System

Abstract

A system is provided.SOLUTION: A system, comprising: means for receiving a question input by a user; means for sending the received question to a server; means for parsing the question and passing the parsed question to a AI model to generate a response by the server; means for returning the response generated by the AI model to the server; and means for sending the response to the user by the server for display 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] Conventional educational support systems are based on the premise of group lessons, making it difficult to provide detailed support to individual learners. Other issues include a heavy burden on teachers and variations in the quality of individual instruction. Furthermore, it is difficult to provide personalized learning tailored to learners' knowledge levels and interests. This makes it difficult to provide effective learning support that meets the needs of diverse learners. [Means for solving the problem]

[0005] This invention provides an AI-based learning support system that passes questions entered by a user into a terminal to an AI model via a server, generates responses in real time, and displays them on the terminal. It also includes a means for a user to request question generation by entering specific conditions, and for the AI ​​model to generate questions based on those conditions and display them on the terminal via the server. This system also includes a means for the server to cause the AI ​​model to generate responses and explanations taking into account the user's knowledge level, and a means for the AI ​​model to provide personalized explanations taking into account the user's past answer history and interests. This improves the quality of individualized instruction and makes it possible to meet the needs of diverse learners.

[0006] "User" refers to an individual learner who uses the educational support system to advance their studies.

[0007] "Terminal" refers to a device used by a user, an electronic device that provides an interface for entering questions and displaying responses from AI.

[0008] "Server" refers to the central system that receives questions and conditions, issues instructions to the AI ​​model, and sends responses and generated problems to the device.

[0009] A "question" refers to a question or question that a user has while studying, entered in text format.

[0010] "Analysis" refers to the interpretation and decomposition of data that the server processes the questions and conditions it receives and passes them appropriately to the AI ​​model.

[0011] An "AI model" refers to a collection of algorithms and programs that use AI (artificial intelligence) technology to generate answers and questions to users' questions and provide learning support.

[0012] A "response" refers to the text answer or explanation that an AI model generates in response to a user's question.

[0013] "Conditions" refer to requirements such as learning level and subject that a user specifies when requesting question generation.

[0014] "Problems" refer to learning tasks or practice problems generated by an AI model based on conditions specified by the user.

[0015] "Answer history" refers to data on questions that a user has answered in the past and the results of those answers.

[0016] "Personalized explanations" refer to individualized explanations and supplemental information generated by an AI model that takes into account the user's knowledge level, interests, and past answer history. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] System Overview

[0039] This invention is a learning support system using AI that analyzes questions entered by users into a terminal in real time, generates responses using an AI model, and displays them on the terminal. It also includes a function that allows users to input specific conditions to request the generation of questions, and the AI ​​model generates and displays questions based on those conditions. Furthermore, the server also provides personalized explanations taking into account the user's knowledge level and past answer history.

[0040] Program processing

[0041] User questions submitted

[0042] If a user has a question while studying, they can open the chat screen on their device, enter their question, and press the "Send" button.

[0043] The device receives the entered question, formats it, and sends an API request to the server.

[0044] The server analyzes the received question and passes it to the AI ​​model.

[0045] AI model response generation

[0046] The AI ​​model analyzes the incoming question, extracts appropriate information from the relevant knowledge base, and generates a response that matches the user's level of knowledge.

[0047] The server receives the response from the AI ​​model, reformats it, and sends it to the device.

[0048] The terminal displays the received response on the chat screen and notifies the user.

[0049] Specific examples

[0050] User: "What is Newton's second law of motion?"

[0051] Terminal: Sends a question to the server.

[0052] Server: Passes the question to the AI ​​model.

[0053] AI model: Generates responses that explain the second law of motion and provide concrete examples.

[0054] Server: Sends the response to the device.

[0055] Terminal: Responses are displayed on the chat screen.

[0056] User: Review responses and gain insight.

[0057] Automatic question creation

[0058] If a user wants to create a question by specifying specific conditions, they enter the conditions such as grade, subject, and difficulty level into a dedicated form on the terminal and press the "Create Question" button.

[0059] The device formats the entered conditions and sends an API request to the server.

[0060] The server passes the conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[0061] Example of problem generation

[0062] User: "Please create a high school physics problem in the mechanics section."

[0063] Terminal: Sends conditions to the server.

[0064] Server: Passes the conditions to the AI ​​model.

[0065] AI model: Generates problems based on specified conditions.

[0066] Server: Sends the generated questions to the device.

[0067] Terminal: displays the questions and allows the user to answer them.

[0068] User: Answer the question.

[0069] Personalized commentary

[0070] The server takes into account the user's knowledge level and answer history and has the AI ​​model generate personalized explanations.

[0071] The AI ​​model uses past data to create the most appropriate explanation for the user.

[0072] The server receives this and sends it to the terminal.

[0073] The terminal displays explanations to help the user understand.

[0074] Examples of personalized commentary

[0075] If a user has previously solved a problem related to the law of conservation of energy, the next time they solve a mechanics problem, the AI ​​model will provide an explanation related to the law of conservation of energy.

[0076] Server: Passes conditions to the AI ​​model based on past answer history.

[0077] AI model: Generate personalized commentary.

[0078] Server: Sends the commentary to the device.

[0079] Terminal: Display explanation and notify user.

[0080] Users: Check out personalized commentary to deepen their understanding.

[0081] In this way, the system provides optimal learning support for individual learners and improves the quality of education.

[0082] The processing flow will be explained below.

[0083] Processing Question Submissions

[0084] Step 1:

[0085] If a user has a question while studying, they can open the chat screen on their device.

[0086] Step 2:

[0087] The user enters a question into the text input field and presses the "Submit" button.

[0088] Step 3:

[0089] The device takes the entered question and prepares an API request formatted in the appropriate format.

[0090] Step 4:

[0091] The device sends an HTTP request to the API endpoint to send question data to the server.

[0092] Step 5:

[0093] The server analyzes the received HTTP request and obtains the question.

[0094] Step 6:

[0095] The server passes the question to a natural language processing model and asks it to generate an appropriate response.

[0096] AI model response generation process

[0097] Step 7:

[0098] The AI ​​model analyzes the questions it receives using natural language processing technology and extracts appropriate information from the relevant knowledge base.

[0099] Step 8:

[0100] An appropriate response text is generated taking into account the user's knowledge level.

[0101] Step 9:

[0102] The AI ​​model sends the generated response text back to the server.

[0103] Response sending process

[0104] Step 10:

[0105] The server receives the response from the AI ​​model and checks the format.

[0106] Step 11:

[0107] The server prepares an API response to send the response text to the device.

[0108] Step 12:

[0109] The server sends the response data to the terminal as an HTTP response.

[0110] Step 13:

[0111] The terminal analyzes the HTTP response received from the server and obtains the response text.

[0112] Step 14:

[0113] The response text acquired by the terminal is displayed on the chat screen.

[0114] Step 15:

[0115] Users can check the AI's responses displayed on the chat screen and resolve any questions they may have.

[0116] Automatic question creation process

[0117] Step 16:

[0118] When a user wants to solve a problem that corresponds to their learning objectives, they enter the necessary conditions (e.g., grade, subject, level, etc.) into a dedicated form on the device.

[0119] Step 17:

[0120] After the user enters the conditions, he or she presses the "Create Question" button.

[0121] Step 18:

[0122] The device formats the input conditions into the appropriate format and prepares the API request.

[0123] Step 19:

[0124] The device sends an HTTP request to the API endpoint to send condition data to the server.

[0125] Server processing of question generation

[0126] Step 20:

[0127] The server analyzes the request received from the terminal and obtains the conditions for creating questions.

[0128] Step 21:

[0129] The server passes the acquired conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[0130] AI model problem generation process

[0131] Step 22:

[0132] The AI ​​model analyzes the received conditions and selects an algorithm to generate an appropriate problem.

[0133] Step 23:

[0134] A question that meets the conditions is generated, and data containing the question and answer is created.

[0135] Step 24:

[0136] The AI ​​model sends the generated problem data back to the server.

[0137] Processing problem data submissions

[0138] Step 25:

[0139] The server receives the problem data from the AI ​​model and checks the format.

[0140] Step 26:

[0141] The server prepares an API response to send the problem data to the device.

[0142] Step 27:

[0143] The server sends the problem data to the terminal as an HTTP response.

[0144] Step 28:

[0145] The terminal analyzes the HTTP response received from the server and obtains the problem data.

[0146] Step 29:

[0147] The problem data acquired by the terminal is displayed on the user interface.

[0148] Step 30:

[0149] The user checks the displayed question and begins answering it.

[0150] Personalized commentary delivery

[0151] Step 31:

[0152] The server takes into account the user's knowledge level and answer history and has the AI ​​model generate personalized explanations.

[0153] Step 32:

[0154] The AI ​​model uses past data to create the most appropriate explanation for the user.

[0155] Step 33:

[0156] The server prepares an API response to send the explanation received from the AI ​​model to the device.

[0157] Step 34:

[0158] The server sends the explanatory data to the terminal as an HTTP response.

[0159] Step 35:

[0160] The terminal analyzes the HTTP response received from the server and obtains the explanatory data.

[0161] Step 36:

[0162] The terminal displays the explanation and notifies the user.

[0163] Step 37:

[0164] Users can check the explanations and deepen their understanding of the material.

[0165] Through these steps, the system allows users to interact with AI in real time as they learn, providing an individually customized learning experience.

[0166] Example 1

[0167] 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."

[0168] Conventional learning support systems have struggled to provide users with prompt and appropriate responses to resolve their questions, and have struggled to provide personalized learning support. This has limited the ability to improve learning efficiency and deepen users' understanding. Furthermore, they lack the ability to automatically generate questions based on specific conditions, or to provide sufficient explanations tailored to the user's knowledge level and answer history.

[0169] 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.

[0170] In this invention, the server includes means for receiving text entered by a user into an information terminal, means for transmitting the received text to a central processing unit, means for the central processing unit to analyze the text and pass it to an artificial intelligence model to generate a response, means for the central processing unit to return the response generated by the artificial intelligence model to the central processing unit, and means for the central processing unit to transmit the response to the information terminal and display it to the user, thereby enabling a quick and appropriate response to a user's question.

[0171] The present invention also includes means for a user to input specific conditions to request the generation of a dataset, means for transmitting the input conditions to a central processing unit, means for the central processing unit to request the generation of a dataset from an artificial intelligence model based on the conditions, means for returning the dataset generated by the artificial intelligence model to the central processing unit, and means for the central processing unit to transmit the generated dataset to an information terminal and display it to the user, thereby enabling the automatic generation of problems according to specific conditions.

[0172] The system further includes a means for the central processing unit to cause the artificial intelligence model to generate responses and explanations taking into account the user's knowledge level, a means for the artificial intelligence model to generate personalized explanations taking into account the user's past answer history and interests, and a means for the central processing unit to send the personalized explanations to the information terminal and display them to the user, thereby enabling optimal learning support according to the individual learning needs of the user.

[0173] A "user" is an entity that uses the learning support system to input information and receive responses.

[0174] "Information terminal" means a device that receives text entered by a user and communicates with a central processing unit. Examples include personal computers, smartphones, and tablets.

[0175] A "central processing unit" is a device that analyzes data received from an information terminal, passes the data to an AI model, and sends responses from the AI ​​model to the information terminal. This mainly applies to servers.

[0176] The "artificial intelligence model" is a system that analyzes the received prompt sentence, extracts appropriate information from a related knowledge base, and generates a response or explanation. This model combines machine learning algorithms and natural language processing technology.

[0177] "Text" refers to questions or requests that users enter into an information terminal, in the form of sentences or words.

[0178] "Response" refers to a reply message generated by an AI model and sent to an information terminal via a central processing unit, which may include an answer or explanation to a question.

[0179] A "dataset" refers to a collection of questions or information that an artificial intelligence model generates based on certain conditions when a user inputs a request.

[0180] "Prompt sentence" refers to text that has been converted into a specific format by the central processing unit to input data into an AI model, such as a question or condition.

[0181] "Personalized explanations" refer to individual explanations and descriptions generated by an artificial intelligence model that take into account a user's knowledge level, past answer history, and interests.

[0182] This invention is a learning support system using AI that analyzes text entered by a user into an information terminal in real time, generates responses using an artificial intelligence model, and displays them on the information terminal. It also includes the function of automatically generating questions based on specific conditions and providing personalized explanations based on the user's knowledge level and answer history.

[0183] Hardware and software used

[0184] Information terminal: A device such as a PC, smartphone, or tablet through which a user inputs text and receives results.

[0185] Central Processing Unit: A high-performance computer such as a server that passes received text to an artificial intelligence model and returns the generated response or commentary to the information terminal.

[0186] Artificial intelligence model: A system that combines machine learning algorithms and natural language processing techniques to extract information from a knowledge base and generate appropriate responses and explanations for users.

[0187] Program processing overview

[0188] User questions submitted

[0189] If a user has a question while studying, they open the chat screen on their information terminal, enter a text question, and press the "Send" button.

[0190] Question analysis and response generation

[0191] The information terminal receives the input text, formats it, and then sends an API request to the central processing unit, which analyzes the received text and passes it to the AI ​​model, which uses the analysis results to extract appropriate information from the relevant knowledge base and generate a response.

[0192] Viewing the response

[0193] The central processing unit reformats the response from the artificial intelligence model and sends it to the information terminal, which displays the response on a chat screen and notifies the user.

[0194] example

[0195] User: "What is Newton's second law of motion?"

[0196] Information terminal: Sends text to a central processing unit.

[0197] Central Processing Unit: Passes the text to the artificial intelligence model.

[0198] Artificial intelligence model: Generates responses that explain the second law of motion and provide concrete examples.

[0199] Central processing unit: Sends the response to the information terminal.

[0200] Information terminal: Responses are displayed on the chat screen.

[0201] User: Review the response and gain insight.

[0202] Automatic question creation

[0203] When a user wants to generate a question based on specific conditions, they enter the conditions, such as grade, subject, and difficulty level, into a dedicated form on the information terminal and press the "Create Question" button. The information terminal formats the entered conditions and sends an API request to the central processing unit. The central processing unit passes the conditions to an artificial intelligence model and asks it to generate a question based on the specified conditions.

[0204] example

[0205] User: "Please create a high school physics problem in the mechanics section."

[0206] Information terminal: Sends conditions to the central processing unit.

[0207] Central Processing Unit: Passes the conditions to the artificial intelligence model.

[0208] Artificial intelligence model: Generates problems based on conditions.

[0209] Central processing unit: Sends the generated questions to the information terminal.

[0210] Information terminal: displays the questions and allows the user to answer them.

[0211] User: Answer the question.

[0212] Personalized commentary

[0213] The central processing unit takes into account the user's knowledge level and answer history and has the AI ​​model generate personalized explanations. The AI ​​model creates the most appropriate explanation for the user based on past data. The central processing unit receives this and sends it to the information terminal. The information terminal displays the explanation, helping the user to understand.

[0214] example

[0215] If a user has previously solved a problem related to the law of conservation of energy, the next time they solve a problem in the field of mechanics, the artificial intelligence model will provide an explanation related to the law of conservation of energy.

[0216] Central processing unit: Passes conditions to the artificial intelligence model based on past answer history.

[0217] Artificial intelligence model: Generate personalized commentary.

[0218] Central processing unit: Sends commentary to information terminal.

[0219] Information terminal: displays explanations and notifies the user.

[0220] Users: Check out personalized commentary to deepen their understanding.

[0221] This allows the system to provide users with prompt and appropriate learning support, improving learning efficiency.

[0222] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0223] Step 1:

[0224] The user opens the chat screen on the information terminal, enters a question, and presses the "send" button.

[0225] Input: The question text that the user types into the terminal (e.g., "What is Newton's second law of motion?")

[0226] Output: Formatted question data (including user ID, question content, and submission time)

[0227] Step 2:

[0228] The device receives input from the user, formats the question text, and then sends the formatted data to the server as an API request.

[0229] Input: User question text

[0230] Data processing: Format the input data to include the user ID, question, and submission time.

[0231] Output: API request (including question)

[0232] Step 3:

[0233] The server analyzes the API request received from the device, extracts the question data, converts it into a prompt, and then passes the prompt to the AI ​​model.

[0234] Input: Formatted question data

[0235] Data processing: Analyze question data and create prompts

[0236] Output: Prompt text (e.g., "Question: What is Newton's second law of motion? User ID: 12345")

[0237] Step 4:

[0238] Based on the prompt received from the server, the artificial intelligence model extracts appropriate information from the relevant knowledge base and generates a response to the question.

[0239] Input: prompt statement

[0240] Data processing: Extracting information from the knowledge base and generating responses

[0241] Output: Response (e.g., "Newton's second law of motion states that the motion of an object is proportional to its mass and acceleration when a force is applied to it.")

[0242] Step 5:

[0243] The server reformats the response received from the AI ​​model and sends it to the device as an API response.

[0244] Input: The response generated by the AI ​​model

[0245] Data manipulation: Reformatting the response to include the user ID and timestamp

[0246] Output: API response (formatted response data)

[0247] Step 6:

[0248] The device analyzes the API response received from the server and displays it on the chat screen so that the user can check the content.

[0249] Input: API response from the server

[0250] Data processing: Analyzes response data and converts it into a format to display on the chat screen

[0251] Output: The answer that is displayed to the user (e.g., "Newton's second law of motion states that the motion of an object is proportional to its mass and acceleration when a force is applied to it.")

[0252] Through these processing steps, the system is able to provide quick and accurate answers to users' questions.

[0253] (Application example 1)

[0254] 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."

[0255] Acquiring and analyzing real-time traffic information for autonomous vehicles is important for users, but current systems lack the ability to provide personalized support for real-time question resolution and learning. In particular, there is a demand for systems that can provide detailed explanations of traffic information and generate questions tailored to the user's knowledge level.

[0256] 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.

[0257] In this invention, the server includes means for receiving a question input by a user to a terminal, means for transmitting the received question to the server, means for the server to analyze the question and pass it to an artificial intelligence model to generate a response, means for the server to return the response generated by the artificial intelligence model to the server, means for the server to transmit the response to the terminal and display it to the user, and means for acquiring and analyzing traffic information in real time and visualizing it for the user, thereby enabling real-time resolution of user questions and personalized learning support in an autonomous vehicle.

[0258] "User" refers to a person who uses the system.

[0259] "Terminal" refers to a device through which a user accesses and operates the system.

[0260] "Server" refers to the central computer that analyzes queries and traffic information and generates responses.

[0261] "Artificial intelligence model" refers to an artificial intelligence algorithm that responds to user questions, generates questions, and provides personalized explanations.

[0262] "Means for receiving" refers to the function of the terminal to obtain information input by the user.

[0263] "Means for transmitting" refers to the function of transferring received information to a server as data.

[0264] "Means for analyzing" refers to the functionality that allows the server to understand and process the information it receives.

[0265] "Means for generating" refers to the ability of the artificial intelligence model to create a response based on the analysis results.

[0266] "Means for sending back" refers to the functionality for returning the generated response to the server.

[0267] "Means of acquiring and analyzing in real time" refers to the function of collecting, analyzing, and visualizing current traffic information.

[0268] "Visualization means" refers to the function of displaying analyzed information in a format that is easy for users to understand.

[0269] "Means for requesting the creation of a question" refers to a function that allows a user to input specific conditions and request the creation of a question.

[0270] "Means for generating personalized explanations" refers to a function that creates explanations according to the user's knowledge level and answer history.

[0271] "Means for transmitting a personalized commentary to a terminal and displaying it to a user" refers to a function for transferring the generated commentary to a user's terminal and displaying it.

[0272] This invention is a system for providing learning support and traffic information to users in autonomous vehicles. Specifically, a server uses an artificial intelligence model to generate and provide real-time responses to questions and requests entered by the user into a terminal. The system also has the function of acquiring and analyzing traffic information in real time and visualizing it for the user.

[0273] System Program Overview

[0274] This system performs the following main processes between the server and the terminal.

[0275] 1. Receiving and sending user questions.

[0276] 2. Parsing the question and generating the response.

[0277] 3. Sending and displaying the generated response.

[0278] 4. Real-time acquisition and analysis of traffic information.

[0279] 5. Visualization and provision of traffic information.

[0280] 6. Generating and delivering personalized commentary.

[0281] Hardware and software used

[0282] Hardware:

[0283] Device: A mobile information device such as a smartphone or tablet held by a user.

[0284] Server: A central computer that processes query analysis and artificial intelligence models.

[0285] software:

[0286] Artificial intelligence model: Used to generate answers to user questions and create problems. This can be done using APIs such as OpenAI.

[0287] Requests library: Used to perform HTTP requests for real-time traffic information.

[0288] Explanation of program processing

[0289] When a user inputs a question into the device, the device receives the question and sends it to the server. The server analyzes the received question and passes it to the AI ​​model to generate a response. The response generated by the AI ​​model is sent back to the server, which then sends it to the device and displays it to the user.

[0290] The server then collects and analyzes traffic information in real time. The analyzed traffic information is then sent to the user's device and visualized. In this process, the Requests library is used to collect and analyze traffic information.

[0291] The server then uses the AI ​​model to generate personalized explanations based on the user's knowledge level and past answer history. The generated explanations are then sent back to the server and displayed on the user's device. This allows users to obtain information tailored to their level of understanding in real time.

[0292] Specific examples

[0293] Specific examples of question-answering:

[0294] When a user types, "What's the current traffic situation at this intersection?", the device sends the question to the server, which passes the question to an artificial intelligence model that generates an appropriate response. The response is then sent back to the device via the server and displayed to the user.

[0295] Examples of obtaining and displaying traffic information:

[0296] The server acquires and analyzes real-time traffic information at a particular intersection. The results are sent to the device and visualized. When the user asks, "How congested is the traffic?", detailed traffic information is displayed.

[0297] Examples of personalized commentary:

[0298] If the user had previously asked the question "Please tell me how traffic lights work," then the user's next question would be "What is the current traffic situation at the intersection?", which would also provide additional commentary related to how traffic lights work.

[0299] This enables the system to provide users with real-time, high-quality information and learning assistance in an autonomous vehicle environment.

[0300] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0301] Step 1:

[0302] Receives a question entered by a user into the terminal. The user enters "What is the current traffic situation at the intersection?" into the terminal and presses the "Send" button. This inputs the question into the terminal.

[0303] Step 2:

[0304] The device formats the received question and sends it to the server as an API request. The question is formatted in the appropriate data format to be sent as an HTTP request.

[0305] Step 3:

[0306] The server analyzes the received question. The server passes the received data to a natural language processing engine to understand the intent of the question. During this process, keywords from the question are extracted and a prompt sentence is formed to be passed to the generative AI model.

[0307] Step 4:

[0308] The server passes the analysis results to the generative AI model and requests it to generate an appropriate response. The prompt sentence is "Question to the environment: What is the current traffic situation at the intersection?\nAnswer:" and is input to the generative AI model. The generative AI model extracts information from the relevant database and generates a response.

[0309] Step 5:

[0310] The generative AI model sends the generated response back to the server, which includes the specific traffic situation and related advice.

[0311] Step 6:

[0312] The server reformats the response received from the generative AI model and sends it to the device as an API response, arranging the received text data in a format that is easy for the user to understand.

[0313] Step 7:

[0314] The device displays the received response on the chat screen and notifies the user. The response "The current traffic situation at the intersection is as follows:" is displayed on the chat screen.

[0315] Step 8:

[0316] The server gets real-time traffic information from the Traffic Data API, sending a request to the appropriate API endpoint to get the current traffic situation data.

[0317] Step 9:

[0318] The server analyzes the acquired traffic data and formats it for visualization by the user, including traffic congestion status, average speed, traffic light timing, etc.

[0319] Step 10:

[0320] The device displays the analyzed traffic information sent from the server and notifies the user. It also displays traffic congestion on a map in different colors and displays the appropriate distance and time.

[0321] Step 11:

[0322] The server analyzes the user's knowledge level and past question history and requests the generative AI model to generate a personalized explanation. For example, if the user previously asked, "How does a traffic light work?", the server takes that historical data into account when generating a response.

[0323] Step 12:

[0324] The generative AI model generates a personalized explanation and sends it back to the server, including information about how the traffic light works and information relevant to the current question.

[0325] Step 13:

[0326] The server then reformats the generated commentary and sends it to the terminal, formatting the content of the commentary to make it easier for the user to understand.

[0327] Step 14:

[0328] The device displays the received personalized commentary to inform the user, including the following information: "Just to clarify how traffic lights work. The traffic lights at the current intersection are connected to a central control system and are adjusted in real time."

[0329] This series of processes allows users to receive real-time traffic information and related learning information in the environment of an autonomous vehicle.

[0330] 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.

[0331] System Overview

[0332] This invention combines an AI-based personalized learning support system with an emotion engine that recognizes the user's emotions. The system analyzes questions entered by the user into a device in real time, generates appropriate responses using an AI model, and displays them on the device. It also includes a function that generates questions based on specific conditions and provides questions and explanations based on those conditions. Furthermore, the system provides personalized explanations taking into account the user's knowledge level and past answer history, and uses the emotion engine to adjust the responses and explanations according to the user's emotions.

[0333] Program processing

[0334] User questions submitted

[0335] If a user has a question while studying, they can open the chat screen on their device, enter their question, and press the "Send" button.

[0336] The device receives the entered question, formats it, and sends an API request to the server.

[0337] The server analyzes the received question and first passes the question content to the emotion engine. The emotion engine analyzes the user's input and behavior to recognize emotions and returns the results to the server. The server then passes the question content and recognized emotion information to the AI ​​model.

[0338] AI model response generation

[0339] The AI ​​model analyzes the received question and emotional information, extracts appropriate information from the relevant knowledge base, and generates an appropriate response according to the user's knowledge level and emotions.

[0340] The server receives the response from the AI ​​model, reformats it, and sends it to the device.

[0341] The terminal displays the received response on the chat screen and notifies the user.

[0342] Specific examples

[0343] User: "What is Newton's second law of motion?"

[0344] Terminal: Sends a question to the server.

[0345] Server: Passes the question to the emotion engine and AI model.

[0346] Emotion engine: Recognizes the user's emotion as "confusion" based on the tone and wording of the question.

[0347] AI model: Considers emotions and knowledge level to provide appropriate responses ("Newton's second law of motion, simply stated...").

[0348] Server: Sends the response to the device.

[0349] Terminal: Responses are displayed on the chat screen.

[0350] User: Check the response and clarify any questions.

[0351] Automatic question creation

[0352] If a user wants to create a question by specifying specific conditions, they enter the conditions such as grade, subject, and difficulty level into a dedicated form on the terminal and press the "Create Question" button.

[0353] The device formats the entered conditions and sends an API request to the server.

[0354] The server passes the conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[0355] Example of problem generation

[0356] User: "Please create a high school physics problem in the mechanics section."

[0357] Terminal: Sends conditions to the server.

[0358] Server: Passes the conditions to the AI ​​model.

[0359] AI model: Generates problems based on specified conditions.

[0360] Server: Sends the generated questions to the device.

[0361] Terminal: displays the questions and allows the user to answer them.

[0362] User: Answer the question.

[0363] Personalized commentary

[0364] The server takes into account the user's knowledge level, answer history, and emotional data from an emotion engine, and has the AI ​​model generate personalized explanations.

[0365] The AI ​​model uses past data and emotional information to create the most appropriate explanation for the user.

[0366] The server receives this and sends it to the terminal.

[0367] The terminal displays an explanation and notifies the user.

[0368] Examples of personalized commentary

[0369] If a user has previously solved a problem related to the law of conservation of energy, the next time they solve a problem in the field of mechanics, the AI ​​model will provide an explanation related to the law of conservation of energy. If the emotion engine recognizes the user's "interest," the explanation will be more detailed and interesting.

[0370] Server: Passes conditions to the AI ​​model based on past answer history and emotional information.

[0371] AI model: Generate personalized commentary.

[0372] Server: Sends the commentary to the device.

[0373] Terminal: Display explanation and notify user.

[0374] Users: Check out personalized commentary to deepen their understanding.

[0375] In this way, by combining the emotional engine, the system provides an individually customized learning experience that takes into account the user's emotions, improving the quality of education.

[0376] The processing flow will be explained below.

[0377] User question submission process

[0378] Step 1:

[0379] If a user has a question while studying, they can open the chat screen on their device.

[0380] Step 2:

[0381] The user enters a question into the text input field and presses the "Submit" button.

[0382] Step 3:

[0383] The device takes the entered question and prepares an API request formatted in the appropriate format.

[0384] Step 4:

[0385] The device sends an HTTP request to the API endpoint to send question data to the server.

[0386] Step 5:

[0387] The server analyzes the received HTTP request and obtains the question.

[0388] Step 6:

[0389] Before the server passes the question to the natural language processing model, it first passes it to an emotion engine to identify the user's emotion.

[0390] Step 7:

[0391] The emotion engine identifies the user's emotion from the tone of the question, wording, typing speed, etc., and sends the results back to the server.

[0392] Step 8:

[0393] The server passes the question content along with the emotional information received from the emotion engine to the AI ​​model.

[0394] AI model response generation process

[0395] Step 9:

[0396] The AI ​​model analyzes the received questions and emotional information using natural language processing technology and extracts appropriate information from the relevant knowledge base.

[0397] Step 10:

[0398] It generates appropriate response text taking into account the user's knowledge level and perceived emotions.

[0399] Step 11:

[0400] The AI ​​model sends the generated response text back to the server.

[0401] Response sending process

[0402] Step 12:

[0403] The server receives the response from the AI ​​model and checks the format.

[0404] Step 13:

[0405] The server prepares an API response to send the response text to the device.

[0406] Step 14:

[0407] The server sends the response data to the terminal as an HTTP response.

[0408] Step 15:

[0409] The terminal analyzes the HTTP response received from the server and obtains the response text.

[0410] Step 16:

[0411] The response text acquired by the terminal is displayed on the chat screen.

[0412] Step 17:

[0413] Users can check the AI's responses displayed on the chat screen and resolve any questions they may have.

[0414] Automatic question creation process

[0415] Step 18:

[0416] When a user wants to solve a problem that corresponds to their learning objectives, they enter the necessary conditions (e.g., grade, subject, level, etc.) into a dedicated form on the device.

[0417] Step 19:

[0418] After the user enters the conditions, he or she presses the "Create Question" button.

[0419] Step 20:

[0420] The device formats the input conditions into the appropriate format and prepares the API request.

[0421] Step 21:

[0422] The device sends an HTTP request to the API endpoint to send condition data to the server.

[0423] Server processing of question generation

[0424] Step 22:

[0425] The server analyzes the request received from the terminal and obtains the conditions for creating questions.

[0426] Step 23:

[0427] The server passes the acquired conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[0428] AI model problem generation process

[0429] Step 24:

[0430] The AI ​​model analyzes the received conditions and selects an algorithm to generate an appropriate problem.

[0431] Step 25:

[0432] A question that meets the conditions is generated, and data containing the question and answer is created.

[0433] Step 26:

[0434] The AI ​​model sends the generated problem data back to the server.

[0435] Processing problem data submissions

[0436] Step 27:

[0437] The server receives the problem data from the AI ​​model and checks the format.

[0438] Step 28:

[0439] The server prepares an API response to send the problem data to the device.

[0440] Step 29:

[0441] The server sends the problem data to the terminal as an HTTP response.

[0442] Step 30:

[0443] The terminal analyzes the HTTP response received from the server and obtains the problem data.

[0444] Step 31:

[0445] The problem data acquired by the terminal is displayed on the user interface.

[0446] Step 32:

[0447] The user checks the displayed question and begins answering it.

[0448] Personalized commentary delivery

[0449] Step 33:

[0450] The server takes into account the user's knowledge level, answer history, and emotional data from an emotion engine, and has the AI ​​model generate personalized explanations.

[0451] Step 34:

[0452] The AI ​​model uses past data and emotional information to create the most appropriate explanation for the user.

[0453] Step 35:

[0454] The server prepares an API response to send the explanation received from the AI ​​model to the device.

[0455] Step 36:

[0456] The server sends the explanatory data to the terminal as an HTTP response.

[0457] Step 37:

[0458] The terminal analyzes the HTTP response received from the server and obtains the explanatory data.

[0459] Step 38:

[0460] The terminal displays the explanation and notifies the user.

[0461] Step 39:

[0462] Users can check the explanations and deepen their understanding of the material.

[0463] Through these steps, the system enables users to learn while interacting with AI in real time, and also provides a learning experience that takes users' emotions into consideration.

[0464] Example 2

[0465] 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."

[0466] Conventional personalized learning support systems lack consideration for users' emotions, which can negatively impact learning motivation and comprehension. Furthermore, they lack personalized explanations and questions, making it difficult to provide an optimal learning experience based on the user's knowledge level and answer history. Therefore, a system that recognizes the user's emotional state and generates appropriate responses and explanations is needed.

[0467] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a question input by a user to a terminal, means for transmitting the received question to the server, means for the server to analyze the question and pass it to an emotion engine to recognize the user's emotion and receive the result, means for the server to pass the question content and the recognized emotion information to an AI model to generate a response, means for returning the response generated by the AI ​​model to the server, and means for the server to send the response to the terminal and display it to the user. This makes it possible to provide an appropriate response or explanation according to the user's emotion.

[0468] A "user" is an individual who uses the system to advance their learning.

[0469] "Terminal" refers to the device used by the user to input learning content and receive responses from the system.

[0470] A "server" is a central computer system that receives requests from users, analyzes them, and performs the necessary processing.

[0471] An "emotion engine" is software that analyzes a user's input and behavior to identify emotions.

[0472] An "AI model" is an algorithm that uses machine learning or deep learning to analyze data and generate responses or questions.

[0473] A "question" is text data that a user inputs into the system via a terminal to express a question that the user has while studying.

[0474] A "response" is an answer to a user's question that the server generates using an AI model.

[0475] A "problem" is a learning task generated by an AI model based on conditions specified by the user.

[0476] "Explanation" is a detailed explanation or additional information provided in response to a user's question or problem.

[0477] "Personalization" is a concept that refers to optimizing the content provided based on the characteristics and history of each individual user.

[0478] MODE FOR CARRYING OUT THE INVENTION

[0479] System Overview

[0480] This invention combines an AI-based personalized learning support system with an emotion engine that recognizes the user's emotions. The system analyzes questions entered by the user into the device in real time, generates appropriate responses, and displays them on the device. It also includes a function that generates questions by entering specific conditions and provides questions and explanations based on those conditions. Furthermore, the system provides personalized explanations taking into account the user's knowledge level and past answer history, and uses the emotion engine to adjust the responses and explanations according to the user's emotions.

[0481] System configuration

[0482] The system consists of the following main components:

[0483] 1. Terminal: A device where the user inputs learning content and receives responses from the system.

[0484] 2. Server: A central computer system that receives and analyzes user requests.

[0485] 3. Emotion engine: Software that analyzes user input and behavior to identify emotions.

[0486] 4. AI Model: An algorithm that uses machine learning or deep learning to analyze data and generate responses or questions.

[0487] User questions submitted

[0488] If a user has a question during learning, they open the chat screen on their device, enter their question, and press the "Send" button. The device receives the entered question, formats it appropriately, and sends it to the server as an API request. The server analyzes the received question and passes the question content to the emotion engine. The emotion engine analyzes the user's input and behavior to recognize emotions and return the results to the server. The server then passes the question content and recognized emotion information to the AI ​​model.

[0489] AI model response generation

[0490] The AI ​​model analyzes the received question and emotional information, extracts appropriate information from the relevant knowledge base, and generates an appropriate response based on the user's knowledge level and emotional state. The server receives the response from the AI ​​model, reformats it, and sends it to the device. The device displays the received response on the chat screen and notifies the user.

[0491] Specific examples

[0492] If a user types, "Tell me about Newton's second law of motion," the device sends the question to the server. The server passes the question to the emotion engine and AI model. The emotion engine recognizes the user's emotion as "confusion" based on the tone and wording of the question. The AI ​​model generates an appropriate response taking into account the emotion and knowledge level. Specifically, it generates a response such as, "Newton's second law of motion states that the acceleration of an object is proportional to the force and inversely proportional to the mass." The server sends the response to the device, which displays it on the chat screen.

[0493] Automatic question creation

[0494] When a user wants to generate a question based on specific conditions, they enter the conditions, such as grade, subject, and difficulty level, into a dedicated form on the device and press the "Create Question" button. The device formats the entered conditions and sends an API request to the server. The server passes the conditions to the AI ​​model and asks it to generate a question based on the specified conditions.

[0495] Example of problem generation

[0496] The user enters "Please create a problem in the field of mechanics for high school physics" and sends the conditions to the device. The server passes the conditions to the AI ​​model. The AI ​​model generates a problem based on the specified conditions, such as "Find the acceleration a when force F is applied to an object with mass m." The server sends the generated problem to the device, which displays the problem so the user can answer it.

[0497] Personalized commentary

[0498] The server takes into account the user's knowledge level, past answer history, and emotional data from the emotion engine, and has the AI ​​model generate a personalized explanation. The AI ​​model creates the optimal explanation for the user based on past data and emotional information. The server receives this and sends it to the device. The device displays the explanation and notifies the user.

[0499] Examples of personalized commentary

[0500] For example, if a user has previously solved a problem related to the law of conservation of energy, the next time they solve a problem in the field of mechanics, the AI ​​model will provide an explanation related to the law of conservation of energy. If the emotion engine recognizes the user's "interest," the explanation will be more detailed and interesting. The server passes conditions to the AI ​​model based on past answer history and emotion information, and the AI ​​model generates a personalized explanation. The server sends the explanation to the device, which then displays the explanation and notifies the user.

[0501] As described above, by combining the emotion engine, the system provides an individually customized learning experience that takes into consideration the user's emotions, thereby improving the quality of education.

[0502] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0503] User questions submitted

[0504] Step 1:

[0505] The user enters the question they are studying into the terminal and presses the "Submit" button.

[0506] Input: User question text (e.g., "What is Newton's second law of motion?")

[0507] Output: A transmission command is output to the terminal

[0508] Step 2:

[0509] The device formats the entered question and sends an API request to the server.

[0510] Input: User question text

[0511] Data processing / calculation: Formatting question text into JSON format

[0512] Output: Formatted question data (JSON format)

[0513] Step 3:

[0514] The server receives the question, analyzes it, and passes it to the emotion engine.

[0515] Input: Formatted question data (JSON format)

[0516] Data processing / calculation: Extracting text from question data and formatting it appropriately to be passed to the emotion engine

[0517] Output: Data to send to the emotion engine

[0518] Step 4:

[0519] The emotion engine analyzes the question text, recognizes the user's emotion, and returns the results to the server.

[0520] Input: Question text from the server

[0521] Data processing / computation: Recognizing emotions using natural language processing and sentiment analysis algorithms (e.g., "confused")

[0522] Output: Recognized emotion data

[0523] Step 5:

[0524] The server passes the question content and recognized emotional information to the AI ​​model.

[0525] Input: Question text and sentiment data

[0526] Data processing / calculation: Combining question text and sentiment data to create a format suitable for the AI ​​model

[0527] Output: Data to send to the AI ​​model

[0528] Step 6:

[0529] The AI ​​model generates a response based on the received question and emotional information and returns it to the server.

[0530] Input: Question text and sentiment data

[0531] Data processing / calculation: Searches for appropriate information from a related knowledge base based on the question and emotional information, and generates a response that matches the user's knowledge level.

[0532] Output: Generated response data

[0533] Step 7:

[0534] The server receives the response from the AI ​​model, reformats it, and sends it to the device.

[0535] Input: Generated response data

[0536] Data processing / calculation: Formatting response data for display to the user

[0537] Output: Formatted response data to send to the terminal

[0538] Step 8:

[0539] The response received by the terminal is displayed on the chat screen and notified to the user.

[0540] Input: Formatted response data

[0541] Data processing / calculation: Formatting response data into a layout for display on the chat screen

[0542] Output: The response displayed on the screen

[0543] Automatic question creation

[0544] Step 1:

[0545] The user inputs the conditions for creating a question and presses the "Create Question" button.

[0546] Input: Grade, subject, difficulty level, etc. (e.g. "High school physics, mechanics, intermediate")

[0547] Output: A transmission command is output to the terminal

[0548] Step 2:

[0549] The device formats the entered conditions and sends an API request to the server.

[0550] Input: User-entered criteria

[0551] Data processing / calculation: Format conditions into JSON format

[0552] Output: Formatted condition data (JSON format)

[0553] Step 3:

[0554] The server receives the conditions, analyzes them, and asks the AI ​​model to generate a problem.

[0555] Input: Formatted condition data (JSON format)

[0556] Data processing / calculation: Format the condition data into a format that can be used to request the AI ​​model to generate questions.

[0557] Output: Data to send to the AI ​​model

[0558] Step 4:

[0559] The AI ​​model generates questions based on the specified conditions and returns them to the server.

[0560] Input: Specified condition data

[0561] Data processing / calculation: Generate problems from the relevant knowledge base based on condition data (e.g., "Find the acceleration a when force F is applied to an object with mass m").

[0562] Output: Generated problem data

[0563] Step 5:

[0564] The server sends the generated questions to the device.

[0565] Input: Generated problem data

[0566] Data processing / calculation: Formatting the problem data for display to the user

[0567] Output: Formatted question data to send to the terminal

[0568] Step 6:

[0569] The terminal displays the received questions and allows the user to answer them.

[0570] Input: Formatted question data

[0571] Data processing / calculation: Formatting the problem data into a layout for display

[0572] Output: The problem as it appears on the screen

[0573] Personalized commentary

[0574] Step 1:

[0575] The server collects the user's knowledge level, past answer history, and emotional data, and passes them on to the AI ​​model.

[0576] Input: User knowledge level, past answer history, emotional data

[0577] Data processing / calculation: Format the collected data to generate the most appropriate explanation for the user.

[0578] Output: Data to send to the AI ​​model

[0579] Step 2:

[0580] The AI ​​model generates personalized commentary based on the collected data and returns it to the server.

[0581] Input: knowledge level data, past answer history, emotion data

[0582] Data processing / calculation: Generate optimal explanations from the relevant knowledge base based on the collected data

[0583] Output: Generated commentary data

[0584] Step 3:

[0585] The server sends the personalized commentary to the device.

[0586] Input: Generated commentary data

[0587] Data processing / calculation: Formatting explanatory data for display to the user

[0588] Output: Formatted commentary data to send to the terminal

[0589] Step 4:

[0590] The terminal displays the received explanation and notifies the user.

[0591] Input: Formatted commentary data

[0592] Data processing / calculation: Formatting the explanatory data into a layout for display

[0593] Output: Explanation displayed on the screen

[0594] (Application example 2)

[0595] 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."

[0596] Conventional individual learning support systems have had the problem of being unable to respond flexibly to users' emotions and individual needs. In particular, when providing customer service support in brick-and-mortar stores, it is difficult for store staff to consistently grasp customers' emotions and respond optimally based on them. This can lead to a decline in customer satisfaction.

[0597] 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 a means for transmitting a question entered by a user to an emotion analysis engine to acquire emotion information, a means for passing the question and emotion information to an AI model to generate an appropriate response, and a means for transmitting the response generated by the AI ​​model to a terminal for display. This enables store clerks in physical stores to consistently provide optimal responses to customers, taking into consideration the user's emotions.

[0598] - "Terminal" means an electronic device that allows a user to input or receive information.

[0599] A "question" is information that the user wants to know or confirm, entered in text format.

[0600] An "emotion analysis engine" is a system that analyzes a user's emotions from input text and outputs the results.

[0601] "Emotion information" is data about the user's emotional state obtained by the emotion analysis engine.

[0602] A "server" is a central computer system and device that processes and analyzes received data.

[0603] An "AI model" is an artificial intelligence algorithm that analyzes user input and generates optimal responses and explanations.

[0604] A "response" is information generated by an AI model in response to a user's question.

[0605] The "knowledge level" is information indicating the level of knowledge that the user has, and is calculated from the past answer history.

[0606] The "answer history" is a record of the answers that the user has given up to now.

[0607] A "personalized commentary" is a commentary content that is individually customized taking into account the user's knowledge level and emotional information.

[0608] This invention is a system that analyzes a user's emotional information and provides individually customized responses, particularly for the purpose of supporting customer service in brick-and-mortar stores, helping store staff to effectively respond to customers.

[0609] The central part of the system is the server, which includes the following means:

[0610] 1. A means of obtaining emotional information from user input using an emotion analysis engine.

[0611] 2. A means of analyzing the question and sentiment information and passing it to an AI model to generate the optimal response.

[0612] 3. A means of sending the responses generated by the AI ​​model to the device and displaying them to the user.

[0613] Specifically, the following processing is performed.

[0614] First, a store clerk inputs a customer's question into the terminal, which then sends the question to the server. The server passes the question to a sentiment analysis engine, which analyzes the user's emotions. The acquired emotional information is then sent to an AI model, which generates an optimal response based on the question and emotional information. The server then reformats this response and sends it to the terminal, where the store clerk displays it to the customer and takes appropriate action.

[0615] For example, if a customer asks, "What material is this shirt made of?", the following prompt sentence is generated:

[0616] "What material is this shirt made of?" (Emotion: Interest, Probability: 0.85)

[0617] This allows the server to utilize its emotion analysis engine and AI model to quickly provide the optimal response based on the user's emotions.

[0618] The software and hardware used include:

[0619] Sentiment analysis engine: A software system for analyzing text.

[0620] AI model: A generative AI model that generates responses based on questions and sentiment information.

[0621] Device: The smartphone or tablet device that users use for input and display.

[0622] Server: A central system that receives, processes, and transmits data.

[0623] This makes it possible to provide effective customer service that is in line with the user's emotions, even in physical stores.

[0624] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0625] Step 1:

[0626] The store clerk inputs the customer's question into the terminal and presses the send button, which sends the question to the server.

[0627] Input: The question entered by the store clerk into the terminal

[0628] Output: The question is sent to the server

[0629] Step 2:

[0630] The server passes the received question to a sentiment analysis engine to obtain the user's sentiment information. The sentiment analysis engine analyzes the tone and wording of the question to generate sentiment information.

[0631] Input: Received question

[0632] Output: Emotion information (e.g., interest, accuracy: 0.85)

[0633] Step 3:

[0634] The server passes the question and emotional information to the AI ​​model and asks it to generate a response. The AI ​​model generates the optimal answer based on the question content and emotional information.

[0635] Input: Question, emotion information

[0636] Output: Best response

[0637] Step 4:

[0638] The server receives the response sent back by the AI ​​model, reformats it, and sends it to the device, which involves converting the response into an appropriate format for display.

[0639] Input: Best response

[0640] Output: Reformatted response

[0641] Step 5:

[0642] The terminal displays the received response and notifies the store clerk, who then relays the displayed response to the customer.

[0643] Input: Reformatted response

[0644] Output: Response displayed to the store clerk

[0645] Step 6:

[0646] The store clerk will check the response and provide the customer with an appropriate answer, allowing the store to respond to the customer's question quickly and accurately.

[0647] Input: Displayed response

[0648] Output: Response to the customer

[0649] This series of processes enables store staff to take into consideration the customer's feelings and provide optimal customer service.

[0650] 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.

[0651] 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.

[0652] 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.

[0653] [Second embodiment]

[0654] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0655] 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.

[0656] 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).

[0657] 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.

[0658] 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.

[0659] 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).

[0660] 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.

[0661] 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.

[0662] 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.

[0663] 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.

[0664] 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.

[0665] 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."

[0666] System Overview

[0667] This invention is a learning support system using AI that analyzes questions entered by users into a terminal in real time, generates responses using an AI model, and displays them on the terminal. It also includes a function that allows users to input specific conditions to request the generation of questions, and the AI ​​model generates and displays questions based on those conditions. Furthermore, the server also provides personalized explanations taking into account the user's knowledge level and past answer history.

[0668] Program processing

[0669] User questions submitted

[0670] If a user has a question while studying, they can open the chat screen on their device, enter their question, and press the "Send" button.

[0671] The device receives the entered question, formats it, and sends an API request to the server.

[0672] The server analyzes the received question and passes it to the AI ​​model.

[0673] AI model response generation

[0674] The AI ​​model analyzes the incoming question, extracts appropriate information from the relevant knowledge base, and generates a response that matches the user's level of knowledge.

[0675] The server receives the response from the AI ​​model, reformats it, and sends it to the device.

[0676] The terminal displays the received response on the chat screen and notifies the user.

[0677] Specific examples

[0678] User: "What is Newton's second law of motion?"

[0679] Terminal: Sends a question to the server.

[0680] Server: Passes the question to the AI ​​model.

[0681] AI model: Generates responses that explain the second law of motion and provide concrete examples.

[0682] Server: Sends the response to the device.

[0683] Terminal: Responses are displayed on the chat screen.

[0684] User: Review responses and gain insight.

[0685] Automatic question creation

[0686] If a user wants to create a question by specifying specific conditions, they enter the conditions such as grade, subject, and difficulty level into a dedicated form on the terminal and press the "Create Question" button.

[0687] The device formats the entered conditions and sends an API request to the server.

[0688] The server passes the conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[0689] Example of problem generation

[0690] User: "Please create a high school physics problem in the mechanics section."

[0691] Terminal: Sends conditions to the server.

[0692] Server: Passes the conditions to the AI ​​model.

[0693] AI model: Generates problems based on specified conditions.

[0694] Server: Sends the generated questions to the device.

[0695] Terminal: displays the questions and allows the user to answer them.

[0696] User: Answer the question.

[0697] Personalized commentary

[0698] The server takes into account the user's knowledge level and answer history and has the AI ​​model generate personalized explanations.

[0699] The AI ​​model uses past data to create the most appropriate explanation for the user.

[0700] The server receives this and sends it to the terminal.

[0701] The terminal displays explanations to help the user understand.

[0702] Examples of personalized commentary

[0703] If a user has previously solved a problem related to the law of conservation of energy, the next time they solve a mechanics problem, the AI ​​model will provide an explanation related to the law of conservation of energy.

[0704] Server: Passes conditions to the AI ​​model based on past answer history.

[0705] AI model: Generate personalized commentary.

[0706] Server: Sends the commentary to the device.

[0707] Terminal: Display explanation and notify user.

[0708] Users: Check out personalized commentary to deepen their understanding.

[0709] In this way, the system provides optimal learning support for individual learners and improves the quality of education.

[0710] The processing flow will be explained below.

[0711] Processing Question Submissions

[0712] Step 1:

[0713] If a user has a question while studying, they can open the chat screen on their device.

[0714] Step 2:

[0715] The user enters a question into the text input field and presses the "Submit" button.

[0716] Step 3:

[0717] The device takes the entered question and prepares an API request formatted in the appropriate format.

[0718] Step 4:

[0719] The device sends an HTTP request to the API endpoint to send question data to the server.

[0720] Step 5:

[0721] The server analyzes the received HTTP request and obtains the question.

[0722] Step 6:

[0723] The server passes the question to a natural language processing model and asks it to generate an appropriate response.

[0724] AI model response generation process

[0725] Step 7:

[0726] The AI ​​model analyzes the questions it receives using natural language processing technology and extracts appropriate information from the relevant knowledge base.

[0727] Step 8:

[0728] An appropriate response text is generated taking into account the user's knowledge level.

[0729] Step 9:

[0730] The AI ​​model sends the generated response text back to the server.

[0731] Response sending process

[0732] Step 10:

[0733] The server receives the response from the AI ​​model and checks the format.

[0734] Step 11:

[0735] The server prepares an API response to send the response text to the device.

[0736] Step 12:

[0737] The server sends the response data to the terminal as an HTTP response.

[0738] Step 13:

[0739] The terminal analyzes the HTTP response received from the server and obtains the response text.

[0740] Step 14:

[0741] The response text acquired by the terminal is displayed on the chat screen.

[0742] Step 15:

[0743] Users can check the AI's responses displayed on the chat screen and resolve any questions they may have.

[0744] Automatic question creation process

[0745] Step 16:

[0746] When a user wants to solve a problem that corresponds to their learning objectives, they enter the necessary conditions (e.g., grade, subject, level, etc.) into a dedicated form on the device.

[0747] Step 17:

[0748] After the user enters the conditions, he or she presses the "Create Question" button.

[0749] Step 18:

[0750] The device formats the input conditions into the appropriate format and prepares the API request.

[0751] Step 19:

[0752] The device sends an HTTP request to the API endpoint to send condition data to the server.

[0753] Server processing of question generation

[0754] Step 20:

[0755] The server analyzes the request received from the terminal and obtains the conditions for creating questions.

[0756] Step 21:

[0757] The server passes the acquired conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[0758] AI model problem generation process

[0759] Step 22:

[0760] The AI ​​model analyzes the received conditions and selects an algorithm to generate an appropriate problem.

[0761] Step 23:

[0762] A question that meets the conditions is generated, and data containing the question and answer is created.

[0763] Step 24:

[0764] The AI ​​model sends the generated problem data back to the server.

[0765] Processing problem data submissions

[0766] Step 25:

[0767] The server receives the problem data from the AI ​​model and checks the format.

[0768] Step 26:

[0769] The server prepares an API response to send the problem data to the device.

[0770] Step 27:

[0771] The server sends the problem data to the terminal as an HTTP response.

[0772] Step 28:

[0773] The terminal analyzes the HTTP response received from the server and obtains the problem data.

[0774] Step 29:

[0775] The problem data acquired by the terminal is displayed on the user interface.

[0776] Step 30:

[0777] The user checks the displayed question and begins answering it.

[0778] Personalized commentary delivery

[0779] Step 31:

[0780] The server takes into account the user's knowledge level and answer history and has the AI ​​model generate personalized explanations.

[0781] Step 32:

[0782] The AI ​​model uses past data to create the most appropriate explanation for the user.

[0783] Step 33:

[0784] The server prepares an API response to send the explanation received from the AI ​​model to the device.

[0785] Step 34:

[0786] The server sends the explanatory data to the terminal as an HTTP response.

[0787] Step 35:

[0788] The terminal analyzes the HTTP response received from the server and obtains the explanatory data.

[0789] Step 36:

[0790] The terminal displays the explanation and notifies the user.

[0791] Step 37:

[0792] Users can check the explanations and deepen their understanding of the material.

[0793] Through these steps, the system allows users to interact with AI in real time as they learn, providing an individually customized learning experience.

[0794] Example 1

[0795] 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."

[0796] Conventional learning support systems have struggled to provide users with prompt and appropriate responses to resolve their questions, and have struggled to provide personalized learning support. This has limited the ability to improve learning efficiency and deepen users' understanding. Furthermore, they lack the ability to automatically generate questions based on specific conditions, or to provide sufficient explanations tailored to the user's knowledge level and answer history.

[0797] 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.

[0798] In this invention, the server includes means for receiving text entered by a user into an information terminal, means for transmitting the received text to a central processing unit, means for the central processing unit to analyze the text and pass it to an artificial intelligence model to generate a response, means for the central processing unit to return the response generated by the artificial intelligence model to the central processing unit, and means for the central processing unit to transmit the response to the information terminal and display it to the user, thereby enabling a quick and appropriate response to a user's question.

[0799] The present invention also includes means for a user to input specific conditions to request the generation of a dataset, means for transmitting the input conditions to a central processing unit, means for the central processing unit to request the generation of a dataset from an artificial intelligence model based on the conditions, means for returning the dataset generated by the artificial intelligence model to the central processing unit, and means for the central processing unit to transmit the generated dataset to an information terminal and display it to the user, thereby enabling the automatic generation of problems according to specific conditions.

[0800] The system further includes a means for the central processing unit to cause the artificial intelligence model to generate responses and explanations taking into account the user's knowledge level, a means for the artificial intelligence model to generate personalized explanations taking into account the user's past answer history and interests, and a means for the central processing unit to send the personalized explanations to the information terminal and display them to the user, thereby enabling optimal learning support according to the individual learning needs of the user.

[0801] A "user" is an entity that uses the learning support system to input information and receive responses.

[0802] "Information terminal" means a device that receives text entered by a user and communicates with a central processing unit. Examples include personal computers, smartphones, and tablets.

[0803] A "central processing unit" is a device that analyzes data received from an information terminal, passes the data to an AI model, and sends responses from the AI ​​model to the information terminal. This mainly applies to servers.

[0804] The "artificial intelligence model" is a system that analyzes the received prompt sentence, extracts appropriate information from a related knowledge base, and generates a response or explanation. This model combines machine learning algorithms and natural language processing technology.

[0805] "Text" refers to questions or requests that users enter into an information terminal, in the form of sentences or words.

[0806] "Response" refers to a reply message generated by an AI model and sent to an information terminal via a central processing unit, which may include an answer or explanation to a question.

[0807] A "dataset" refers to a collection of questions or information that an artificial intelligence model generates based on certain conditions when a user inputs a request.

[0808] "Prompt sentence" refers to text that has been converted into a specific format by the central processing unit to input data into an AI model, such as a question or condition.

[0809] "Personalized explanations" refer to individual explanations and descriptions generated by an artificial intelligence model that take into account a user's knowledge level, past answer history, and interests.

[0810] This invention is a learning support system using AI that analyzes text entered by a user into an information terminal in real time, generates responses using an artificial intelligence model, and displays them on the information terminal. It also includes the function of automatically generating questions based on specific conditions and providing personalized explanations based on the user's knowledge level and answer history.

[0811] Hardware and software used

[0812] Information terminal: A device such as a PC, smartphone, or tablet through which a user inputs text and receives results.

[0813] Central Processing Unit: A high-performance computer such as a server that passes received text to an artificial intelligence model and returns the generated response or commentary to the information terminal.

[0814] Artificial intelligence model: A system that combines machine learning algorithms and natural language processing techniques to extract information from a knowledge base and generate appropriate responses and explanations for users.

[0815] Program processing overview

[0816] User questions submitted

[0817] If a user has a question while studying, they open the chat screen on their information terminal, enter a text question, and press the "Send" button.

[0818] Question analysis and response generation

[0819] The information terminal receives the input text, formats it, and then sends an API request to the central processing unit, which analyzes the received text and passes it to the AI ​​model, which uses the analysis results to extract appropriate information from the relevant knowledge base and generate a response.

[0820] Viewing the response

[0821] The central processing unit reformats the response from the artificial intelligence model and sends it to the information terminal, which displays the response on a chat screen and notifies the user.

[0822] example

[0823] User: "What is Newton's second law of motion?"

[0824] Information terminal: Sends text to a central processing unit.

[0825] Central Processing Unit: Passes the text to the artificial intelligence model.

[0826] Artificial intelligence model: Generates responses that explain the second law of motion and provide concrete examples.

[0827] Central processing unit: Sends the response to the information terminal.

[0828] Information terminal: Responses are displayed on the chat screen.

[0829] User: Review the response and gain insight.

[0830] Automatic question creation

[0831] When a user wants to generate a question based on specific conditions, they enter the conditions, such as grade, subject, and difficulty level, into a dedicated form on the information terminal and press the "Create Question" button. The information terminal formats the entered conditions and sends an API request to the central processing unit. The central processing unit passes the conditions to an artificial intelligence model and asks it to generate a question based on the specified conditions.

[0832] example

[0833] User: "Please create a high school physics problem in the mechanics section."

[0834] Information terminal: Sends conditions to the central processing unit.

[0835] Central Processing Unit: Passes the conditions to the artificial intelligence model.

[0836] Artificial intelligence model: Generates problems based on conditions.

[0837] Central processing unit: Sends the generated questions to the information terminal.

[0838] Information terminal: displays the questions and allows the user to answer them.

[0839] User: Answer the question.

[0840] Personalized commentary

[0841] The central processing unit takes into account the user's knowledge level and answer history and has the AI ​​model generate personalized explanations. The AI ​​model creates the most appropriate explanation for the user based on past data. The central processing unit receives this and sends it to the information terminal. The information terminal displays the explanation, helping the user to understand.

[0842] example

[0843] If a user has previously solved a problem related to the law of conservation of energy, the next time they solve a problem in the field of mechanics, the artificial intelligence model will provide an explanation related to the law of conservation of energy.

[0844] Central processing unit: Passes conditions to the artificial intelligence model based on past answer history.

[0845] Artificial intelligence model: Generate personalized commentary.

[0846] Central processing unit: Sends commentary to information terminal.

[0847] Information terminal: displays explanations and notifies the user.

[0848] Users: Check out personalized commentary to deepen their understanding.

[0849] This allows the system to provide users with prompt and appropriate learning support, improving learning efficiency.

[0850] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0851] Step 1:

[0852] The user opens the chat screen on the information terminal, enters a question, and presses the "send" button.

[0853] Input: The question text that the user types into the terminal (e.g., "What is Newton's second law of motion?")

[0854] Output: Formatted question data (including user ID, question content, and submission time)

[0855] Step 2:

[0856] The device receives input from the user, formats the question text, and then sends the formatted data to the server as an API request.

[0857] Input: User question text

[0858] Data processing: Format the input data to include the user ID, question, and submission time.

[0859] Output: API request (including question)

[0860] Step 3:

[0861] The server analyzes the API request received from the device, extracts the question data, converts it into a prompt, and then passes the prompt to the AI ​​model.

[0862] Input: Formatted question data

[0863] Data processing: Analyze question data and create prompts

[0864] Output: Prompt text (e.g., "Question: What is Newton's second law of motion? User ID: 12345")

[0865] Step 4:

[0866] Based on the prompt received from the server, the artificial intelligence model extracts appropriate information from the relevant knowledge base and generates a response to the question.

[0867] Input: prompt statement

[0868] Data processing: Extracting information from the knowledge base and generating responses

[0869] Output: Response (e.g., "Newton's second law of motion states that the motion of an object is proportional to its mass and acceleration when a force is applied to it.")

[0870] Step 5:

[0871] The server reformats the response received from the AI ​​model and sends it to the device as an API response.

[0872] Input: The response generated by the AI ​​model

[0873] Data manipulation: Reformatting the response to include the user ID and timestamp

[0874] Output: API response (formatted response data)

[0875] Step 6:

[0876] The device analyzes the API response received from the server and displays it on the chat screen so that the user can check the content.

[0877] Input: API response from the server

[0878] Data processing: Analyzes response data and converts it into a format to display on the chat screen

[0879] Output: The answer that is displayed to the user (e.g., "Newton's second law of motion states that the motion of an object is proportional to its mass and acceleration when a force is applied to it.")

[0880] Through these processing steps, the system is able to provide quick and accurate answers to users' questions.

[0881] (Application example 1)

[0882] 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."

[0883] Acquiring and analyzing real-time traffic information for autonomous vehicles is important for users, but current systems lack the ability to provide personalized support for real-time question resolution and learning. In particular, there is a demand for systems that can provide detailed explanations of traffic information and generate questions tailored to the user's knowledge level.

[0884] 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.

[0885] In this invention, the server includes means for receiving a question input by a user to a terminal, means for transmitting the received question to the server, means for the server to analyze the question and pass it to an artificial intelligence model to generate a response, means for the server to return the response generated by the artificial intelligence model to the server, means for the server to transmit the response to the terminal and display it to the user, and means for acquiring and analyzing traffic information in real time and visualizing it for the user, thereby enabling real-time resolution of user questions and personalized learning support in an autonomous vehicle.

[0886] "User" refers to a person who uses the system.

[0887] "Terminal" refers to a device through which a user accesses and operates the system.

[0888] "Server" refers to the central computer that analyzes queries and traffic information and generates responses.

[0889] "Artificial intelligence model" refers to an artificial intelligence algorithm that responds to user questions, generates questions, and provides personalized explanations.

[0890] "Means for receiving" refers to the function of the terminal to obtain information input by the user.

[0891] "Means for transmitting" refers to the function of transferring received information to a server as data.

[0892] "Means for analyzing" refers to the functionality that allows the server to understand and process the information it receives.

[0893] "Means for generating" refers to the ability of the artificial intelligence model to create a response based on the analysis results.

[0894] "Means for sending back" refers to the functionality for returning the generated response to the server.

[0895] "Means of acquiring and analyzing in real time" refers to the function of collecting, analyzing, and visualizing current traffic information.

[0896] "Visualization means" refers to the function of displaying analyzed information in a format that is easy for users to understand.

[0897] "Means for requesting the creation of a question" refers to a function that allows a user to input specific conditions and request the creation of a question.

[0898] "Means for generating personalized explanations" refers to a function that creates explanations according to the user's knowledge level and answer history.

[0899] "Means for transmitting a personalized commentary to a terminal and displaying it to a user" refers to a function for transferring the generated commentary to a user's terminal and displaying it.

[0900] This invention is a system for providing learning support and traffic information to users in autonomous vehicles. Specifically, a server uses an artificial intelligence model to generate and provide real-time responses to questions and requests entered by the user into a terminal. The system also has the function of acquiring and analyzing traffic information in real time and visualizing it for the user.

[0901] System Program Overview

[0902] This system performs the following main processes between the server and the terminal.

[0903] 1. Receiving and sending user questions.

[0904] 2. Parsing the question and generating the response.

[0905] 3. Sending and displaying the generated response.

[0906] 4. Real-time acquisition and analysis of traffic information.

[0907] 5. Visualization and provision of traffic information.

[0908] 6. Generating and delivering personalized commentary.

[0909] Hardware and software used

[0910] Hardware:

[0911] Device: A mobile information device such as a smartphone or tablet held by a user.

[0912] Server: A central computer that processes query analysis and artificial intelligence models.

[0913] software:

[0914] Artificial intelligence model: Used to generate answers to user questions and create problems. This can be done using APIs such as OpenAI.

[0915] Requests library: Used to perform HTTP requests for real-time traffic information.

[0916] Explanation of program processing

[0917] When a user inputs a question into the device, the device receives the question and sends it to the server. The server analyzes the received question and passes it to the AI ​​model to generate a response. The response generated by the AI ​​model is sent back to the server, which then sends it to the device and displays it to the user.

[0918] The server then collects and analyzes traffic information in real time. The analyzed traffic information is then sent to the user's device and visualized. In this process, the Requests library is used to collect and analyze traffic information.

[0919] The server then uses the AI ​​model to generate personalized explanations based on the user's knowledge level and past answer history. The generated explanations are then sent back to the server and displayed on the user's device. This allows users to obtain information tailored to their level of understanding in real time.

[0920] Specific examples

[0921] Specific examples of question-answering:

[0922] When a user types, "What's the current traffic situation at this intersection?", the device sends the question to the server, which passes the question to an artificial intelligence model that generates an appropriate response. The response is then sent back to the device via the server and displayed to the user.

[0923] Examples of obtaining and displaying traffic information:

[0924] The server acquires and analyzes real-time traffic information at a particular intersection. The results are sent to the device and visualized. When the user asks, "How congested is the traffic?", detailed traffic information is displayed.

[0925] Examples of personalized commentary:

[0926] If the user had previously asked the question "Please tell me how traffic lights work," then the user's next question would be "What is the current traffic situation at the intersection?", which would also provide additional commentary related to how traffic lights work.

[0927] This enables the system to provide users with real-time, high-quality information and learning assistance in an autonomous vehicle environment.

[0928] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0929] Step 1:

[0930] Receives a question entered by a user into the terminal. The user enters "What is the current traffic situation at the intersection?" into the terminal and presses the "Send" button. This inputs the question into the terminal.

[0931] Step 2:

[0932] The device formats the received question and sends it to the server as an API request. The question is formatted in the appropriate data format to be sent as an HTTP request.

[0933] Step 3:

[0934] The server analyzes the received question. The server passes the received data to a natural language processing engine to understand the intent of the question. During this process, keywords from the question are extracted and a prompt sentence is formed to be passed to the generative AI model.

[0935] Step 4:

[0936] The server passes the analysis results to the generative AI model and requests it to generate an appropriate response. The prompt sentence is "Question to the environment: What is the current traffic situation at the intersection?\nAnswer:" and is input to the generative AI model. The generative AI model extracts information from the relevant database and generates a response.

[0937] Step 5:

[0938] The generative AI model sends the generated response back to the server, which includes the specific traffic situation and related advice.

[0939] Step 6:

[0940] The server reformats the response received from the generative AI model and sends it to the device as an API response, arranging the received text data in a format that is easy for the user to understand.

[0941] Step 7:

[0942] The device displays the received response on the chat screen and notifies the user. The response "The current traffic situation at the intersection is as follows:" is displayed on the chat screen.

[0943] Step 8:

[0944] The server gets real-time traffic information from the Traffic Data API, sending a request to the appropriate API endpoint to get the current traffic situation data.

[0945] Step 9:

[0946] The server analyzes the acquired traffic data and formats it for visualization by the user, including traffic congestion status, average speed, traffic light timing, etc.

[0947] Step 10:

[0948] The device displays the analyzed traffic information sent from the server and notifies the user. It also displays traffic congestion on a map in different colors and displays the appropriate distance and time.

[0949] Step 11:

[0950] The server analyzes the user's knowledge level and past question history and requests the generative AI model to generate a personalized explanation. For example, if the user previously asked, "How does a traffic light work?", the server takes that historical data into account when generating a response.

[0951] Step 12:

[0952] The generative AI model generates a personalized explanation and sends it back to the server, including information about how the traffic light works and information relevant to the current question.

[0953] Step 13:

[0954] The server then reformats the generated commentary and sends it to the terminal, formatting the content of the commentary to make it easier for the user to understand.

[0955] Step 14:

[0956] The device displays the received personalized commentary to inform the user, including the following information: "Just to clarify how traffic lights work. The traffic lights at the current intersection are connected to a central control system and are adjusted in real time."

[0957] This series of processes allows users to receive real-time traffic information and related learning information in the environment of an autonomous vehicle.

[0958] 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.

[0959] System Overview

[0960] This invention combines an AI-based personalized learning support system with an emotion engine that recognizes the user's emotions. The system analyzes questions entered by the user into a device in real time, generates appropriate responses using an AI model, and displays them on the device. It also includes a function that generates questions based on specific conditions and provides questions and explanations based on those conditions. Furthermore, the system provides personalized explanations taking into account the user's knowledge level and past answer history, and uses the emotion engine to adjust the responses and explanations according to the user's emotions.

[0961] Program processing

[0962] User questions submitted

[0963] If a user has a question while studying, they can open the chat screen on their device, enter their question, and press the "Send" button.

[0964] The device receives the entered question, formats it, and sends an API request to the server.

[0965] The server analyzes the received question and first passes the question content to the emotion engine. The emotion engine analyzes the user's input and behavior to recognize emotions and returns the results to the server. The server then passes the question content and recognized emotion information to the AI ​​model.

[0966] AI model response generation

[0967] The AI ​​model analyzes the received question and emotional information, extracts appropriate information from the relevant knowledge base, and generates an appropriate response according to the user's knowledge level and emotions.

[0968] The server receives the response from the AI ​​model, reformats it, and sends it to the device.

[0969] The terminal displays the received response on the chat screen and notifies the user.

[0970] Specific examples

[0971] User: "What is Newton's second law of motion?"

[0972] Terminal: Sends a question to the server.

[0973] Server: Passes the question to the emotion engine and AI model.

[0974] Emotion engine: Recognizes the user's emotion as "confusion" based on the tone and wording of the question.

[0975] AI model: Considers emotions and knowledge level to provide appropriate responses ("Newton's second law of motion, simply stated...").

[0976] Server: Sends the response to the device.

[0977] Terminal: Responses are displayed on the chat screen.

[0978] User: Check the response and clarify any questions.

[0979] Automatic question creation

[0980] If a user wants to create a question by specifying specific conditions, they enter the conditions such as grade, subject, and difficulty level into a dedicated form on the terminal and press the "Create Question" button.

[0981] The device formats the entered conditions and sends an API request to the server.

[0982] The server passes the conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[0983] Example of problem generation

[0984] User: "Please create a high school physics problem in the mechanics section."

[0985] Terminal: Sends conditions to the server.

[0986] Server: Passes the conditions to the AI ​​model.

[0987] AI model: Generates problems based on specified conditions.

[0988] Server: Sends the generated questions to the device.

[0989] Terminal: displays the questions and allows the user to answer them.

[0990] User: Answer the question.

[0991] Personalized commentary

[0992] The server takes into account the user's knowledge level, answer history, and emotional data from an emotion engine, and has the AI ​​model generate personalized explanations.

[0993] The AI ​​model uses past data and emotional information to create the most appropriate explanation for the user.

[0994] The server receives this and sends it to the terminal.

[0995] The terminal displays an explanation and notifies the user.

[0996] Examples of personalized commentary

[0997] If a user has previously solved a problem related to the law of conservation of energy, the next time they solve a problem in the field of mechanics, the AI ​​model will provide an explanation related to the law of conservation of energy. If the emotion engine recognizes the user's "interest," the explanation will be more detailed and interesting.

[0998] Server: Passes conditions to the AI ​​model based on past answer history and emotional information.

[0999] AI model: Generate personalized commentary.

[1000] Server: Sends the commentary to the device.

[1001] Terminal: Display explanation and notify user.

[1002] Users: Check out personalized commentary to deepen their understanding.

[1003] In this way, by combining the emotional engine, the system provides an individually customized learning experience that takes into account the user's emotions, improving the quality of education.

[1004] The processing flow will be explained below.

[1005] User question submission process

[1006] Step 1:

[1007] If a user has a question while studying, they can open the chat screen on their device.

[1008] Step 2:

[1009] The user enters a question into the text input field and presses the "Submit" button.

[1010] Step 3:

[1011] The device takes the entered question and prepares an API request formatted in the appropriate format.

[1012] Step 4:

[1013] The device sends an HTTP request to the API endpoint to send question data to the server.

[1014] Step 5:

[1015] The server analyzes the received HTTP request and obtains the question.

[1016] Step 6:

[1017] Before the server passes the question to the natural language processing model, it first passes it to an emotion engine to identify the user's emotion.

[1018] Step 7:

[1019] The emotion engine identifies the user's emotion from the tone of the question, wording, typing speed, etc., and sends the results back to the server.

[1020] Step 8:

[1021] The server passes the question content along with the emotional information received from the emotion engine to the AI ​​model.

[1022] AI model response generation process

[1023] Step 9:

[1024] The AI ​​model analyzes the received questions and emotional information using natural language processing technology and extracts appropriate information from the relevant knowledge base.

[1025] Step 10:

[1026] It generates appropriate response text taking into account the user's knowledge level and perceived emotions.

[1027] Step 11:

[1028] The AI ​​model sends the generated response text back to the server.

[1029] Response sending process

[1030] Step 12:

[1031] The server receives the response from the AI ​​model and checks the format.

[1032] Step 13:

[1033] The server prepares an API response to send the response text to the device.

[1034] Step 14:

[1035] The server sends the response data to the terminal as an HTTP response.

[1036] Step 15:

[1037] The terminal analyzes the HTTP response received from the server and obtains the response text.

[1038] Step 16:

[1039] The response text acquired by the terminal is displayed on the chat screen.

[1040] Step 17:

[1041] Users can check the AI's responses displayed on the chat screen and resolve any questions they may have.

[1042] Automatic question creation process

[1043] Step 18:

[1044] When a user wants to solve a problem that corresponds to their learning objectives, they enter the necessary conditions (e.g., grade, subject, level, etc.) into a dedicated form on the device.

[1045] Step 19:

[1046] After the user enters the conditions, he or she presses the "Create Question" button.

[1047] Step 20:

[1048] The device formats the input conditions into the appropriate format and prepares the API request.

[1049] Step 21:

[1050] The device sends an HTTP request to the API endpoint to send condition data to the server.

[1051] Server processing of question generation

[1052] Step 22:

[1053] The server analyzes the request received from the terminal and obtains the conditions for creating questions.

[1054] Step 23:

[1055] The server passes the acquired conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[1056] AI model problem generation process

[1057] Step 24:

[1058] The AI ​​model analyzes the received conditions and selects an algorithm to generate an appropriate problem.

[1059] Step 25:

[1060] A question that meets the conditions is generated, and data containing the question and answer is created.

[1061] Step 26:

[1062] The AI ​​model sends the generated problem data back to the server.

[1063] Processing problem data submissions

[1064] Step 27:

[1065] The server receives the problem data from the AI ​​model and checks the format.

[1066] Step 28:

[1067] The server prepares an API response to send the problem data to the device.

[1068] Step 29:

[1069] The server sends the problem data to the terminal as an HTTP response.

[1070] Step 30:

[1071] The terminal analyzes the HTTP response received from the server and obtains the problem data.

[1072] Step 31:

[1073] The problem data acquired by the terminal is displayed on the user interface.

[1074] Step 32:

[1075] The user checks the displayed question and begins answering it.

[1076] Personalized commentary delivery

[1077] Step 33:

[1078] The server takes into account the user's knowledge level, answer history, and emotional data from an emotion engine, and has the AI ​​model generate personalized explanations.

[1079] Step 34:

[1080] The AI ​​model uses past data and emotional information to create the most appropriate explanation for the user.

[1081] Step 35:

[1082] The server prepares an API response to send the explanation received from the AI ​​model to the device.

[1083] Step 36:

[1084] The server sends the explanatory data to the terminal as an HTTP response.

[1085] Step 37:

[1086] The terminal analyzes the HTTP response received from the server and obtains the explanatory data.

[1087] Step 38:

[1088] The terminal displays the explanation and notifies the user.

[1089] Step 39:

[1090] Users can check the explanations and deepen their understanding of the material.

[1091] Through these steps, the system enables users to learn while interacting with AI in real time, and also provides a learning experience that takes users' emotions into consideration.

[1092] Example 2

[1093] 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."

[1094] Conventional personalized learning support systems lack consideration for users' emotions, which can negatively impact learning motivation and comprehension. Furthermore, they lack personalized explanations and questions, making it difficult to provide an optimal learning experience based on the user's knowledge level and answer history. Therefore, a system that recognizes the user's emotional state and generates appropriate responses and explanations is needed.

[1095] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a question input by a user to a terminal, means for transmitting the received question to the server, means for the server to analyze the question and pass it to an emotion engine to recognize the user's emotion and receive the result, means for the server to pass the question content and the recognized emotion information to an AI model to generate a response, means for returning the response generated by the AI ​​model to the server, and means for the server to send the response to the terminal and display it to the user. This makes it possible to provide an appropriate response or explanation according to the user's emotion.

[1096] A "user" is an individual who uses the system to advance their learning.

[1097] "Terminal" refers to the device used by the user to input learning content and receive responses from the system.

[1098] A "server" is a central computer system that receives requests from users, analyzes them, and performs the necessary processing.

[1099] An "emotion engine" is software that analyzes a user's input and behavior to identify emotions.

[1100] An "AI model" is an algorithm that uses machine learning or deep learning to analyze data and generate responses or questions.

[1101] A "question" is text data that a user inputs into the system via a terminal to express a question that the user has while studying.

[1102] A "response" is an answer to a user's question that the server generates using an AI model.

[1103] A "problem" is a learning task generated by an AI model based on conditions specified by the user.

[1104] "Explanation" is a detailed explanation or additional information provided in response to a user's question or problem.

[1105] "Personalization" is a concept that refers to optimizing the content provided based on the characteristics and history of each individual user.

[1106] MODE FOR CARRYING OUT THE INVENTION

[1107] System Overview

[1108] This invention combines an AI-based personalized learning support system with an emotion engine that recognizes the user's emotions. The system analyzes questions entered by the user into the device in real time, generates appropriate responses, and displays them on the device. It also includes a function that generates questions by entering specific conditions and provides questions and explanations based on those conditions. Furthermore, the system provides personalized explanations taking into account the user's knowledge level and past answer history, and uses the emotion engine to adjust the responses and explanations according to the user's emotions.

[1109] System configuration

[1110] The system consists of the following main components:

[1111] 1. Terminal: A device where the user inputs learning content and receives responses from the system.

[1112] 2. Server: A central computer system that receives and analyzes user requests.

[1113] 3. Emotion engine: Software that analyzes user input and behavior to identify emotions.

[1114] 4. AI Model: An algorithm that uses machine learning or deep learning to analyze data and generate responses or questions.

[1115] User questions submitted

[1116] If a user has a question during learning, they open the chat screen on their device, enter their question, and press the "Send" button. The device receives the entered question, formats it appropriately, and sends it to the server as an API request. The server analyzes the received question and passes the question content to the emotion engine. The emotion engine analyzes the user's input and behavior to recognize emotions and return the results to the server. The server then passes the question content and recognized emotion information to the AI ​​model.

[1117] AI model response generation

[1118] The AI ​​model analyzes the received question and emotional information, extracts appropriate information from the relevant knowledge base, and generates an appropriate response based on the user's knowledge level and emotional state. The server receives the response from the AI ​​model, reformats it, and sends it to the device. The device displays the received response on the chat screen and notifies the user.

[1119] Specific examples

[1120] If a user types, "Tell me about Newton's second law of motion," the device sends the question to the server. The server passes the question to the emotion engine and AI model. The emotion engine recognizes the user's emotion as "confusion" based on the tone and wording of the question. The AI ​​model generates an appropriate response taking into account the emotion and knowledge level. Specifically, it generates a response such as, "Newton's second law of motion states that the acceleration of an object is proportional to the force and inversely proportional to the mass." The server sends the response to the device, which displays it on the chat screen.

[1121] Automatic question creation

[1122] When a user wants to generate a question based on specific conditions, they enter the conditions, such as grade, subject, and difficulty level, into a dedicated form on the device and press the "Create Question" button. The device formats the entered conditions and sends an API request to the server. The server passes the conditions to the AI ​​model and asks it to generate a question based on the specified conditions.

[1123] Example of problem generation

[1124] The user enters "Please create a problem in the field of mechanics for high school physics" and sends the conditions to the device. The server passes the conditions to the AI ​​model. The AI ​​model generates a problem based on the specified conditions, such as "Find the acceleration a when force F is applied to an object with mass m." The server sends the generated problem to the device, which displays the problem so the user can answer it.

[1125] Personalized commentary

[1126] The server takes into account the user's knowledge level, past answer history, and emotional data from the emotion engine, and has the AI ​​model generate a personalized explanation. The AI ​​model creates the optimal explanation for the user based on past data and emotional information. The server receives this and sends it to the device. The device displays the explanation and notifies the user.

[1127] Examples of personalized commentary

[1128] For example, if a user has previously solved a problem related to the law of conservation of energy, the next time they solve a problem in the field of mechanics, the AI ​​model will provide an explanation related to the law of conservation of energy. If the emotion engine recognizes the user's "interest," the explanation will be more detailed and interesting. The server passes conditions to the AI ​​model based on past answer history and emotion information, and the AI ​​model generates a personalized explanation. The server sends the explanation to the device, which then displays the explanation and notifies the user.

[1129] As described above, by combining the emotion engine, the system provides an individually customized learning experience that takes into consideration the user's emotions, thereby improving the quality of education.

[1130] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1131] User questions submitted

[1132] Step 1:

[1133] The user enters the question they are studying into the terminal and presses the "Submit" button.

[1134] Input: User question text (e.g., "What is Newton's second law of motion?")

[1135] Output: A transmission command is output to the terminal

[1136] Step 2:

[1137] The device formats the entered question and sends an API request to the server.

[1138] Input: User question text

[1139] Data processing / calculation: Formatting question text into JSON format

[1140] Output: Formatted question data (JSON format)

[1141] Step 3:

[1142] The server receives the question, analyzes it, and passes it to the emotion engine.

[1143] Input: Formatted question data (JSON format)

[1144] Data processing / calculation: Extracting text from question data and formatting it appropriately to be passed to the emotion engine

[1145] Output: Data to send to the emotion engine

[1146] Step 4:

[1147] The emotion engine analyzes the question text, recognizes the user's emotion, and returns the results to the server.

[1148] Input: Question text from the server

[1149] Data processing / computation: Recognizing emotions using natural language processing and sentiment analysis algorithms (e.g., "confused")

[1150] Output: Recognized emotion data

[1151] Step 5:

[1152] The server passes the question content and recognized emotional information to the AI ​​model.

[1153] Input: Question text and sentiment data

[1154] Data processing / calculation: Combining question text and sentiment data to create a format suitable for the AI ​​model

[1155] Output: Data to send to the AI ​​model

[1156] Step 6:

[1157] The AI ​​model generates a response based on the received question and emotional information and returns it to the server.

[1158] Input: Question text and sentiment data

[1159] Data processing / calculation: Searches for appropriate information from a related knowledge base based on the question and emotional information, and generates a response that matches the user's knowledge level.

[1160] Output: Generated response data

[1161] Step 7:

[1162] The server receives the response from the AI ​​model, reformats it, and sends it to the device.

[1163] Input: Generated response data

[1164] Data processing / calculation: Formatting response data for display to the user

[1165] Output: Formatted response data to send to the terminal

[1166] Step 8:

[1167] The response received by the terminal is displayed on the chat screen and notified to the user.

[1168] Input: Formatted response data

[1169] Data processing / calculation: Formatting response data into a layout for display on the chat screen

[1170] Output: The response displayed on the screen

[1171] Automatic question creation

[1172] Step 1:

[1173] The user inputs the conditions for creating a question and presses the "Create Question" button.

[1174] Input: Grade, subject, difficulty level, etc. (e.g. "High school physics, mechanics, intermediate")

[1175] Output: A transmission command is output to the terminal

[1176] Step 2:

[1177] The device formats the entered conditions and sends an API request to the server.

[1178] Input: User-entered criteria

[1179] Data processing / calculation: Format conditions into JSON format

[1180] Output: Formatted condition data (JSON format)

[1181] Step 3:

[1182] The server receives the conditions, analyzes them, and asks the AI ​​model to generate a problem.

[1183] Input: Formatted condition data (JSON format)

[1184] Data processing / calculation: Format the condition data into a format that can be used to request the AI ​​model to generate questions.

[1185] Output: Data to send to the AI ​​model

[1186] Step 4:

[1187] The AI ​​model generates questions based on the specified conditions and returns them to the server.

[1188] Input: Specified condition data

[1189] Data processing / calculation: Generate problems from the relevant knowledge base based on condition data (e.g., "Find the acceleration a when force F is applied to an object with mass m").

[1190] Output: Generated problem data

[1191] Step 5:

[1192] The server sends the generated questions to the device.

[1193] Input: Generated problem data

[1194] Data processing / calculation: Formatting the problem data for display to the user

[1195] Output: Formatted question data to send to the terminal

[1196] Step 6:

[1197] The terminal displays the received questions and allows the user to answer them.

[1198] Input: Formatted question data

[1199] Data processing / calculation: Formatting the problem data into a layout for display

[1200] Output: The problem as it appears on the screen

[1201] Personalized commentary

[1202] Step 1:

[1203] The server collects the user's knowledge level, past answer history, and emotional data, and passes them on to the AI ​​model.

[1204] Input: User knowledge level, past answer history, emotional data

[1205] Data processing / calculation: Format the collected data to generate the most appropriate explanation for the user.

[1206] Output: Data to send to the AI ​​model

[1207] Step 2:

[1208] The AI ​​model generates personalized commentary based on the collected data and returns it to the server.

[1209] Input: knowledge level data, past answer history, emotion data

[1210] Data processing / calculation: Generate optimal explanations from the relevant knowledge base based on the collected data

[1211] Output: Generated commentary data

[1212] Step 3:

[1213] The server sends the personalized commentary to the device.

[1214] Input: Generated commentary data

[1215] Data processing / calculation: Formatting explanatory data for display to the user

[1216] Output: Formatted commentary data to send to the terminal

[1217] Step 4:

[1218] The terminal displays the received explanation and notifies the user.

[1219] Input: Formatted commentary data

[1220] Data processing / calculation: Formatting the explanatory data into a layout for display

[1221] Output: Explanation displayed on the screen

[1222] (Application example 2)

[1223] 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."

[1224] Conventional individual learning support systems have had the problem of being unable to respond flexibly to users' emotions and individual needs. In particular, when providing customer service support in brick-and-mortar stores, it is difficult for store staff to consistently grasp customers' emotions and respond optimally based on them. This can lead to a decline in customer satisfaction.

[1225] 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 a means for transmitting a question entered by a user to an emotion analysis engine to acquire emotion information, a means for passing the question and emotion information to an AI model to generate an appropriate response, and a means for transmitting the response generated by the AI ​​model to a terminal for display. This enables store clerks in physical stores to consistently provide optimal responses to customers, taking into consideration the user's emotions.

[1226] - "Terminal" means an electronic device that allows a user to input or receive information.

[1227] A "question" is information that the user wants to know or confirm, entered in text format.

[1228] An "emotion analysis engine" is a system that analyzes a user's emotions from input text and outputs the results.

[1229] "Emotion information" is data about the user's emotional state obtained by the emotion analysis engine.

[1230] A "server" is a central computer system and device that processes and analyzes received data.

[1231] An "AI model" is an artificial intelligence algorithm that analyzes user input and generates optimal responses and explanations.

[1232] A "response" is information generated by an AI model in response to a user's question.

[1233] The "knowledge level" is information indicating the level of knowledge that the user has, and is calculated from the past answer history.

[1234] The "answer history" is a record of the answers that the user has given up to now.

[1235] A "personalized commentary" is a commentary content that is individually customized taking into account the user's knowledge level and emotional information.

[1236] This invention is a system that analyzes a user's emotional information and provides individually customized responses, particularly for the purpose of supporting customer service in brick-and-mortar stores, helping store staff to effectively respond to customers.

[1237] The central part of the system is the server, which includes the following means:

[1238] 1. A means of obtaining emotional information from user input using an emotion analysis engine.

[1239] 2. A means of analyzing the question and sentiment information and passing it to an AI model to generate the optimal response.

[1240] 3. A means of sending the responses generated by the AI ​​model to the device and displaying them to the user.

[1241] Specifically, the following processing is performed.

[1242] First, a store clerk inputs a customer's question into the terminal, which then sends the question to the server. The server passes the question to a sentiment analysis engine, which analyzes the user's emotions. The acquired emotional information is then sent to an AI model, which generates an optimal response based on the question and emotional information. The server then reformats this response and sends it to the terminal, where the store clerk displays it to the customer and takes appropriate action.

[1243] For example, if a customer asks, "What material is this shirt made of?", the following prompt sentence is generated:

[1244] "What material is this shirt made of?" (Emotion: Interest, Probability: 0.85)

[1245] This allows the server to utilize its emotion analysis engine and AI model to quickly provide the optimal response based on the user's emotions.

[1246] The software and hardware used include:

[1247] Sentiment analysis engine: A software system for analyzing text.

[1248] AI model: A generative AI model that generates responses based on questions and sentiment information.

[1249] Device: The smartphone or tablet device that users use for input and display.

[1250] Server: A central system that receives, processes, and transmits data.

[1251] This makes it possible to provide effective customer service that is in line with the user's emotions, even in physical stores.

[1252] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1253] Step 1:

[1254] The store clerk inputs the customer's question into the terminal and presses the send button, which sends the question to the server.

[1255] Input: The question entered by the store clerk into the terminal

[1256] Output: The question is sent to the server

[1257] Step 2:

[1258] The server passes the received question to a sentiment analysis engine to obtain the user's sentiment information. The sentiment analysis engine analyzes the tone and wording of the question to generate sentiment information.

[1259] Input: Received question

[1260] Output: Emotion information (e.g., interest, accuracy: 0.85)

[1261] Step 3:

[1262] The server passes the question and emotional information to the AI ​​model and asks it to generate a response. The AI ​​model generates the optimal answer based on the question content and emotional information.

[1263] Input: Question, emotion information

[1264] Output: Best response

[1265] Step 4:

[1266] The server receives the response sent back by the AI ​​model, reformats it, and sends it to the device, which involves converting the response into an appropriate format for display.

[1267] Input: Best response

[1268] Output: Reformatted response

[1269] Step 5:

[1270] The terminal displays the received response and notifies the store clerk, who then relays the displayed response to the customer.

[1271] Input: Reformatted response

[1272] Output: Response displayed to the store clerk

[1273] Step 6:

[1274] The store clerk will check the response and provide the customer with an appropriate answer, allowing the store to respond to the customer's question quickly and accurately.

[1275] Input: Displayed response

[1276] Output: Response to the customer

[1277] This series of processes enables store staff to take into consideration the customer's feelings and provide optimal customer service.

[1278] 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.

[1279] 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.

[1280] 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.

[1281] [Third embodiment]

[1282] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1283] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1284] 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).

[1285] 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.

[1286] 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.

[1287] 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).

[1288] 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.

[1289] 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.

[1290] 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.

[1291] 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.

[1292] 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.

[1293] 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."

[1294] System Overview

[1295] This invention is a learning support system using AI that analyzes questions entered by users into a terminal in real time, generates responses using an AI model, and displays them on the terminal. It also includes a function that allows users to input specific conditions to request the generation of questions, and the AI ​​model generates and displays questions based on those conditions. Furthermore, the server also provides personalized explanations taking into account the user's knowledge level and past answer history.

[1296] Program processing

[1297] User questions submitted

[1298] If a user has a question while studying, they can open the chat screen on their device, enter their question, and press the "Send" button.

[1299] The device receives the entered question, formats it, and sends an API request to the server.

[1300] The server analyzes the received question and passes it to the AI ​​model.

[1301] AI model response generation

[1302] The AI ​​model analyzes the incoming question, extracts appropriate information from the relevant knowledge base, and generates a response that matches the user's level of knowledge.

[1303] The server receives the response from the AI ​​model, reformats it, and sends it to the device.

[1304] The terminal displays the received response on the chat screen and notifies the user.

[1305] Specific examples

[1306] User: "What is Newton's second law of motion?"

[1307] Terminal: Sends a question to the server.

[1308] Server: Passes the question to the AI ​​model.

[1309] AI model: Generates responses that explain the second law of motion and provide concrete examples.

[1310] Server: Sends the response to the device.

[1311] Terminal: Responses are displayed on the chat screen.

[1312] User: Review responses and gain insight.

[1313] Automatic question creation

[1314] If a user wants to create a question by specifying specific conditions, they enter the conditions such as grade, subject, and difficulty level into a dedicated form on the terminal and press the "Create Question" button.

[1315] The device formats the entered conditions and sends an API request to the server.

[1316] The server passes the conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[1317] Example of problem generation

[1318] User: "Please create a high school physics problem in the mechanics section."

[1319] Terminal: Sends conditions to the server.

[1320] Server: Passes the conditions to the AI ​​model.

[1321] AI model: Generates problems based on specified conditions.

[1322] Server: Sends the generated questions to the device.

[1323] Terminal: displays the questions and allows the user to answer them.

[1324] User: Answer the question.

[1325] Personalized commentary

[1326] The server takes into account the user's knowledge level and answer history and has the AI ​​model generate personalized explanations.

[1327] The AI ​​model uses past data to create the most appropriate explanation for the user.

[1328] The server receives this and sends it to the terminal.

[1329] The terminal displays explanations to help the user understand.

[1330] Examples of personalized commentary

[1331] If a user has previously solved a problem related to the law of conservation of energy, the next time they solve a mechanics problem, the AI ​​model will provide an explanation related to the law of conservation of energy.

[1332] Server: Passes conditions to the AI ​​model based on past answer history.

[1333] AI model: Generate personalized commentary.

[1334] Server: Sends the commentary to the device.

[1335] Terminal: Display explanation and notify user.

[1336] Users: Check out personalized commentary to deepen their understanding.

[1337] In this way, the system provides optimal learning support for individual learners and improves the quality of education.

[1338] The processing flow will be explained below.

[1339] Processing Question Submissions

[1340] Step 1:

[1341] If a user has a question while studying, they can open the chat screen on their device.

[1342] Step 2:

[1343] The user enters a question into the text input field and presses the "Submit" button.

[1344] Step 3:

[1345] The device takes the entered question and prepares an API request formatted in the appropriate format.

[1346] Step 4:

[1347] The device sends an HTTP request to the API endpoint to send question data to the server.

[1348] Step 5:

[1349] The server analyzes the received HTTP request and obtains the question.

[1350] Step 6:

[1351] The server passes the question to a natural language processing model and asks it to generate an appropriate response.

[1352] AI model response generation process

[1353] Step 7:

[1354] The AI ​​model analyzes the questions it receives using natural language processing technology and extracts appropriate information from the relevant knowledge base.

[1355] Step 8:

[1356] An appropriate response text is generated taking into account the user's knowledge level.

[1357] Step 9:

[1358] The AI ​​model sends the generated response text back to the server.

[1359] Response sending process

[1360] Step 10:

[1361] The server receives the response from the AI ​​model and checks the format.

[1362] Step 11:

[1363] The server prepares an API response to send the response text to the device.

[1364] Step 12:

[1365] The server sends the response data to the terminal as an HTTP response.

[1366] Step 13:

[1367] The terminal analyzes the HTTP response received from the server and obtains the response text.

[1368] Step 14:

[1369] The response text acquired by the terminal is displayed on the chat screen.

[1370] Step 15:

[1371] Users can check the AI's responses displayed on the chat screen and resolve any questions they may have.

[1372] Automatic question creation process

[1373] Step 16:

[1374] When a user wants to solve a problem that corresponds to their learning objectives, they enter the necessary conditions (e.g., grade, subject, level, etc.) into a dedicated form on the device.

[1375] Step 17:

[1376] After the user enters the conditions, he or she presses the "Create Question" button.

[1377] Step 18:

[1378] The device formats the input conditions into the appropriate format and prepares the API request.

[1379] Step 19:

[1380] The device sends an HTTP request to the API endpoint to send condition data to the server.

[1381] Server processing of question generation

[1382] Step 20:

[1383] The server analyzes the request received from the terminal and obtains the conditions for creating questions.

[1384] Step 21:

[1385] The server passes the acquired conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[1386] AI model problem generation process

[1387] Step 22:

[1388] The AI ​​model analyzes the received conditions and selects an algorithm to generate an appropriate problem.

[1389] Step 23:

[1390] A question that meets the conditions is generated, and data containing the question and answer is created.

[1391] Step 24:

[1392] The AI ​​model sends the generated problem data back to the server.

[1393] Processing problem data submissions

[1394] Step 25:

[1395] The server receives the problem data from the AI ​​model and checks the format.

[1396] Step 26:

[1397] The server prepares an API response to send the problem data to the device.

[1398] Step 27:

[1399] The server sends the problem data to the terminal as an HTTP response.

[1400] Step 28:

[1401] The terminal analyzes the HTTP response received from the server and obtains the problem data.

[1402] Step 29:

[1403] The problem data acquired by the terminal is displayed on the user interface.

[1404] Step 30:

[1405] The user checks the displayed question and begins answering it.

[1406] Personalized commentary delivery

[1407] Step 31:

[1408] The server takes into account the user's knowledge level and answer history and has the AI ​​model generate personalized explanations.

[1409] Step 32:

[1410] The AI ​​model uses past data to create the most appropriate explanation for the user.

[1411] Step 33:

[1412] The server prepares an API response to send the explanation received from the AI ​​model to the device.

[1413] Step 34:

[1414] The server sends the explanatory data to the terminal as an HTTP response.

[1415] Step 35:

[1416] The terminal analyzes the HTTP response received from the server and obtains the explanatory data.

[1417] Step 36:

[1418] The terminal displays the explanation and notifies the user.

[1419] Step 37:

[1420] Users can check the explanations and deepen their understanding of the material.

[1421] Through these steps, the system allows users to interact with AI in real time as they learn, providing an individually customized learning experience.

[1422] Example 1

[1423] 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."

[1424] Conventional learning support systems have struggled to provide users with prompt and appropriate responses to resolve their questions, and have struggled to provide personalized learning support. This has limited the ability to improve learning efficiency and deepen users' understanding. Furthermore, they lack the ability to automatically generate questions based on specific conditions, or to provide sufficient explanations tailored to the user's knowledge level and answer history.

[1425] 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.

[1426] In this invention, the server includes means for receiving text entered by a user into an information terminal, means for transmitting the received text to a central processing unit, means for the central processing unit to analyze the text and pass it to an artificial intelligence model to generate a response, means for the central processing unit to return the response generated by the artificial intelligence model to the central processing unit, and means for the central processing unit to transmit the response to the information terminal and display it to the user, thereby enabling a quick and appropriate response to a user's question.

[1427] The present invention also includes means for a user to input specific conditions to request the generation of a dataset, means for transmitting the input conditions to a central processing unit, means for the central processing unit to request the generation of a dataset from an artificial intelligence model based on the conditions, means for returning the dataset generated by the artificial intelligence model to the central processing unit, and means for the central processing unit to transmit the generated dataset to an information terminal and display it to the user, thereby enabling the automatic generation of problems according to specific conditions.

[1428] The system further includes a means for the central processing unit to cause the artificial intelligence model to generate responses and explanations taking into account the user's knowledge level, a means for the artificial intelligence model to generate personalized explanations taking into account the user's past answer history and interests, and a means for the central processing unit to send the personalized explanations to the information terminal and display them to the user, thereby enabling optimal learning support according to the individual learning needs of the user.

[1429] A "user" is an entity that uses the learning support system to input information and receive responses.

[1430] "Information terminal" means a device that receives text entered by a user and communicates with a central processing unit. Examples include personal computers, smartphones, and tablets.

[1431] A "central processing unit" is a device that analyzes data received from an information terminal, passes the data to an AI model, and sends responses from the AI ​​model to the information terminal. This mainly applies to servers.

[1432] The "artificial intelligence model" is a system that analyzes the received prompt sentence, extracts appropriate information from a related knowledge base, and generates a response or explanation. This model combines machine learning algorithms and natural language processing technology.

[1433] "Text" refers to questions or requests that users enter into an information terminal, in the form of sentences or words.

[1434] "Response" refers to a reply message generated by an AI model and sent to an information terminal via a central processing unit, which may include an answer or explanation to a question.

[1435] A "dataset" refers to a collection of questions or information that an artificial intelligence model generates based on certain conditions when a user inputs a request.

[1436] "Prompt sentence" refers to text that has been converted into a specific format by the central processing unit to input data into an AI model, such as a question or condition.

[1437] "Personalized explanations" refer to individual explanations and descriptions generated by an artificial intelligence model that take into account a user's knowledge level, past answer history, and interests.

[1438] This invention is a learning support system using AI that analyzes text entered by a user into an information terminal in real time, generates responses using an artificial intelligence model, and displays them on the information terminal. It also includes the function of automatically generating questions based on specific conditions and providing personalized explanations based on the user's knowledge level and answer history.

[1439] Hardware and software used

[1440] Information terminal: A device such as a PC, smartphone, or tablet through which a user inputs text and receives results.

[1441] Central Processing Unit: A high-performance computer such as a server that passes received text to an artificial intelligence model and returns the generated response or commentary to the information terminal.

[1442] Artificial intelligence model: A system that combines machine learning algorithms and natural language processing techniques to extract information from a knowledge base and generate appropriate responses and explanations for users.

[1443] Program processing overview

[1444] User questions submitted

[1445] If a user has a question while studying, they open the chat screen on their information terminal, enter a text question, and press the "Send" button.

[1446] Question analysis and response generation

[1447] The information terminal receives the input text, formats it, and then sends an API request to the central processing unit, which analyzes the received text and passes it to the AI ​​model, which uses the analysis results to extract appropriate information from the relevant knowledge base and generate a response.

[1448] Viewing the response

[1449] The central processing unit reformats the response from the artificial intelligence model and sends it to the information terminal, which displays the response on a chat screen and notifies the user.

[1450] example

[1451] User: "What is Newton's second law of motion?"

[1452] Information terminal: Sends text to a central processing unit.

[1453] Central Processing Unit: Passes the text to the artificial intelligence model.

[1454] Artificial intelligence model: Generates responses that explain the second law of motion and provide concrete examples.

[1455] Central processing unit: Sends the response to the information terminal.

[1456] Information terminal: Responses are displayed on the chat screen.

[1457] User: Review the response and gain insight.

[1458] Automatic question creation

[1459] When a user wants to generate a question based on specific conditions, they enter the conditions, such as grade, subject, and difficulty level, into a dedicated form on the information terminal and press the "Create Question" button. The information terminal formats the entered conditions and sends an API request to the central processing unit. The central processing unit passes the conditions to an artificial intelligence model and asks it to generate a question based on the specified conditions.

[1460] example

[1461] User: "Please create a high school physics problem in the mechanics section."

[1462] Information terminal: Sends conditions to the central processing unit.

[1463] Central Processing Unit: Passes the conditions to the artificial intelligence model.

[1464] Artificial intelligence model: Generates problems based on conditions.

[1465] Central processing unit: Sends the generated questions to the information terminal.

[1466] Information terminal: displays the questions and allows the user to answer them.

[1467] User: Answer the question.

[1468] Personalized commentary

[1469] The central processing unit takes into account the user's knowledge level and answer history and has the AI ​​model generate personalized explanations. The AI ​​model creates the most appropriate explanation for the user based on past data. The central processing unit receives this and sends it to the information terminal. The information terminal displays the explanation, helping the user to understand.

[1470] example

[1471] If a user has previously solved a problem related to the law of conservation of energy, the next time they solve a problem in the field of mechanics, the artificial intelligence model will provide an explanation related to the law of conservation of energy.

[1472] Central processing unit: Passes conditions to the artificial intelligence model based on past answer history.

[1473] Artificial intelligence model: Generate personalized commentary.

[1474] Central processing unit: Sends commentary to information terminal.

[1475] Information terminal: displays explanations and notifies the user.

[1476] Users: Check out personalized commentary to deepen their understanding.

[1477] This allows the system to provide users with prompt and appropriate learning support, improving learning efficiency.

[1478] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1479] Step 1:

[1480] The user opens the chat screen on the information terminal, enters a question, and presses the "send" button.

[1481] Input: The question text that the user types into the terminal (e.g., "What is Newton's second law of motion?")

[1482] Output: Formatted question data (including user ID, question content, and submission time)

[1483] Step 2:

[1484] The device receives input from the user, formats the question text, and then sends the formatted data to the server as an API request.

[1485] Input: User question text

[1486] Data processing: Format the input data to include the user ID, question, and submission time.

[1487] Output: API request (including question)

[1488] Step 3:

[1489] The server analyzes the API request received from the device, extracts the question data, converts it into a prompt, and then passes the prompt to the AI ​​model.

[1490] Input: Formatted question data

[1491] Data processing: Analyze question data and create prompts

[1492] Output: Prompt text (e.g., "Question: What is Newton's second law of motion? User ID: 12345")

[1493] Step 4:

[1494] Based on the prompt received from the server, the artificial intelligence model extracts appropriate information from the relevant knowledge base and generates a response to the question.

[1495] Input: prompt statement

[1496] Data processing: Extracting information from the knowledge base and generating responses

[1497] Output: Response (e.g., "Newton's second law of motion states that the motion of an object is proportional to its mass and acceleration when a force is applied to it.")

[1498] Step 5:

[1499] The server reformats the response received from the AI ​​model and sends it to the device as an API response.

[1500] Input: The response generated by the AI ​​model

[1501] Data manipulation: Reformatting the response to include the user ID and timestamp

[1502] Output: API response (formatted response data)

[1503] Step 6:

[1504] The device analyzes the API response received from the server and displays it on the chat screen so that the user can check the content.

[1505] Input: API response from the server

[1506] Data processing: Analyzes response data and converts it into a format to display on the chat screen

[1507] Output: The answer that is displayed to the user (e.g., "Newton's second law of motion states that the motion of an object is proportional to its mass and acceleration when a force is applied to it.")

[1508] Through these processing steps, the system is able to provide quick and accurate answers to users' questions.

[1509] (Application example 1)

[1510] 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."

[1511] Acquiring and analyzing real-time traffic information for autonomous vehicles is important for users, but current systems lack the ability to provide personalized support for real-time question resolution and learning. In particular, there is a demand for systems that can provide detailed explanations of traffic information and generate questions tailored to the user's knowledge level.

[1512] 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.

[1513] In this invention, the server includes means for receiving a question input by a user to a terminal, means for transmitting the received question to the server, means for the server to analyze the question and pass it to an artificial intelligence model to generate a response, means for the server to return the response generated by the artificial intelligence model to the server, means for the server to transmit the response to the terminal and display it to the user, and means for acquiring and analyzing traffic information in real time and visualizing it for the user, thereby enabling real-time resolution of user questions and personalized learning support in an autonomous vehicle.

[1514] "User" refers to a person who uses the system.

[1515] "Terminal" refers to a device through which a user accesses and operates the system.

[1516] "Server" refers to the central computer that analyzes queries and traffic information and generates responses.

[1517] "Artificial intelligence model" refers to an artificial intelligence algorithm that responds to user questions, generates questions, and provides personalized explanations.

[1518] "Means for receiving" refers to the function of the terminal to obtain information input by the user.

[1519] "Means for transmitting" refers to the function of transferring received information to a server as data.

[1520] "Means for analyzing" refers to the functionality that allows the server to understand and process the information it receives.

[1521] "Means for generating" refers to the ability of the artificial intelligence model to create a response based on the analysis results.

[1522] "Means for sending back" refers to the functionality for returning the generated response to the server.

[1523] "Means of acquiring and analyzing in real time" refers to the function of collecting, analyzing, and visualizing current traffic information.

[1524] "Visualization means" refers to the function of displaying analyzed information in a format that is easy for users to understand.

[1525] "Means for requesting the creation of a question" refers to a function that allows a user to input specific conditions and request the creation of a question.

[1526] "Means for generating personalized explanations" refers to a function that creates explanations according to the user's knowledge level and answer history.

[1527] "Means for transmitting a personalized commentary to a terminal and displaying it to a user" refers to a function for transferring the generated commentary to a user's terminal and displaying it.

[1528] This invention is a system for providing learning support and traffic information to users in autonomous vehicles. Specifically, a server uses an artificial intelligence model to generate and provide real-time responses to questions and requests entered by the user into a terminal. The system also has the function of acquiring and analyzing traffic information in real time and visualizing it for the user.

[1529] System Program Overview

[1530] This system performs the following main processes between the server and the terminal.

[1531] 1. Receiving and sending user questions.

[1532] 2. Parsing the question and generating the response.

[1533] 3. Sending and displaying the generated response.

[1534] 4. Real-time acquisition and analysis of traffic information.

[1535] 5. Visualization and provision of traffic information.

[1536] 6. Generating and delivering personalized commentary.

[1537] Hardware and software used

[1538] Hardware:

[1539] Device: A mobile information device such as a smartphone or tablet held by a user.

[1540] Server: A central computer that processes query analysis and artificial intelligence models.

[1541] software:

[1542] Artificial intelligence model: Used to generate answers to user questions and create problems. This can be done using APIs such as OpenAI.

[1543] Requests library: Used to perform HTTP requests for real-time traffic information.

[1544] Explanation of program processing

[1545] When a user inputs a question into the device, the device receives the question and sends it to the server. The server analyzes the received question and passes it to the AI ​​model to generate a response. The response generated by the AI ​​model is sent back to the server, which then sends it to the device and displays it to the user.

[1546] The server then collects and analyzes traffic information in real time. The analyzed traffic information is then sent to the user's device and visualized. In this process, the Requests library is used to collect and analyze traffic information.

[1547] The server then uses the AI ​​model to generate personalized explanations based on the user's knowledge level and past answer history. The generated explanations are then sent back to the server and displayed on the user's device. This allows users to obtain information tailored to their level of understanding in real time.

[1548] Specific examples

[1549] Specific examples of question-answering:

[1550] When a user types, "What's the current traffic situation at this intersection?", the device sends the question to the server, which passes the question to an artificial intelligence model that generates an appropriate response. The response is then sent back to the device via the server and displayed to the user.

[1551] Examples of obtaining and displaying traffic information:

[1552] The server acquires and analyzes real-time traffic information at a particular intersection. The results are sent to the device and visualized. When the user asks, "How congested is the traffic?", detailed traffic information is displayed.

[1553] Examples of personalized commentary:

[1554] If the user had previously asked the question "Please tell me how traffic lights work," then the user's next question would be "What is the current traffic situation at the intersection?", which would also provide additional commentary related to how traffic lights work.

[1555] This enables the system to provide users with real-time, high-quality information and learning assistance in an autonomous vehicle environment.

[1556] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1557] Step 1:

[1558] Receives a question entered by a user into the terminal. The user enters "What is the current traffic situation at the intersection?" into the terminal and presses the "Send" button. This inputs the question into the terminal.

[1559] Step 2:

[1560] The device formats the received question and sends it to the server as an API request. The question is formatted in the appropriate data format to be sent as an HTTP request.

[1561] Step 3:

[1562] The server analyzes the received question. The server passes the received data to a natural language processing engine to understand the intent of the question. During this process, keywords from the question are extracted and a prompt sentence is formed to be passed to the generative AI model.

[1563] Step 4:

[1564] The server passes the analysis results to the generative AI model and requests it to generate an appropriate response. The prompt sentence is "Question to the environment: What is the current traffic situation at the intersection?\nAnswer:" and is input to the generative AI model. The generative AI model extracts information from the relevant database and generates a response.

[1565] Step 5:

[1566] The generative AI model sends the generated response back to the server, which includes the specific traffic situation and related advice.

[1567] Step 6:

[1568] The server reformats the response received from the generative AI model and sends it to the device as an API response, arranging the received text data in a format that is easy for the user to understand.

[1569] Step 7:

[1570] The device displays the received response on the chat screen and notifies the user. The response "The current traffic situation at the intersection is as follows:" is displayed on the chat screen.

[1571] Step 8:

[1572] The server gets real-time traffic information from the Traffic Data API, sending a request to the appropriate API endpoint to get the current traffic situation data.

[1573] Step 9:

[1574] The server analyzes the acquired traffic data and formats it for visualization by the user, including traffic congestion status, average speed, traffic light timing, etc.

[1575] Step 10:

[1576] The device displays the analyzed traffic information sent from the server and notifies the user. It also displays traffic congestion on a map in different colors and displays the appropriate distance and time.

[1577] Step 11:

[1578] The server analyzes the user's knowledge level and past question history and requests the generative AI model to generate a personalized explanation. For example, if the user previously asked, "How does a traffic light work?", the server takes that historical data into account when generating a response.

[1579] Step 12:

[1580] The generative AI model generates a personalized explanation and sends it back to the server, including information about how the traffic light works and information relevant to the current question.

[1581] Step 13:

[1582] The server then reformats the generated commentary and sends it to the terminal, formatting the content of the commentary to make it easier for the user to understand.

[1583] Step 14:

[1584] The device displays the received personalized commentary to inform the user, including the following information: "Just to clarify how traffic lights work. The traffic lights at the current intersection are connected to a central control system and are adjusted in real time."

[1585] This series of processes allows users to receive real-time traffic information and related learning information in the environment of an autonomous vehicle.

[1586] 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.

[1587] System Overview

[1588] This invention combines an AI-based personalized learning support system with an emotion engine that recognizes the user's emotions. The system analyzes questions entered by the user into a device in real time, generates appropriate responses using an AI model, and displays them on the device. It also includes a function that generates questions based on specific conditions and provides questions and explanations based on those conditions. Furthermore, the system provides personalized explanations taking into account the user's knowledge level and past answer history, and uses the emotion engine to adjust the responses and explanations according to the user's emotions.

[1589] Program processing

[1590] User questions submitted

[1591] If a user has a question while studying, they can open the chat screen on their device, enter their question, and press the "Send" button.

[1592] The device receives the entered question, formats it, and sends an API request to the server.

[1593] The server analyzes the received question and first passes the question content to the emotion engine. The emotion engine analyzes the user's input and behavior to recognize emotions and returns the results to the server. The server then passes the question content and recognized emotion information to the AI ​​model.

[1594] AI model response generation

[1595] The AI ​​model analyzes the received question and emotional information, extracts appropriate information from the relevant knowledge base, and generates an appropriate response according to the user's knowledge level and emotions.

[1596] The server receives the response from the AI ​​model, reformats it, and sends it to the device.

[1597] The terminal displays the received response on the chat screen and notifies the user.

[1598] Specific examples

[1599] User: "What is Newton's second law of motion?"

[1600] Terminal: Sends a question to the server.

[1601] Server: Passes the question to the emotion engine and AI model.

[1602] Emotion engine: Recognizes the user's emotion as "confusion" based on the tone and wording of the question.

[1603] AI model: Considers emotions and knowledge level to provide appropriate responses ("Newton's second law of motion, simply stated...").

[1604] Server: Sends the response to the device.

[1605] Terminal: Responses are displayed on the chat screen.

[1606] User: Check the response and clarify any questions.

[1607] Automatic question creation

[1608] If a user wants to create a question by specifying specific conditions, they enter the conditions such as grade, subject, and difficulty level into a dedicated form on the terminal and press the "Create Question" button.

[1609] The device formats the entered conditions and sends an API request to the server.

[1610] The server passes the conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[1611] Example of problem generation

[1612] User: "Please create a high school physics problem in the mechanics section."

[1613] Terminal: Sends conditions to the server.

[1614] Server: Passes the conditions to the AI ​​model.

[1615] AI model: Generates problems based on specified conditions.

[1616] Server: Sends the generated questions to the device.

[1617] Terminal: displays the questions and allows the user to answer them.

[1618] User: Answer the question.

[1619] Personalized commentary

[1620] The server takes into account the user's knowledge level, answer history, and emotional data from an emotion engine, and has the AI ​​model generate personalized explanations.

[1621] The AI ​​model uses past data and emotional information to create the most appropriate explanation for the user.

[1622] The server receives this and sends it to the terminal.

[1623] The terminal displays an explanation and notifies the user.

[1624] Examples of personalized commentary

[1625] If a user has previously solved a problem related to the law of conservation of energy, the next time they solve a problem in the field of mechanics, the AI ​​model will provide an explanation related to the law of conservation of energy. If the emotion engine recognizes the user's "interest," the explanation will be more detailed and interesting.

[1626] Server: Passes conditions to the AI ​​model based on past answer history and emotional information.

[1627] AI model: Generate personalized commentary.

[1628] Server: Sends the commentary to the device.

[1629] Terminal: Display explanation and notify user.

[1630] Users: Check out personalized commentary to deepen their understanding.

[1631] In this way, by combining the emotional engine, the system provides an individually customized learning experience that takes into account the user's emotions, improving the quality of education.

[1632] The processing flow will be explained below.

[1633] User question submission process

[1634] Step 1:

[1635] If a user has a question while studying, they can open the chat screen on their device.

[1636] Step 2:

[1637] The user enters a question into the text input field and presses the "Submit" button.

[1638] Step 3:

[1639] The device takes the entered question and prepares an API request formatted in the appropriate format.

[1640] Step 4:

[1641] The device sends an HTTP request to the API endpoint to send question data to the server.

[1642] Step 5:

[1643] The server analyzes the received HTTP request and obtains the question.

[1644] Step 6:

[1645] Before the server passes the question to the natural language processing model, it first passes it to an emotion engine to identify the user's emotion.

[1646] Step 7:

[1647] The emotion engine identifies the user's emotion from the tone of the question, wording, typing speed, etc., and sends the results back to the server.

[1648] Step 8:

[1649] The server passes the question content along with the emotional information received from the emotion engine to the AI ​​model.

[1650] AI model response generation process

[1651] Step 9:

[1652] The AI ​​model analyzes the received questions and emotional information using natural language processing technology and extracts appropriate information from the relevant knowledge base.

[1653] Step 10:

[1654] It generates appropriate response text taking into account the user's knowledge level and perceived emotions.

[1655] Step 11:

[1656] The AI ​​model sends the generated response text back to the server.

[1657] Response sending process

[1658] Step 12:

[1659] The server receives the response from the AI ​​model and checks the format.

[1660] Step 13:

[1661] The server prepares an API response to send the response text to the device.

[1662] Step 14:

[1663] The server sends the response data to the terminal as an HTTP response.

[1664] Step 15:

[1665] The terminal analyzes the HTTP response received from the server and obtains the response text.

[1666] Step 16:

[1667] The response text acquired by the terminal is displayed on the chat screen.

[1668] Step 17:

[1669] Users can check the AI's responses displayed on the chat screen and resolve any questions they may have.

[1670] Automatic question creation process

[1671] Step 18:

[1672] When a user wants to solve a problem that corresponds to their learning objectives, they enter the necessary conditions (e.g., grade, subject, level, etc.) into a dedicated form on the device.

[1673] Step 19:

[1674] After the user enters the conditions, he or she presses the "Create Question" button.

[1675] Step 20:

[1676] The device formats the input conditions into the appropriate format and prepares the API request.

[1677] Step 21:

[1678] The device sends an HTTP request to the API endpoint to send condition data to the server.

[1679] Server processing of question generation

[1680] Step 22:

[1681] The server analyzes the request received from the terminal and obtains the conditions for creating questions.

[1682] Step 23:

[1683] The server passes the acquired conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[1684] AI model problem generation process

[1685] Step 24:

[1686] The AI ​​model analyzes the received conditions and selects an algorithm to generate an appropriate problem.

[1687] Step 25:

[1688] A question that meets the conditions is generated, and data containing the question and answer is created.

[1689] Step 26:

[1690] The AI ​​model sends the generated problem data back to the server.

[1691] Processing problem data submissions

[1692] Step 27:

[1693] The server receives the problem data from the AI ​​model and checks the format.

[1694] Step 28:

[1695] The server prepares an API response to send the problem data to the device.

[1696] Step 29:

[1697] The server sends the problem data to the terminal as an HTTP response.

[1698] Step 30:

[1699] The terminal analyzes the HTTP response received from the server and obtains the problem data.

[1700] Step 31:

[1701] The problem data acquired by the terminal is displayed on the user interface.

[1702] Step 32:

[1703] The user checks the displayed question and begins answering it.

[1704] Personalized commentary delivery

[1705] Step 33:

[1706] The server takes into account the user's knowledge level, answer history, and emotional data from an emotion engine, and has the AI ​​model generate personalized explanations.

[1707] Step 34:

[1708] The AI ​​model uses past data and emotional information to create the most appropriate explanation for the user.

[1709] Step 35:

[1710] The server prepares an API response to send the explanation received from the AI ​​model to the device.

[1711] Step 36:

[1712] The server sends the explanatory data to the terminal as an HTTP response.

[1713] Step 37:

[1714] The terminal analyzes the HTTP response received from the server and obtains the explanatory data.

[1715] Step 38:

[1716] The terminal displays the explanation and notifies the user.

[1717] Step 39:

[1718] Users can check the explanations and deepen their understanding of the material.

[1719] Through these steps, the system enables users to learn while interacting with AI in real time, and also provides a learning experience that takes users' emotions into consideration.

[1720] Example 2

[1721] 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."

[1722] Conventional personalized learning support systems lack consideration for users' emotions, which can negatively impact learning motivation and comprehension. Furthermore, they lack personalized explanations and questions, making it difficult to provide an optimal learning experience based on the user's knowledge level and answer history. Therefore, a system that recognizes the user's emotional state and generates appropriate responses and explanations is needed.

[1723] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a question input by a user to a terminal, means for transmitting the received question to the server, means for the server to analyze the question and pass it to an emotion engine to recognize the user's emotion and receive the result, means for the server to pass the question content and the recognized emotion information to an AI model to generate a response, means for returning the response generated by the AI ​​model to the server, and means for the server to send the response to the terminal and display it to the user. This makes it possible to provide an appropriate response or explanation according to the user's emotion.

[1724] A "user" is an individual who uses the system to advance their learning.

[1725] "Terminal" refers to the device used by the user to input learning content and receive responses from the system.

[1726] A "server" is a central computer system that receives requests from users, analyzes them, and performs the necessary processing.

[1727] An "emotion engine" is software that analyzes a user's input and behavior to identify emotions.

[1728] An "AI model" is an algorithm that uses machine learning or deep learning to analyze data and generate responses or questions.

[1729] A "question" is text data that a user inputs into the system via a terminal to express a question that the user has while studying.

[1730] A "response" is an answer to a user's question that the server generates using an AI model.

[1731] A "problem" is a learning task generated by an AI model based on conditions specified by the user.

[1732] "Explanation" is a detailed explanation or additional information provided in response to a user's question or problem.

[1733] "Personalization" is a concept that refers to optimizing the content provided based on the characteristics and history of each individual user.

[1734] MODE FOR CARRYING OUT THE INVENTION

[1735] System Overview

[1736] This invention combines an AI-based personalized learning support system with an emotion engine that recognizes the user's emotions. The system analyzes questions entered by the user into the device in real time, generates appropriate responses, and displays them on the device. It also includes a function that generates questions by entering specific conditions and provides questions and explanations based on those conditions. Furthermore, the system provides personalized explanations taking into account the user's knowledge level and past answer history, and uses the emotion engine to adjust the responses and explanations according to the user's emotions.

[1737] System configuration

[1738] The system consists of the following main components:

[1739] 1. Terminal: A device where the user inputs learning content and receives responses from the system.

[1740] 2. Server: A central computer system that receives and analyzes user requests.

[1741] 3. Emotion engine: Software that analyzes user input and behavior to identify emotions.

[1742] 4. AI Model: An algorithm that uses machine learning or deep learning to analyze data and generate responses or questions.

[1743] User questions submitted

[1744] If a user has a question during learning, they open the chat screen on their device, enter their question, and press the "Send" button. The device receives the entered question, formats it appropriately, and sends it to the server as an API request. The server analyzes the received question and passes the question content to the emotion engine. The emotion engine analyzes the user's input and behavior to recognize emotions and return the results to the server. The server then passes the question content and recognized emotion information to the AI ​​model.

[1745] AI model response generation

[1746] The AI ​​model analyzes the received question and emotional information, extracts appropriate information from the relevant knowledge base, and generates an appropriate response based on the user's knowledge level and emotional state. The server receives the response from the AI ​​model, reformats it, and sends it to the device. The device displays the received response on the chat screen and notifies the user.

[1747] Specific examples

[1748] If a user types, "Tell me about Newton's second law of motion," the device sends the question to the server. The server passes the question to the emotion engine and AI model. The emotion engine recognizes the user's emotion as "confusion" based on the tone and wording of the question. The AI ​​model generates an appropriate response taking into account the emotion and knowledge level. Specifically, it generates a response such as, "Newton's second law of motion states that the acceleration of an object is proportional to the force and inversely proportional to the mass." The server sends the response to the device, which displays it on the chat screen.

[1749] Automatic question creation

[1750] When a user wants to generate a question based on specific conditions, they enter the conditions, such as grade, subject, and difficulty level, into a dedicated form on the device and press the "Create Question" button. The device formats the entered conditions and sends an API request to the server. The server passes the conditions to the AI ​​model and asks it to generate a question based on the specified conditions.

[1751] Example of problem generation

[1752] The user enters "Please create a problem in the field of mechanics for high school physics" and sends the conditions to the device. The server passes the conditions to the AI ​​model. The AI ​​model generates a problem based on the specified conditions, such as "Find the acceleration a when force F is applied to an object with mass m." The server sends the generated problem to the device, which displays the problem so the user can answer it.

[1753] Personalized commentary

[1754] The server takes into account the user's knowledge level, past answer history, and emotional data from the emotion engine, and has the AI ​​model generate a personalized explanation. The AI ​​model creates the optimal explanation for the user based on past data and emotional information. The server receives this and sends it to the device. The device displays the explanation and notifies the user.

[1755] Examples of personalized commentary

[1756] For example, if a user has previously solved a problem related to the law of conservation of energy, the next time they solve a problem in the field of mechanics, the AI ​​model will provide an explanation related to the law of conservation of energy. If the emotion engine recognizes the user's "interest," the explanation will be more detailed and interesting. The server passes conditions to the AI ​​model based on past answer history and emotion information, and the AI ​​model generates a personalized explanation. The server sends the explanation to the device, which then displays the explanation and notifies the user.

[1757] As described above, by combining the emotion engine, the system provides an individually customized learning experience that takes into consideration the user's emotions, thereby improving the quality of education.

[1758] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1759] User questions submitted

[1760] Step 1:

[1761] The user enters the question they are studying into the terminal and presses the "Submit" button.

[1762] Input: User question text (e.g., "What is Newton's second law of motion?")

[1763] Output: A transmission command is output to the terminal

[1764] Step 2:

[1765] The device formats the entered question and sends an API request to the server.

[1766] Input: User question text

[1767] Data processing / calculation: Formatting question text into JSON format

[1768] Output: Formatted question data (JSON format)

[1769] Step 3:

[1770] The server receives the question, analyzes it, and passes it to the emotion engine.

[1771] Input: Formatted question data (JSON format)

[1772] Data processing / calculation: Extracting text from question data and formatting it appropriately to be passed to the emotion engine

[1773] Output: Data to send to the emotion engine

[1774] Step 4:

[1775] The emotion engine analyzes the question text, recognizes the user's emotion, and returns the results to the server.

[1776] Input: Question text from the server

[1777] Data processing / computation: Recognizing emotions using natural language processing and sentiment analysis algorithms (e.g., "confused")

[1778] Output: Recognized emotion data

[1779] Step 5:

[1780] The server passes the question content and recognized emotional information to the AI ​​model.

[1781] Input: Question text and sentiment data

[1782] Data processing / calculation: Combining question text and sentiment data to create a format suitable for the AI ​​model

[1783] Output: Data to send to the AI ​​model

[1784] Step 6:

[1785] The AI ​​model generates a response based on the received question and emotional information and returns it to the server.

[1786] Input: Question text and sentiment data

[1787] Data processing / calculation: Searches for appropriate information from a related knowledge base based on the question and emotional information, and generates a response that matches the user's knowledge level.

[1788] Output: Generated response data

[1789] Step 7:

[1790] The server receives the response from the AI ​​model, reformats it, and sends it to the device.

[1791] Input: Generated response data

[1792] Data processing / calculation: Formatting response data for display to the user

[1793] Output: Formatted response data to send to the terminal

[1794] Step 8:

[1795] The response received by the terminal is displayed on the chat screen and notified to the user.

[1796] Input: Formatted response data

[1797] Data processing / calculation: Formatting response data into a layout for display on the chat screen

[1798] Output: The response displayed on the screen

[1799] Automatic question creation

[1800] Step 1:

[1801] The user inputs the conditions for creating a question and presses the "Create Question" button.

[1802] Input: Grade, subject, difficulty level, etc. (e.g. "High school physics, mechanics, intermediate")

[1803] Output: A transmission command is output to the terminal

[1804] Step 2:

[1805] The device formats the entered conditions and sends an API request to the server.

[1806] Input: User-entered criteria

[1807] Data processing / calculation: Format conditions into JSON format

[1808] Output: Formatted condition data (JSON format)

[1809] Step 3:

[1810] The server receives the conditions, analyzes them, and asks the AI ​​model to generate a problem.

[1811] Input: Formatted condition data (JSON format)

[1812] Data processing / calculation: Format the condition data into a format that can be used to request the AI ​​model to generate questions.

[1813] Output: Data to send to the AI ​​model

[1814] Step 4:

[1815] The AI ​​model generates questions based on the specified conditions and returns them to the server.

[1816] Input: Specified condition data

[1817] Data processing / calculation: Generate problems from the relevant knowledge base based on condition data (e.g., "Find the acceleration a when force F is applied to an object with mass m").

[1818] Output: Generated problem data

[1819] Step 5:

[1820] The server sends the generated questions to the device.

[1821] Input: Generated problem data

[1822] Data processing / calculation: Formatting the problem data for display to the user

[1823] Output: Formatted question data to send to the terminal

[1824] Step 6:

[1825] The terminal displays the received questions and allows the user to answer them.

[1826] Input: Formatted question data

[1827] Data processing / calculation: Formatting the problem data into a layout for display

[1828] Output: The problem as it appears on the screen

[1829] Personalized commentary

[1830] Step 1:

[1831] The server collects the user's knowledge level, past answer history, and emotional data, and passes them on to the AI ​​model.

[1832] Input: User knowledge level, past answer history, emotional data

[1833] Data processing / calculation: Format the collected data to generate the most appropriate explanation for the user.

[1834] Output: Data to send to the AI ​​model

[1835] Step 2:

[1836] The AI ​​model generates personalized commentary based on the collected data and returns it to the server.

[1837] Input: knowledge level data, past answer history, emotion data

[1838] Data processing / calculation: Generate optimal explanations from the relevant knowledge base based on the collected data

[1839] Output: Generated commentary data

[1840] Step 3:

[1841] The server sends the personalized commentary to the device.

[1842] Input: Generated commentary data

[1843] Data processing / calculation: Formatting explanatory data for display to the user

[1844] Output: Formatted commentary data to send to the terminal

[1845] Step 4:

[1846] The terminal displays the received explanation and notifies the user.

[1847] Input: Formatted commentary data

[1848] Data processing / calculation: Formatting the explanatory data into a layout for display

[1849] Output: Explanation displayed on the screen

[1850] (Application example 2)

[1851] 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."

[1852] Conventional individual learning support systems have had the problem of being unable to respond flexibly to users' emotions and individual needs. In particular, when providing customer service support in brick-and-mortar stores, it is difficult for store staff to consistently grasp customers' emotions and respond optimally based on them. This can lead to a decline in customer satisfaction.

[1853] 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 a means for transmitting a question entered by a user to an emotion analysis engine to acquire emotion information, a means for passing the question and emotion information to an AI model to generate an appropriate response, and a means for transmitting the response generated by the AI ​​model to a terminal for display. This enables store clerks in physical stores to consistently provide optimal responses to customers, taking into consideration the user's emotions.

[1854] - "Terminal" means an electronic device that allows a user to input or receive information.

[1855] A "question" is information that the user wants to know or confirm, entered in text format.

[1856] An "emotion analysis engine" is a system that analyzes a user's emotions from input text and outputs the results.

[1857] "Emotion information" is data about the user's emotional state obtained by the emotion analysis engine.

[1858] A "server" is a central computer system and device that processes and analyzes received data.

[1859] An "AI model" is an artificial intelligence algorithm that analyzes user input and generates optimal responses and explanations.

[1860] A "response" is information generated by an AI model in response to a user's question.

[1861] The "knowledge level" is information indicating the level of knowledge that the user has, and is calculated from the past answer history.

[1862] The "answer history" is a record of the answers that the user has given up to now.

[1863] A "personalized commentary" is a commentary content that is individually customized taking into account the user's knowledge level and emotional information.

[1864] This invention is a system that analyzes a user's emotional information and provides individually customized responses, particularly for the purpose of supporting customer service in brick-and-mortar stores, helping store staff to effectively respond to customers.

[1865] The central part of the system is the server, which includes the following means:

[1866] 1. A means of obtaining emotional information from user input using an emotion analysis engine.

[1867] 2. A means of analyzing the question and sentiment information and passing it to an AI model to generate the optimal response.

[1868] 3. A means of sending the responses generated by the AI ​​model to the device and displaying them to the user.

[1869] Specifically, the following processing is performed.

[1870] First, a store clerk inputs a customer's question into the terminal, which then sends the question to the server. The server passes the question to a sentiment analysis engine, which analyzes the user's emotions. The acquired emotional information is then sent to an AI model, which generates an optimal response based on the question and emotional information. The server then reformats this response and sends it to the terminal, where the store clerk displays it to the customer and takes appropriate action.

[1871] For example, if a customer asks, "What material is this shirt made of?", the following prompt sentence is generated:

[1872] "What material is this shirt made of?" (Emotion: Interest, Probability: 0.85)

[1873] This allows the server to utilize its emotion analysis engine and AI model to quickly provide the optimal response based on the user's emotions.

[1874] The software and hardware used include:

[1875] Sentiment analysis engine: A software system for analyzing text.

[1876] AI model: A generative AI model that generates responses based on questions and sentiment information.

[1877] Device: The smartphone or tablet device that users use for input and display.

[1878] Server: A central system that receives, processes, and transmits data.

[1879] This makes it possible to provide effective customer service that is in line with the user's emotions, even in physical stores.

[1880] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1881] Step 1:

[1882] The store clerk inputs the customer's question into the terminal and presses the send button, which sends the question to the server.

[1883] Input: The question entered by the store clerk into the terminal

[1884] Output: The question is sent to the server

[1885] Step 2:

[1886] The server passes the received question to a sentiment analysis engine to obtain the user's sentiment information. The sentiment analysis engine analyzes the tone and wording of the question to generate sentiment information.

[1887] Input: Received question

[1888] Output: Emotion information (e.g., interest, accuracy: 0.85)

[1889] Step 3:

[1890] The server passes the question and emotional information to the AI ​​model and asks it to generate a response. The AI ​​model generates the optimal answer based on the question content and emotional information.

[1891] Input: Question, emotion information

[1892] Output: Best response

[1893] Step 4:

[1894] The server receives the response sent back by the AI ​​model, reformats it, and sends it to the device, which involves converting the response into an appropriate format for display.

[1895] Input: Best response

[1896] Output: Reformatted response

[1897] Step 5:

[1898] The terminal displays the received response and notifies the store clerk, who then relays the displayed response to the customer.

[1899] Input: Reformatted response

[1900] Output: Response displayed to the store clerk

[1901] Step 6:

[1902] The store clerk will check the response and provide the customer with an appropriate answer, allowing the store to respond to the customer's question quickly and accurately.

[1903] Input: Displayed response

[1904] Output: Response to the customer

[1905] This series of processes enables store staff to take into consideration the customer's feelings and provide optimal customer service.

[1906] 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.

[1907] 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.

[1908] 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.

[1909] [Fourth embodiment]

[1910] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1911] 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.

[1912] 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).

[1913] 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.

[1914] 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.

[1915] 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).

[1916] 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.

[1917] 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.

[1918] 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.

[1919] 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.

[1920] 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.

[1921] 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.

[1922] 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."

[1923] System Overview

[1924] This invention is a learning support system using AI that analyzes questions entered by users into a terminal in real time, generates responses using an AI model, and displays them on the terminal. It also includes a function that allows users to input specific conditions to request the generation of questions, and the AI ​​model generates and displays questions based on those conditions. Furthermore, the server also provides personalized explanations taking into account the user's knowledge level and past answer history.

[1925] Program processing

[1926] User questions submitted

[1927] If a user has a question while studying, they can open the chat screen on their device, enter their question, and press the "Send" button.

[1928] The device receives the entered question, formats it, and sends an API request to the server.

[1929] The server analyzes the received question and passes it to the AI ​​model.

[1930] AI model response generation

[1931] The AI ​​model analyzes the incoming question, extracts appropriate information from the relevant knowledge base, and generates a response that matches the user's level of knowledge.

[1932] The server receives the response from the AI ​​model, reformats it, and sends it to the device.

[1933] The terminal displays the received response on the chat screen and notifies the user.

[1934] Specific examples

[1935] User: "What is Newton's second law of motion?"

[1936] Terminal: Sends a question to the server.

[1937] Server: Passes the question to the AI ​​model.

[1938] AI model: Generates responses that explain the second law of motion and provide concrete examples.

[1939] Server: Sends the response to the device.

[1940] Terminal: Responses are displayed on the chat screen.

[1941] User: Review responses and gain insight.

[1942] Automatic question creation

[1943] If a user wants to create a question by specifying specific conditions, they enter the conditions such as grade, subject, and difficulty level into a dedicated form on the terminal and press the "Create Question" button.

[1944] The device formats the entered conditions and sends an API request to the server.

[1945] The server passes the conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[1946] Example of problem generation

[1947] User: "Please create a high school physics problem in the mechanics section."

[1948] Terminal: Sends conditions to the server.

[1949] Server: Passes the conditions to the AI ​​model.

[1950] AI model: Generates problems based on specified conditions.

[1951] Server: Sends the generated questions to the device.

[1952] Terminal: displays the questions and allows the user to answer them.

[1953] User: Answer the question.

[1954] Personalized commentary

[1955] The server takes into account the user's knowledge level and answer history and has the AI ​​model generate personalized explanations.

[1956] The AI ​​model uses past data to create the most appropriate explanation for the user.

[1957] The server receives this and sends it to the terminal.

[1958] The terminal displays explanations to help the user understand.

[1959] Examples of personalized commentary

[1960] If a user has previously solved a problem related to the law of conservation of energy, the next time they solve a mechanics problem, the AI ​​model will provide an explanation related to the law of conservation of energy.

[1961] Server: Passes conditions to the AI ​​model based on past answer history.

[1962] AI model: Generate personalized commentary.

[1963] Server: Sends the commentary to the device.

[1964] Terminal: Display explanation and notify user.

[1965] Users: Check out personalized commentary to deepen their understanding.

[1966] In this way, the system provides optimal learning support for individual learners and improves the quality of education.

[1967] The processing flow will be explained below.

[1968] Processing Question Submissions

[1969] Step 1:

[1970] If a user has a question while studying, they can open the chat screen on their device.

[1971] Step 2:

[1972] The user enters a question into the text input field and presses the "Submit" button.

[1973] Step 3:

[1974] The device takes the entered question and prepares an API request formatted in the appropriate format.

[1975] Step 4:

[1976] The device sends an HTTP request to the API endpoint to send question data to the server.

[1977] Step 5:

[1978] The server analyzes the received HTTP request and obtains the question.

[1979] Step 6:

[1980] The server passes the question to a natural language processing model and asks it to generate an appropriate response.

[1981] AI model response generation process

[1982] Step 7:

[1983] The AI ​​model analyzes the questions it receives using natural language processing technology and extracts appropriate information from the relevant knowledge base.

[1984] Step 8:

[1985] An appropriate response text is generated taking into account the user's knowledge level.

[1986] Step 9:

[1987] The AI ​​model sends the generated response text back to the server.

[1988] Response sending process

[1989] Step 10:

[1990] The server receives the response from the AI ​​model and checks the format.

[1991] Step 11:

[1992] The server prepares an API response to send the response text to the device.

[1993] Step 12:

[1994] The server sends the response data to the terminal as an HTTP response.

[1995] Step 13:

[1996] The terminal analyzes the HTTP response received from the server and obtains the response text.

[1997] Step 14:

[1998] The response text acquired by the terminal is displayed on the chat screen.

[1999] Step 15:

[2000] Users can check the AI's responses displayed on the chat screen and resolve any questions they may have.

[2001] Automatic question creation process

[2002] Step 16:

[2003] When a user wants to solve a problem that corresponds to their learning objectives, they enter the necessary conditions (e.g., grade, subject, level, etc.) into a dedicated form on the device.

[2004] Step 17:

[2005] After the user enters the conditions, he or she presses the "Create Question" button.

[2006] Step 18:

[2007] The device formats the input conditions into the appropriate format and prepares the API request.

[2008] Step 19:

[2009] The device sends an HTTP request to the API endpoint to send condition data to the server.

[2010] Server processing of question generation

[2011] Step 20:

[2012] The server analyzes the request received from the terminal and obtains the conditions for creating questions.

[2013] Step 21:

[2014] The server passes the acquired conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[2015] AI model problem generation process

[2016] Step 22:

[2017] The AI ​​model analyzes the received conditions and selects an algorithm to generate an appropriate problem.

[2018] Step 23:

[2019] A question that meets the conditions is generated, and data containing the question and answer is created.

[2020] Step 24:

[2021] The AI ​​model sends the generated problem data back to the server.

[2022] Processing problem data submissions

[2023] Step 25:

[2024] The server receives the problem data from the AI ​​model and checks the format.

[2025] Step 26:

[2026] The server prepares an API response to send the problem data to the device.

[2027] Step 27:

[2028] The server sends the problem data to the terminal as an HTTP response.

[2029] Step 28:

[2030] The terminal analyzes the HTTP response received from the server and obtains the problem data.

[2031] Step 29:

[2032] The problem data acquired by the terminal is displayed on the user interface.

[2033] Step 30:

[2034] The user checks the displayed question and begins answering it.

[2035] Personalized commentary delivery

[2036] Step 31:

[2037] The server takes into account the user's knowledge level and answer history and has the AI ​​model generate personalized explanations.

[2038] Step 32:

[2039] The AI ​​model uses past data to create the most appropriate explanation for the user.

[2040] Step 33:

[2041] The server prepares an API response to send the explanation received from the AI ​​model to the device.

[2042] Step 34:

[2043] The server sends the explanatory data to the terminal as an HTTP response.

[2044] Step 35:

[2045] The terminal analyzes the HTTP response received from the server and obtains the explanatory data.

[2046] Step 36:

[2047] The terminal displays the explanation and notifies the user.

[2048] Step 37:

[2049] Users can check the explanations and deepen their understanding of the material.

[2050] Through these steps, the system allows users to interact with AI in real time as they learn, providing an individually customized learning experience.

[2051] Example 1

[2052] 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."

[2053] Conventional learning support systems have struggled to provide users with prompt and appropriate responses to resolve their questions, and have struggled to provide personalized learning support. This has limited the ability to improve learning efficiency and deepen users' understanding. Furthermore, they lack the ability to automatically generate questions based on specific conditions, or to provide sufficient explanations tailored to the user's knowledge level and answer history.

[2054] 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.

[2055] In this invention, the server includes means for receiving text entered by a user into an information terminal, means for transmitting the received text to a central processing unit, means for the central processing unit to analyze the text and pass it to an artificial intelligence model to generate a response, means for the central processing unit to return the response generated by the artificial intelligence model to the central processing unit, and means for the central processing unit to transmit the response to the information terminal and display it to the user, thereby enabling a quick and appropriate response to a user's question.

[2056] The present invention also includes means for a user to input specific conditions to request the generation of a dataset, means for transmitting the input conditions to a central processing unit, means for the central processing unit to request the generation of a dataset from an artificial intelligence model based on the conditions, means for returning the dataset generated by the artificial intelligence model to the central processing unit, and means for the central processing unit to transmit the generated dataset to an information terminal and display it to the user, thereby enabling the automatic generation of problems according to specific conditions.

[2057] The system further includes a means for the central processing unit to cause the artificial intelligence model to generate responses and explanations taking into account the user's knowledge level, a means for the artificial intelligence model to generate personalized explanations taking into account the user's past answer history and interests, and a means for the central processing unit to send the personalized explanations to the information terminal and display them to the user, thereby enabling optimal learning support according to the individual learning needs of the user.

[2058] A "user" is an entity that uses the learning support system to input information and receive responses.

[2059] "Information terminal" means a device that receives text entered by a user and communicates with a central processing unit. Examples include personal computers, smartphones, and tablets.

[2060] A "central processing unit" is a device that analyzes data received from an information terminal, passes the data to an AI model, and sends responses from the AI ​​model to the information terminal. This mainly applies to servers.

[2061] The "artificial intelligence model" is a system that analyzes the received prompt sentence, extracts appropriate information from a related knowledge base, and generates a response or explanation. This model combines machine learning algorithms and natural language processing technology.

[2062] "Text" refers to questions or requests that users enter into an information terminal, in the form of sentences or words.

[2063] "Response" refers to a reply message generated by an AI model and sent to an information terminal via a central processing unit, which may include an answer or explanation to a question.

[2064] A "dataset" refers to a collection of questions or information that an artificial intelligence model generates based on certain conditions when a user inputs a request.

[2065] "Prompt sentence" refers to text that has been converted into a specific format by the central processing unit to input data into an AI model, such as a question or condition.

[2066] "Personalized explanations" refer to individual explanations and descriptions generated by an artificial intelligence model that take into account a user's knowledge level, past answer history, and interests.

[2067] This invention is a learning support system using AI that analyzes text entered by a user into an information terminal in real time, generates responses using an artificial intelligence model, and displays them on the information terminal. It also includes the function of automatically generating questions based on specific conditions and providing personalized explanations based on the user's knowledge level and answer history.

[2068] Hardware and software used

[2069] Information terminal: A device such as a PC, smartphone, or tablet through which a user inputs text and receives results.

[2070] Central Processing Unit: A high-performance computer such as a server that passes received text to an artificial intelligence model and returns the generated response or commentary to the information terminal.

[2071] Artificial intelligence model: A system that combines machine learning algorithms and natural language processing techniques to extract information from a knowledge base and generate appropriate responses and explanations for users.

[2072] Program processing overview

[2073] User questions submitted

[2074] If a user has a question while studying, they open the chat screen on their information terminal, enter a text question, and press the "Send" button.

[2075] Question analysis and response generation

[2076] The information terminal receives the input text, formats it, and then sends an API request to the central processing unit, which analyzes the received text and passes it to the AI ​​model, which uses the analysis results to extract appropriate information from the relevant knowledge base and generate a response.

[2077] Viewing the response

[2078] The central processing unit reformats the response from the artificial intelligence model and sends it to the information terminal, which displays the response on a chat screen and notifies the user.

[2079] example

[2080] User: "What is Newton's second law of motion?"

[2081] Information terminal: Sends text to a central processing unit.

[2082] Central Processing Unit: Passes the text to the artificial intelligence model.

[2083] Artificial intelligence model: Generates responses that explain the second law of motion and provide concrete examples.

[2084] Central processing unit: Sends the response to the information terminal.

[2085] Information terminal: Responses are displayed on the chat screen.

[2086] User: Review the response and gain insight.

[2087] Automatic question creation

[2088] When a user wants to generate a question based on specific conditions, they enter the conditions, such as grade, subject, and difficulty level, into a dedicated form on the information terminal and press the "Create Question" button. The information terminal formats the entered conditions and sends an API request to the central processing unit. The central processing unit passes the conditions to an artificial intelligence model and asks it to generate a question based on the specified conditions.

[2089] example

[2090] User: "Please create a high school physics problem in the mechanics section."

[2091] Information terminal: Sends conditions to the central processing unit.

[2092] Central Processing Unit: Passes the conditions to the artificial intelligence model.

[2093] Artificial intelligence model: Generates problems based on conditions.

[2094] Central processing unit: Sends the generated questions to the information terminal.

[2095] Information terminal: displays the questions and allows the user to answer them.

[2096] User: Answer the question.

[2097] Personalized commentary

[2098] The central processing unit takes into account the user's knowledge level and answer history and has the AI ​​model generate personalized explanations. The AI ​​model creates the most appropriate explanation for the user based on past data. The central processing unit receives this and sends it to the information terminal. The information terminal displays the explanation, helping the user to understand.

[2099] example

[2100] If a user has previously solved a problem related to the law of conservation of energy, the next time they solve a problem in the field of mechanics, the artificial intelligence model will provide an explanation related to the law of conservation of energy.

[2101] Central processing unit: Passes conditions to the artificial intelligence model based on past answer history.

[2102] Artificial intelligence model: Generate personalized commentary.

[2103] Central processing unit: Sends commentary to information terminal.

[2104] Information terminal: displays explanations and notifies the user.

[2105] Users: Check out personalized commentary to deepen their understanding.

[2106] This allows the system to provide users with prompt and appropriate learning support, improving learning efficiency.

[2107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2108] Step 1:

[2109] The user opens the chat screen on the information terminal, enters a question, and presses the "send" button.

[2110] Input: The question text that the user types into the terminal (e.g., "What is Newton's second law of motion?")

[2111] Output: Formatted question data (including user ID, question content, and submission time)

[2112] Step 2:

[2113] The device receives input from the user, formats the question text, and then sends the formatted data to the server as an API request.

[2114] Input: User question text

[2115] Data processing: Format the input data to include the user ID, question, and submission time.

[2116] Output: API request (including question)

[2117] Step 3:

[2118] The server analyzes the API request received from the device, extracts the question data, converts it into a prompt, and then passes the prompt to the AI ​​model.

[2119] Input: Formatted question data

[2120] Data processing: Analyze question data and create prompts

[2121] Output: Prompt text (e.g., "Question: What is Newton's second law of motion? User ID: 12345")

[2122] Step 4:

[2123] Based on the prompt received from the server, the artificial intelligence model extracts appropriate information from the relevant knowledge base and generates a response to the question.

[2124] Input: prompt statement

[2125] Data processing: Extracting information from the knowledge base and generating responses

[2126] Output: Response (e.g., "Newton's second law of motion states that the motion of an object is proportional to its mass and acceleration when a force is applied to it.")

[2127] Step 5:

[2128] The server reformats the response received from the AI ​​model and sends it to the device as an API response.

[2129] Input: The response generated by the AI ​​model

[2130] Data manipulation: Reformatting the response to include the user ID and timestamp

[2131] Output: API response (formatted response data)

[2132] Step 6:

[2133] The device analyzes the API response received from the server and displays it on the chat screen so that the user can check the content.

[2134] Input: API response from the server

[2135] Data processing: Analyzes response data and converts it into a format to display on the chat screen

[2136] Output: The answer that is displayed to the user (e.g., "Newton's second law of motion states that the motion of an object is proportional to its mass and acceleration when a force is applied to it.")

[2137] Through these processing steps, the system is able to provide quick and accurate answers to users' questions.

[2138] (Application example 1)

[2139] 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."

[2140] Acquiring and analyzing real-time traffic information for autonomous vehicles is important for users, but current systems lack the ability to provide personalized support for real-time question resolution and learning. In particular, there is a demand for systems that can provide detailed explanations of traffic information and generate questions tailored to the user's knowledge level.

[2141] 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.

[2142] In this invention, the server includes means for receiving a question input by a user to a terminal, means for transmitting the received question to the server, means for the server to analyze the question and pass it to an artificial intelligence model to generate a response, means for the server to return the response generated by the artificial intelligence model to the server, means for the server to transmit the response to the terminal and display it to the user, and means for acquiring and analyzing traffic information in real time and visualizing it for the user, thereby enabling real-time resolution of user questions and personalized learning support in an autonomous vehicle.

[2143] "User" refers to a person who uses the system.

[2144] "Terminal" refers to a device through which a user accesses and operates the system.

[2145] "Server" refers to the central computer that analyzes queries and traffic information and generates responses.

[2146] "Artificial intelligence model" refers to an artificial intelligence algorithm that responds to user questions, generates questions, and provides personalized explanations.

[2147] "Means for receiving" refers to the function of the terminal to obtain information input by the user.

[2148] "Means for transmitting" refers to the function of transferring received information to a server as data.

[2149] "Means for analyzing" refers to the functionality that allows the server to understand and process the information it receives.

[2150] "Means for generating" refers to the ability of the artificial intelligence model to create a response based on the analysis results.

[2151] "Means for sending back" refers to the functionality for returning the generated response to the server.

[2152] "Means of acquiring and analyzing in real time" refers to the function of collecting, analyzing, and visualizing current traffic information.

[2153] "Visualization means" refers to the function of displaying analyzed information in a format that is easy for users to understand.

[2154] "Means for requesting the creation of a question" refers to a function that allows a user to input specific conditions and request the creation of a question.

[2155] "Means for generating personalized explanations" refers to a function that creates explanations according to the user's knowledge level and answer history.

[2156] "Means for transmitting a personalized commentary to a terminal and displaying it to a user" refers to a function for transferring the generated commentary to a user's terminal and displaying it.

[2157] This invention is a system for providing learning support and traffic information to users in autonomous vehicles. Specifically, a server uses an artificial intelligence model to generate and provide real-time responses to questions and requests entered by the user into a terminal. The system also has the function of acquiring and analyzing traffic information in real time and visualizing it for the user.

[2158] System Program Overview

[2159] This system performs the following main processes between the server and the terminal.

[2160] 1. Receiving and sending user questions.

[2161] 2. Parsing the question and generating the response.

[2162] 3. Sending and displaying the generated response.

[2163] 4. Real-time acquisition and analysis of traffic information.

[2164] 5. Visualization and provision of traffic information.

[2165] 6. Generating and delivering personalized commentary.

[2166] Hardware and software used

[2167] Hardware:

[2168] Device: A mobile information device such as a smartphone or tablet held by a user.

[2169] Server: A central computer that processes query analysis and artificial intelligence models.

[2170] software:

[2171] Artificial intelligence model: Used to generate answers to user questions and create problems. This can be done using APIs such as OpenAI.

[2172] Requests library: Used to perform HTTP requests for real-time traffic information.

[2173] Explanation of program processing

[2174] When a user inputs a question into the device, the device receives the question and sends it to the server. The server analyzes the received question and passes it to the AI ​​model to generate a response. The response generated by the AI ​​model is sent back to the server, which then sends it to the device and displays it to the user.

[2175] The server then collects and analyzes traffic information in real time. The analyzed traffic information is then sent to the user's device and visualized. In this process, the Requests library is used to collect and analyze traffic information.

[2176] The server then uses the AI ​​model to generate personalized explanations based on the user's knowledge level and past answer history. The generated explanations are then sent back to the server and displayed on the user's device. This allows users to obtain information tailored to their level of understanding in real time.

[2177] Specific examples

[2178] Specific examples of question-answering:

[2179] When a user types, "What's the current traffic situation at this intersection?", the device sends the question to the server, which passes the question to an artificial intelligence model that generates an appropriate response. The response is then sent back to the device via the server and displayed to the user.

[2180] Examples of obtaining and displaying traffic information:

[2181] The server acquires and analyzes real-time traffic information at a particular intersection. The results are sent to the device and visualized. When the user asks, "How congested is the traffic?", detailed traffic information is displayed.

[2182] Examples of personalized commentary:

[2183] If the user had previously asked the question "Please tell me how traffic lights work," then the user's next question would be "What is the current traffic situation at the intersection?", which would also provide additional commentary related to how traffic lights work.

[2184] This enables the system to provide users with real-time, high-quality information and learning assistance in an autonomous vehicle environment.

[2185] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2186] Step 1:

[2187] Receives a question entered by a user into the terminal. The user enters "What is the current traffic situation at the intersection?" into the terminal and presses the "Send" button. This inputs the question into the terminal.

[2188] Step 2:

[2189] The device formats the received question and sends it to the server as an API request. The question is formatted in the appropriate data format to be sent as an HTTP request.

[2190] Step 3:

[2191] The server analyzes the received question. The server passes the received data to a natural language processing engine to understand the intent of the question. During this process, keywords from the question are extracted and a prompt sentence is formed to be passed to the generative AI model.

[2192] Step 4:

[2193] The server passes the analysis results to the generative AI model and requests it to generate an appropriate response. The prompt sentence is "Question to the environment: What is the current traffic situation at the intersection?\nAnswer:" and is input to the generative AI model. The generative AI model extracts information from the relevant database and generates a response.

[2194] Step 5:

[2195] The generative AI model sends the generated response back to the server, which includes the specific traffic situation and related advice.

[2196] Step 6:

[2197] The server reformats the response received from the generative AI model and sends it to the device as an API response, arranging the received text data in a format that is easy for the user to understand.

[2198] Step 7:

[2199] The device displays the received response on the chat screen and notifies the user. The response "The current traffic situation at the intersection is as follows:" is displayed on the chat screen.

[2200] Step 8:

[2201] The server gets real-time traffic information from the Traffic Data API, sending a request to the appropriate API endpoint to get the current traffic situation data.

[2202] Step 9:

[2203] The server analyzes the acquired traffic data and formats it for visualization by the user, including traffic congestion status, average speed, traffic light timing, etc.

[2204] Step 10:

[2205] The device displays the analyzed traffic information sent from the server and notifies the user. It also displays traffic congestion on a map in different colors and displays the appropriate distance and time.

[2206] Step 11:

[2207] The server analyzes the user's knowledge level and past question history and requests the generative AI model to generate a personalized explanation. For example, if the user previously asked, "How does a traffic light work?", the server takes that historical data into account when generating a response.

[2208] Step 12:

[2209] The generative AI model generates a personalized explanation and sends it back to the server, including information about how the traffic light works and information relevant to the current question.

[2210] Step 13:

[2211] The server then reformats the generated commentary and sends it to the terminal, formatting the content of the commentary to make it easier for the user to understand.

[2212] Step 14:

[2213] The device displays the received personalized commentary to inform the user, including the following information: "Just to clarify how traffic lights work. The traffic lights at the current intersection are connected to a central control system and are adjusted in real time."

[2214] This series of processes allows users to receive real-time traffic information and related learning information in the environment of an autonomous vehicle.

[2215] 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.

[2216] System Overview

[2217] This invention combines an AI-based personalized learning support system with an emotion engine that recognizes the user's emotions. The system analyzes questions entered by the user into a device in real time, generates appropriate responses using an AI model, and displays them on the device. It also includes a function that generates questions based on specific conditions and provides questions and explanations based on those conditions. Furthermore, the system provides personalized explanations taking into account the user's knowledge level and past answer history, and uses the emotion engine to adjust the responses and explanations according to the user's emotions.

[2218] Program processing

[2219] User questions submitted

[2220] If a user has a question while studying, they can open the chat screen on their device, enter their question, and press the "Send" button.

[2221] The device receives the entered question, formats it, and sends an API request to the server.

[2222] The server analyzes the received question and first passes the question content to the emotion engine. The emotion engine analyzes the user's input and behavior to recognize emotions and returns the results to the server. The server then passes the question content and recognized emotion information to the AI ​​model.

[2223] AI model response generation

[2224] The AI ​​model analyzes the received question and emotional information, extracts appropriate information from the relevant knowledge base, and generates an appropriate response according to the user's knowledge level and emotions.

[2225] The server receives the response from the AI ​​model, reformats it, and sends it to the device.

[2226] The terminal displays the received response on the chat screen and notifies the user.

[2227] Specific examples

[2228] User: "What is Newton's second law of motion?"

[2229] Terminal: Sends a question to the server.

[2230] Server: Passes the question to the emotion engine and AI model.

[2231] Emotion engine: Recognizes the user's emotion as "confusion" based on the tone and wording of the question.

[2232] AI model: Considers emotions and knowledge level to provide appropriate responses ("Newton's second law of motion, simply stated...").

[2233] Server: Sends the response to the device.

[2234] Terminal: Responses are displayed on the chat screen.

[2235] User: Check the response and clarify any questions.

[2236] Automatic question creation

[2237] If a user wants to create a question by specifying specific conditions, they enter the conditions such as grade, subject, and difficulty level into a dedicated form on the terminal and press the "Create Question" button.

[2238] The device formats the entered conditions and sends an API request to the server.

[2239] The server passes the conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[2240] Example of problem generation

[2241] User: "Please create a high school physics problem in the mechanics section."

[2242] Terminal: Sends conditions to the server.

[2243] Server: Passes the conditions to the AI ​​model.

[2244] AI model: Generates problems based on specified conditions.

[2245] Server: Sends the generated questions to the device.

[2246] Terminal: displays the questions and allows the user to answer them.

[2247] User: Answer the question.

[2248] Personalized commentary

[2249] The server takes into account the user's knowledge level, answer history, and emotional data from an emotion engine, and has the AI ​​model generate personalized explanations.

[2250] The AI ​​model uses past data and emotional information to create the most appropriate explanation for the user.

[2251] The server receives this and sends it to the terminal.

[2252] The terminal displays an explanation and notifies the user.

[2253] Examples of personalized commentary

[2254] If a user has previously solved a problem related to the law of conservation of energy, the next time they solve a problem in the field of mechanics, the AI ​​model will provide an explanation related to the law of conservation of energy. If the emotion engine recognizes the user's "interest," the explanation will be more detailed and interesting.

[2255] Server: Passes conditions to the AI ​​model based on past answer history and emotional information.

[2256] AI model: Generate personalized commentary.

[2257] Server: Sends the commentary to the device.

[2258] Terminal: Display explanation and notify user.

[2259] Users: Check out personalized commentary to deepen their understanding.

[2260] In this way, by combining the emotional engine, the system provides an individually customized learning experience that takes into account the user's emotions, improving the quality of education.

[2261] The processing flow will be explained below.

[2262] User question submission process

[2263] Step 1:

[2264] If a user has a question while studying, they can open the chat screen on their device.

[2265] Step 2:

[2266] The user enters a question into the text input field and presses the "Submit" button.

[2267] Step 3:

[2268] The device takes the entered question and prepares an API request formatted in the appropriate format.

[2269] Step 4:

[2270] The device sends an HTTP request to the API endpoint to send question data to the server.

[2271] Step 5:

[2272] The server analyzes the received HTTP request and obtains the question.

[2273] Step 6:

[2274] Before the server passes the question to the natural language processing model, it first passes it to an emotion engine to identify the user's emotion.

[2275] Step 7:

[2276] The emotion engine identifies the user's emotion from the tone of the question, wording, typing speed, etc., and sends the results back to the server.

[2277] Step 8:

[2278] The server passes the question content along with the emotional information received from the emotion engine to the AI ​​model.

[2279] AI model response generation process

[2280] Step 9:

[2281] The AI ​​model analyzes the received questions and emotional information using natural language processing technology and extracts appropriate information from the relevant knowledge base.

[2282] Step 10:

[2283] It generates appropriate response text taking into account the user's knowledge level and perceived emotions.

[2284] Step 11:

[2285] The AI ​​model sends the generated response text back to the server.

[2286] Response sending process

[2287] Step 12:

[2288] The server receives the response from the AI ​​model and checks the format.

[2289] Step 13:

[2290] The server prepares an API response to send the response text to the device.

[2291] Step 14:

[2292] The server sends the response data to the terminal as an HTTP response.

[2293] Step 15:

[2294] The terminal analyzes the HTTP response received from the server and obtains the response text.

[2295] Step 16:

[2296] The response text acquired by the terminal is displayed on the chat screen.

[2297] Step 17:

[2298] Users can check the AI's responses displayed on the chat screen and resolve any questions they may have.

[2299] Automatic question creation process

[2300] Step 18:

[2301] When a user wants to solve a problem that corresponds to their learning objectives, they enter the necessary conditions (e.g., grade, subject, level, etc.) into a dedicated form on the device.

[2302] Step 19:

[2303] After the user enters the conditions, he or she presses the "Create Question" button.

[2304] Step 20:

[2305] The device formats the input conditions into the appropriate format and prepares the API request.

[2306] Step 21:

[2307] The device sends an HTTP request to the API endpoint to send condition data to the server.

[2308] Server processing of question generation

[2309] Step 22:

[2310] The server analyzes the request received from the terminal and obtains the conditions for creating questions.

[2311] Step 23:

[2312] The server passes the acquired conditions to the AI ​​model and asks it to generate a problem based on the specified conditions.

[2313] AI model problem generation process

[2314] Step 24:

[2315] The AI ​​model analyzes the received conditions and selects an algorithm to generate an appropriate problem.

[2316] Step 25:

[2317] A question that meets the conditions is generated, and data containing the question and answer is created.

[2318] Step 26:

[2319] The AI ​​model sends the generated problem data back to the server.

[2320] Processing problem data submissions

[2321] Step 27:

[2322] The server receives the problem data from the AI ​​model and checks the format.

[2323] Step 28:

[2324] The server prepares an API response to send the problem data to the device.

[2325] Step 29:

[2326] The server sends the problem data to the terminal as an HTTP response.

[2327] Step 30:

[2328] The terminal analyzes the HTTP response received from the server and obtains the problem data.

[2329] Step 31:

[2330] The problem data acquired by the terminal is displayed on the user interface.

[2331] Step 32:

[2332] The user checks the displayed question and begins answering it.

[2333] Personalized commentary delivery

[2334] Step 33:

[2335] The server takes into account the user's knowledge level, answer history, and emotional data from an emotion engine, and has the AI ​​model generate personalized explanations.

[2336] Step 34:

[2337] The AI ​​model uses past data and emotional information to create the most appropriate explanation for the user.

[2338] Step 35:

[2339] The server prepares an API response to send the explanation received from the AI ​​model to the device.

[2340] Step 36:

[2341] The server sends the explanatory data to the terminal as an HTTP response.

[2342] Step 37:

[2343] The terminal analyzes the HTTP response received from the server and obtains the explanatory data.

[2344] Step 38:

[2345] The terminal displays the explanation and notifies the user.

[2346] Step 39:

[2347] Users can check the explanations and deepen their understanding of the material.

[2348] Through these steps, the system enables users to learn while interacting with AI in real time, and also provides a learning experience that takes users' emotions into consideration.

[2349] Example 2

[2350] 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."

[2351] Conventional personalized learning support systems lack consideration for users' emotions, which can negatively impact learning motivation and comprehension. Furthermore, they lack personalized explanations and questions, making it difficult to provide an optimal learning experience based on the user's knowledge level and answer history. Therefore, a system that recognizes the user's emotional state and generates appropriate responses and explanations is needed.

[2352] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving a question input by a user to a terminal, means for transmitting the received question to the server, means for the server to analyze the question and pass it to an emotion engine to recognize the user's emotion and receive the result, means for the server to pass the question content and the recognized emotion information to an AI model to generate a response, means for returning the response generated by the AI ​​model to the server, and means for the server to send the response to the terminal and display it to the user. This makes it possible to provide an appropriate response or explanation according to the user's emotion.

[2353] A "user" is an individual who uses the system to advance their learning.

[2354] "Terminal" refers to the device used by the user to input learning content and receive responses from the system.

[2355] A "server" is a central computer system that receives requests from users, analyzes them, and performs the necessary processing.

[2356] An "emotion engine" is software that analyzes a user's input and behavior to identify emotions.

[2357] An "AI model" is an algorithm that uses machine learning or deep learning to analyze data and generate responses or questions.

[2358] A "question" is text data that a user inputs into the system via a terminal to express a question that the user has while studying.

[2359] A "response" is an answer to a user's question that the server generates using an AI model.

[2360] A "problem" is a learning task generated by an AI model based on conditions specified by the user.

[2361] "Explanation" is a detailed explanation or additional information provided in response to a user's question or problem.

[2362] "Personalization" is a concept that refers to optimizing the content provided based on the characteristics and history of each individual user.

[2363] MODE FOR CARRYING OUT THE INVENTION

[2364] System Overview

[2365] This invention combines an AI-based personalized learning support system with an emotion engine that recognizes the user's emotions. The system analyzes questions entered by the user into the device in real time, generates appropriate responses, and displays them on the device. It also includes a function that generates questions by entering specific conditions and provides questions and explanations based on those conditions. Furthermore, the system provides personalized explanations taking into account the user's knowledge level and past answer history, and uses the emotion engine to adjust the responses and explanations according to the user's emotions.

[2366] System configuration

[2367] The system consists of the following main components:

[2368] 1. Terminal: A device where the user inputs learning content and receives responses from the system.

[2369] 2. Server: A central computer system that receives and analyzes user requests.

[2370] 3. Emotion engine: Software that analyzes user input and behavior to identify emotions.

[2371] 4. AI Model: An algorithm that uses machine learning or deep learning to analyze data and generate responses or questions.

[2372] User questions submitted

[2373] If a user has a question during learning, they open the chat screen on their device, enter their question, and press the "Send" button. The device receives the entered question, formats it appropriately, and sends it to the server as an API request. The server analyzes the received question and passes the question content to the emotion engine. The emotion engine analyzes the user's input and behavior to recognize emotions and return the results to the server. The server then passes the question content and recognized emotion information to the AI ​​model.

[2374] AI model response generation

[2375] The AI ​​model analyzes the received question and emotional information, extracts appropriate information from the relevant knowledge base, and generates an appropriate response based on the user's knowledge level and emotional state. The server receives the response from the AI ​​model, reformats it, and sends it to the device. The device displays the received response on the chat screen and notifies the user.

[2376] Specific examples

[2377] If a user types, "Tell me about Newton's second law of motion," the device sends the question to the server. The server passes the question to the emotion engine and AI model. The emotion engine recognizes the user's emotion as "confusion" based on the tone and wording of the question. The AI ​​model generates an appropriate response taking into account the emotion and knowledge level. Specifically, it generates a response such as, "Newton's second law of motion states that the acceleration of an object is proportional to the force and inversely proportional to the mass." The server sends the response to the device, which displays it on the chat screen.

[2378] Automatic question creation

[2379] When a user wants to generate a question based on specific conditions, they enter the conditions, such as grade, subject, and difficulty level, into a dedicated form on the device and press the "Create Question" button. The device formats the entered conditions and sends an API request to the server. The server passes the conditions to the AI ​​model and asks it to generate a question based on the specified conditions.

[2380] Example of problem generation

[2381] The user enters "Please create a problem in the field of mechanics for high school physics" and sends the conditions to the device. The server passes the conditions to the AI ​​model. The AI ​​model generates a problem based on the specified conditions, such as "Find the acceleration a when force F is applied to an object with mass m." The server sends the generated problem to the device, which displays the problem so the user can answer it.

[2382] Personalized commentary

[2383] The server takes into account the user's knowledge level, past answer history, and emotional data from the emotion engine, and has the AI ​​model generate a personalized explanation. The AI ​​model creates the optimal explanation for the user based on past data and emotional information. The server receives this and sends it to the device. The device displays the explanation and notifies the user.

[2384] Examples of personalized commentary

[2385] For example, if a user has previously solved a problem related to the law of conservation of energy, the next time they solve a problem in the field of mechanics, the AI ​​model will provide an explanation related to the law of conservation of energy. If the emotion engine recognizes the user's "interest," the explanation will be more detailed and interesting. The server passes conditions to the AI ​​model based on past answer history and emotion information, and the AI ​​model generates a personalized explanation. The server sends the explanation to the device, which then displays the explanation and notifies the user.

[2386] As described above, by combining the emotion engine, the system provides an individually customized learning experience that takes into consideration the user's emotions, thereby improving the quality of education.

[2387] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2388] User questions submitted

[2389] Step 1:

[2390] The user enters the question they are studying into the terminal and presses the "Submit" button.

[2391] Input: User question text (e.g., "What is Newton's second law of motion?")

[2392] Output: A transmission command is output to the terminal

[2393] Step 2:

[2394] The device formats the entered question and sends an API request to the server.

[2395] Input: User question text

[2396] Data processing / calculation: Formatting question text into JSON format

[2397] Output: Formatted question data (JSON format)

[2398] Step 3:

[2399] The server receives the question, analyzes it, and passes it to the emotion engine.

[2400] Input: Formatted question data (JSON format)

[2401] Data processing / calculation: Extracting text from question data and formatting it appropriately to be passed to the emotion engine

[2402] Output: Data to send to the emotion engine

[2403] Step 4:

[2404] The emotion engine analyzes the question text, recognizes the user's emotion, and returns the results to the server.

[2405] Input: Question text from the server

[2406] Data processing / computation: Recognizing emotions using natural language processing and sentiment analysis algorithms (e.g., "confused")

[2407] Output: Recognized emotion data

[2408] Step 5:

[2409] The server passes the question content and recognized emotional information to the AI ​​model.

[2410] Input: Question text and sentiment data

[2411] Data processing / calculation: Combining question text and sentiment data to create a format suitable for the AI ​​model

[2412] Output: Data to send to the AI ​​model

[2413] Step 6:

[2414] The AI ​​model generates a response based on the received question and emotional information and returns it to the server.

[2415] Input: Question text and sentiment data

[2416] Data processing / calculation: Searches for appropriate information from a related knowledge base based on the question and emotional information, and generates a response that matches the user's knowledge level.

[2417] Output: Generated response data

[2418] Step 7:

[2419] The server receives the response from the AI ​​model, reformats it, and sends it to the device.

[2420] Input: Generated response data

[2421] Data processing / calculation: Formatting response data for display to the user

[2422] Output: Formatted response data to send to the terminal

[2423] Step 8:

[2424] The response received by the terminal is displayed on the chat screen and notified to the user.

[2425] Input: Formatted response data

[2426] Data processing / calculation: Formatting response data into a layout for display on the chat screen

[2427] Output: The response displayed on the screen

[2428] Automatic question creation

[2429] Step 1:

[2430] The user inputs the conditions for creating a question and presses the "Create Question" button.

[2431] Input: Grade, subject, difficulty level, etc. (e.g. "High school physics, mechanics, intermediate")

[2432] Output: A transmission command is output to the terminal

[2433] Step 2:

[2434] The device formats the entered conditions and sends an API request to the server.

[2435] Input: User-entered criteria

[2436] Data processing / calculation: Format conditions into JSON format

[2437] Output: Formatted condition data (JSON format)

[2438] Step 3:

[2439] The server receives the conditions, analyzes them, and asks the AI ​​model to generate a problem.

[2440] Input: Formatted condition data (JSON format)

[2441] Data processing / calculation: Format the condition data into a format that can be used to request the AI ​​model to generate questions.

[2442] Output: Data to send to the AI ​​model

[2443] Step 4:

[2444] The AI ​​model generates questions based on the specified conditions and returns them to the server.

[2445] Input: Specified condition data

[2446] Data processing / calculation: Generate problems from the relevant knowledge base based on condition data (e.g., "Find the acceleration a when force F is applied to an object with mass m").

[2447] Output: Generated problem data

[2448] Step 5:

[2449] The server sends the generated questions to the device.

[2450] Input: Generated problem data

[2451] Data processing / calculation: Formatting the problem data for display to the user

[2452] Output: Formatted question data to send to the terminal

[2453] Step 6:

[2454] The terminal displays the received questions and allows the user to answer them.

[2455] Input: Formatted question data

[2456] Data processing / calculation: Formatting the problem data into a layout for display

[2457] Output: The problem as it appears on the screen

[2458] Personalized commentary

[2459] Step 1:

[2460] The server collects the user's knowledge level, past answer history, and emotional data, and passes them on to the AI ​​model.

[2461] Input: User knowledge level, past answer history, emotional data

[2462] Data processing / calculation: Format the collected data to generate the most appropriate explanation for the user.

[2463] Output: Data to send to the AI ​​model

[2464] Step 2:

[2465] The AI ​​model generates personalized commentary based on the collected data and returns it to the server.

[2466] Input: knowledge level data, past answer history, emotion data

[2467] Data processing / calculation: Generate optimal explanations from the relevant knowledge base based on the collected data

[2468] Output: Generated commentary data

[2469] Step 3:

[2470] The server sends the personalized commentary to the device.

[2471] Input: Generated commentary data

[2472] Data processing / calculation: Formatting explanatory data for display to the user

[2473] Output: Formatted commentary data to send to the terminal

[2474] Step 4:

[2475] The terminal displays the received explanation and notifies the user.

[2476] Input: Formatted commentary data

[2477] Data processing / calculation: Formatting the explanatory data into a layout for display

[2478] Output: Explanation displayed on the screen

[2479] (Application example 2)

[2480] 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."

[2481] Conventional individual learning support systems have had the problem of being unable to respond flexibly to users' emotions and individual needs. In particular, when providing customer service support in brick-and-mortar stores, it is difficult for store staff to consistently grasp customers' emotions and respond optimally based on them. This can lead to a decline in customer satisfaction.

[2482] 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 a means for transmitting a question entered by a user to an emotion analysis engine to acquire emotion information, a means for passing the question and emotion information to an AI model to generate an appropriate response, and a means for transmitting the response generated by the AI ​​model to a terminal for display. This enables store clerks in physical stores to consistently provide optimal responses to customers, taking into consideration the user's emotions.

[2483] - "Terminal" means an electronic device that allows a user to input or receive information.

[2484] A "question" is information that the user wants to know or confirm, entered in text format.

[2485] An "emotion analysis engine" is a system that analyzes a user's emotions from input text and outputs the results.

[2486] "Emotion information" is data about the user's emotional state obtained by the emotion analysis engine.

[2487] A "server" is a central computer system and device that processes and analyzes received data.

[2488] An "AI model" is an artificial intelligence algorithm that analyzes user input and generates optimal responses and explanations.

[2489] A "response" is information generated by an AI model in response to a user's question.

[2490] The "knowledge level" is information indicating the level of knowledge that the user has, and is calculated from the past answer history.

[2491] The "answer history" is a record of the answers that the user has given up to now.

[2492] A "personalized commentary" is a commentary content that is individually customized taking into account the user's knowledge level and emotional information.

[2493] This invention is a system that analyzes a user's emotional information and provides individually customized responses, particularly for the purpose of supporting customer service in brick-and-mortar stores, helping store staff to effectively respond to customers.

[2494] The central part of the system is the server, which includes the following means:

[2495] 1. A means of obtaining emotional information from user input using an emotion analysis engine.

[2496] 2. A means of analyzing the question and sentiment information and passing it to an AI model to generate the optimal response.

[2497] 3. A means of sending the responses generated by the AI ​​model to the device and displaying them to the user.

[2498] Specifically, the following processing is performed.

[2499] First, a store clerk inputs a customer's question into the terminal, which then sends the question to the server. The server passes the question to a sentiment analysis engine, which analyzes the user's emotions. The acquired emotional information is then sent to an AI model, which generates an optimal response based on the question and emotional information. The server then reformats this response and sends it to the terminal, where the store clerk displays it to the customer and takes appropriate action.

[2500] For example, if a customer asks, "What material is this shirt made of?", the following prompt sentence is generated:

[2501] "What material is this shirt made of?" (Emotion: Interest, Probability: 0.85)

[2502] This allows the server to utilize its emotion analysis engine and AI model to quickly provide the optimal response based on the user's emotions.

[2503] The software and hardware used include:

[2504] Sentiment analysis engine: A software system for analyzing text.

[2505] AI model: A generative AI model that generates responses based on questions and sentiment information.

[2506] Device: The smartphone or tablet device that users use for input and display.

[2507] Server: A central system that receives, processes, and transmits data.

[2508] This makes it possible to provide effective customer service that is in line with the user's emotions, even in physical stores.

[2509] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2510] Step 1:

[2511] The store clerk inputs the customer's question into the terminal and presses the send button, which sends the question to the server.

[2512] Input: The question entered by the store clerk into the terminal

[2513] Output: The question is sent to the server

[2514] Step 2:

[2515] The server passes the received question to a sentiment analysis engine to obtain the user's sentiment information. The sentiment analysis engine analyzes the tone and wording of the question to generate sentiment information.

[2516] Input: Received question

[2517] Output: Emotion information (e.g., interest, accuracy: 0.85)

[2518] Step 3:

[2519] The server passes the question and emotional information to the AI ​​model and asks it to generate a response. The AI ​​model generates the optimal answer based on the question content and emotional information.

[2520] Input: Question, emotion information

[2521] Output: Best response

[2522] Step 4:

[2523] The server receives the response sent back by the AI ​​model, reformats it, and sends it to the device, which involves converting the response into an appropriate format for display.

[2524] Input: Best response

[2525] Output: Reformatted response

[2526] Step 5:

[2527] The terminal displays the received response and notifies the store clerk, who then relays the displayed response to the customer.

[2528] Input: Reformatted response

[2529] Output: Response displayed to the store clerk

[2530] Step 6:

[2531] The store clerk will check the response and provide the customer with an appropriate answer, allowing the store to respond to the customer's question quickly and accurately.

[2532] Input: Displayed response

[2533] Output: Response to the customer

[2534] This series of processes enables store staff to take into consideration the customer's feelings and provide optimal customer service.

[2535] 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.

[2536] 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 obt...

Claims

1. means for receiving a question input by a user into a terminal; means for transmitting the received query to a server; A means by which the server parses the question and passes it to the AI ​​model to generate a response; a means for transmitting the response generated by the AI ​​model back to the server; means for the server to send a response to the terminal and display it to the user; A system including:

2. A means for a user to input specific conditions and request the generation of a problem; means for transmitting the input conditions to a server; A means for the server to request the AI ​​model to generate a problem based on the conditions; A means for sending the problems generated by the AI ​​model back to the server; and a means for the server to transmit the generated questions to a terminal and display them to a user; The system of claim 1 , comprising:

3. A means for the server to generate responses and explanations from the AI ​​model taking into account the user's knowledge level; A means for the AI ​​model to generate personalized explanations taking into account the user's past answer history and interests; a means for the server to transmit the personalized commentary to the terminal and display it to the user; The system of claim 1 , comprising:

Images