the specific processing steps for carrying out the invention.

[0629] 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.

[0630] This invention is a system for supporting online learning and remote training, which analyzes user questions, recognizes the user's emotional state using an emotion engine, and provides fast and personalized answers using a generative AI model.The invention aims to improve the learning experience by referring to the user's learning progress data and providing answers and learning resources tailored by the emotion engine.

[0631] Explanation of program processing

[0632] Accepting user questions

[0633] A user logs into the learning application using their device and enters a question, for example, "What is the basic definition of differential calculus?" The user's device then sends the entered question to the server via an API, which receives metadata such as the question text, user ID, and timestamp.

[0634] Question Analysis

[0635] The server analyzes the received question using a natural language processing (NLP) module. Through the analysis, it identifies the intent of the question and recognizes it as a "question about the definition of differential." The emotion engine also analyzes the question text and recognizes the user's emotional state (e.g., excitement, stress, frustration, etc.).

[0636] Generating sentiment-based answers

[0637] The server sends appropriate instructions to the generative AI model based on the analysis results. At this time, the emotion engine adjusts the tone and content of the response based on the user's emotional state. For example, if the user is feeling stressed, the generative AI model will generate a response with a more polite and supportive tone. For example, in addition to the response "Differentiation is a way to find the rate of change of a function...", it will also include the advice "Take your time and learn slowly."

[0638] Formatting and Sending

[0639] The server receives the generated answer and formats it for the user to see (for example, by formatting the answer text in HTML or plain text), then sends the formatted answer to the user's device, where the user can view the answer.

[0640] Personalized learning support

[0641] When a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Referring to the user's past courses and current progress, the server asks the generative AI model to generate personalized learning resources. The emotion engine also references the user's emotional data and provides learning resources tailored to the user's specific emotional state. For example, if the user is interested, the server will include challenging content. Conversely, if the user is feeling stressed, the server will provide basic, easy-to-understand content.

[0642] Specific examples

[0643] Example 1: Math Question

[0644] 1. The user sends a question to the server from their terminal: "Please tell me the basic definition of differentiation."

[0645] 2. The server uses NLP to analyze the question and uses an emotion engine to recognize that the user is feeling stressed.

[0646] 3. The generative AI model generates a polite answer such as, "Differentiation is a way to find the rate of change of a function..." and adds the advice, "Take your time and learn."

[0647] 4. The server formats the answers and sends them to the user's device, where they review the answers and receive an emotionally supportive learning experience.

[0648] Example 2: Personalized learning support

[0649] 1. The user sends a request to the server from their device saying, "I want to learn more about linear algebra."

[0650] 2. The server references the user's learning history and progress data and uses an emotion engine to recognize the user's interests.

[0651] 3. The generative AI model generates a "detailed explanation of vector spaces in linear algebra" and a "set of applied problems."

[0652] 4. The server formats and sends these resources to the user's device, where the user can review the resources and receive a personalized learning experience based on their interests.

[0653] The system of the present invention can significantly enhance the learning experience by recognizing the user's emotional state and providing appropriate answers and learning resources based on that.

[0654] The processing flow will be explained below.

[0655] Step 1:

[0656] A user logs into a learning application using a terminal and types a question, for example, "What is the basic definition of differentiation?"

[0657] Step 2:

[0658] The user's device sends the entered question to the server via API, along with metadata such as the question text, user ID, and timestamp.

[0659] Step 3:

[0660] The server receives the question sent from the terminal and records the received data in a log, including the question text, user ID, and timestamp.

[0661] Step 4:

[0662] The server analyzes the received question using a natural language processing (NLP) module, identifying the intent of the question and recognizing it as a question about the definition of differential.

[0663] Step 5:

[0664] The emotion engine analyzes the question text and recognizes the user's emotional state, for example, determining whether the user is stressed or excited.

[0665] Step 6:

[0666] The server sends appropriate instructions to the generative AI model based on the analysis results and the emotion engine's recognition results, such as "Explain the definition of differentiation," and also instructs the model to adjust the tone and content of the response based on the user's emotional state.

[0667] Step 7:

[0668] Generative AI models receive instructions and generate optimal answers based on their internal database and trained algorithms, such as "Differentiation is a method for determining the rate of change of a function, and it represents the ratio of change in y to change in x."

[0669] Step 8:

[0670] The server receives the generated response and formats it in a user-friendly format, for example, in HTML or plain text.

[0671] Step 9:

[0672] The server sends the formatted response to the user's terminal, including the response text.

[0673] Step 10:

[0674] The user's device displays the received answers on the screen, allowing the user to review the answers and enjoy an emotionally supportive learning experience.

[0675] Step 11:

[0676] The server retrieves the user's learning progress data from the database and prepares to provide learning support based on the user's progress and interests.

[0677] Step 12:

[0678] The server references the user's progress data and asks the generative AI model to generate personalized learning resources, for example, in response to a request to "learn more about linear algebra."

[0679] Step 13:

[0680] The generative AI model generates optimal learning resources based on the user's progress and weaknesses, such as a detailed explanation of vector spaces in linear algebra or a set of exercises.

[0681] Step 14:

[0682] The server receives the generated learning resources, formats them in a user-friendly format, and organizes resource links, files, etc.

[0683] Step 15:

[0684] The server transmits the learning resources to the user's terminal so that the user can view them.

[0685] Step 16:

[0686] The user's device displays the received learning resources, and the user browses the content, resulting in a personalized learning experience based on their interests.

[0687] Through these steps, the system of the present invention can quickly and appropriately answer the user's questions and provide personalized assistance based on the user's learning progress and emotional state.

[0688] Example 2

[0689] 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."

[0690] Conventional online learning systems have the problem that they provide mechanical answers to user questions and do not provide personalized answers that reflect the user's emotions or learning progress. As a result, users may lose motivation to learn and feel stressed.

[0691] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving a question from a user, a means for performing natural language processing based on the received question, a means for analyzing the question and recognizing the emotional state, a means for generating an answer using a generative AI model based on the analysis and recognition results, and a means for sending the generated answer to the user. This makes it possible to provide personalized appropriate answers and learning resources based on the user's emotional state and learning progress.

[0692] A "user" is an individual or entity that utilizes the system to enter questions and receive answers.

[0693] A "question" is a text message that requests information that the user enters into the system.

[0694] "Terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[0695] A "server" is a computer system that receives and processes user questions, and generates and transmits answers.

[0696] "API" stands for Application Programming Interface, which provides rules and procedures for different software programs to communicate with each other.

[0697] "Natural language processing (NLP)" is a technology that allows computers to understand, analyze, and generate human language (natural language).

[0698] An "emotion engine" is a software module for analyzing and recognizing the emotional state from a user's text.

[0699] A "generative AI model" is an artificial intelligence model that generates appropriate answers based on analysis results.

[0700] "Metadata" refers to additional information related to the question text (e.g., user ID and timestamp).

[0701] "Personalization" means providing content that is customized according to the characteristics, emotional state, learning progress, etc. of each individual user.

[0702] "Formatting" refers to converting generated answers or resources into a user-friendly format (e.g., HTML or plain text).

[0703] "Learning resources" refers to educational materials and information provided to assist users in their learning.

[0704] This invention is a system for supporting online learning and remote training, which analyzes user questions, recognizes the user's emotional state using an emotion engine, and provides fast and personalized answers using a generative AI model.The invention aims to improve the learning experience by referring to the user's learning progress data and providing answers and learning resources tailored by the emotion engine.

[0705] Accepting user questions

[0706] A user logs in to the learning application using a device and enters a question, for example, "Please tell me the basic definition of differential calculus." The user's device sends the question text along with metadata including the user ID and timestamp to the server via an API. The server receives this data.

[0707] Question Analysis

[0708] The server analyzes the received question using a natural language processing (NLP) module. This analysis identifies the intent of the question and recognizes that it is a question about the definition of differential. The emotion engine also analyzes the question text and recognizes the user's emotional state (e.g., excitement, stress, frustration, etc.).

[0709] Generating sentiment-based answers

[0710] The server sends appropriate instructions to the generative AI model based on the analysis results and emotion recognition results, such as the following prompt:

[0711] Example prompt sentence:

[0712] "Explain the definition of differentiation in detail and respond in a gentle tone because the user is stressed."

[0713] Based on the instructions, the generative AI model generates a polite answer, such as "Differentiation is a way to find the rate of change of a function..." It also adds advice such as "Take your time and learn slowly."

[0714] Formatting and Sending

[0715] The server receives the generated answer, formats it into a user-friendly format (e.g., HTML or plain text), and sends the formatted answer back to the user's device via the API, where the user can view the answer.

[0716] Personalized learning support

[0717] When a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Based on this, it asks the generative AI model to generate personalized learning resources. At this time, the emotion engine also references the user's emotional data and provides learning resources tailored to the user's specific emotional state. For example, if the user is interested, it will include challenging content, and conversely, if the user is feeling stressed, it will provide basic, easy-to-understand content.

[0718] Specific examples

[0719] Example 1: Math Question

[0720] 1. The user sends a question to the server from their terminal: "Please tell me the basic definition of differentiation."

[0721] 2. The server uses NLP to analyze the question and uses an emotion engine to recognize that the user is feeling stressed.

[0722] 3. The generative AI model generates the answer, "Differentiation is a way to find the rate of change of a function..." and adds the advice, "Take your time and learn."

[0723] 4. The server formats the answers and sends them to the user's device, where they review the answers and receive an emotionally supportive learning experience.

[0724] Example 2: Personalized learning support

[0725] 1. The user sends a request to the server from their device saying, "I want to learn more about linear algebra."

[0726] 2. The server references the user's learning history and progress data and uses an emotion engine to recognize the user's interests.

[0727] 3. The generative AI model generates a "detailed explanation of vector spaces in linear algebra" and a "set of applied problems."

[0728] 4. The server formats and sends these resources to the user's device, where the user can review the resources and receive a personalized learning experience based on their interests.

[0729] The system of the present invention can significantly improve the learning experience by taking into account the user's emotional state and learning progress.

[0730] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0731] Step 1: Accepting user questions

[0732] A user uses a terminal to log in to a learning application and enter a question, for example, "What is the basic definition of differential calculus?"

[0733] The device sends the entered question text along with metadata including the user ID and timestamp to the server via API.

[0734] Input: The question text, user ID, and timestamp entered by the user on the terminal.

[0735] Output: Question data sent to the server (question text, user ID, timestamp).

[0736] Step 2: Parsing the Question

[0737] The server passes the received question data to a natural language processing (NLP) module, which analyzes the intent of the question. For example, it identifies the question as "a question about the definition of differential."

[0738] An emotion engine analyzes the question text and recognizes the user's emotional state (e.g., excitement, stress, frustration, etc.).

[0739] Input: Received question data (question text, user ID, timestamp).

[0740] Output: Parsed question content and user emotional state data.

[0741] Step 3: Generate sentiment-based answers

[0742] The server sends appropriate instructions to the generative AI model based on the analysis results (question content and emotional state), sending the following prompt to the generative AI model:

[0743] Example prompt: "Explain the definition of differentiation in detail and respond in a gentle tone as the user is stressed."

[0744] Based on the instructions, the generative AI model generates a polite answer, such as "Differentiation is a way to find the rate of change of a function..." It also adds advice such as "Take your time and learn slowly."

[0745] Input: The parsed question, the user's emotional state, and the prompt for the generative AI model.

[0746] Output: The generated answer text.

[0747] Step 4: Format and send

[0748] The server receives the generated response text and formats it into a user-friendly format (e.g., HTML or plain text).

[0749] The server then sends the formatted response back to the user's device via the API.

[0750] The user checks the answer on the terminal.

[0751] Input: The generated answer text.

[0752] Output: The formatted answer text and the answer sent to the user's device.

[0753] Step 5: Personalized learning support

[0754] If a user requests, "I want to learn more about linear algebra,"

[0755] The server retrieves the user's learning history and progress data from the database.

[0756] The server requests the generative AI model to generate personalized learning resources based on the referenced data and the user's emotional state as determined by the emotion engine.

[0757] For example, if a user is interested, include challenging content, but if they are stressed, provide basic, easy-to-understand content.

[0758] The generative AI model generates learning resources (e.g., a detailed explanation of vector spaces in linear algebra or a set of applied problems) based on instructions.

[0759] The server formats the generated learning resources and sends them to the user's terminal.

[0760] The user checks the learning resources on the device.

[0761] Input: User learning history, progress data, emotional state, and instructions to the generative AI model.

[0762] Output: The formatted learning resource and the learning resource sent to the user's device.

[0763] (Application example 2)

[0764] 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."

[0765] In modern manufacturing, operators and engineers working on factory floors need to receive technical information and training quickly and effectively. However, existing systems generally provide general learning content, making it difficult to provide personalized assistance based on individual users' emotional state and learning progress. Furthermore, there is a lack of means to provide appropriate support that takes emotions into account when users ask questions. This can reduce the effectiveness of operators and engineers' learning, negatively impacting on-site efficiency and quality.

[0766] The identification process by the identification 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 receiving a question from a user, means for analyzing the received question, means for generating an answer using a generative AI model based on the analysis result, means for sending the generated answer to the user, means for recognizing the user's emotional state, means for adjusting the tone and content of the answer based on the recognized emotional state, means for referencing the user's learning progress data, and means for providing personalized learning resources using a generative AI model based on the referenced data. This enables personalized support according to the user's emotional state and learning progress, thereby improving the effectiveness of technical information and training at the factory floor.

[0767] The "means for receiving a question from a user" is a function for transmitting a question entered by a user using a terminal to a server or related systems.

[0768] "Means for analyzing received questions" refers to a function that includes natural language processing (NLP) technology used to analyze questions received by the server and understand their content and intent.

[0769] "Means for generating answers using a generative AI model" refers to a function that utilizes an AI model to automatically generate appropriate answers based on the analysis results.

[0770] The "means for transmitting the generated answer to the user" is a function that formats the generated answer and transmits it to the user's terminal for display.

[0771] The "means for recognizing the user's emotional state" is a technology for analyzing the question text and the user's voice data to detect the user's emotional state (for example, excitement, stress, dissatisfaction, etc.).

[0772] The "means for adjusting the tone and content of the response based on the recognized emotional state" is a function that appropriately adjusts the expression method and content of the response according to the user's emotional state.

[0773] The "means for referencing user's learning progress data" is a function for retrieving and referencing the user's past learning history and progress status from a database.

[0774] "Means for providing personalized learning resources using a generative AI model based on referenced data" refers to a function that utilizes an AI model to generate individually optimized learning resources based on referenced learning progress data.

[0775] The "means for formatting and sending to the user's terminal" is a function for formatting the generated answers and learning resources into an appropriate format and sending them to the user's terminal.

[0776] The "means for displaying formatted answers to the user" is a function for displaying formatted answers and learning resources on the user's terminal.

[0777] "Means for viewing answers and learning resources using a head-mounted display" is a function for viewing answers and learning resources through the screen of a head-mounted display worn by the user.

[0778]

[0779] The system for realizing this invention provides a learning support application "SmartFactoryTutor" that is installed on a factory robot. A detailed embodiment of this system will be described below.

[0780] The server receives and analyzes input from the device used by the user (e.g., a tablet or head-mounted display). Specifically, the user enters a question in voice or text format. For example, the user might enter, "Please tell me the maintenance procedure for the machine."

[0781] The received question is sent to the server via an API, which receives metadata such as the question text, user ID, and timestamp. The server then analyzes the received question using a natural language processing (NLP) module (e.g., SpaCy or NLTK). This identifies the intent of the question and recognizes that it is a "question about maintenance procedures." An emotion engine (e.g., IBM Watson) is then used to analyze the question text and recognize the user's emotional state (e.g., impatience, anxiety, excitement, etc.).

[0782] Based on the analysis results, the server sends instructions to a generative AI model (such as OpenAI GPT-3) to generate a response. The tone and content of the response are adjusted based on the user's emotional state as recognized by the emotion engine. For example, if the user is feeling impatient, the generative AI model will generate a polite and supportive response such as, "Machine maintenance is a very important process. Let's take it easy and check each step one by one."

[0783] The generated answers are formatted in HTML or plain text and sent from the server to the user's device, where they can view the answers via a tablet or head-mounted display.

[0784] Furthermore, when a user requests more detailed training materials or videos, the server retrieves the user's learning history and progress data from a database (e.g., PostgreSQL). If the emotion engine recognizes the user's interest, the generative AI model generates personalized training materials, such as "We've prepared new training videos based on what we learned during past maintenance work."

[0785] Specific examples

[0786] For example, if the user speaks, "Please tell me today's maintenance procedure," the server processes as follows:

[0787] 1. The tablet or HMD receives the user's question and sends it to the server via API.

[0788] 2. The server analyzes the question and uses its emotion engine to recognize that the user is anxious.

[0789] 3. Based on the analysis results, a prompt statement is sent to the generative AI model: "The user has asked about machine maintenance procedures. The user seems a little anxious. Please generate a polite and supportive answer.", and an answer is generated.

[0790] 4. Format the generated answers into HTML and send them to the tablet or HMD.

[0791] In this way, "SmartFactoryTutor" can efficiently support technical information and training on the factory floor.

[0792] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0793] Step 1: Accepting user questions

[0794] Users input questions in voice or text format using a tablet or head-mounted display. The input questions are sent to the server via an API. Inputs include specific technical questions such as "Please tell me the maintenance procedure for the machine." The output is metadata such as the question text, user ID, and timestamp.

[0795] Step 2: Parsing the Question

[0796] The server parses the received question using a natural language processing (NLP) module (e.g., SpaCy or NLTK). The input is the question text, which the NLP module parses to identify the intent of the question, recognizing it as a "question about maintenance procedures." The output is metadata about the question's category and intent.

[0797] Step 3: Recognizing your emotional state

[0798] The server uses an emotion engine (e.g., IBM Watson) to analyze the question text and recognize the user's emotional state (e.g., impatience, anxiety, excitement, etc.). The input is the question text, and the emotion engine analyzes the user's emotion based on this. The output is metadata that indicates the user's emotional state.

[0799] Step 4: Generate an answer

[0800] Based on the analysis results, the server sends instructions to a generative AI model (e.g., OpenAI GPT-3) to generate an answer. The tone and content of the answer are adjusted based on the user's emotional state as recognized by the emotion engine. The input is the question category, intent, and emotional state metadata, and the generative AI model generates an appropriate answer based on this. The output is the generated answer text.

[0801] Step 5: Format your response

[0802] The server formats the generated answer text into HTML or plain text. The input is the generated answer text, and the formatting engine formats it into the appropriate format. The output is the formatted answer text.

[0803] Step 6: Submit your response

[0804] The server sends the formatted answer to the user's device. The input is the formatted answer text, which the server sends via an API to the user's tablet or head-mounted display. The output is the answer text that is displayed to the user.

[0805] Step 7: Provide learning resources

[0806] When a user requests additional learning resources, the server retrieves the user's learning history and progress data from a database (e.g., PostgreSQL). The input is the user's request data, and the output is the user's learning history and progress data. The server then sends instructions to the generative AI model to generate personalized learning resources. The output is personalized learning resources (e.g., training videos and materials).

[0807] Step 8: Format and submit your learning resources

[0808] The server formats the generated learning resources into HTML or plain text format and sends them to the user's device. The input is the generated learning resources, which the formatting engine formats into an appropriate format. The output is the formatted learning resources displayed on the user's tablet or head-mounted display.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] [Third embodiment]

[0813] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0814] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0815] 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).

[0816] 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.

[0817] 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.

[0818] 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).

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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."

[0825] This invention is a system for supporting online learning and training, in which a server receives questions sent by users from their devices and provides quick answers using a generative AI model. It also includes a function to provide personalized learning support based on the user's learning progress and interests.

[0826] Explanation of program processing

[0827] Accepting user questions

[0828] A user logs in to the learning application using a device and inputs a question. For example, "Please tell me the basic definition of differential calculus." The device then sends this question to the server via an API. The server receives the question data and also retrieves metadata such as the user ID and timestamp.

[0829] Question Analysis

[0830] The server analyzes the received question using a natural language processing (NLP) module. Here, it identifies the intent and gist of the question and recognizes it as a "question about the definition of differential." Based on the results of this analysis, the server requests the generative AI model to generate an answer.

[0831] Generating answers

[0832] The server calls a generative AI model based on the analysis results. The generative AI model generates an appropriate answer based on its internal database and trained algorithms. Specifically, it generates an answer such as, "Differentiation is a method for determining the rate of change of a function, and represents the ratio of change in y to change in x." The server receives this answer, formats it in a user-friendly format, and sends it to the device. The device displays this answer to the user.

[0833] Personalized learning support

[0834] When a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Referring to the user's past courses and current progress, the server asks the generative AI model to generate personalized learning resources. Based on the user's weaknesses and interests, the generative AI model generates, for example, "a detailed explanation of vector spaces in linear algebra" or "a set of exercises." The server then sends these resources to the user to support their learning.

[0835] Specific examples

[0836] Example 1: Question about a math problem

[0837] 1. The user sends the question "Please tell me the basic definition of differentiation" to the server from their terminal.

[0838] 2. The server receives the question and parses it using NLP.

[0839] 3. The server calls the generative AI model and asks it to generate an appropriate answer to the question.

[0840] 4. The generative AI model generates the answer, "Differentiation is a method for finding the rate of change of a function, and represents the ratio of change in y to change in x."

[0841] 5. The server sends this response to the user, who then checks the response on their device.

[0842] Example 2: Personalized learning support

[0843] 1. The user sends a request to the server from their device saying, "I want to learn more about linear algebra."

[0844] 2. The server references the user's learning history and progress data and asks the generative AI model to generate personalized learning resources.

[0845] 3. The generative AI model generates a "detailed explanation of vector spaces in linear algebra" and a "set of exercises."

[0846] 4. The server sends these resources to the user, who then checks them on the device.

[0847] As described above, the system of the present invention can provide users with fast and appropriate answers to their questions and enhance their learning experience through personalized learning resources.

[0848] The processing flow will be explained below.

[0849] Step 1:

[0850] A user logs into a learning application using a terminal and types a question, for example, "What is the basic definition of differentiation?"

[0851] Step 2:

[0852] The user's device sends the entered question to the server via API, along with metadata such as the question text, user ID, and timestamp.

[0853] Step 3:

[0854] The server receives the question sent from the terminal and records the received data in a log, including the question text, user ID, and timestamp.

[0855] Step 4:

[0856] The server uses a natural language processing (NLP) module to analyze the intent of the question, for example, identifying that the question is about "definition of differential."

[0857] Step 5:

[0858] The server sends appropriate instructions to the generative AI model based on the analysis results. In this case, the instruction sent to the generative AI model is "Explain the definition of differentiation."

[0859] Step 6:

[0860] A generative AI model receives instructions and generates an optimal answer based on its internal database and trained algorithms, such as "Differentiation is a way to find the rate of change of a function..."

[0861] Step 7:

[0862] The server receives the generated response and formats it in a user-friendly format, for example, in HTML or plain text.

[0863] Step 8:

[0864] The server sends the formatted response to the user's terminal, including the response text.

[0865] Step 9:

[0866] The user's device will display the received answer on the screen, where the user can check the "basic definition of differentiation."

[0867] Step 10:

[0868] The server retrieves the user's learning progress data from the database and prepares to provide learning support based on the user's progress and interests.

[0869] Step 11:

[0870] The server references the user's progress data and asks the generative AI model to generate personalized learning resources, for example, in response to a request to "learn more about linear algebra."

[0871] Step 12:

[0872] The generative AI model generates optimal learning resources based on the user's progress and weaknesses, such as a detailed explanation of vector spaces in linear algebra or a set of exercises.

[0873] Step 13:

[0874] The server receives the generated learning resources, formats them in a user-friendly format, and organizes resource links, files, etc.

[0875] Step 14:

[0876] The server transmits the learning resources to the user's terminal so that the user can view them.

[0877] Step 15:

[0878] The user's terminal displays the received learning resource, and the user views the content.

[0879] Through the above steps, the system of the present invention can quickly and appropriately answer the user's questions and provide personalized assistance based on the user's learning progress.

[0880] Example 1

[0881] 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."

[0882] Conventional online learning support systems have difficulty providing prompt and appropriate answers to users' questions and requests, and have had issues with not providing sufficient personalized learning support based on the user's progress and interests. Furthermore, there is a lack of automated processing for generating answers and providing learning support resources, which requires a lot of time and effort.

[0883] 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.

[0884] In this invention, the server includes means for receiving input from a user, means for analyzing the received input, means for invoking a generative AI model based on the analysis result to generate an answer, and means for formatting the generated answer and sending it to the user, thereby enabling the provision of prompt and appropriate answers to user questions and personalized learning support.

[0885] "User" refers to an individual who uses the system to learn or search for information.

[0886] "Input" refers to information such as a question or request that a user provides to a system.

[0887] "Terminal" refers to the device a user uses to access the system, such as a PC or smartphone.

[0888] "Server" refers to a central computer system that receives input from users and performs processing such as analysis and response generation.

[0889] "Communication means" refers to the method or protocol for sending and receiving data between a terminal and a server. A typical example is the Internet Protocol (IP).

[0890] "Means for receiving" refers to the function by which the server receives input sent from the terminal.

[0891] "Means for analyzing" refers to the function of understanding the content of received input and performing processing to identify its intent and gist.

[0892] A "generative AI model" refers to an algorithm that uses machine learning and databases to automatically generate appropriate answers or resources from specific inputs.

[0893] "Means for generating answers" refers to the function of calling a generative AI model based on the analysis results and creating answers to users' questions.

[0894] "Means for formatting and sending" refers to a function for formatting generated answers and the like into a format that is easy for the user to view and sending it to the user's terminal.

[0895] "Progress data" refers to information about the progress of a user's learning, such as their learning status and past history.

[0896] "Personalized learning resources" refers to learning content and materials that are specifically customized based on a user's progress data and interests.

[0897] "Personalization" refers to providing services and content that are individualized according to each user's needs and past history.

[0898] This invention is a system for supporting online learning and training, in which a server receives questions sent by users from their devices and provides quick answers using a generative AI model. It also provides personalized learning support based on the user's learning progress and interests.

[0899] First, the user logs in to the learning application using their device. The learning application can be provided in various forms, such as a web browser or a dedicated application. When the user enters a question, the device sends this input to the server via an API. For example, if the user enters "Please tell me the basic definition of differentiation," the device sends this question data to the server.

[0900] The server receives the question data and acquires metadata such as the user ID and timestamp. The received question is analyzed by a natural language processing (NLP) module. The NLP module analyzes the input question and identifies its intent and gist. For example, it may recognize that the question is about the definition of differential. Based on the analysis results, the server invokes a generative AI model to generate an answer.

[0901] The generative AI model is equipped with an internal database and machine learning algorithms to generate appropriate answers. As a specific example of an answer, it might generate the following: "Differentiation is a method for determining the rate of change of a function, and represents the ratio of change in y to change in x." The server receives the generated answer and formats it in a format that is easy for the user to view. The formatted answer is then sent to the device, where the user can view it.

[0902] Furthermore, if a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Based on the user's past courses and current progress, the server asks the generative AI model to generate personalized learning resources. Based on the user's weaknesses and interests, the generative AI model generates, for example, "a detailed explanation of vector spaces in linear algebra" or "a set of exercises." The server formats these resources and sends them to the user's device. The user can view the resources on their device and use them for their studies.

[0903] As an example, the following prompt sentence is used for a generative AI model:

[0904] Question and Answer Generation

[0905] Generate a detailed answer to the user's question, "What is the basic definition of differentiation?"

[0906] Personalized learning resource generation

[0907] Based on a user's request to "learn more about linear algebra," suggest personalized learning resources based on the user's past learning history.

[0908] As described above, the present invention can quickly and appropriately answer user questions and provide personalized learning support according to the user's progress and interests, thereby enabling the user to study efficiently and effectively.

[0909] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0910] Step 1: Accepting user questions

[0911] 1. A user logs in to a learning application using a terminal. The input is the user's login information, and the output is a notification of login success or failure.

[0912] 2. The user inputs a question into the learning application. For example, "Please tell me the basic definition of differential calculus." The input is the user's question text, and the output is the transmission of the question data from the terminal to the server.

[0913] 3. The device uses the API to send the user's question data to the server. The input is the question text and metadata (user ID, timestamp), and the output is the status of successful submission.

[0914] Step 2: Parsing the Question

[0915] 1. The server receives the user's query data. The input is the query data sent from the device, and the output is the saving of the query data and metadata to the internal storage.

[0916] 2. The server's natural language processing (NLP) module analyzes the received question. The input is the question text, and the output is the analysis results that identify the intent and gist of the question.

[0917] 3. Based on the intent of the question, the server prepares data to be passed to the generative AI model. The input is the analysis result of the NLP module, and the output is the input data for the generative AI model.

[0918] Step 3: Generate the answer

[0919] 1. The server invokes the generative AI model based on the analysis results. The input is the analysis results, and the output is the success status of the generation request.

[0920] 2. Generative AI models generate answers using internal databases and machine learning algorithms. The input is the analysis result, and the output is the generated answer text.

[0921] 3. The server receives and formats the generated answer: the input is the generated answer text, and the output is the answer converted into a user-friendly format.

[0922] Step 4: Returning the Answer

[0923] 1. The server sends a formatted answer to the user's terminal. The input is the formatted answer, and the output is the success status of the answer transmission.

[0924] 2. The terminal displays the answer received from the server to the user. The input is the formatted answer and the output is the display of the answer to the user.

[0925] 3. The user checks the answers on the device and uses them to help them learn. The input is the displayed answer text, and the output is the user's learning progress.

[0926] Step 5: Personalized learning support

[0927] 1. A user requests, "I want to learn more about linear algebra." The input is the user's request text, and the output is the transmission of the request data from the terminal to the server.

[0928] 2. The device uses the API to send a request to the server. The input is the request text and metadata, and the output is a successful transmission status.

[0929] 3. The server retrieves the user's learning history and progress data from the database. The input is the user ID, and the output is the retrieved learning history and progress data.

[0930] 4. The server requests the generative AI model to generate personalized learning resources. The input is the learning history and progress data, and the output is the success status of the generation request.

[0931] 5. The generative AI model generates learning resources tailored to the user. For example, it generates a "detailed explanation of vector spaces in linear algebra" or a "set of exercises." The input is learning history and progress data, and the output is the generated learning resource.

[0932] 6. The server formats the generated learning resource and sends it to the user's terminal. The input is the generated learning resource, and the output is the successful transmission status of the formatted learning resource.

[0933] 7. The user checks the resources on the device and uses them for learning. The input is the formatted learning resource, and the output is the enrichment of the user's learning.

[0934] (Application example 1)

[0935] 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."

[0936] Conventional online learning systems have difficulty in providing quick and accurate answers to user questions, and they lack personalized learning support. They also have difficulty effectively utilizing users' learning history and progress information to provide optimal learning resources.

[0937] 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.

[0938] In this invention, the server includes means for receiving questions from users, means for analyzing the received questions, means for generating answers using a generative AI model based on the analysis results, means for sending the generated answers to the users, means for sending questions sent from the users' devices to the server via an API, means for formatting the generated answers and sending them to the users' devices, means for acquiring the users' learning history and progress information and providing personalized learning resources, and means for generating personalized learning content using the generative AI model. This makes it possible to quickly and accurately answer users' questions and provide optimal learning resources based on the users' learning progress and interests.

[0939] The "means for receiving a question from a user" refers to a device or system that has the function of receiving a question entered by a user through a terminal or interface.

[0940] The "means for analyzing the received question" refers to a device or system that has the function of analyzing the received question using natural language processing technology or the like and identifying the intent and content of the question.

[0941] "Means for generating answers using a generative AI model based on the analysis results" refers to devices or systems that have the functionality to utilize a generative AI model to generate appropriate answers based on the content of the analyzed question.

[0942] The "means for transmitting the generated answer to the user" refers to a device or system that has the function of formatting the generated answer and transmitting it to the terminal used by the user.

[0943] "Means for sending questions sent from a user's terminal to a server via an API" refers to a device or system that has the function of sending questions entered by a user to a server via an application programming interface.

[0944] "Means for formatting the generated answer and sending it to the user's device" refers to a device or system that has the function of converting the answer generated by the generative AI model into a format that is easy for the user to view and sending it to the user's device.

[0945] "Means for acquiring a user's learning history and progress information and providing personalized learning resources" refers to a device or system that has the function of acquiring a user's past learning data and current progress status and providing personalized learning resources based on that data.

[0946] "Means for generating personalized learning content using generative AI models" refers to devices or systems that utilize generative AI models to generate optimal learning content based on a user's learning history and interests.

[0947] The present invention is a system for supporting online learning and training, in which a server receives questions sent by a user from a terminal and provides quick answers using a generative AI model. It also provides personalized learning support based on the user's learning progress and interests. Specific embodiments of the system are described below.

[0948] Hardware and software used

[0949] To realize the system of the present invention, the following hardware and software are required.

[0950] Hardware: Smartphones, tablets, personal computers, etc.

[0951] Software: Python, Requests library, generative AI models (e.g., OpenAI GPT-3), natural language processing modules (e.g., SpaCy, NLTK)

[0952] System Configuration

[0953] Accepting user questions

[0954] Users log in to the learning application using a device such as a smartphone or tablet and enter a question. This question is sent to the server via an application programming interface (API). The server receives the question data and also acquires metadata such as the user ID and timestamp.

[0955] Question Analysis

[0956] The server analyzes the received question using a natural language processing module. Here, it identifies the intent and gist of the question and performs an appropriate analysis based on the content of the question. Based on the results of this analysis, it requests a generative AI model to generate an answer.

[0957] Generating answers

[0958] The server calls the generative AI model to generate an appropriate answer to the question. The generative AI model generates an answer based on its internal database and trained algorithms and returns it to the server. The server receives this answer, formats it in a user-friendly format, and sends it to the device. The device displays this answer to the user.

[0959] Personalized learning support

[0960] When a user inputs a learning request such as "I want to learn more," the server retrieves the user's learning history and progress data. Based on the user's past courses and current progress, the server requests the generative AI model to generate personalized learning resources. The generative AI model generates optimal learning content (for example, "A detailed explanation of vector spaces in linear algebra" or "Practice problems") based on the user's weaknesses and interests. The server then sends these resources to the user to support their learning.

[0961] Specific examples

[0962] Accepting questions and providing answers

[0963] 1. A user types a question into a smartphone app: "Please tell me the basic definition of differentiation."

[0964] 2. The server receives this question and parses it using the NLP module.

[0965] 3. The server calls the generative AI model, which generates an appropriate answer to the question, and obtains the answer, "Differentiation is a method for finding the rate of change of a function, and represents the ratio of change in y to change in x."

[0966] 4. This response is sent to the user's device and displayed.

[0967] Personalized learning support

[0968] 1. A user requests, "I want to learn more about linear algebra."

[0969] 2. The server obtains the user's learning history and progress.

[0970] 3. Using a generative AI model, we generate personalized resources such as "Detailed explanations of vector spaces in linear algebra" and "Practice problems" based on the user's learning history and interests.

[0971] 4. The generated resource is provided to the user.

[0972] Prompt Sentence Examples

[0973] "A user has entered the question 'What is the basic definition of derivative?' Use a generative AI model to generate the best answer to answer this question quickly and accurately."

[0974] The above is a specific embodiment and flow for carrying out the invention.

[0975] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0976] Step 1:

[0977] A user logs into the learning application on a terminal and enters a question.

[0978] Input: Username, password, question (e.g. "What is the basic definition of differentiation?")

[0979] Processing: After user authentication, obtain the question content

[0980] Output: Request data to send the question to the server via API

[0981] Step 2:

[0982] The server receives the question data via API and obtains the metadata (user ID, timestamp, etc.).

[0983] Input: Request data (question content, user ID, timestamp)

[0984] Processing: Parse the received question data and extract metadata

[0985] Output: Analysis data using the query and metadata

[0986] Step 3:

[0987] The server analyzes the received question using a natural language processing (NLP) module.

[0988] Input: Analysis data (question content, user ID, timestamp)

[0989] Processing: The NLP module identifies the intent and gist of the question (e.g., "Question about the definition of differential")

[0990] Output: NLP analysis results (analyzed question intent and summary)

[0991] Step 4:

[0992] The server requests the generation of an answer based on the analysis results and a generative AI model.

[0993] Input: NLP analysis results

[0994] Processing: Enter a prompt (e.g., "Please tell me the basic definition of differentiation") into the generative AI model and generate an answer.

[0995] Output: Generated answer (e.g., "Derivative is a way to find the rate of change of a function; it is the ratio of change in y to change in x.")

[0996] Step 5:

[0997] The server formats the generated answers in a user-friendly format and sends them to the device via an API.

[0998] Input: Generated Answer

[0999] Processing: Reformatting the response (e.g., converting it to JSON) and sending it

[1000] Output: The formatted answer sent to the user's terminal

[1001] Step 6:

[1002] The user checks the generated answer on the device.

[1003] Input: Formatted answer (e.g., "Derivative is a way to find the rate of change of a function; it is the ratio of change in y to change in x.")

[1004] Processing: Displayed by application

[1005] Output: User views displayed answer

[1006] Step 7:

[1007] When a user requests to "learn more," the server retrieves the user's learning history and progress data.

[1008] Input: User's new request (e.g., "I want to learn more about linear algebra"), User ID

[1009] Processing: Retrieve user learning history and progress information from the database

[1010] Output: Acquired learning history and progress data

[1011] Step 8:

[1012] The server generates personalized learning content using a generative AI model based on the acquired learning history.

[1013] Input: Acquired learning history and progress data, generative AI model

[1014] Processing: Generate personalized learning content (e.g., "Detailed explanation of vector spaces in linear algebra" or "Practice problems") using learning history and progress information

[1015] Output: Generated learning content

[1016] Step 9:

[1017] The server transmits the generated study content to the user terminal, and the user checks the study content.

[1018] Input: Generated learning content

[1019] Processing: Sending personalized learning content via API

[1020] Output: Learning content sent to the user's device, the user views the content

[1021] The above are the specific processing steps for carrying out the invention.

[1022] 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.

[1023] This invention is a system for supporting online learning and remote training, which analyzes user questions, recognizes the user's emotional state using an emotion engine, and provides fast and personalized answers using a generative AI model.The invention aims to improve the learning experience by referring to the user's learning progress data and providing answers and learning resources tailored by the emotion engine.

[1024] Explanation of program processing

[1025] Accepting user questions

[1026] A user logs into the learning application using their device and enters a question, for example, "What is the basic definition of differential calculus?" The user's device then sends the entered question to the server via an API, which receives metadata such as the question text, user ID, and timestamp.

[1027] Question Analysis

[1028] The server analyzes the received question using a natural language processing (NLP) module. Through the analysis, it identifies the intent of the question and recognizes it as a "question about the definition of differential." The emotion engine also analyzes the question text and recognizes the user's emotional state (e.g., excitement, stress, frustration, etc.).

[1029] Generating sentiment-based answers

[1030] The server sends appropriate instructions to the generative AI model based on the analysis results. At this time, the emotion engine adjusts the tone and content of the response based on the user's emotional state. For example, if the user is feeling stressed, the generative AI model will generate a response with a more polite and supportive tone. For example, in addition to the response "Differentiation is a way to find the rate of change of a function...", it will also include the advice "Take your time and learn slowly."

[1031] Formatting and Sending

[1032] The server receives the generated answer and formats it for the user to see (for example, by formatting the answer text in HTML or plain text), then sends the formatted answer to the user's device, where the user can view the answer.

[1033] Personalized learning support

[1034] When a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Referring to the user's past courses and current progress, the server asks the generative AI model to generate personalized learning resources. The emotion engine also references the user's emotional data and provides learning resources tailored to the user's specific emotional state. For example, if the user is interested, the server will include challenging content. Conversely, if the user is feeling stressed, the server will provide basic, easy-to-understand content.

[1035] Specific examples

[1036] Example 1: Math Question

[1037] 1. The user sends a question to the server from their terminal: "Please tell me the basic definition of differentiation."

[1038] 2. The server uses NLP to analyze the question and uses an emotion engine to recognize that the user is feeling stressed.

[1039] 3. The generative AI model generates a polite answer such as, "Differentiation is a way to find the rate of change of a function..." and adds the advice, "Take your time and learn."

[1040] 4. The server formats the answers and sends them to the user's device, where they review the answers and receive an emotionally supportive learning experience.

[1041] Example 2: Personalized learning support

[1042] 1. The user sends a request to the server from their device saying, "I want to learn more about linear algebra."

[1043] 2. The server references the user's learning history and progress data and uses an emotion engine to recognize the user's interests.

[1044] 3. The generative AI model generates a "detailed explanation of vector spaces in linear algebra" and a "set of applied problems."

[1045] 4. The server formats and sends these resources to the user's device, where the user can review the resources and receive a personalized learning experience based on their interests.

[1046] The system of the present invention can significantly enhance the learning experience by recognizing the user's emotional state and providing appropriate answers and learning resources based on that.

[1047] The processing flow will be explained below.

[1048] Step 1:

[1049] A user logs into a learning application using a terminal and types a question, for example, "What is the basic definition of differentiation?"

[1050] Step 2:

[1051] The user's device sends the entered question to the server via API, along with metadata such as the question text, user ID, and timestamp.

[1052] Step 3:

[1053] The server receives the question sent from the terminal and records the received data in a log, including the question text, user ID, and timestamp.

[1054] Step 4:

[1055] The server analyzes the received question using a natural language processing (NLP) module, identifying the intent of the question and recognizing it as a question about the definition of differential.

[1056] Step 5:

[1057] The emotion engine analyzes the question text and recognizes the user's emotional state, for example, determining whether the user is stressed or excited.

[1058] Step 6:

[1059] The server sends appropriate instructions to the generative AI model based on the analysis results and the emotion engine's recognition results, such as "Explain the definition of differentiation," and also instructs the model to adjust the tone and content of the response based on the user's emotional state.

[1060] Step 7:

[1061] Generative AI models receive instructions and generate optimal answers based on their internal database and trained algorithms, such as "Differentiation is a method for determining the rate of change of a function, and it represents the ratio of change in y to change in x."

[1062] Step 8:

[1063] The server receives the generated response and formats it in a user-friendly format, for example, in HTML or plain text.

[1064] Step 9:

[1065] The server sends the formatted response to the user's terminal, including the response text.

[1066] Step 10:

[1067] The user's device displays the received answers on the screen, allowing the user to review the answers and enjoy an emotionally supportive learning experience.

[1068] Step 11:

[1069] The server retrieves the user's learning progress data from the database and prepares to provide learning support based on the user's progress and interests.

[1070] Step 12:

[1071] The server references the user's progress data and asks the generative AI model to generate personalized learning resources, for example, in response to a request to "learn more about linear algebra."

[1072] Step 13:

[1073] The generative AI model generates optimal learning resources based on the user's progress and weaknesses, such as a detailed explanation of vector spaces in linear algebra or a set of exercises.

[1074] Step 14:

[1075] The server receives the generated learning resources, formats them in a user-friendly format, and organizes resource links, files, etc.

[1076] Step 15:

[1077] The server transmits the learning resources to the user's terminal so that the user can view them.

[1078] Step 16:

[1079] The user's device displays the received learning resources, and the user browses the content, resulting in a personalized learning experience based on their interests.

[1080] Through these steps, the system of the present invention can quickly and appropriately answer the user's questions and provide personalized assistance based on the user's learning progress and emotional state.

[1081] Example 2

[1082] 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."

[1083] Conventional online learning systems have the problem that they provide mechanical answers to user questions and do not provide personalized answers that reflect the user's emotions or learning progress. As a result, users may lose motivation to learn and feel stressed.

[1084] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving a question from a user, a means for performing natural language processing based on the received question, a means for analyzing the question and recognizing the emotional state, a means for generating an answer using a generative AI model based on the analysis and recognition results, and a means for sending the generated answer to the user. This makes it possible to provide personalized appropriate answers and learning resources based on the user's emotional state and learning progress.

[1085] A "user" is an individual or entity that utilizes the system to enter questions and receive answers.

[1086] A "question" is a text message that requests information that the user enters into the system.

[1087] "Terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[1088] A "server" is a computer system that receives and processes user questions, and generates and transmits answers.

[1089] "API" stands for Application Programming Interface, which provides rules and procedures for different software programs to communicate with each other.

[1090] "Natural language processing (NLP)" is a technology that allows computers to understand, analyze, and generate human language (natural language).

[1091] An "emotion engine" is a software module for analyzing and recognizing the emotional state from a user's text.

[1092] A "generative AI model" is an artificial intelligence model that generates appropriate answers based on analysis results.

[1093] "Metadata" refers to additional information related to the question text (e.g., user ID and timestamp).

[1094] "Personalization" means providing content that is customized according to the characteristics, emotional state, learning progress, etc. of each individual user.

[1095] "Formatting" refers to converting generated answers or resources into a user-friendly format (e.g., HTML or plain text).

[1096] "Learning resources" refers to educational materials and information provided to assist users in their learning.

[1097] This invention is a system for supporting online learning and remote training, which analyzes user questions, recognizes the user's emotional state using an emotion engine, and provides fast and personalized answers using a generative AI model.The invention aims to improve the learning experience by referring to the user's learning progress data and providing answers and learning resources tailored by the emotion engine.

[1098] Accepting user questions

[1099] A user logs in to the learning application using a device and enters a question, for example, "Please tell me the basic definition of differential calculus." The user's device sends the question text along with metadata including the user ID and timestamp to the server via an API. The server receives this data.

[1100] Question Analysis

[1101] The server analyzes the received question using a natural language processing (NLP) module. This analysis identifies the intent of the question and recognizes that it is a question about the definition of differential. The emotion engine also analyzes the question text and recognizes the user's emotional state (e.g., excitement, stress, frustration, etc.).

[1102] Generating sentiment-based answers

[1103] The server sends appropriate instructions to the generative AI model based on the analysis results and emotion recognition results, such as the following prompt:

[1104] Example prompt sentence:

[1105] "Explain the definition of differentiation in detail and respond in a gentle tone because the user is stressed."

[1106] Based on the instructions, the generative AI model generates a polite answer, such as "Differentiation is a way to find the rate of change of a function..." It also adds advice such as "Take your time and learn slowly."

[1107] Formatting and Sending

[1108] The server receives the generated answer, formats it into a user-friendly format (e.g., HTML or plain text), and sends the formatted answer back to the user's device via the API, where the user can view the answer.

[1109] Personalized learning support

[1110] When a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Based on this, it asks the generative AI model to generate personalized learning resources. At this time, the emotion engine also references the user's emotional data and provides learning resources tailored to the user's specific emotional state. For example, if the user is interested, it will include challenging content, and conversely, if the user is feeling stressed, it will provide basic, easy-to-understand content.

[1111] Specific examples

[1112] Example 1: Math Question

[1113] 1. The user sends a question to the server from their terminal: "Please tell me the basic definition of differentiation."

[1114] 2. The server uses NLP to analyze the question and uses an emotion engine to recognize that the user is feeling stressed.

[1115] 3. The generative AI model generates the answer, "Differentiation is a way to find the rate of change of a function..." and adds the advice, "Take your time and learn."

[1116] 4. The server formats the answers and sends them to the user's device, where they review the answers and receive an emotionally supportive learning experience.

[1117] Example 2: Personalized learning support

[1118] 1. The user sends a request to the server from their device saying, "I want to learn more about linear algebra."

[1119] 2. The server references the user's learning history and progress data and uses an emotion engine to recognize the user's interests.

[1120] 3. The generative AI model generates a "detailed explanation of vector spaces in linear algebra" and a "set of applied problems."

[1121] 4. The server formats and sends these resources to the user's device, where the user can review the resources and receive a personalized learning experience based on their interests.

[1122] The system of the present invention can significantly improve the learning experience by taking into account the user's emotional state and learning progress.

[1123] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1124] Step 1: Accepting user questions

[1125] A user uses a terminal to log in to a learning application and enter a question, for example, "What is the basic definition of differential calculus?"

[1126] The device sends the entered question text along with metadata including the user ID and timestamp to the server via API.

[1127] Input: The question text, user ID, and timestamp entered by the user on the terminal.

[1128] Output: Question data sent to the server (question text, user ID, timestamp).

[1129] Step 2: Parsing the Question

[1130] The server passes the received question data to a natural language processing (NLP) module, which analyzes the intent of the question. For example, it identifies the question as "a question about the definition of differential."

[1131] An emotion engine analyzes the question text and recognizes the user's emotional state (e.g., excitement, stress, frustration, etc.).

[1132] Input: Received question data (question text, user ID, timestamp).

[1133] Output: Parsed question content and user emotional state data.

[1134] Step 3: Generate sentiment-based answers

[1135] The server sends appropriate instructions to the generative AI model based on the analysis results (question content and emotional state), sending the following prompt to the generative AI model:

[1136] Example prompt: "Explain the definition of differentiation in detail and respond in a gentle tone as the user is stressed."

[1137] Based on the instructions, the generative AI model generates a polite answer, such as "Differentiation is a way to find the rate of change of a function..." It also adds advice such as "Take your time and learn slowly."

[1138] Input: The parsed question, the user's emotional state, and the prompt for the generative AI model.

[1139] Output: The generated answer text.

[1140] Step 4: Format and send

[1141] The server receives the generated response text and formats it into a user-friendly format (e.g., HTML or plain text).

[1142] The server then sends the formatted response back to the user's device via the API.

[1143] The user checks the answer on the terminal.

[1144] Input: The generated answer text.

[1145] Output: The formatted answer text and the answer sent to the user's device.

[1146] Step 5: Personalized learning support

[1147] If a user requests, "I want to learn more about linear algebra,"

[1148] The server retrieves the user's learning history and progress data from the database.

[1149] The server requests the generative AI model to generate personalized learning resources based on the referenced data and the user's emotional state as determined by the emotion engine.

[1150] For example, if a user is interested, include challenging content, but if they are stressed, provide basic, easy-to-understand content.

[1151] The generative AI model generates learning resources (e.g., a detailed explanation of vector spaces in linear algebra or a set of applied problems) based on instructions.

[1152] The server formats the generated learning resources and sends them to the user's terminal.

[1153] The user checks the learning resources on the device.

[1154] Input: User learning history, progress data, emotional state, and instructions to the generative AI model.

[1155] Output: The formatted learning resource and the learning resource sent to the user's device.

[1156] (Application example 2)

[1157] 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."

[1158] In modern manufacturing, operators and engineers working on factory floors need to receive technical information and training quickly and effectively. However, existing systems generally provide general learning content, making it difficult to provide personalized assistance based on individual users' emotional state and learning progress. Furthermore, there is a lack of means to provide appropriate support that takes emotions into account when users ask questions. This can reduce the effectiveness of operators and engineers' learning, negatively impacting on-site efficiency and quality.

[1159] The identification process by the identification 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 receiving a question from a user, means for analyzing the received question, means for generating an answer using a generative AI model based on the analysis result, means for sending the generated answer to the user, means for recognizing the user's emotional state, means for adjusting the tone and content of the answer based on the recognized emotional state, means for referencing the user's learning progress data, and means for providing personalized learning resources using a generative AI model based on the referenced data. This enables personalized support according to the user's emotional state and learning progress, thereby improving the effectiveness of technical information and training at the factory floor.

[1160] The "means for receiving a question from a user" is a function for transmitting a question entered by a user using a terminal to a server or related systems.

[1161] "Means for analyzing received questions" refers to a function that includes natural language processing (NLP) technology used to analyze questions received by the server and understand their content and intent.

[1162] "Means for generating answers using a generative AI model" refers to a function that utilizes an AI model to automatically generate appropriate answers based on the analysis results.

[1163] The "means for transmitting the generated answer to the user" is a function that formats the generated answer and transmits it to the user's terminal for display.

[1164] The "means for recognizing the user's emotional state" is a technology for analyzing the question text and the user's voice data to detect the user's emotional state (for example, excitement, stress, dissatisfaction, etc.).

[1165] The "means for adjusting the tone and content of the response based on the recognized emotional state" is a function that appropriately adjusts the expression method and content of the response according to the user's emotional state.

[1166] The "means for referencing user's learning progress data" is a function for retrieving and referencing the user's past learning history and progress status from a database.

[1167] "Means for providing personalized learning resources using a generative AI model based on referenced data" refers to a function that utilizes an AI model to generate individually optimized learning resources based on referenced learning progress data.

[1168] The "means for formatting and sending to the user's terminal" is a function for formatting the generated answers and learning resources into an appropriate format and sending them to the user's terminal.

[1169] The "means for displaying formatted answers to the user" is a function for displaying formatted answers and learning resources on the user's terminal.

[1170] "Means for viewing answers and learning resources using a head-mounted display" is a function for viewing answers and learning resources through the screen of a head-mounted display worn by the user.

[1171]

[1172] The system for realizing this invention provides a learning support application "SmartFactoryTutor" that is installed on a factory robot. A detailed embodiment of this system will be described below.

[1173] The server receives and analyzes input from the device used by the user (e.g., a tablet or head-mounted display). Specifically, the user enters a question in voice or text format. For example, the user might enter, "Please tell me the maintenance procedure for the machine."

[1174] The received question is sent to the server via an API, which receives metadata such as the question text, user ID, and timestamp. The server then analyzes the received question using a natural language processing (NLP) module (e.g., SpaCy or NLTK). This identifies the intent of the question and recognizes that it is a "question about maintenance procedures." An emotion engine (e.g., IBM Watson) is then used to analyze the question text and recognize the user's emotional state (e.g., impatience, anxiety, excitement, etc.).

[1175] Based on the analysis results, the server sends instructions to a generative AI model (such as OpenAI GPT-3) to generate a response. The tone and content of the response are adjusted based on the user's emotional state as recognized by the emotion engine. For example, if the user is feeling impatient, the generative AI model will generate a polite and supportive response such as, "Machine maintenance is a very important process. Let's take it easy and check each step one by one."

[1176] The generated answers are formatted in HTML or plain text and sent from the server to the user's device, where they can view the answers via a tablet or head-mounted display.

[1177] Furthermore, when a user requests more detailed training materials or videos, the server retrieves the user's learning history and progress data from a database (e.g., PostgreSQL). If the emotion engine recognizes the user's interest, the generative AI model generates personalized training materials, such as "We've prepared new training videos based on what we learned during past maintenance work."

[1178] Specific examples

[1179] For example, if the user speaks, "Please tell me today's maintenance procedure," the server processes as follows:

[1180] 1. The tablet or HMD receives the user's question and sends it to the server via API.

[1181] 2. The server analyzes the question and uses its emotion engine to recognize that the user is anxious.

[1182] 3. Based on the analysis results, a prompt statement is sent to the generative AI model: "The user has asked about machine maintenance procedures. The user seems a little anxious. Please generate a polite and supportive answer.", and an answer is generated.

[1183] 4. Format the generated answers into HTML and send them to the tablet or HMD.

[1184] In this way, "SmartFactoryTutor" can efficiently support technical information and training on the factory floor.

[1185] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1186] Step 1: Accepting user questions

[1187] Users input questions in voice or text format using a tablet or head-mounted display. The input questions are sent to the server via an API. Inputs include specific technical questions such as "Please tell me the maintenance procedure for the machine." The output is metadata such as the question text, user ID, and timestamp.

[1188] Step 2: Parsing the Question

[1189] The server parses the received question using a natural language processing (NLP) module (e.g., SpaCy or NLTK). The input is the question text, which the NLP module parses to identify the intent of the question, recognizing it as a "question about maintenance procedures." The output is metadata about the question's category and intent.

[1190] Step 3: Recognizing your emotional state

[1191] The server uses an emotion engine (e.g., IBM Watson) to analyze the question text and recognize the user's emotional state (e.g., impatience, anxiety, excitement, etc.). The input is the question text, and the emotion engine analyzes the user's emotion based on this. The output is metadata that indicates the user's emotional state.

[1192] Step 4: Generate an answer

[1193] Based on the analysis results, the server sends instructions to a generative AI model (e.g., OpenAI GPT-3) to generate an answer. The tone and content of the answer are adjusted based on the user's emotional state as recognized by the emotion engine. The input is the question category, intent, and emotional state metadata, and the generative AI model generates an appropriate answer based on this. The output is the generated answer text.

[1194] Step 5: Format your response

[1195] The server formats the generated answer text into HTML or plain text. The input is the generated answer text, and the formatting engine formats it into the appropriate format. The output is the formatted answer text.

[1196] Step 6: Submit your response

[1197] The server sends the formatted answer to the user's device. The input is the formatted answer text, which the server sends via an API to the user's tablet or head-mounted display. The output is the answer text that is displayed to the user.

[1198] Step 7: Provide learning resources

[1199] When a user requests additional learning resources, the server retrieves the user's learning history and progress data from a database (e.g., PostgreSQL). The input is the user's request data, and the output is the user's learning history and progress data. The server then sends instructions to the generative AI model to generate personalized learning resources. The output is personalized learning resources (e.g., training videos and materials).

[1200] Step 8: Format and submit your learning resources

[1201] The server formats the generated learning resources into HTML or plain text format and sends them to the user's device. The input is the generated learning resources, which the formatting engine formats into an appropriate format. The output is the formatted learning resources displayed on the user's tablet or head-mounted display.

[1202] 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.

[1203] 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.

[1204] 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.

[1205] [Fourth embodiment]

[1206] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1207] 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.

[1208] 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).

[1209] 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.

[1210] 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.

[1211] 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).

[1212] 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.

[1213] 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.

[1214] 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.

[1215] 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.

[1216] 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.

[1217] 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.

[1218] 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."

[1219] This invention is a system for supporting online learning and training, in which a server receives questions sent by users from their devices and provides quick answers using a generative AI model. It also includes a function to provide personalized learning support based on the user's learning progress and interests.

[1220] Explanation of program processing

[1221] Accepting user questions

[1222] A user logs in to the learning application using a device and inputs a question. For example, "Please tell me the basic definition of differential calculus." The device then sends this question to the server via an API. The server receives the question data and also retrieves metadata such as the user ID and timestamp.

[1223] Question Analysis

[1224] The server analyzes the received question using a natural language processing (NLP) module. Here, it identifies the intent and gist of the question and recognizes it as a "question about the definition of differential." Based on the results of this analysis, the server requests the generative AI model to generate an answer.

[1225] Generating answers

[1226] The server calls a generative AI model based on the analysis results. The generative AI model generates an appropriate answer based on its internal database and trained algorithms. Specifically, it generates an answer such as, "Differentiation is a method for determining the rate of change of a function, and represents the ratio of change in y to change in x." The server receives this answer, formats it in a user-friendly format, and sends it to the device. The device displays this answer to the user.

[1227] Personalized learning support

[1228] When a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Referring to the user's past courses and current progress, the server asks the generative AI model to generate personalized learning resources. Based on the user's weaknesses and interests, the generative AI model generates, for example, "a detailed explanation of vector spaces in linear algebra" or "a set of exercises." The server then sends these resources to the user to support their learning.

[1229] Specific examples

[1230] Example 1: Question about a math problem

[1231] 1. The user sends the question "Please tell me the basic definition of differentiation" to the server from their terminal.

[1232] 2. The server receives the question and parses it using NLP.

[1233] 3. The server calls the generative AI model and asks it to generate an appropriate answer to the question.

[1234] 4. The generative AI model generates the answer, "Differentiation is a method for finding the rate of change of a function, and represents the ratio of change in y to change in x."

[1235] 5. The server sends this response to the user, who then checks the response on their device.

[1236] Example 2: Personalized learning support

[1237] 1. The user sends a request to the server from their device saying, "I want to learn more about linear algebra."

[1238] 2. The server references the user's learning history and progress data and asks the generative AI model to generate personalized learning resources.

[1239] 3. The generative AI model generates a "detailed explanation of vector spaces in linear algebra" and a "set of exercises."

[1240] 4. The server sends these resources to the user, who then checks them on the device.

[1241] As described above, the system of the present invention can provide users with fast and appropriate answers to their questions and enhance their learning experience through personalized learning resources.

[1242] The processing flow will be explained below.

[1243] Step 1:

[1244] A user logs into a learning application using a terminal and types a question, for example, "What is the basic definition of differentiation?"

[1245] Step 2:

[1246] The user's device sends the entered question to the server via API, along with metadata such as the question text, user ID, and timestamp.

[1247] Step 3:

[1248] The server receives the question sent from the terminal and records the received data in a log, including the question text, user ID, and timestamp.

[1249] Step 4:

[1250] The server uses a natural language processing (NLP) module to analyze the intent of the question, for example, identifying that the question is about "definition of differential."

[1251] Step 5:

[1252] The server sends appropriate instructions to the generative AI model based on the analysis results. In this case, the instruction sent to the generative AI model is "Explain the definition of differentiation."

[1253] Step 6:

[1254] A generative AI model receives instructions and generates an optimal answer based on its internal database and trained algorithms, such as "Differentiation is a way to find the rate of change of a function..."

[1255] Step 7:

[1256] The server receives the generated response and formats it in a user-friendly format, for example, in HTML or plain text.

[1257] Step 8:

[1258] The server sends the formatted response to the user's terminal, including the response text.

[1259] Step 9:

[1260] The user's device will display the received answer on the screen, where the user can check the "basic definition of differentiation."

[1261] Step 10:

[1262] The server retrieves the user's learning progress data from the database and prepares to provide learning support based on the user's progress and interests.

[1263] Step 11:

[1264] The server references the user's progress data and asks the generative AI model to generate personalized learning resources, for example, in response to a request to "learn more about linear algebra."

[1265] Step 12:

[1266] The generative AI model generates optimal learning resources based on the user's progress and weaknesses, such as a detailed explanation of vector spaces in linear algebra or a set of exercises.

[1267] Step 13:

[1268] The server receives the generated learning resources, formats them in a user-friendly format, and organizes resource links, files, etc.

[1269] Step 14:

[1270] The server transmits the learning resources to the user's terminal so that the user can view them.

[1271] Step 15:

[1272] The user's terminal displays the received learning resource, and the user views the content.

[1273] Through the above steps, the system of the present invention can quickly and appropriately answer the user's questions and provide personalized assistance based on the user's learning progress.

[1274] Example 1

[1275] 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."

[1276] Conventional online learning support systems have difficulty providing prompt and appropriate answers to users' questions and requests, and have had issues with not providing sufficient personalized learning support based on the user's progress and interests. Furthermore, there is a lack of automated processing for generating answers and providing learning support resources, which requires a lot of time and effort.

[1277] 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.

[1278] In this invention, the server includes means for receiving input from a user, means for analyzing the received input, means for invoking a generative AI model based on the analysis result to generate an answer, and means for formatting the generated answer and sending it to the user, thereby enabling the provision of prompt and appropriate answers to user questions and personalized learning support.

[1279] "User" refers to an individual who uses the system to learn or search for information.

[1280] "Input" refers to information such as a question or request that a user provides to a system.

[1281] "Terminal" refers to the device a user uses to access the system, such as a PC or smartphone.

[1282] "Server" refers to a central computer system that receives input from users and performs processing such as analysis and response generation.

[1283] "Communication means" refers to the method or protocol for sending and receiving data between a terminal and a server. A typical example is the Internet Protocol (IP).

[1284] "Means for receiving" refers to the function by which the server receives input sent from the terminal.

[1285] "Means for analyzing" refers to the function of understanding the content of received input and performing processing to identify its intent and gist.

[1286] A "generative AI model" refers to an algorithm that uses machine learning and databases to automatically generate appropriate answers or resources from specific inputs.

[1287] "Means for generating answers" refers to the function of calling a generative AI model based on the analysis results and creating answers to users' questions.

[1288] "Means for formatting and sending" refers to a function for formatting generated answers and the like into a format that is easy for the user to view and sending it to the user's terminal.

[1289] "Progress data" refers to information about the progress of a user's learning, such as their learning status and past history.

[1290] "Personalized learning resources" refers to learning content and materials that are specifically customized based on a user's progress data and interests.

[1291] "Personalization" refers to providing services and content that are individualized according to each user's needs and past history.

[1292] This invention is a system for supporting online learning and training, in which a server receives questions sent by users from their devices and provides quick answers using a generative AI model. It also provides personalized learning support based on the user's learning progress and interests.

[1293] First, the user logs in to the learning application using their device. The learning application can be provided in various forms, such as a web browser or a dedicated application. When the user enters a question, the device sends this input to the server via an API. For example, if the user enters "Please tell me the basic definition of differentiation," the device sends this question data to the server.

[1294] The server receives the question data and acquires metadata such as the user ID and timestamp. The received question is analyzed by a natural language processing (NLP) module. The NLP module analyzes the input question and identifies its intent and gist. For example, it may recognize that the question is about the definition of differential. Based on the analysis results, the server invokes a generative AI model to generate an answer.

[1295] The generative AI model is equipped with an internal database and machine learning algorithms to generate appropriate answers. As a specific example of an answer, it might generate the following: "Differentiation is a method for determining the rate of change of a function, and represents the ratio of change in y to change in x." The server receives the generated answer and formats it in a format that is easy for the user to view. The formatted answer is then sent to the device, where the user can view it.

[1296] Furthermore, if a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Based on the user's past courses and current progress, the server asks the generative AI model to generate personalized learning resources. Based on the user's weaknesses and interests, the generative AI model generates, for example, "a detailed explanation of vector spaces in linear algebra" or "a set of exercises." The server formats these resources and sends them to the user's device. The user can view the resources on their device and use them for their studies.

[1297] As an example, the following prompt sentence is used for a generative AI model:

[1298] Question and Answer Generation

[1299] Generate a detailed answer to the user's question, "What is the basic definition of differentiation?"

[1300] Personalized learning resource generation

[1301] Based on a user's request to "learn more about linear algebra," suggest personalized learning resources based on the user's past learning history.

[1302] As described above, the present invention can quickly and appropriately answer user questions and provide personalized learning support according to the user's progress and interests, thereby enabling the user to study efficiently and effectively.

[1303] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1304] Step 1: Accepting user questions

[1305] 1. A user logs in to a learning application using a terminal. The input is the user's login information, and the output is a notification of login success or failure.

[1306] 2. The user inputs a question into the learning application. For example, "Please tell me the basic definition of differential calculus." The input is the user's question text, and the output is the transmission of the question data from the terminal to the server.

[1307] 3. The device uses the API to send the user's question data to the server. The input is the question text and metadata (user ID, timestamp), and the output is the status of successful submission.

[1308] Step 2: Parsing the Question

[1309] 1. The server receives the user's query data. The input is the query data sent from the device, and the output is the saving of the query data and metadata to the internal storage.

[1310] 2. The server's natural language processing (NLP) module analyzes the received question. The input is the question text, and the output is the analysis results that identify the intent and gist of the question.

[1311] 3. Based on the intent of the question, the server prepares data to be passed to the generative AI model. The input is the analysis result of the NLP module, and the output is the input data for the generative AI model.

[1312] Step 3: Generate the answer

[1313] 1. The server invokes the generative AI model based on the analysis results. The input is the analysis results, and the output is the success status of the generation request.

[1314] 2. Generative AI models generate answers using internal databases and machine learning algorithms. The input is the analysis result, and the output is the generated answer text.

[1315] 3. The server receives and formats the generated answer: the input is the generated answer text, and the output is the answer converted into a user-friendly format.

[1316] Step 4: Returning the Answer

[1317] 1. The server sends a formatted answer to the user's terminal. The input is the formatted answer, and the output is the success status of the answer transmission.

[1318] 2. The terminal displays the answer received from the server to the user. The input is the formatted answer and the output is the display of the answer to the user.

[1319] 3. The user checks the answers on the device and uses them to help them learn. The input is the displayed answer text, and the output is the user's learning progress.

[1320] Step 5: Personalized learning support

[1321] 1. A user requests, "I want to learn more about linear algebra." The input is the user's request text, and the output is the transmission of the request data from the terminal to the server.

[1322] 2. The device uses the API to send a request to the server. The input is the request text and metadata, and the output is a successful transmission status.

[1323] 3. The server retrieves the user's learning history and progress data from the database. The input is the user ID, and the output is the retrieved learning history and progress data.

[1324] 4. The server requests the generative AI model to generate personalized learning resources. The input is the learning history and progress data, and the output is the success status of the generation request.

[1325] 5. The generative AI model generates learning resources tailored to the user. For example, it generates a "detailed explanation of vector spaces in linear algebra" or a "set of exercises." The input is learning history and progress data, and the output is the generated learning resource.

[1326] 6. The server formats the generated learning resource and sends it to the user's terminal. The input is the generated learning resource, and the output is the successful transmission status of the formatted learning resource.

[1327] 7. The user checks the resources on the device and uses them for learning. The input is the formatted learning resource, and the output is the enrichment of the user's learning.

[1328] (Application example 1)

[1329] 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."

[1330] Conventional online learning systems have difficulty in providing quick and accurate answers to user questions, and they lack personalized learning support. They also have difficulty effectively utilizing users' learning history and progress information to provide optimal learning resources.

[1331] 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.

[1332] In this invention, the server includes means for receiving questions from users, means for analyzing the received questions, means for generating answers using a generative AI model based on the analysis results, means for sending the generated answers to the users, means for sending questions sent from the users' devices to the server via an API, means for formatting the generated answers and sending them to the users' devices, means for acquiring the users' learning history and progress information and providing personalized learning resources, and means for generating personalized learning content using the generative AI model. This makes it possible to quickly and accurately answer users' questions and provide optimal learning resources based on the users' learning progress and interests.

[1333] The "means for receiving a question from a user" refers to a device or system that has the function of receiving a question entered by a user through a terminal or interface.

[1334] The "means for analyzing the received question" refers to a device or system that has the function of analyzing the received question using natural language processing technology or the like and identifying the intent and content of the question.

[1335] "Means for generating answers using a generative AI model based on the analysis results" refers to devices or systems that have the functionality to utilize a generative AI model to generate appropriate answers based on the content of the analyzed question.

[1336] The "means for transmitting the generated answer to the user" refers to a device or system that has the function of formatting the generated answer and transmitting it to the terminal used by the user.

[1337] "Means for sending questions sent from a user's terminal to a server via an API" refers to a device or system that has the function of sending questions entered by a user to a server via an application programming interface.

[1338] "Means for formatting the generated answer and sending it to the user's device" refers to a device or system that has the function of converting the answer generated by the generative AI model into a format that is easy for the user to view and sending it to the user's device.

[1339] "Means for acquiring a user's learning history and progress information and providing personalized learning resources" refers to a device or system that has the function of acquiring a user's past learning data and current progress status and providing personalized learning resources based on that data.

[1340] "Means for generating personalized learning content using generative AI models" refers to devices or systems that utilize generative AI models to generate optimal learning content based on a user's learning history and interests.

[1341] The present invention is a system for supporting online learning and training, in which a server receives questions sent by a user from a terminal and provides quick answers using a generative AI model. It also provides personalized learning support based on the user's learning progress and interests. Specific embodiments of the system are described below.

[1342] Hardware and software used

[1343] To realize the system of the present invention, the following hardware and software are required.

[1344] Hardware: Smartphones, tablets, personal computers, etc.

[1345] Software: Python, Requests library, generative AI models (e.g., OpenAI GPT-3), natural language processing modules (e.g., SpaCy, NLTK)

[1346] System Configuration

[1347] Accepting user questions

[1348] Users log in to the learning application using a device such as a smartphone or tablet and enter a question. This question is sent to the server via an application programming interface (API). The server receives the question data and also acquires metadata such as the user ID and timestamp.

[1349] Question Analysis

[1350] The server analyzes the received question using a natural language processing module. Here, it identifies the intent and gist of the question and performs an appropriate analysis based on the content of the question. Based on the results of this analysis, it requests a generative AI model to generate an answer.

[1351] Generating answers

[1352] The server calls the generative AI model to generate an appropriate answer to the question. The generative AI model generates an answer based on its internal database and trained algorithms and returns it to the server. The server receives this answer, formats it in a user-friendly format, and sends it to the device. The device displays this answer to the user.

[1353] Personalized learning support

[1354] When a user inputs a learning request such as "I want to learn more," the server retrieves the user's learning history and progress data. Based on the user's past courses and current progress, the server requests the generative AI model to generate personalized learning resources. The generative AI model generates optimal learning content (for example, "A detailed explanation of vector spaces in linear algebra" or "Practice problems") based on the user's weaknesses and interests. The server then sends these resources to the user to support their learning.

[1355] Specific examples

[1356] Accepting questions and providing answers

[1357] 1. A user types a question into a smartphone app: "Please tell me the basic definition of differentiation."

[1358] 2. The server receives this question and parses it using the NLP module.

[1359] 3. The server calls the generative AI model, which generates an appropriate answer to the question, and obtains the answer, "Differentiation is a method for finding the rate of change of a function, and represents the ratio of change in y to change in x."

[1360] 4. This response is sent to the user's device and displayed.

[1361] Personalized learning support

[1362] 1. A user requests, "I want to learn more about linear algebra."

[1363] 2. The server obtains the user's learning history and progress.

[1364] 3. Using a generative AI model, we generate personalized resources such as "Detailed explanations of vector spaces in linear algebra" and "Practice problems" based on the user's learning history and interests.

[1365] 4. The generated resource is provided to the user.

[1366] Prompt Sentence Examples

[1367] "A user has entered the question 'What is the basic definition of derivative?' Use a generative AI model to generate the best answer to answer this question quickly and accurately."

[1368] The above is a specific embodiment and flow for carrying out the invention.

[1369] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1370] Step 1:

[1371] A user logs into the learning application on a terminal and enters a question.

[1372] Input: Username, password, question (e.g. "What is the basic definition of differentiation?")

[1373] Processing: After user authentication, obtain the question content

[1374] Output: Request data to send the question to the server via API

[1375] Step 2:

[1376] The server receives the question data via API and obtains the metadata (user ID, timestamp, etc.).

[1377] Input: Request data (question content, user ID, timestamp)

[1378] Processing: Parse the received question data and extract metadata

[1379] Output: Analysis data using the query and metadata

[1380] Step 3:

[1381] The server analyzes the received question using a natural language processing (NLP) module.

[1382] Input: Analysis data (question content, user ID, timestamp)

[1383] Processing: The NLP module identifies the intent and gist of the question (e.g., "Question about the definition of differential")

[1384] Output: NLP analysis results (analyzed question intent and summary)

[1385] Step 4:

[1386] The server requests the generation of an answer based on the analysis results and a generative AI model.

[1387] Input: NLP analysis results

[1388] Processing: Enter a prompt (e.g., "Please tell me the basic definition of differentiation") into the generative AI model and generate an answer.

[1389] Output: Generated answer (e.g., "Derivative is a way to find the rate of change of a function; it is the ratio of change in y to change in x.")

[1390] Step 5:

[1391] The server formats the generated answers in a user-friendly format and sends them to the device via an API.

[1392] Input: Generated Answer

[1393] Processing: Reformatting the response (e.g., converting it to JSON) and sending it

[1394] Output: The formatted answer sent to the user's terminal

[1395] Step 6:

[1396] The user checks the generated answer on the device.

[1397] Input: Formatted answer (e.g., "Derivative is a way to find the rate of change of a function; it is the ratio of change in y to change in x.")

[1398] Processing: Displayed by application

[1399] Output: User views displayed answer

[1400] Step 7:

[1401] When a user requests to "learn more," the server retrieves the user's learning history and progress data.

[1402] Input: User's new request (e.g., "I want to learn more about linear algebra"), User ID

[1403] Processing: Retrieve user learning history and progress information from the database

[1404] Output: Acquired learning history and progress data

[1405] Step 8:

[1406] The server generates personalized learning content using a generative AI model based on the acquired learning history.

[1407] Input: Acquired learning history and progress data, generative AI model

[1408] Processing: Generate personalized learning content (e.g., "Detailed explanation of vector spaces in linear algebra" or "Practice problems") using learning history and progress information

[1409] Output: Generated learning content

[1410] Step 9:

[1411] The server transmits the generated study content to the user terminal, and the user checks the study content.

[1412] Input: Generated learning content

[1413] Processing: Sending personalized learning content via API

[1414] Output: Learning content sent to the user's device, the user views the content

[1415] The above are the specific processing steps for carrying out the invention.

[1416] 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.

[1417] This invention is a system for supporting online learning and remote training, which analyzes user questions, recognizes the user's emotional state using an emotion engine, and provides fast and personalized answers using a generative AI model.The invention aims to improve the learning experience by referring to the user's learning progress data and providing answers and learning resources tailored by the emotion engine.

[1418] Explanation of program processing

[1419] Accepting user questions

[1420] A user logs into the learning application using their device and enters a question, for example, "What is the basic definition of differential calculus?" The user's device then sends the entered question to the server via an API, which receives metadata such as the question text, user ID, and timestamp.

[1421] Question Analysis

[1422] The server analyzes the received question using a natural language processing (NLP) module. Through the analysis, it identifies the intent of the question and recognizes it as a "question about the definition of differential." The emotion engine also analyzes the question text and recognizes the user's emotional state (e.g., excitement, stress, frustration, etc.).

[1423] Generating sentiment-based answers

[1424] The server sends appropriate instructions to the generative AI model based on the analysis results. At this time, the emotion engine adjusts the tone and content of the response based on the user's emotional state. For example, if the user is feeling stressed, the generative AI model will generate a response with a more polite and supportive tone. For example, in addition to the response "Differentiation is a way to find the rate of change of a function...", it will also include the advice "Take your time and learn slowly."

[1425] Formatting and Sending

[1426] The server receives the generated answer and formats it for the user to see (for example, by formatting the answer text in HTML or plain text), then sends the formatted answer to the user's device, where the user can view the answer.

[1427] Personalized learning support

[1428] When a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Referring to the user's past courses and current progress, the server asks the generative AI model to generate personalized learning resources. The emotion engine also references the user's emotional data and provides learning resources tailored to the user's specific emotional state. For example, if the user is interested, the server will include challenging content. Conversely, if the user is feeling stressed, the server will provide basic, easy-to-understand content.

[1429] Specific examples

[1430] Example 1: Math Question

[1431] 1. The user sends a question to the server from their terminal: "Please tell me the basic definition of differentiation."

[1432] 2. The server uses NLP to analyze the question and uses an emotion engine to recognize that the user is feeling stressed.

[1433] 3. The generative AI model generates a polite answer such as, "Differentiation is a way to find the rate of change of a function..." and adds the advice, "Take your time and learn."

[1434] 4. The server formats the answers and sends them to the user's device, where they review the answers and receive an emotionally supportive learning experience.

[1435] Example 2: Personalized learning support

[1436] 1. The user sends a request to the server from their device saying, "I want to learn more about linear algebra."

[1437] 2. The server references the user's learning history and progress data and uses an emotion engine to recognize the user's interests.

[1438] 3. The generative AI model generates a "detailed explanation of vector spaces in linear algebra" and a "set of applied problems."

[1439] 4. The server formats and sends these resources to the user's device, where the user can review the resources and receive a personalized learning experience based on their interests.

[1440] The system of the present invention can significantly enhance the learning experience by recognizing the user's emotional state and providing appropriate answers and learning resources based on that.

[1441] The processing flow will be explained below.

[1442] Step 1:

[1443] A user logs into a learning application using a terminal and types a question, for example, "What is the basic definition of differentiation?"

[1444] Step 2:

[1445] The user's device sends the entered question to the server via API, along with metadata such as the question text, user ID, and timestamp.

[1446] Step 3:

[1447] The server receives the question sent from the terminal and records the received data in a log, including the question text, user ID, and timestamp.

[1448] Step 4:

[1449] The server analyzes the received question using a natural language processing (NLP) module, identifying the intent of the question and recognizing it as a question about the definition of differential.

[1450] Step 5:

[1451] The emotion engine analyzes the question text and recognizes the user's emotional state, for example, determining whether the user is stressed or excited.

[1452] Step 6:

[1453] The server sends appropriate instructions to the generative AI model based on the analysis results and the emotion engine's recognition results, such as "Explain the definition of differentiation," and also instructs the model to adjust the tone and content of the response based on the user's emotional state.

[1454] Step 7:

[1455] Generative AI models receive instructions and generate optimal answers based on their internal database and trained algorithms, such as "Differentiation is a method for determining the rate of change of a function, and it represents the ratio of change in y to change in x."

[1456] Step 8:

[1457] The server receives the generated response and formats it in a user-friendly format, for example, in HTML or plain text.

[1458] Step 9:

[1459] The server sends the formatted response to the user's terminal, including the response text.

[1460] Step 10:

[1461] The user's device displays the received answers on the screen, allowing the user to review the answers and enjoy an emotionally supportive learning experience.

[1462] Step 11:

[1463] The server retrieves the user's learning progress data from the database and prepares to provide learning support based on the user's progress and interests.

[1464] Step 12:

[1465] The server references the user's progress data and asks the generative AI model to generate personalized learning resources, for example, in response to a request to "learn more about linear algebra."

[1466] Step 13:

[1467] The generative AI model generates optimal learning resources based on the user's progress and weaknesses, such as a detailed explanation of vector spaces in linear algebra or a set of exercises.

[1468] Step 14:

[1469] The server receives the generated learning resources, formats them in a user-friendly format, and organizes resource links, files, etc.

[1470] Step 15:

[1471] The server transmits the learning resources to the user's terminal so that the user can view them.

[1472] Step 16:

[1473] The user's device displays the received learning resources, and the user browses the content, resulting in a personalized learning experience based on their interests.

[1474] Through these steps, the system of the present invention can quickly and appropriately answer the user's questions and provide personalized assistance based on the user's learning progress and emotional state.

[1475] Example 2

[1476] 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."

[1477] Conventional online learning systems have the problem that they provide mechanical answers to user questions and do not provide personalized answers that reflect the user's emotions or learning progress. As a result, users may lose motivation to learn and feel stressed.

[1478] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for receiving a question from a user, a means for performing natural language processing based on the received question, a means for analyzing the question and recognizing the emotional state, a means for generating an answer using a generative AI model based on the analysis and recognition results, and a means for sending the generated answer to the user. This makes it possible to provide personalized appropriate answers and learning resources based on the user's emotional state and learning progress.

[1479] A "user" is an individual or entity that utilizes the system to enter questions and receive answers.

[1480] A "question" is a text message that requests information that the user enters into the system.

[1481] "Terminal" refers to a device used by a user, such as a computer, smartphone, or tablet.

[1482] A "server" is a computer system that receives and processes user questions, and generates and transmits answers.

[1483] "API" stands for Application Programming Interface, which provides rules and procedures for different software programs to communicate with each other.

[1484] "Natural language processing (NLP)" is a technology that allows computers to understand, analyze, and generate human language (natural language).

[1485] An "emotion engine" is a software module for analyzing and recognizing the emotional state from a user's text.

[1486] A "generative AI model" is an artificial intelligence model that generates appropriate answers based on analysis results.

[1487] "Metadata" refers to additional information related to the question text (e.g., user ID and timestamp).

[1488] "Personalization" means providing content that is customized according to the characteristics, emotional state, learning progress, etc. of each individual user.

[1489] "Formatting" refers to converting generated answers or resources into a user-friendly format (e.g., HTML or plain text).

[1490] "Learning resources" refers to educational materials and information provided to assist users in their learning.

[1491] This invention is a system for supporting online learning and remote training, which analyzes user questions, recognizes the user's emotional state using an emotion engine, and provides fast and personalized answers using a generative AI model.The invention aims to improve the learning experience by referring to the user's learning progress data and providing answers and learning resources tailored by the emotion engine.

[1492] Accepting user questions

[1493] A user logs in to the learning application using a device and enters a question, for example, "Please tell me the basic definition of differential calculus." The user's device sends the question text along with metadata including the user ID and timestamp to the server via an API. The server receives this data.

[1494] Question Analysis

[1495] The server analyzes the received question using a natural language processing (NLP) module. This analysis identifies the intent of the question and recognizes that it is a question about the definition of differential. The emotion engine also analyzes the question text and recognizes the user's emotional state (e.g., excitement, stress, frustration, etc.).

[1496] Generating sentiment-based answers

[1497] The server sends appropriate instructions to the generative AI model based on the analysis results and emotion recognition results, such as the following prompt:

[1498] Example prompt sentence:

[1499] "Explain the definition of differentiation in detail and respond in a gentle tone because the user is stressed."

[1500] Based on the instructions, the generative AI model generates a polite answer, such as "Differentiation is a way to find the rate of change of a function..." It also adds advice such as "Take your time and learn slowly."

[1501] Formatting and Sending

[1502] The server receives the generated answer, formats it into a user-friendly format (e.g., HTML or plain text), and sends the formatted answer back to the user's device via the API, where the user can view the answer.

[1503] Personalized learning support

[1504] When a user requests, "I want to learn more about linear algebra," the server retrieves the user's learning history and progress data from the database. Based on this, it asks the generative AI model to generate personalized learning resources. At this time, the emotion engine also references the user's emotional data and provides learning resources tailored to the user's specific emotional state. For example, if the user is interested, it will include challenging content, and conversely, if the user is feeling stressed, it will provide basic, easy-to-understand content.

[1505] Specific examples

[1506] Example 1: Math Question

[1507] 1. The user sends a question to the server from their terminal: "Please tell me the basic definition of differentiation."

[1508] 2. The server uses NLP to analyze the question and uses an emotion engine to recognize that the user is feeling stressed.

[1509] 3. The generative AI model generates the answer, "Differentiation is a way to find the rate of change of a function..." and adds the advice, "Take your time and learn."

[1510] 4. The server formats the answers and sends them to the user's device, where they review the answers and receive an emotionally supportive learning experience.

[1511] Example 2: Personalized learning support

[1512] 1. The user sends a request to the server from their device saying, "I want to learn more about linear algebra."

[1513] 2. The server references the user's learning history and progress data and uses an emotion engine to recognize the user's interests.

[1514] 3. The generative AI model generates a "detailed explanation of vector spaces in linear algebra" and a "set of applied problems."

[1515] 4. The server formats and sends these resources to the user's device, where the user can review the resources and receive a personalized learning experience based on their interests.

[1516] The system of the present invention can significantly improve the learning experience by taking into account the user's emotional state and learning progress.

[1517] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1518] Step 1: Accepting user questions

[1519] A user uses a terminal to log in to a learning application and enter a question, for example, "What is the basic definition of differential calculus?"

[1520] The device sends the entered question text along with metadata including the user ID and timestamp to the server via API.

[1521] Input: The question text, user ID, and timestamp entered by the user on the terminal.

[1522] Output: Question data sent to the server (question text, user ID, timestamp).

[1523] Step 2: Parsing the Question

[1524] The server passes the received question data to a natural language processing (NLP) module, which analyzes the intent of the question. For example, it identifies the question as "a question about the definition of differential."

[1525] An emotion engine analyzes the question text and recognizes the user's emotional state (e.g., excitement, stress, frustration, etc.).

[1526] Input: Received question data (question text, user ID, timestamp).

[1527] Output: Parsed question content and user emotional state data.

[1528] Step 3: Generate sentiment-based answers

[1529] The server sends appropriate instructions to the generative AI model based on the analysis results (question content and emotional state), sending the following prompt to the generative AI model:

[1530] Example prompt: "Explain the definition of differentiation in detail and respond in a gentle tone as the user is stressed."

[1531] Based on the instructions, the generative AI model generates a polite answer, such as "Differentiation is a way to find the rate of change of a function..." It also adds advice such as "Take your time and learn slowly."

[1532] Input: The parsed question, the user's emotional state, and the prompt for the generative AI model.

[1533] Output: The generated answer text.

[1534] Step 4: Format and send

[1535] The server receives the generated response text and formats it into a user-friendly format (e.g., HTML or plain text).

[1536] The server then sends the formatted response back to the user's device via the API.

[1537] The user checks the answer on the terminal.

[1538] Input: The generated answer text.

[1539] Output: The formatted answer text and the answer sent to the user's device.

[1540] Step 5: Personalized learning support

[1541] If a user requests, "I want to learn more about linear algebra,"

[1542] The server retrieves the user's learning history and progress data from the database.

[1543] The server requests the generative AI model to generate personalized learning resources based on the referenced data and the user's emotional state as determined by the emotion engine.

[1544] For example, if a user is interested, include challenging content, but if they are stressed, provide basic, easy-to-understand content.

[1545] The generative AI model generates learning resources (e.g., a detailed explanation of vector spaces in linear algebra or a set of applied problems) based on instructions.

[1546] The server formats the generated learning resources and sends them to the user's terminal.

[1547] The user checks the learning resources on the device.

[1548] Input: User learning history, progress data, emotional state, and instructions to the generative AI model.

[1549] Output: The formatted learning resource and the learning resource sent to the user's device.

[1550] (Application example 2)

[1551] 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."

[1552] In modern manufacturing, operators and engineers working on factory floors need to receive technical information and training quickly and effectively. However, existing systems generally provide general learning content, making it difficult to provide personalized assistance based on individual users' emotional state and learning progress. Furthermore, there is a lack of means to provide appropriate support that takes emotions into account when users ask questions. This can reduce the effectiveness of operators and engineers' learning, negatively impacting on-site efficiency and quality.

[1553] The identification process by the identification 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 receiving a question from a user, means for analyzing the received question, means for generating an answer using a generative AI model based on the analysis result, means for sending the generated answer to the user, means for recognizing the user's emotional state, means for adjusting the tone and content of the answer based on the recognized emotional state, means for referencing the user's learning progress data, and means for providing personalized learning resources using a generative AI model based on the referenced data. This enables personalized support according to the user's emotional state and learning progress, thereby improving the effectiveness of technical information and training at the factory floor.

[1554] The "means for receiving a question from a user" is a function for transmitting a question entered by a user using a terminal to a server or related systems.

[1555] "Means for analyzing received questions" refers to a function that includes natural language processing (NLP) technology used to analyze questions received by the server and understand their content and intent.

[1556] "Means for generating answers using a generative AI model" refers to a function that utilizes an AI model to automatically generate appropriate answers based on the analysis results.

[1557] The "means for transmitting the generated answer to the user" is a function that formats the generated answer and transmits it to the user's terminal for display.

[1558] The "means for recognizing the user's emotional state" is a technology for analyzing the question text and the user's voice data to detect the user's emotional state (for example, excitement, stress, dissatisfaction, etc.).

[1559] The "means for adjusting the tone and content of the response based on the recognized emotional state" is a function that appropriately adjusts the expression method and content of the response according to the user's emotional state.

[1560] The "means for referencing user's learning progress data" is a function for retrieving and referencing the user's past learning history and progress status from a database.

[1561] "Means for providing personalized learning resources using a generative AI model based on referenced data" refers to a function that utilizes an AI model to generate individually optimized learning resources based on referenced learning progress data.

[1562] The "means for formatting and sending to the user's terminal" is a function for formatting the generated answers and learning resources into an appropriate format and sending them to the user's terminal.

[1563] The "means for displaying formatted answers to the user" is a function for displaying formatted answers and learning resources on the user's terminal.

[1564] "Means for viewing answers and learning resources using a head-mounted display" is a function for viewing answers and learning resources through the screen of a head-mounted display worn by the user.

[1565]

[1566] The system for realizing this invention provides a learning support application "SmartFactoryTutor" that is installed on a factory robot. A detailed embodiment of this system will be described below.

[1567] The server receives and analyzes input from the device used by the user (e.g., a tablet or head-mounted display). Specifically, the user enters a question in voice or text format. For example, the user might enter, "Please tell me the maintenance procedure for the machine."

[1568] The received question is sent to the server via an API, which receives metadata such as the question text, user ID, and timestamp. The server then analyzes the received question using a natural language processing (NLP) module (e.g., SpaCy or NLTK). This identifies the intent of the question and recognizes that it is a "question about maintenance procedures." An emotion engine (e.g., IBM Watson) is then used to analyze the question text and recognize the user's emotional state (e.g., impatience, anxiety, excitement, etc.).

[1569] Based on the analysis results, the server sends instructions to a generative AI model (such as OpenAI GPT-3) to generate a response. The tone and content of the response are adjusted based on the user's emotional state as recognized by the emotion engine. For example, if the user is feeling impatient, the generative AI model will generate a polite and supportive response such as, "Machine maintenance is a very important process. Let's take it easy and check each step one by one."

[1570] The generated answers are formatted in HTML or plain text and sent from the server to the user's device, where they can view the answers via a tablet or head-mounted display.

[1571] Furthermore, when a user requests more detailed training materials or videos, the server retrieves the user's learning history and progress data from a database (e.g., PostgreSQL). If the emotion engine recognizes the user's interest, the generative AI model generates personalized training materials, such as "We've prepared new training videos based on what we learned during past maintenance work."

[1572] Specific examples

[1573] For example, if the user speaks, "Please tell me today's maintenance procedure," the server processes as follows:

[1574] 1. The tablet or HMD receives the user's question and sends it to the server via API.

[1575] 2. The server analyzes the question and uses its emotion engine to recognize that the user is anxious.

[1576] 3. Based on the analysis results, a prompt statement is sent to the generative AI model: "The user has asked about machine maintenance procedures. The user seems a little anxious. Please generate a polite and supportive answer.", and an answer is generated.

[1577] 4. Format the generated answers into HTML and send them to the tablet or HMD.

[1578] In this way, "SmartFactoryTutor" can efficiently support technical information and training on the factory floor.

[1579] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1580] Step 1: Accepting user questions

[1581] Users input questions in voice or text format using a tablet or head-mounted display. The input questions are sent to the server via an API. Inputs include specific technical questions such as "Please tell me the maintenance procedure for the machine." The output is metadata such as the question text, user ID, and timestamp.

[1582] Step 2: Parsing the Question

[1583] The server parses the received question using a natural language processing (NLP) module (e.g., SpaCy or NLTK). The input is the question text, which the NLP module parses to identify the intent of the question, recognizing it as a "question about maintenance procedures." The output is metadata about the question's category and intent.

[1584] Step 3: Recognizing your emotional state

[1585] The server uses an emotion engine (e.g., IBM Watson) to analyze the question text and recognize the user's emotional state (e.g., impatience, anxiety, excitement, etc.). The input is the question text, and the emotion engine analyzes the user's emotion based on this. The output is metadata that indicates the user's emotional state.

[1586] Step 4: Generate an answer

[1587] Based on the analysis results, the server sends instructions to a generative AI model (e.g., OpenAI GPT-3) to generate an answer. The tone and content of the answer are adjusted based on the user's emotional state as recognized by the emotion engine. The input is the question category, intent, and emotional state metadata, and the generative AI model generates an appropriate answer based on this. The output is the generated answer text.

[1588] Step 5: Format your response

[1589] The server formats the generated answer text into HTML or plain text. The input is the generated answer text, and the formatting engine formats it into the appropriate format. The output is the formatted answer text.

[1590] Step 6: Submit your response

[1591] The server sends the formatted answer to the user's device. The input is the formatted answer text, which the server sends via an API to the user's tablet or head-mounted display. The output is the answer text that is displayed to the user.

[1592] Step 7: Provide learning resources

[1593] When a user requests additional learning resources, the server retrieves the user's learning history and progress data from a database (e.g., PostgreSQL). The input is the user's request data, and the output is the user's learning history and progress data. The server then sends instructions to the generative AI model to generate personalized learning resources. The output is personalized learning resources (e.g., training videos and materials).

[1594] Step 8: Format and submit your learning resources

[1595] The server formats the generated learning resources into HTML or plain text format and sends them to the user's device. The input is the generated learning resources, which the formatting engine formats into an appropriate format. The output is the formatted learning resources displayed on the user's tablet or head-mounted display.

[1596] 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.

[1597] 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.

[1598] 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 robot 414.

[1599] 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.

[1600] 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.

[1601] 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.

[1602] 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).

[1603] 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.

[1604] 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."

[1605] 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.

[1606] 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).

[1607] 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.

[1608] 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.

[1609] 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.

[1610] 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.

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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.

[1615] 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.

[1616] 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.

[1617] The following is further disclosed regarding the above embodiment.

[1618] (Claim 1)

[1619] means for receiving a query from a user;

[1620] means for analyzing the received query;

[1621] A means for generating an answer using a generative AI model based on the analysis results;

[1622] A means to send the generated answers to the user

[1623] Including system.

[1624] (Claim 2)

[1625] a means for accessing the user's learning progress data;

[1626] A means to provide personalized learning resources using generative AI models based on reference data

[1627] 10. The system of claim 1, comprising:

[1628] (Claim 3)

[1629] A means for sending questions sent from a user's device to a server via an API;

[1630] a means for performing natural language processing based on the received question;

[1631] A means for invoking a generative AI model that generates optimal answers according to the question content identified by natural language processing;

[1632] A means to format the generated answer and send it to the user's device.

[1633] 10. The system of claim 1, comprising:

[1634] "Example 1"

[1635] (Claim 1)

[1636] means for receiving input from a user;

[1637] means for parsing received input;

[1638] A means for invoking a generative AI model based on the analysis results and generating an answer;

[1639] means for formatting and transmitting the generated answers to the user;

[1640] A system including:

[1641] (Claim 2)

[1642] a means for viewing user progress data;

[1643] A means to provide personalized learning resources using generative AI models based on reference data

[1644] 10. The system of claim 1, comprising:

[1645] (Claim 3)

[1646] means for transmitting input sent from a user's terminal to a server via a communication means;

[1647] means for performing analysis based on the received input;

[1648] A means for invoking a generative AI model that generates appropriate answers according to the content identified by the analysis results;

[1649] A means to format the generated answer and send it to the user's device.

[1650] 10. The system of claim 1, comprising:

[1651] "Application Example 1"

[1652] (Claim 1)

[1653] means for receiving a query from a user;

[1654] means for analyzing the received query;

[1655] A means for generating an answer using a generative AI model based on the analysis results;

[1656] means for transmitting the generated answer to the user;

[1657] A means for sending questions sent from a user's device to a server via an API;

[1658] means for formatting and transmitting the generated answer to the user's terminal;

[1659] A means for acquiring user learning history and progress information and providing personalized learning resources;

[1660] A means to generate personalized learning content using generative AI models

[1661] Including system.

[1662] (Claim 2)

[1663] a means for accessing the user's learning progress data;

[1664] A means to provide personalized learning resources using generative AI models based on reference data

[1665] 10. The system of claim 1, comprising:

[1666] (Claim 3)

[1667] A means for sending questions sent from a user's device to a server via an API;

[1668] a means for performing natural language processing based on the received question;

[1669] A means for invoking a generative AI model that generates optimal answers according to the question content identified by natural language processing;

[1670] A means to format the generated answer and send it to the user's device.

[1671] 10. The system of claim 1, comprising:

[1672] "Example 2: Combining Emotion Engines"

[1673] (Claim 1)

[1674] means for receiving a query from a user;

[1675] a means for performing natural language processing based on the received question;

[1676] means for parsing questions and recognizing emotional states;

[1677] A means for generating an answer using a generative AI model based on the analysis and recognition results;

[1678] A means to send the generated answers to the user

[1679] Including system.

[1680] (Claim 2)

[1681] a means for accessing the user's learning progress data;

[1682] A means to provide personalized learning resources using generative AI models based on reference data and the user's emotional state data.

[1683] 10. The system of claim 1, comprising:

[1684] (Claim 3)

[1685] a means for transmitting the question text along with metadata including a user ID and a timestamp to a server via an API;

[1686] A means for calling a generative AI model that generates an appropriate answer according to the analyzed question content; and

[1687] The generated answers can be formatted as HTML or plain text and sent to the user's device.

[1688] 10. The system of claim 1, comprising:

[1689] "Application example 2 when combining emotion engines"

[1690] (Claim 1)

[1691] means for receiving a query from a user;

[1692] means for analyzing the received query;

[1693] A means for generating an answer using a generative AI model based on the analysis results;

[1694] means for transmitting the generated answer to the user;

[1695] means for recognizing the emotional state of a user;

[1696] A means to adjust the tone and content of responses based on perceived emotional states.

[1697] Including system.

[1698] (Claim 2)

[1699] a means for accessing the user's learning progress data;

[1700] A means for providing personalized learning resources using a generative AI model based on the referenced data; and

[1701] A means to tailor the content of learning resources based on perceived emotional states.

[1702] 10. The system of claim 1, comprising:

[1703] (Claim 3)

[1704] A means for sending questions sent from a user's device to a server via an API;

[1705] a means for performing natural language processing based on the received question;

[1706] A means for invoking a generative AI model that generates optimal answers according to the question content identified by natural language processing;

[1707] means for formatting and transmitting the generated answer to the user's terminal;

[1708] means for displaying the formatted response to the user;

[1709] A means for users to view answers and learning resources using a head-mounted display

[1710] 10. The system of claim 1, comprising: [Explanation of symbols]

[1711] 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. means for receiving a query from a user; means for analyzing the received query; A means for generating an answer using a generative AI model based on the analysis results; A means to send the generated answers to the user Including system.

2. a means for accessing the user's learning progress data; A means to provide personalized learning resources using generative AI models based on reference data The system of claim 1 .

3. A means for sending questions sent from a user's device to a server via an API; a means for performing natural language processing based on the received question; A means for invoking a generative AI model that generates optimal answers according to the question content identified by natural language processing; A means to format the generated answer and send it to the user's device. The system of claim 1 .

Images