system

Abstract

We provide the system. [Solution] A means of receiving questions entered by the user, A means of sending the received question to the server, A means by which a server analyzes a question and generates an answer using generative artificial intelligence, A means of sending the generated response to the user's device, A means of displaying the generated answer on the user's device, A system that includes means for proposing individually optimized learning plans.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern educational settings, it is very important to provide individually optimized learning support for each student or pupil. However, in conventional educational systems, it has been difficult to provide quick and accurate answers to a large number of questions and further propose an individualized learning plan. In addition, conventional systems have not been able to respond flexibly according to the learning progress and comprehension level of users, and efficient learning support has not been provided. The present invention aims to solve these problems and maximize the learning effect of users.

Means for Solving the Problems

[0005] The educational chatbot system according to the present invention includes means for receiving questions entered by a user and sending the received questions to a server. It also includes means for the server to analyze the questions and generate answers using generative artificial intelligence. Furthermore, it includes means for sending the generated answers to the user's terminal and displaying the generated answers on the user's terminal. In addition, it also includes means for proposing individually optimized learning plans, enabling flexible responses according to the user's learning progress and level of understanding, thereby providing efficient and effective learning support.

[0006] "Users" refer to students who use this educational chatbot system to input questions and receive learning support.

[0007] "Terminal" refers to a device such as a computer, smartphone, or tablet that a user uses to input information and receive and display responses.

[0008] A "server" refers to a computer system that analyzes questions sent by users, generates answers using generative artificial intelligence, and sends them to the terminal.

[0009] "Generative artificial intelligence" refers to an AI system that includes natural language processing techniques and related algorithms for analyzing user questions and generating appropriate answers.

[0010] A "question" refers to a query or inquiry that a user enters into an educational chatbot system to deepen their understanding of the learning material.

[0011] "Answer" refers to the information and explanations that generative artificial intelligence generates based on a question and sends to the user's terminal via a server.

[0012] A "learning plan" refers to a plan in which a generative artificial intelligence proposes individually optimized learning content and methods based on the user's learning progress and level of understanding. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the 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.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0027] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] The educational chatbot system according to the present invention receives questions entered by the user, generates appropriate answers using generative artificial intelligence, and provides those answers to the user, thereby providing individually optimized learning support. The configuration for implementing this system is described in detail below.

[0035] 1. User enters question

[0036] Users input questions into the educational chatbot using their device. This device can be a variety of devices, including PCs, smartphones, and tablets. For example, a user might input, "I want to learn about Newton's laws of motion."

[0037] 2. Submit your question

[0038] The terminal receives the entered question and generates an HTTP request, along with additional information such as the user ID and session ID, which it sends to the server. This request includes the user's input text.

[0039] 3. Receiving and analyzing questions

[0040] The server analyzes the received request and extracts the question content. In doing so, it has a mechanism to extract the user's input text from the request parameters and convert it into a format suitable for passing to a generative artificial intelligence (AI) for natural language processing.

[0041] 4. Question analysis and answer generation

[0042] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to a question about "Newton's laws of motion," the AI ​​would generate the following answer: "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0043] 5. Preparing to submit your response

[0044] The server formats the responses received from the generative artificial intelligence into a user-friendly format (e.g., HTML or JSON). This ensures that the responses are organized and displayed appropriately.

[0045] 6. Submit your response

[0046] The server generates a formatted response as an HTTP response and sends it to the user's terminal.

[0047] 7. Display the answer

[0048] The device analyzes the HTTP response received from the server, extracts the answer, and displays it. The user can then read this and continue their learning. For example, the text "Newton's laws of motion include the following three..." might appear on the device screen.

[0049] 8. Additional learning support

[0050] If the user needs more detailed information, they can enter another question into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?"

[0051] In this case, the terminal sends a new question to the server, and the analysis and answer generation process is repeated. The generative artificial intelligence provides a concrete example, such as, "When a force of 10N is applied to an object with a mass of 1kg, the acceleration will be 10 m / s²."

[0052] 9. Proposal of an individualized learning plan

[0053] Generative artificial intelligence generates an optimal learning plan based on the user's learning history and level of understanding. For example, if a user asks multiple questions about mechanics, it will suggest additional learning materials and practice problems related to that topic.

[0054] The server sends this learning plan to the user's device. The device displays the learning plan to the user and provides further learning support.

[0055] In this way, the educational chatbot system according to the present invention provides appropriate answers to user questions and proposes individually optimized learning plans, thereby achieving effective learning support.

[0056] The following describes the processing flow.

[0057] Step 1:

[0058] The user enters a question into the chatbot interface from their device. For example, they might type, "I want to know about Newton's laws of motion."

[0059] Step 2:

[0060] The terminal receives user input and generates an HTTP request containing the question. This request may also include additional information such as the user ID and session ID.

[0061] Step 3:

[0062] The terminal generates an HTTP request and sends it to the server. This allows the server to receive the user's question.

[0063] Step 4:

[0064] The server parses the received request and extracts the question content. Specifically, it extracts the user's input text from the request parameters.

[0065] Step 5:

[0066] The server formats the extracted question content for transmission to a generative artificial intelligence (AI) for natural language processing. It converts it to an appropriate format.

[0067] Step 6:

[0068] Generative artificial intelligence analyzes questions received from a server. It understands the intent of the question and retrieves information from relevant knowledge databases and trained models.

[0069] Step 7:

[0070] The generative artificial intelligence generates an answer based on the analysis results. For example, it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0071] Step 8:

[0072] The server receives the generated response and formats it for transmission to the user, such as HTML or JSON.

[0073] Step 9:

[0074] The server generates a formatted response as an HTTP response and sends it to the user's terminal.

[0075] Step 10:

[0076] The terminal analyzes the HTTP response received from the server and extracts the response content. If necessary, it converts it to a display format.

[0077] Step 11:

[0078] The device displays the answer to the user. For example, the text "Newton's laws of motion include the following three..." might appear on the device screen.

[0079] Step 12:

[0080] If a user wants more detailed information or additional questions, they can enter their questions into the chatbot again. For example, they might type, "Can you give me a concrete example of the equations of motion?"

[0081] Step 13:

[0082] The terminal sends a new question to the server, and a similar process is repeated starting from step 4.

[0083] Step 14:

[0084] Generative artificial intelligence generates a personalized learning plan based on the user's learning history and level of understanding. For example, it may suggest additional learning materials or practice problems related to mechanics.

[0085] Step 15:

[0086] The server generates an individualized learning plan and sends it to the user's device.

[0087] Step 16:

[0088] The device displays a learning plan to the user. For example, it may suggest text materials and practice problems that the user needs.

[0089] (Example 1)

[0090] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0091] Conventional educational support systems have a problem in that they do not adequately provide personalized learning support in response to questions entered by users. Furthermore, because the generated answers are not optimized based on the user's level of understanding or learning history, effective learning is difficult to achieve.

[0092] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0093] In this invention, the server includes means for receiving questions entered by the user, means for transmitting the received questions from the terminal to the server, means for the server to analyze the questions and generate answers using generative artificial intelligence, means for transmitting the generated answers from the server to the user's terminal, means for displaying the generated answers on the user's terminal, and means for proposing individually optimized learning plans. This enables individually optimized learning support for the user, thereby achieving effective learning.

[0094] A "user" refers to an individual or group that uses the system to input questions and receive answers.

[0095] "Device" refers to any device used by a user to input questions or view generated answers. Specifically, this includes PCs, smartphones, and tablets.

[0096] A "server" refers to a central computer system that receives questions submitted by users, analyzes them, and generates answers.

[0097] "Means of acceptance" refers to the process or mechanism by which the system accepts questions entered by the user.

[0098] "Means of transmission" refers to the methods and technologies used to send questions received from users and generated answers to the appropriate recipients.

[0099] "Means of analyzing questions" refers to methods and technologies for understanding the content of questions entered by users and extracting the information necessary to generate appropriate answers.

[0100] "Generative artificial intelligence" refers to AI models used to generate appropriate answers to questions entered by users. It utilizes natural language processing technology.

[0101] "Means of generating answers" refers to the process or mechanism that uses AI to create answers in order to provide appropriate responses to user questions.

[0102] "Means of display" refers to methods and technologies for visually presenting the generated answers on a device.

[0103] "Means of proposing learning plans" refers to the process and system for suggesting the most suitable learning methods and materials based on the user's learning history and level of understanding.

[0104] The educational chatbot system according to the present invention receives questions entered by the user, generates appropriate answers using generative artificial intelligence, and provides those answers to the user, thereby providing individually optimized learning support. The configuration for implementing this system is described in detail below.

[0105] First, users input questions into the educational chatbot using devices such as PCs, smartphones, or tablets. These devices can communicate with the server via the internet. For example, a user might input, "I want to learn about Newton's laws of motion."

[0106] The terminal receives the entered question and generates an HTTP request along with the user ID and session ID. This request is sent to the server, for example, using the JavaScript® fetch API executed in the browser. This request contains the user's input text.

[0107] The server parses the received HTTP request and extracts the question content. During this process, the server uses a Python script to convert the request data into JSON format, formatting it for transmission to a generative artificial intelligence (AI) for natural language processing. A specific AI model used might be OpenAI's GPT-3®.

[0108] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to a question about "Newton's laws of motion," it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0109] Next, the server formats the generated response into a user-friendly format. For example, it might use a Python library or a template engine to assemble the response as HTML. The formatted response is then generated as an HTTP response and sent from the server to the user's terminal.

[0110] The device analyzes the HTTP response received from the server, extracts the answer, and displays it. For example, the device's browser can render HTML and display text such as, "Newton's laws of motion include the following three..." on the screen.

[0111] Furthermore, if the user needs more detailed information, they can enter another question into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?" In this case, the device similarly sends a new question to the server, and the generative artificial intelligence provides a concrete example. It might generate an example such as, "When a force of 10N is applied to an object with a mass of 1kg, the acceleration will be 10m / s²."

[0112] Finally, the generative artificial intelligence generates an optimal learning plan based on the user's learning history and level of understanding. For example, if the user asks several questions about mechanics, it will suggest additional learning materials and practice problems related to that topic. The server sends this learning plan to the user's device, which can then display the learning plan to the user, providing further learning support.

[0113] As a concrete example, in response to the input prompt "Please tell me about Newton's laws of motion," the generated answer "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)." can be presented.

[0114] As described above, the educational chatbot system according to the present invention provides appropriate answers to user questions and proposes individually optimized learning plans, thereby achieving effective learning support.

[0115] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0116] Step 1:

[0117] Users enter questions into the educational chatbot using devices such as PCs, smartphones, and tablets. The entered questions are displayed as text in the input field. For example, when entering a question, a user might type "I want to know about Newton's laws of motion." The input data consists of the user's question text.

[0118] Step 2:

[0119] The terminal receives the entered question, adds the user ID and session ID, and generates an HTTP request. This request is then sent to the server. Specifically, the HTTP request is generated and sent using the JavaScript fetch API. The input data includes the user's question text, user ID, and session ID. The output is a structured HTTP request to be sent to the server.

[0120] Step 3:

[0121] The server receives the incoming HTTP request and parses the request data. Using a Python script, the server extracts the user's input text, which has been converted to JSON format, and then converts it back into a format suitable for a generative artificial intelligence (AI) for natural language processing. At this point, the user's question text is converted into a format that can be input to the AI ​​model. The input data is the HTTP request, and the output is the converted question text.

[0122] Step 4:

[0123] Generative artificial intelligence analyzes a given question and generates an answer using a trained model and knowledge database. Examples of generative AI models used include OpenAI's GPT-3. The AI ​​model generates answers such as, "Newton's laws of motion include the first law (law of inertia), the second law (equations of motion), and the third law (law of action and reaction)." The input data is a formatted question text, and the output is the generated answer text.

[0124] Step 5:

[0125] The server formats the responses received from the generative artificial intelligence into a user-friendly format. Specifically, it uses a Python template engine to format the response text into HTML or JSON format. The input data is the generated response text, and the output is the formatted response in HTML or JSON format.

[0126] Step 6:

[0127] The server generates a formatted response as an HTTP response and sends it to the user's terminal. The technologies used include web frameworks such as Flask and Django. Input data is formatted HTML or JSON, and output is the generated HTTP response.

[0128] Step 7:

[0129] The terminal analyzes the HTTP response received from the server, extracts the answer, and displays it. At this time, the browser renders HTML, visually presenting the answer to the user. Text such as "Newton's laws of motion include the following three..." is displayed on the screen. The input data is the HTTP response, and the output is the displayable answer text.

[0130] Step 8:

[0131] If the user needs more detailed information, they can enter another question into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?" This question will be processed again from step 1. The input data will be the new question text, and the output will be the newly generated answer text.

[0132] Step 9:

[0133] Generative artificial intelligence generates an optimal learning plan based on the user's learning history and level of understanding. For example, if a user asks several questions about mechanics, it will suggest additional learning materials and practice problems related to that topic. The server sends this learning plan to the user's terminal, which then displays it. The input data consists of the user's learning history and level of understanding, and the output is the generated learning plan.

[0134] (Application Example 1)

[0135] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0136] In modern online shopping, consumers face the challenge of selecting the best product from a vast amount of information. Therefore, there is a need for systems that efficiently answer consumer questions and recommend optimal products. Furthermore, there is a growing need for systems that can provide immediate and appropriate answers even when consumer questions are vague or when specific product information is requested.

[0137] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0138] In this invention, the server includes means for receiving questions entered by the user, means for analyzing the questions and generating answers using generative artificial intelligence, means for transmitting the generated answers to the user's terminal, and means for recommending the most suitable products and their information. This enables consumers to quickly obtain the most suitable product information.

[0139] "A means of receiving user-entered questions" refers to an interface that takes questions entered by the user using a terminal into the system and sends them to the server as the first step in processing.

[0140] "Means for sending received questions to the server" refers to a device or program that sends questions entered on the user terminal to the server in the form of an HTTP request or similar, and converts the data into a format that can be processed on the server side.

[0141] "A means by which a server analyzes a question and generates an answer using generative artificial intelligence" refers to a function in which a server analyzes a question received from a user through natural language processing and generates the optimal answer using generative artificial intelligence.

[0142] "Means of sending generated responses to the user's terminal" refers to a function that sends the responses generated on the server back to the user's terminal in the form of an HTTP response or similar, providing them in a format that the user can view.

[0143] "Means for displaying responses generated on the user's device" refers to an interface that displays responses received on the user's device in an easy-to-read format, allowing the user to confirm and use those responses.

[0144] "Means of proposing individually optimized learning plans" refers to a function that generates an individually optimized learning plan based on the user's learning history and question content, and then proposes it to the user.

[0145] "A means of analyzing product-related questions and recommending the most suitable products and their information" refers to a function that analyzes product-related questions entered by the user and uses generative artificial intelligence to recommend the most suitable products and related information for the user.

[0146] The intelligent purchasing assistant system for virtual stores according to the present invention generates appropriate answers to product-related questions entered by the user using generative artificial intelligence. The configuration for implementing this system is described in detail below.

[0147] 1. User enters question

[0148] Users use their smartphones to enter questions into an intelligent purchasing assistant app for a virtual store. These questions can include information about the category of product they want to buy or specific products. For example, a user might type, "Which laptop do you recommend?"

[0149] 2. Submit your question

[0150] The terminal receives the question entered by the user and generates an HTTP request, along with additional information such as the user ID and session ID, and sends it to the server. This request includes the user's input text. The software used here is a library for handling HTTP requests.

[0151] 3. Receiving and analyzing questions

[0152] The server parses the received request and extracts the question content. During this process, it has a means of extracting the user's input text from the request parameters and converting it into a format suitable for generative artificial intelligence (AI) for natural language processing. For example, the Python requests library can be used.

[0153] 4. Question analysis and answer generation

[0154] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to the question, "Which laptop do you recommend?", the AI ​​would generate the following answer: "We provide comparison information on products. Product name: Laptop A, Price: 80,000 yen, Review rating: 4.5."

[0155] 5. Preparing to submit your response

[0156] The server formats the responses received from the generative artificial intelligence into a user-friendly format (e.g., HTML or JSON). This ensures that the responses are organized and displayed appropriately.

[0157] 6. Submit your response

[0158] The server generates a formatted response as an HTTP response and sends it to the user's terminal.

[0159] 7. Display the answer

[0160] The terminal analyzes the HTTP response received from the server, extracts the answer, and displays it. The user can then view this information and select the most suitable product. For example, the terminal screen might display text such as "Product comparison information: Product name: Laptop A, Price: 80,000 yen, Review rating: 4.5."

[0161] 8. Additional Questions and Answers

[0162] If the user needs more detailed information, they can enter another question into the assistant app. For example, they might ask, "What are the features of laptop A?" In this case, the device sends the new question to the server, and the analysis and answer generation process is repeated. The generative artificial intelligence generates the answer, "The features of laptop A are its long battery life, high-resolution display, and fast processing speed."

[0163] 9. Individual Recommendations

[0164] Generative artificial intelligence suggests the most suitable products and plans for each user based on their past questions and purchase history. For example, if a user asks multiple questions about laptops, the system will suggest additional recommended products and promotional information related to that category. The server sends this recommendation information to the user's device. The device then displays the recommendations to the user, providing further options.

[0165] Example of a prompt

[0166] "Which laptop do you recommend?"

[0167] "What are the features of laptop A?"

[0168] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0169] Step 1:

[0170] Users access an intelligent purchasing assistant app for a virtual store using their smartphones and enter questions about the category of product they want to buy or specific products. This input is in text format, for example, "Which laptop do you recommend?"

[0171] Step 2:

[0172] The terminal receives the question entered by the user and generates an HTTP request, along with additional information such as the user ID and session ID, and sends it to the server. This request includes the user's input text. Specifically, the data obtained from the input form on the terminal is serialized using the json.dumps function and sent using the requests.post function.

[0173] Step 3:

[0174] The server parses the received HTTP request and extracts the user's question. Here, it extracts the user's input text from the request parameters and converts it into a format to be passed to a generative artificial intelligence for natural language processing. Specifically, it deserializes the request body using Python's json.loads function and extracts the text portion.

[0175] Step 4:

[0176] The server uses generative artificial intelligence to analyze user questions and generates answers using a trained model and knowledge database. For example, in response to the question, "Which laptop do you recommend?", the generative AI generates the answer, "We will provide comparison information on products. Product name: Laptop A, Price: 80,000 yen, Review rating: 4.5." In this process, the AI ​​model refers to a pre-trained dataset to predict the most appropriate answer.

[0177] Step 5:

[0178] The server formats the responses received from the generative artificial intelligence into a user-friendly format. Here, the response data is converted to HTML or JSON format so that it can be easily displayed on the user's device. Specifically, the generated responses are converted to the appropriate format using Python's HTML and JSON libraries.

[0179] Step 6:

[0180] The server generates a formatted response as an HTTP response and sends it to the user's device. Specifically, it creates a response object using the requests.post function and embeds the response data within it.

[0181] Step 7:

[0182] The terminal analyzes the HTTP response received from the server, extracts the generated response content, and displays it. The user can then view this and select the most suitable product. Specifically, the response body is deserialized and embedded into the corresponding HTML element.

[0183] Step 8:

[0184] If the user needs more detailed information, they can re-enter the question into the assistant app. For example, they might ask, "What are the features of laptop A?" The device sends the new question to the server, and the analysis and answer generation process is repeated.

[0185] Step 9:

[0186] Generative artificial intelligence suggests the most suitable products and plans for each user based on their past questions and purchase history. The server sends this recommendation information to the user's device, which then displays the recommendations to the user. Specifically, the AI ​​generates a recommendation model based on the user's interaction data and provides additional product and campaign information.

[0187] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0188] The educational chatbot system according to the present invention not only receives user questions, generates answers using generative artificial intelligence, displays the answers, and proposes individualized learning plans, but also recognizes the user's emotions and provides learning support. This system uses an emotion engine to analyze the user's emotions and provides an individually optimized learning experience.

[0189] 1. User enters question

[0190] The user enters their question into the chatbot interface from their device. For example, they might type, "I want to know about Newton's laws of motion."

[0191] 2. Submit your question

[0192] The terminal receives the entered question and generates an HTTP request containing the question content. This request may also include additional information such as the user ID and session ID.

[0193] 3. Receiving and analyzing questions

[0194] The server analyzes the received request and extracts the question content. During this process, it extracts the user's input text from the request parameters and converts it into a format suitable for generative artificial intelligence (AI) for natural language processing.

[0195] 4. Question analysis and answer generation

[0196] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to a question about "Newton's laws of motion," it might generate the answer, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0197] 5. Emotion analysis

[0198] The emotion engine analyzes the user's emotions based on their text input and conversation history. For example, if a user types "I'm confused and don't understand," the emotion engine recognizes that the user is confused.

[0199] 6. Preparing to submit your response

[0200] The server adjusts the generated responses based on the results of the emotion engine's analysis. For example, it can include clearer language and additional explanations for confused users.

[0201] 7. Submit your response

[0202] The server generates a formatted and adjusted response as an HTTP response and sends it to the user's terminal.

[0203] 8. Display the answer

[0204] The terminal analyzes the HTTP response received from the server, extracts the answer, and displays it. For example, it might display text such as, "Newton's laws of motion include the following three..."

[0205] 9. Additional learning support

[0206] If a user wants more detailed information or additional questions, they can enter their questions into the chatbot again. For example, they might ask, "Can you give me a concrete example of the equations of motion?"

[0207] 10. Proposal of an individualized learning plan

[0208] Generative artificial intelligence generates an optimal learning plan based on the user's learning history, understanding level, and the results of the emotion engine's analysis. For example, it may suggest additional learning materials or practice problems related to mechanics.

[0209] 11. Submitting and displaying your study plan

[0210] The server formats this learning plan and sends it to the user's device. The device displays it to the user and provides further learning support. For example, it may present the user with necessary text materials and practice problems.

[0211] The educational chatbot system according to the present invention enables efficient and effective learning by providing interactive learning support that also takes into account the user's emotions.

[0212] The following describes the processing flow.

[0213] Step 1:

[0214] The user enters a question into the chatbot interface from their device. For example, they might type, "I want to know about Newton's laws of motion."

[0215] Step 2:

[0216] The terminal receives user input and generates an HTTP request containing the question. This request also includes additional information such as the user ID and session ID.

[0217] Step 3:

[0218] The question is transmitted to the server by sending an HTTP request generated by the terminal to the server.

[0219] Step 4:

[0220] The server analyzes the received request and extracts the question content. It then extracts the user's input text from the request parameters and converts it into a format suitable for generative artificial intelligence (AI) for natural language processing.

[0221] Step 5:

[0222] Generative artificial intelligence analyzes questions received from the server and understands their intent. It then retrieves relevant information using a trained model and knowledge database.

[0223] Step 6:

[0224] Generative artificial intelligence generates appropriate answers. For example, it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0225] Step 7:

[0226] The emotion engine analyzes the user's emotions based on their input text and conversation history. For example, if a user inputs "I'm confused and don't understand," the emotion engine recognizes that the user is confused.

[0227] Step 8:

[0228] The server adjusts the content and tone of the responses based on the generated responses and the results of the sentiment engine's analysis. For example, it adds clear and polite explanations to confused users.

[0229] Step 9:

[0230] The server generates the adjusted response as an HTTP response and sends it to the user's terminal.

[0231] Step 10:

[0232] The terminal analyzes the HTTP response received from the server and extracts the response content. It then converts it to a display format as needed.

[0233] Step 11:

[0234] The device displays the answer to the user. For example, the text "Newton's laws of motion include the following three..." is displayed on the screen.

[0235] Step 12:

[0236] If a user wants more detailed information or additional questions, they can simply type their question back into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?"

[0237] Step 13:

[0238] The terminal sends a new question to the server, and a similar process is repeated starting from step 4.

[0239] Step 14:

[0240] Generative artificial intelligence generates an optimal learning plan based on the user's learning history, understanding level, and the results of the emotion engine's analysis. For example, it may suggest additional learning materials or practice problems related to mechanics.

[0241] Step 15:

[0242] The server formats the individual learning plan and sends it to the user's device.

[0243] Step 16:

[0244] The device displays a learning plan to the user. For example, it might suggest necessary text materials and practice exercises.

[0245] This invention realizes learning support that also takes into account the user's emotions through the steps described above.

[0246] (Example 2)

[0247] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0248] Conventional educational chatbot systems only mechanically respond to user questions, failing to recognize and appropriately address user emotions or confusion. As a result, learning effectiveness is limited, and improving user comprehension and motivation is difficult. Furthermore, they lack the ability to propose individually optimized learning plans, preventing them from providing effective learning support tailored to individual users.

[0249] The specific processing performed by the specific 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 analyzing the user's question and generating an answer using generative artificial intelligence, means for analyzing the user's emotions, and means for adjusting the answer generated based on the emotion analysis results. This makes it possible to provide an optimal answer that takes the user's emotions into consideration and propose an individually optimized learning plan.

[0250] A "user" is an individual or organization that uses this system to enter a question.

[0251] A "means of receiving questions" refers to an input device or interface for receiving text entered by a user.

[0252] A "data processing device" is a server or computer system used for the purpose of analyzing questions and generating answers.

[0253] "Means of analysis" refer to algorithms and software used to understand the received question and generate an appropriate answer.

[0254] "Generative artificial intelligence" refers to machine learning models and AI technologies trained to generate appropriate answers to user questions.

[0255] "Means for generating answers" refers to processes or systems that use generative artificial intelligence to produce answers to user questions.

[0256] A "display device" is a display or screen that visually shows the generated answer to the user.

[0257] A "learning plan" is a personalized suggestion of learning materials and practice problems designed to maximize the user's learning effectiveness.

[0258] "Means of analyzing emotions" refer to engines or software that determine an emotional state based on user input and history.

[0259] "Means of adjustment" refer to processes or systems that adapt the generated responses, based on the results of sentiment analysis, to the user's emotions.

[0260] The educational chatbot system according to the present invention receives user questions, generates answers using generative artificial intelligence, and provides a personalized learning experience by recognizing the user's emotions. Specifically, this system is implemented using the following hardware and software.

[0261] Hardware to use

[0262] Server: As a high-performance data processing unit, it performs question analysis, answer generation, sentiment analysis, and proposes learning plans.

[0263] Terminal: A device that provides an interface for users to access (such as a PC, smartphone, or tablet).

[0264] Software to use

[0265] Chatbot interface: A graphical user interface (GUI) for users to input questions.

[0266] Generative artificial intelligence: Machine learning models for generating answers to questions (e.g., GPT-4®).

[0267] Sentiment analysis engine: Software that analyzes user text and recognizes emotions (e.g., IBM Watson® Tone Analyzer).

[0268] Overview of program processing

[0269] 1. User Question Input: The user enters a specific question into the chatbot interface. For example, they might type, "I want to know about Newton's laws of motion."

[0270] 2. Sending the Question: The terminal generates an HTTP request based on the question received from the user and sends it to the server.

[0271] 3. Question analysis on the server: The server analyzes the received request, extracts the question content, and converts it into a format for passing to the generative artificial intelligence.

[0272] 4. Answer Generation: Generative artificial intelligence uses a trained model to generate the best possible answer to a question. For example, it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0273] 5. Sentiment Analysis: The sentiment analysis engine analyzes the user's emotions based on their text and conversation history. For example, if a user enters "I'm confused and don't understand," the sentiment engine recognizes that the user is confused.

[0274] 6. Adjusting and Sending Responses: The server adjusts the responses generated based on the sentiment analysis results and sends them to the device. If the user is confused, it can add clearer language or additional explanations.

[0275] 7. Displaying the answer: The terminal displays the answer received from the server to the user. For example, it might display text such as, "Newton's laws of motion include the following three..."

[0276] 8. Proposal of an individually optimized learning plan: The generative artificial intelligence generates an optimal learning plan including additional teaching materials and practice questions based on the user's learning history, understanding level, and the results of sentiment analysis.

[0277] 9. Display of the learning plan: The server sends the generated learning plan to the terminal, and the terminal displays it to the user. For example, additional practice questions related to mechanics are presented.

[0278] With this system, appropriate answers and learning support can be provided while considering the user's emotions, enabling efficient and effective learning. Therefore, an individually optimized learning experience can be provided, and it is possible to improve the user's understanding level and learning motivation.

[0279] The flow of the specific process in Example 2 will be described using FIG. 13.

[0280] Step 1: User question input

[0281] The user opens the chatbot interface on the terminal and enters the question in the text input field. For example, enter "I want to know about Newton's laws of motion".

[0282] Input: User question text

[0283] Output: The question text is displayed on the chatbot interface

[0284] Specific operation: The user enters the question with the keyboard and clicks the send button.

[0285] Step 2: Sending the question

[0286] The terminal obtains the question text entered by the user, generates an HTTP request, and sends it to the server.

[0287] Input: Question text entered by the user, User ID, Session ID

[0288] Output: HTTP request sent to server

[0289] Specific operation: An HTTP request containing the question text "I want to know about Newton's laws of motion" is generated and sent to a specific URL on the server.

[0290] Step 3: Receiving and analyzing questions

[0291] The server receives an HTTP request sent from the terminal and extracts the question content from the request body. It then converts the extracted question content into a format suitable for natural language processing.

[0292] Input: HTTP Request

[0293] Output: The question content is converted into structured data such as JSON format.

[0294] Specific operation: The server parses the request body and converts the question text into JSON format.

[0295] Step 4: Question analysis and answer generation

[0296] Generative artificial intelligence analyzes questions received from a server and generates answers using a trained model.

[0297] Input: Structured question data

[0298] Output: Generated answer text

[0299] Specific operation: In response to the question "I want to know about Newton's laws of motion," it generates an answer such as "Newton's laws of motion include the first law, the second law, and the third law."

[0300] Step 5: Emotion Analysis

[0301] The emotion engine analyzes emotions based on the user's text input and conversation history.

[0302] Input: User's text input, conversation history

[0303] Output: Emotion analysis result (e.g., confused)

[0304] Specific operation: When the user inputs "I'm having trouble understanding", the emotion engine analyzes the tone of this text and determines that there is confusion.

[0305] Step 6: Preparation for sending the answer

[0306] The server adjusts the answer according to the user's emotion based on the generated answer and the analysis result of the emotion engine.

[0307] Input: Generated answer text, emotion analysis result

[0308] Output: Adjusted answer text

[0309] Specific operation: For a confused user, format a more friendly explanation text such as "There are three of Newton's laws of motion..."

[0310] Step 7: Sending the answer

[0311] The server generates the adjusted answer as an HTTP response and sends it to the user's terminal.

[0312] Input: Adjusted answer text

[0313] Output: The HTTP response is sent to the terminal

[0314] Specific operation: The server generates an HTTP response containing an answer such as "There are three of Newton's laws of motion..." and sends it to the terminal.

[0315] Step 8: Display the answer

[0316] The terminal analyzes the HTTP response received from the server, extracts the answer content, and displays it to the user.

[0317] Input: HTTP response

[0318] Output: The response will be displayed on the chatbot interface.

[0319] Specific action: The chatbot interface displays the following three statements: "Newton's laws of motion are..."

[0320] Step 9: Additional Learning Support

[0321] If the user has further questions or would like more information, they can enter their questions into the chatbot again.

[0322] Input: Request text

[0323] Output: The follow-up question text is sent to the server.

[0324] Specific action: The user enters a new question, "Please give me a concrete example of the equations of motion," and clicks the submit button.

[0325] Step 10: Proposing an Individualized Learning Plan

[0326] Generative artificial intelligence generates an optimal learning plan based on the user's learning history, level of understanding, and analysis results of the emotion engine.

[0327] Input: Learning history, comprehension level, sentiment analysis results

[0328] Output: Study plan

[0329] Specific operation: The generative artificial intelligence creates a learning plan that suggests additional learning materials and practice problems related to mechanics.

[0330] Step 11: Submit and view your study plan

[0331] The server formats the newly generated training plan and sends it to the user's terminal.

[0332] The device receives the learning plan and displays it to the user.

[0333] Input: Study plan

[0334] Output: The learning plan is displayed on the chatbot interface.

[0335] Specific operation: The learning plan sent from the server is displayed on the chatbot interface, and "additional learning materials and practice problems related to mechanics" are presented to the user.

[0336] (Application Example 2)

[0337] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0338] Traditional educational chatbot systems and virtual store support systems often fail to adequately consider user emotions, leading to user confusion and unsatisfactory support. Furthermore, they lacked personalized suggestions and optimization tailored to specific user needs. This resulted in a diminished user experience and hindered the development of efficient and effective learning and purchasing experiences.

[0339] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0340] In this invention, the server includes means for receiving questions entered by the user, means for analyzing the user's emotions, and means for proposing individually optimized learning plans or product suggestions. This enables the generation of emotionally conscious answers and personalized suggestions.

[0341] "A means of receiving questions entered by the user" refers to a function that receives the content of questions entered by the user using a device.

[0342] "Means of sending received questions to the server" refers to the function of transferring questions entered by the user to the server via the internet.

[0343] "A means by which a server analyzes a question and generates an answer using generative artificial intelligence" refers to a function in which a server analyzes a received question and uses generative artificial intelligence to generate an appropriate answer.

[0344] "Means of sending generated responses to the user's terminal" refers to a function that sends back the responses generated on the server to the terminal being operated by the user.

[0345] "Means for displaying the generated response on the user's device" refers to a function that displays the response sent from the server on the user's device screen.

[0346] "An emotion analysis tool for analyzing user emotions" refers to a function that analyzes the user's emotional state based on the user's input text and dialogue history.

[0347] "Means for generating personalized suggestions based on sentiment analysis results" refers to a function that generates suggestions optimized for the user based on the results of sentiment analysis.

[0348] "Means of suggesting individually optimized learning plans or product recommendations" refers to a function that suggests the most suitable learning plan or product for a user based on their learning history, purchase history, level of understanding, and emotional state.

[0349] The system according to this invention provides personalized support using emotion analysis and generative artificial intelligence to improve the user's shopping experience in virtual stores. The embodiments of this system are described in detail below.

[0350] Hardware configuration

[0351] 1. User's device:

[0352] Mobile devices that can connect to the internet, such as smartphones and tablets.

[0353] This function allows you to input questions and display the generated answers.

[0354] 2. Server:

[0355] Cloud servers or dedicated servers are used.

[0356] It performs processing that includes generative artificial intelligence and an emotion analysis engine.

[0357] Software Configuration

[0358] 1. Generative artificial intelligence:

[0359] An artificial intelligence model that analyzes the content of a question and generates an appropriate answer.

[0360] It runs on a server.

[0361] 2. Emotion analysis engine:

[0362] Software for analyzing user emotions.

[0363] The system determines the user's emotional state based on their input text and dialogue history.

[0364] 3. Natural Language Processing (NLP) Module:

[0365] The system analyzes the question content and converts it into a format suitable for generative artificial intelligence.

[0366] Processing flow

[0367] When a user enters a question using a terminal, the question is sent from the terminal to the server. The server analyzes the received question and passes it to a generative artificial intelligence (AI) through a natural language processing module. The generative AI generates an appropriate answer, which the server then receives.

[0368] The server further analyzes the user's emotions using an emotion analysis engine and adjusts the generated responses and suggestions according to that emotional state. For example, if the user is confused, it will provide more attentive support and supplementary information.

[0369] Based on this, formatted and adjusted answers and personalized product suggestions are sent to the user's device and displayed on it. The user can review the answers and ask additional questions.

[0370] Specific examples and prompt statements

[0371] Specific example:

[0372] If a user asks, "What is the battery life of this smartphone?", the generative artificial intelligence will generate the answer, "The battery life of this smartphone is approximately 24 hours." If the emotion analysis engine determines that the user's emotion is "interest," a "battery pack" will also be suggested as a related product.

[0373] Examples of prompts for a generative AI model:

[0374] Please generate the correct answer to the following question: "What is the battery life of this smartphone?"

[0375] This allows generative AI models to generate appropriate answers to questions.

[0376] In this way, this invention can provide personalized learning support and product suggestions that take user emotions into consideration, thereby improving the user experience.

[0377] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0378] Step 1:

[0379] The user enters a question from their device. The user uses a smartphone or tablet to enter a question and expects some kind of response. The entered data is sent in text format through the device's input interface.

[0380] Step 2:

[0381] The terminal sends the question to the server. The text entered by the user is sent to the server as an HTTP request by the terminal's application. The request also includes additional information such as the user ID and session ID.

[0382] Step 3:

[0383] The server analyzes the question and formats it for transmission to the generative artificial intelligence. The server analyzes the received HTTP request and extracts the question content. Next, it uses a natural language processing module to convert the data into a format that the AI ​​model can understand. The input is raw text data, and the output is structured data passed to the generative artificial intelligence model.

[0384] Step 4:

[0385] Generative artificial intelligence generates the answer. The generative AI on the server receives a formatted question and generates an answer using a trained model and knowledge database. For example, if the question is "What is the battery life of this smartphone?", it will generate the answer "The battery life of this smartphone is approximately 24 hours."

[0386] Step 5:

[0387] The sentiment analysis engine analyzes the user's emotions. Based on the generated response and the user's input text, the sentiment analysis engine determines the user's emotional state. For example, if the text indicates that the user is "confused," the sentiment analysis result will be labeled "confused." The input is text data, and the output is a label indicating the emotional state.

[0388] Step 6:

[0389] The server generates personalized suggestions based on the generated responses and sentiment analysis results. Taking the sentiment analysis results into account, the server adjusts the responses, including additional explanations and related products. For example, a user who is "confused" will be offered more detailed explanations and support options. The input is the generated responses and sentiment analysis results, and the output is the adjusted and formatted responses.

[0390] Step 7:

[0391] The server sends the formatted and refined response to the terminal. The refined response and suggestions are then sent back to the user's terminal as an HTTP response. The input is the formatted and refined response data, and the output is the HTTP response data.

[0392] Step 8:

[0393] The terminal displays the received response to the user. The user's terminal parses the received HTTP response and displays it on the screen as text data. The input is the HTTP response data, and the output is the text information displayed on the user's terminal's display.

[0394] Step 9:

[0395] The user enters additional questions or comments. The user reviews the displayed answers and enters further questions if they have any unclear points or additional questions. This process is repeated as needed. The input is new questions or comments, and the output is updated question data.

[0396] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0397] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0398] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0399] [Second Embodiment]

[0400] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0401] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0402] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0403] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0404] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0405] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0406] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0407] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0408] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0409] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0410] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0411] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0412] The educational chatbot system according to the present invention receives questions entered by the user, generates appropriate answers using generative artificial intelligence, and provides those answers to the user, thereby providing individually optimized learning support. The configuration for implementing this system is described in detail below.

[0413] 1. User enters question

[0414] Users input questions into the educational chatbot using their device. This device can be a variety of devices, including PCs, smartphones, and tablets. For example, a user might input, "I want to learn about Newton's laws of motion."

[0415] 2. Submit your question

[0416] The terminal receives the entered question and generates an HTTP request, along with additional information such as the user ID and session ID, which it sends to the server. This request includes the user's input text.

[0417] 3. Receiving and analyzing questions

[0418] The server analyzes the received request and extracts the question content. In doing so, it has a mechanism to extract the user's input text from the request parameters and convert it into a format suitable for passing to a generative artificial intelligence (AI) for natural language processing.

[0419] 4. Question analysis and answer generation

[0420] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to a question about "Newton's laws of motion," the AI ​​would generate the following answer: "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0421] 5. Preparing to submit your response

[0422] The server formats the responses received from the generative artificial intelligence into a user-friendly format (e.g., HTML or JSON). This ensures that the responses are organized and displayed appropriately.

[0423] 6. Submit your response

[0424] The server generates a formatted response as an HTTP response and sends it to the user's terminal.

[0425] 7. Display the answer

[0426] The device analyzes the HTTP response received from the server, extracts the answer, and displays it. The user can then read this and continue their learning. For example, the text "Newton's laws of motion include the following three..." might appear on the device screen.

[0427] 8. Additional learning support

[0428] If the user needs more detailed information, they can enter another question into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?"

[0429] In this case, the terminal sends a new question to the server, and the analysis and answer generation process is repeated. The generative artificial intelligence provides a concrete example, such as, "When a force of 10N is applied to an object with a mass of 1kg, the acceleration will be 10 m / s²."

[0430] 9. Proposal of an individualized learning plan

[0431] Generative artificial intelligence generates an optimal learning plan based on the user's learning history and level of understanding. For example, if a user asks multiple questions about mechanics, it will suggest additional learning materials and practice problems related to that topic.

[0432] The server sends this learning plan to the user's device. The device displays the learning plan to the user and provides further learning support.

[0433] In this way, the educational chatbot system according to the present invention provides appropriate answers to user questions and proposes individually optimized learning plans, thereby achieving effective learning support.

[0434] The following describes the processing flow.

[0435] Step 1:

[0436] The user enters a question into the chatbot interface from their device. For example, they might type, "I want to know about Newton's laws of motion."

[0437] Step 2:

[0438] The terminal receives user input and generates an HTTP request containing the question. This request may also include additional information such as the user ID and session ID.

[0439] Step 3:

[0440] The terminal generates an HTTP request and sends it to the server. This allows the server to receive the user's question.

[0441] Step 4:

[0442] The server parses the received request and extracts the question content. Specifically, it extracts the user's input text from the request parameters.

[0443] Step 5:

[0444] The server formats the extracted question content for transmission to a generative artificial intelligence (AI) for natural language processing. It converts it to an appropriate format.

[0445] Step 6:

[0446] Generative artificial intelligence analyzes questions received from a server. It understands the intent of the question and retrieves information from relevant knowledge databases and trained models.

[0447] Step 7:

[0448] The generative artificial intelligence generates an answer based on the analysis results. For example, it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0449] Step 8:

[0450] The server receives the generated response and formats it for transmission to the user, such as HTML or JSON.

[0451] Step 9:

[0452] The server generates a formatted response as an HTTP response and sends it to the user's terminal.

[0453] Step 10:

[0454] The terminal analyzes the HTTP response received from the server and extracts the response content. If necessary, it converts it to a display format.

[0455] Step 11:

[0456] The device displays the answer to the user. For example, the text "Newton's laws of motion include the following three..." might appear on the device screen.

[0457] Step 12:

[0458] If a user wants more detailed information or additional questions, they can enter their questions into the chatbot again. For example, they might type, "Can you give me a concrete example of the equations of motion?"

[0459] Step 13:

[0460] The terminal sends a new question to the server, and a similar process is repeated starting from step 4.

[0461] Step 14:

[0462] Generative artificial intelligence generates a personalized learning plan based on the user's learning history and level of understanding. For example, it may suggest additional learning materials or practice problems related to mechanics.

[0463] Step 15:

[0464] The server generates an individualized learning plan and sends it to the user's device.

[0465] Step 16:

[0466] The device displays a learning plan to the user. For example, it may suggest text materials and practice problems that the user needs.

[0467] (Example 1)

[0468] Next, we will describe Example 1. 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."

[0469] Conventional educational support systems have a problem in that they do not adequately provide personalized learning support in response to questions entered by users. Furthermore, because the generated answers are not optimized based on the user's level of understanding or learning history, effective learning is difficult to achieve.

[0470] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0471] In this invention, the server includes means for receiving questions entered by the user, means for transmitting the received questions from the terminal to the server, means for the server to analyze the questions and generate answers using generative artificial intelligence, means for transmitting the generated answers from the server to the user's terminal, means for displaying the generated answers on the user's terminal, and means for proposing individually optimized learning plans. This enables individually optimized learning support for the user, thereby achieving effective learning.

[0472] A "user" refers to an individual or group that uses the system to input questions and receive answers.

[0473] "Device" refers to any device used by a user to input questions or view generated answers. Specifically, this includes PCs, smartphones, and tablets.

[0474] A "server" refers to a central computer system that receives questions submitted by users, analyzes them, and generates answers.

[0475] "Means of acceptance" refers to the process or mechanism by which the system accepts questions entered by the user.

[0476] "Means of transmission" refers to the methods and technologies used to send questions received from users and generated answers to the appropriate recipients.

[0477] "Means of analyzing questions" refers to methods and technologies for understanding the content of questions entered by users and extracting the information necessary to generate appropriate answers.

[0478] "Generative artificial intelligence" refers to AI models used to generate appropriate answers to questions entered by users. It utilizes natural language processing technology.

[0479] "Means of generating answers" refers to the process or mechanism that uses AI to create answers in order to provide appropriate responses to user questions.

[0480] "Means of display" refers to methods and technologies for visually presenting the generated answers on a device.

[0481] "Means of proposing learning plans" refers to the process and system for suggesting the most suitable learning methods and materials based on the user's learning history and level of understanding.

[0482] The educational chatbot system according to the present invention receives questions entered by the user, generates appropriate answers using generative artificial intelligence, and provides those answers to the user, thereby providing individually optimized learning support. The configuration for implementing this system is described in detail below.

[0483] First, users input questions into the educational chatbot using devices such as PCs, smartphones, or tablets. These devices can communicate with the server via the internet. For example, a user might input, "I want to learn about Newton's laws of motion."

[0484] The terminal receives the entered question and generates an HTTP request along with the user ID and session ID. This request is sent to the server, for example, using the JavaScript fetch API executed in the browser. This request contains the user's input text.

[0485] The server parses the received HTTP request and extracts the question content. During this process, the server uses a Python script to convert the request data into JSON format, which is then formatted for use with a generative artificial intelligence (AI) for natural language processing. A specific AI model used might be OpenAI's GPT-3.

[0486] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to a question about "Newton's laws of motion," it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0487] Next, the server formats the generated response into a user-friendly format. For example, it might use a Python library or a template engine to assemble the response as HTML. The formatted response is then generated as an HTTP response and sent from the server to the user's terminal.

[0488] The device analyzes the HTTP response received from the server, extracts the answer, and displays it. For example, the device's browser can render HTML and display text such as, "Newton's laws of motion include the following three..." on the screen.

[0489] Furthermore, if the user needs more detailed information, they can enter another question into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?" In this case, the device similarly sends a new question to the server, and the generative artificial intelligence provides a concrete example. It might generate an example such as, "When a force of 10N is applied to an object with a mass of 1kg, the acceleration will be 10m / s²."

[0490] Finally, the generative artificial intelligence generates an optimal learning plan based on the user's learning history and level of understanding. For example, if the user asks several questions about mechanics, it will suggest additional learning materials and practice problems related to that topic. The server sends this learning plan to the user's device, which can then display the learning plan to the user, providing further learning support.

[0491] As a concrete example, in response to the input prompt "Please tell me about Newton's laws of motion," the generated answer "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)." can be presented.

[0492] As described above, the educational chatbot system according to the present invention provides appropriate answers to user questions and proposes individually optimized learning plans, thereby achieving effective learning support.

[0493] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0494] Step 1:

[0495] Users enter questions into the educational chatbot using devices such as PCs, smartphones, and tablets. The entered questions are displayed as text in the input field. For example, when entering a question, a user might type "I want to know about Newton's laws of motion." The input data consists of the user's question text.

[0496] Step 2:

[0497] The terminal receives the entered question, adds the user ID and session ID, and generates an HTTP request. This request is then sent to the server. Specifically, the HTTP request is generated and sent using the JavaScript fetch API. The input data includes the user's question text, user ID, and session ID. The output is a structured HTTP request to be sent to the server.

[0498] Step 3:

[0499] The server receives the incoming HTTP request and parses the request data. Using a Python script, the server extracts the user's input text, which has been converted to JSON format, and then converts it back into a format suitable for a generative artificial intelligence (AI) for natural language processing. At this point, the user's question text is converted into a format that can be input to the AI ​​model. The input data is the HTTP request, and the output is the converted question text.

[0500] Step 4:

[0501] Generative artificial intelligence analyzes a given question and generates an answer using a trained model and knowledge database. Examples of generative AI models used include OpenAI's GPT-3. The AI ​​model generates answers such as, "Newton's laws of motion include the first law (law of inertia), the second law (equations of motion), and the third law (law of action and reaction)." The input data is a formatted question text, and the output is the generated answer text.

[0502] Step 5:

[0503] The server formats the responses received from the generative artificial intelligence into a user-friendly format. Specifically, it uses a Python template engine to format the response text into HTML or JSON format. The input data is the generated response text, and the output is the formatted response in HTML or JSON format.

[0504] Step 6:

[0505] The server generates a formatted response as an HTTP response and sends it to the user's terminal. The technologies used include web frameworks such as Flask and Django. Input data is formatted HTML or JSON, and output is the generated HTTP response.

[0506] Step 7:

[0507] The terminal analyzes the HTTP response received from the server, extracts the answer, and displays it. At this time, the browser renders HTML, visually presenting the answer to the user. Text such as "Newton's laws of motion include the following three..." is displayed on the screen. The input data is the HTTP response, and the output is the displayable answer text.

[0508] Step 8:

[0509] If the user needs more detailed information, they can enter another question into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?" This question will be processed again from step 1. The input data will be the new question text, and the output will be the newly generated answer text.

[0510] Step 9:

[0511] Generative artificial intelligence generates an optimal learning plan based on the user's learning history and level of understanding. For example, if a user asks several questions about mechanics, it will suggest additional learning materials and practice problems related to that topic. The server sends this learning plan to the user's terminal, which then displays it. The input data consists of the user's learning history and level of understanding, and the output is the generated learning plan.

[0512] (Application Example 1)

[0513] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0514] In modern online shopping, consumers face the challenge of selecting the best product from a vast amount of information. Therefore, there is a need for systems that efficiently answer consumer questions and recommend optimal products. Furthermore, there is a growing need for systems that can provide immediate and appropriate answers even when consumer questions are vague or when specific product information is requested.

[0515] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0516] In this invention, the server includes means for receiving questions entered by the user, means for analyzing the questions and generating answers using generative artificial intelligence, means for transmitting the generated answers to the user's terminal, and means for recommending the most suitable products and their information. This enables consumers to quickly obtain the most suitable product information.

[0517] "A means of receiving user-entered questions" refers to an interface that takes questions entered by the user using a terminal into the system and sends them to the server as the first step in processing.

[0518] "Means for sending received questions to the server" refers to a device or program that sends questions entered on the user terminal to the server in the form of an HTTP request or similar, and converts the data into a format that can be processed on the server side.

[0519] "A means by which a server analyzes a question and generates an answer using generative artificial intelligence" refers to a function in which a server analyzes a question received from a user through natural language processing and generates the optimal answer using generative artificial intelligence.

[0520] "Means of sending generated responses to the user's terminal" refers to a function that sends the responses generated on the server back to the user's terminal in the form of an HTTP response or similar, providing them in a format that the user can view.

[0521] "Means for displaying responses generated on the user's device" refers to an interface that displays responses received on the user's device in an easy-to-read format, allowing the user to confirm and use those responses.

[0522] "Means of proposing individually optimized learning plans" refers to a function that generates an individually optimized learning plan based on the user's learning history and question content, and then proposes it to the user.

[0523] "A means of analyzing product-related questions and recommending the most suitable products and their information" refers to a function that analyzes product-related questions entered by the user and uses generative artificial intelligence to recommend the most suitable products and related information for the user.

[0524] The intelligent purchasing assistant system for virtual stores according to the present invention generates appropriate answers to product-related questions entered by the user using generative artificial intelligence. The configuration for implementing this system is described in detail below.

[0525] 1. User enters question

[0526] Users use their smartphones to enter questions into an intelligent purchasing assistant app for a virtual store. These questions can include information about the category of product they want to buy or specific products. For example, a user might type, "Which laptop do you recommend?"

[0527] 2. Submit your question

[0528] The terminal receives the question entered by the user and generates an HTTP request, along with additional information such as the user ID and session ID, and sends it to the server. This request includes the user's input text. The software used here is a library for handling HTTP requests.

[0529] 3. Receiving and analyzing questions

[0530] The server parses the received request and extracts the question content. During this process, it has a means of extracting the user's input text from the request parameters and converting it into a format suitable for generative artificial intelligence (AI) for natural language processing. For example, the Python requests library can be used.

[0531] 4. Question analysis and answer generation

[0532] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to the question, "Which laptop do you recommend?", the AI ​​would generate the following answer: "We provide comparison information on products. Product name: Laptop A, Price: 80,000 yen, Review rating: 4.5."

[0533] 5. Preparing to submit your response

[0534] The server formats the responses received from the generative artificial intelligence into a user-friendly format (e.g., HTML or JSON). This ensures that the responses are organized and displayed appropriately.

[0535] 6. Submit your response

[0536] The server generates a formatted response as an HTTP response and sends it to the user's terminal.

[0537] 7. Display the answer

[0538] The terminal analyzes the HTTP response received from the server, extracts the answer, and displays it. The user can then view this information and select the most suitable product. For example, the terminal screen might display text such as "Product comparison information: Product name: Laptop A, Price: 80,000 yen, Review rating: 4.5."

[0539] 8. Additional Questions and Answers

[0540] If the user needs more detailed information, they can enter another question into the assistant app. For example, they might ask, "What are the features of laptop A?" In this case, the device sends the new question to the server, and the analysis and answer generation process is repeated. The generative artificial intelligence generates the answer, "The features of laptop A are its long battery life, high-resolution display, and fast processing speed."

[0541] 9. Individual Recommendations

[0542] Generative artificial intelligence suggests the most suitable products and plans for each user based on their past questions and purchase history. For example, if a user asks multiple questions about laptops, the system will suggest additional recommended products and promotional information related to that category. The server sends this recommendation information to the user's device. The device then displays the recommendations to the user, providing further options.

[0543] Example of a prompt

[0544] "Which laptop do you recommend?"

[0545] "What are the features of laptop A?"

[0546] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0547] Step 1:

[0548] Users access an intelligent purchasing assistant app for a virtual store using their smartphones and enter questions about the category of product they want to buy or specific products. This input is in text format, for example, "Which laptop do you recommend?"

[0549] Step 2:

[0550] The terminal receives the question entered by the user and generates an HTTP request, along with additional information such as the user ID and session ID, and sends it to the server. This request includes the user's input text. Specifically, the data obtained from the input form on the terminal is serialized using the json.dumps function and sent using the requests.post function.

[0551] Step 3:

[0552] The server parses the received HTTP request and extracts the user's question. Here, it extracts the user's input text from the request parameters and converts it into a format to be passed to a generative artificial intelligence for natural language processing. Specifically, it deserializes the request body using Python's json.loads function and extracts the text portion.

[0553] Step 4:

[0554] The server uses generative artificial intelligence to analyze user questions and generates answers using a trained model and knowledge database. For example, in response to the question, "Which laptop do you recommend?", the generative AI generates the answer, "We will provide comparison information on products. Product name: Laptop A, Price: 80,000 yen, Review rating: 4.5." In this process, the AI ​​model refers to a pre-trained dataset to predict the most appropriate answer.

[0555] Step 5:

[0556] The server formats the responses received from the generative artificial intelligence into a user-friendly format. Here, the response data is converted to HTML or JSON format so that it can be easily displayed on the user's device. Specifically, the generated responses are converted to the appropriate format using Python's HTML and JSON libraries.

[0557] Step 6:

[0558] The server generates a formatted response as an HTTP response and sends it to the user's device. Specifically, it creates a response object using the requests.post function and embeds the response data within it.

[0559] Step 7:

[0560] The terminal analyzes the HTTP response received from the server, extracts the generated response content, and displays it. The user can then view this and select the most suitable product. Specifically, the response body is deserialized and embedded into the corresponding HTML element.

[0561] Step 8:

[0562] If the user needs more detailed information, they can re-enter the question into the assistant app. For example, they might ask, "What are the features of laptop A?" The device sends the new question to the server, and the analysis and answer generation process is repeated.

[0563] Step 9:

[0564] Generative artificial intelligence suggests the most suitable products and plans for each user based on their past questions and purchase history. The server sends this recommendation information to the user's device, which then displays the recommendations to the user. Specifically, the AI ​​generates a recommendation model based on the user's interaction data and provides additional product and campaign information.

[0565] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0566] The educational chatbot system according to the present invention not only receives user questions, generates answers using generative artificial intelligence, displays the answers, and proposes individualized learning plans, but also recognizes the user's emotions and provides learning support. This system uses an emotion engine to analyze the user's emotions and provides an individually optimized learning experience.

[0567] 1. User enters question

[0568] The user enters their question into the chatbot interface from their device. For example, they might type, "I want to know about Newton's laws of motion."

[0569] 2. Submit your question

[0570] The terminal receives the entered question and generates an HTTP request containing the question content. This request may also include additional information such as the user ID and session ID.

[0571] 3. Receiving and analyzing questions

[0572] The server analyzes the received request and extracts the question content. During this process, it extracts the user's input text from the request parameters and converts it into a format suitable for generative artificial intelligence (AI) for natural language processing.

[0573] 4. Question analysis and answer generation

[0574] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to a question about "Newton's laws of motion," it might generate the answer, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0575] 5. Emotion analysis

[0576] The emotion engine analyzes the user's emotions based on their text input and conversation history. For example, if a user types "I'm confused and don't understand," the emotion engine recognizes that the user is confused.

[0577] 6. Preparing to submit your response

[0578] The server adjusts the generated responses based on the results of the emotion engine's analysis. For example, it can include clearer language and additional explanations for confused users.

[0579] 7. Submit your response

[0580] The server generates a formatted and adjusted response as an HTTP response and sends it to the user's terminal.

[0581] 8. Display the answer

[0582] The terminal analyzes the HTTP response received from the server, extracts the answer, and displays it. For example, it might display text such as, "Newton's laws of motion include the following three..."

[0583] 9. Additional learning support

[0584] If a user wants more detailed information or additional questions, they can enter their questions into the chatbot again. For example, they might ask, "Can you give me a concrete example of the equations of motion?"

[0585] 10. Proposal of an individualized learning plan

[0586] Generative artificial intelligence generates an optimal learning plan based on the user's learning history, understanding level, and the results of the emotion engine's analysis. For example, it may suggest additional learning materials or practice problems related to mechanics.

[0587] 11. Submitting and displaying your study plan

[0588] The server formats this learning plan and sends it to the user's device. The device displays it to the user and provides further learning support. For example, it may present the user with necessary text materials and practice problems.

[0589] The educational chatbot system according to the present invention enables efficient and effective learning by providing interactive learning support that also takes into account the user's emotions.

[0590] The following describes the processing flow.

[0591] Step 1:

[0592] The user enters a question into the chatbot interface from their device. For example, they might type, "I want to know about Newton's laws of motion."

[0593] Step 2:

[0594] The terminal receives user input and generates an HTTP request containing the question. This request also includes additional information such as the user ID and session ID.

[0595] Step 3:

[0596] The question is transmitted to the server by sending an HTTP request generated by the terminal to the server.

[0597] Step 4:

[0598] The server analyzes the received request and extracts the question content. It then extracts the user's input text from the request parameters and converts it into a format suitable for generative artificial intelligence (AI) for natural language processing.

[0599] Step 5:

[0600] Generative artificial intelligence analyzes questions received from the server and understands their intent. It then retrieves relevant information using a trained model and knowledge database.

[0601] Step 6:

[0602] Generative artificial intelligence generates appropriate answers. For example, it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0603] Step 7:

[0604] The emotion engine analyzes the user's emotions based on their input text and conversation history. For example, if a user inputs "I'm confused and don't understand," the emotion engine recognizes that the user is confused.

[0605] Step 8:

[0606] The server adjusts the content and tone of the responses based on the generated responses and the results of the sentiment engine's analysis. For example, it adds clear and polite explanations to confused users.

[0607] Step 9:

[0608] The server generates the adjusted response as an HTTP response and sends it to the user's terminal.

[0609] Step 10:

[0610] The terminal analyzes the HTTP response received from the server and extracts the response content. It then converts it to a display format as needed.

[0611] Step 11:

[0612] The device displays the answer to the user. For example, the text "Newton's laws of motion include the following three..." is displayed on the screen.

[0613] Step 12:

[0614] If a user wants more detailed information or additional questions, they can simply type their question back into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?"

[0615] Step 13:

[0616] The terminal sends a new question to the server, and a similar process is repeated starting from step 4.

[0617] Step 14:

[0618] Generative artificial intelligence generates an optimal learning plan based on the user's learning history, understanding level, and the results of the emotion engine's analysis. For example, it may suggest additional learning materials or practice problems related to mechanics.

[0619] Step 15:

[0620] The server formats the individual learning plan and sends it to the user's device.

[0621] Step 16:

[0622] The device displays a learning plan to the user. For example, it might suggest necessary text materials and practice exercises.

[0623] This invention realizes learning support that also takes into account the user's emotions through the steps described above.

[0624] (Example 2)

[0625] Next, we will describe Example 2. 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".

[0626] Conventional educational chatbot systems only mechanically respond to user questions, failing to recognize and appropriately address user emotions or confusion. As a result, learning effectiveness is limited, and improving user comprehension and motivation is difficult. Furthermore, they lack the ability to propose individually optimized learning plans, preventing them from providing effective learning support tailored to individual users.

[0627] The specific processing performed by the specific 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 analyzing the user's question and generating an answer using generative artificial intelligence, means for analyzing the user's emotions, and means for adjusting the answer generated based on the emotion analysis results. This makes it possible to provide an optimal answer that takes the user's emotions into consideration and propose an individually optimized learning plan.

[0628] A "user" is an individual or organization that uses this system to enter a question.

[0629] A "means of receiving questions" refers to an input device or interface for receiving text entered by a user.

[0630] A "data processing device" is a server or computer system used for the purpose of analyzing questions and generating answers.

[0631] "Means of analysis" refer to algorithms and software used to understand the received question and generate an appropriate answer.

[0632] "Generative artificial intelligence" refers to machine learning models and AI technologies trained to generate appropriate answers to user questions.

[0633] "Means for generating answers" refers to processes or systems that use generative artificial intelligence to produce answers to user questions.

[0634] A "display device" is a display or screen that visually shows the generated answer to the user.

[0635] A "learning plan" is a personalized suggestion of learning materials and practice problems designed to maximize the user's learning effectiveness.

[0636] "Means of analyzing emotions" refer to engines or software that determine an emotional state based on user input and history.

[0637] "Means of adjustment" refer to processes or systems that adapt the generated responses, based on the results of sentiment analysis, to the user's emotions.

[0638] The educational chatbot system according to the present invention receives user questions, generates answers using generative artificial intelligence, and provides a personalized learning experience by recognizing the user's emotions. Specifically, this system is implemented using the following hardware and software.

[0639] Hardware to use

[0640] Server: As a high-performance data processing unit, it performs question analysis, answer generation, sentiment analysis, and proposes learning plans.

[0641] Terminal: A device that provides an interface for users to access (such as a PC, smartphone, or tablet).

[0642] Software to use

[0643] Chatbot interface: A graphical user interface (GUI) for users to input questions.

[0644] Generative artificial intelligence: Machine learning models for generating answers to questions (e.g., GPT-4).

[0645] Sentiment analysis engine: Software that analyzes user text and recognizes emotions (e.g., IBM Watson Tone Analyzer).

[0646] Overview of program processing

[0647] 1. User Question Input: The user enters a specific question into the chatbot interface. For example, they might type, "I want to know about Newton's laws of motion."

[0648] 2. Sending the Question: The terminal generates an HTTP request based on the question received from the user and sends it to the server.

[0649] 3. Question analysis on the server: The server analyzes the received request, extracts the question content, and converts it into a format for passing to the generative artificial intelligence.

[0650] 4. Answer Generation: Generative artificial intelligence uses a trained model to generate the best possible answer to a question. For example, it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0651] 5. Sentiment Analysis: The sentiment analysis engine analyzes the user's emotions based on their text and conversation history. For example, if a user enters "I'm confused and don't understand," the sentiment engine recognizes that the user is confused.

[0652] 6. Adjusting and Sending Responses: The server adjusts the responses generated based on the sentiment analysis results and sends them to the device. If the user is confused, it can add clearer language or additional explanations.

[0653] 7. Displaying the answer: The terminal displays the answer received from the server to the user. For example, it might display text such as, "Newton's laws of motion include the following three..."

[0654] 8. Proposal of Personalized Learning Plans: Generative artificial intelligence generates an optimal learning plan, including additional learning materials and practice problems, based on the user's learning history, comprehension level, and sentiment analysis results.

[0655] 9. Displaying the learning plan: The server sends the generated learning plan to the terminal, which then displays it to the user. For example, additional practice problems related to mechanics might be presented.

[0656] This system allows for efficient and effective learning by providing appropriate answers and learning support while considering the user's emotions. Therefore, it offers a personalized learning experience, improving the user's understanding and motivation.

[0657] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0658] Step 1: User Question Input

[0659] The user opens the chatbot interface on their device and enters their question in the text input field. For example, they might type, "I want to know about Newton's laws of motion."

[0660] Input: User's question text

[0661] Output: The question text is displayed in the chatbot interface.

[0662] Specific action: The user types a question using the keyboard and clicks the submit button.

[0663] Step 2: Submit your question

[0664] The terminal retrieves the question text entered by the user, generates an HTTP request, and sends it to the server.

[0665] Input: Question text entered by the user, User ID, Session ID

[0666] Output: HTTP request sent to server

[0667] Specific operation: An HTTP request containing the question text "I want to know about Newton's laws of motion" is generated and sent to a specific URL on the server.

[0668] Step 3: Receiving and analyzing questions

[0669] The server receives an HTTP request sent from the terminal and extracts the question content from the request body. It then converts the extracted question content into a format suitable for natural language processing.

[0670] Input: HTTP Request

[0671] Output: The question content is converted into structured data such as JSON format.

[0672] Specific operation: The server parses the request body and converts the question text into JSON format.

[0673] Step 4: Question analysis and answer generation

[0674] Generative artificial intelligence analyzes questions received from a server and generates answers using a trained model.

[0675] Input: Structured question data

[0676] Output: Generated answer text

[0677] Specific operation: In response to the question "I want to know about Newton's laws of motion," it generates an answer such as "Newton's laws of motion include the first law, the second law, and the third law."

[0678] Step 5: Emotion Analysis

[0679] The emotion engine analyzes the user's emotions based on their text input and conversation history.

[0680] Input: User text input, conversation history

[0681] Output: Sentiment analysis result (e.g., confused)

[0682] Specific operation: If a user types "I'm confused and don't understand," the sentiment engine analyzes the tone of this text and determines that the user is confused.

[0683] Step 6: Prepare to submit your response

[0684] The server adjusts the response to match the user's emotions based on the generated response and the analysis results of the emotion engine.

[0685] Input: Generated response text, sentiment analysis results

[0686] Output: Adjusted answer text

[0687] Specific action: For confused users, the explanation will be formatted to be more helpful, such as "Newton's laws of motion consist of the following three..."

[0688] Step 7: Submit your response

[0689] The server generates the adjusted response as an HTTP response and sends it to the user's terminal.

[0690] Input: Adjusted response text

[0691] Output: HTTP response is sent to the terminal.

[0692] Specific operation: The server generates an HTTP response containing an answer such as "Newton's laws of motion include the following three..." and sends it to the terminal.

[0693] Step 8: Display the answer

[0694] The terminal analyzes the HTTP response received from the server, extracts the answer content, and displays it to the user.

[0695] Input: HTTP response

[0696] Output: The response will be displayed on the chatbot interface.

[0697] Specific action: The chatbot interface displays the following three statements: "Newton's laws of motion are..."

[0698] Step 9: Additional Learning Support

[0699] If the user has further questions or would like more information, they can enter their questions into the chatbot again.

[0700] Input: Request text

[0701] Output: The follow-up question text is sent to the server.

[0702] Specific action: The user enters a new question, "Please give me a concrete example of the equations of motion," and clicks the submit button.

[0703] Step 10: Proposing an Individualized Learning Plan

[0704] Generative artificial intelligence generates an optimal learning plan based on the user's learning history, level of understanding, and analysis results of the emotion engine.

[0705] Input: Learning history, comprehension level, sentiment analysis results

[0706] Output: Study plan

[0707] Specific operation: The generative artificial intelligence creates a learning plan that suggests additional learning materials and practice problems related to mechanics.

[0708] Step 11: Submit and view your study plan

[0709] The server formats the newly generated training plan and sends it to the user's terminal.

[0710] The device receives the learning plan and displays it to the user.

[0711] Input: Study plan

[0712] Output: The learning plan is displayed on the chatbot interface.

[0713] Specific operation: The learning plan sent from the server is displayed on the chatbot interface, and "additional learning materials and practice problems related to mechanics" are presented to the user.

[0714] (Application Example 2)

[0715] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0716] Traditional educational chatbot systems and virtual store support systems often fail to adequately consider user emotions, leading to user confusion and unsatisfactory support. Furthermore, they lacked personalized suggestions and optimization tailored to specific user needs. This resulted in a diminished user experience and hindered the development of efficient and effective learning and purchasing experiences.

[0717] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0718] In this invention, the server includes means for receiving questions entered by the user, means for analyzing the user's emotions, and means for proposing individually optimized learning plans or product suggestions. This enables the generation of emotionally conscious answers and personalized suggestions.

[0719] "A means of receiving questions entered by the user" refers to a function that receives the content of questions entered by the user using a device.

[0720] "Means of sending received questions to the server" refers to the function of transferring questions entered by the user to the server via the internet.

[0721] "A means by which a server analyzes a question and generates an answer using generative artificial intelligence" refers to a function in which a server analyzes a received question and uses generative artificial intelligence to generate an appropriate answer.

[0722] "Means of sending generated responses to the user's terminal" refers to a function that sends back the responses generated on the server to the terminal being operated by the user.

[0723] "Means for displaying the generated response on the user's device" refers to a function that displays the response sent from the server on the user's device screen.

[0724] "An emotion analysis tool for analyzing user emotions" refers to a function that analyzes the user's emotional state based on the user's input text and dialogue history.

[0725] "Means for generating personalized suggestions based on sentiment analysis results" refers to a function that generates suggestions optimized for the user based on the results of sentiment analysis.

[0726] "Means of suggesting individually optimized learning plans or product recommendations" refers to a function that suggests the most suitable learning plan or product for a user based on their learning history, purchase history, level of understanding, and emotional state.

[0727] The system according to this invention provides personalized support using emotion analysis and generative artificial intelligence to improve the user's shopping experience in virtual stores. The embodiments of this system are described in detail below.

[0728] Hardware configuration

[0729] 1. User's device:

[0730] Mobile devices that can connect to the internet, such as smartphones and tablets.

[0731] This function allows you to input questions and display the generated answers.

[0732] 2. Server:

[0733] Cloud servers or dedicated servers are used.

[0734] It performs processing that includes generative artificial intelligence and an emotion analysis engine.

[0735] Software Configuration

[0736] 1. Generative artificial intelligence:

[0737] An artificial intelligence model that analyzes the content of a question and generates an appropriate answer.

[0738] It runs on a server.

[0739] 2. Emotion analysis engine:

[0740] Software for analyzing user emotions.

[0741] The system determines the user's emotional state based on their input text and dialogue history.

[0742] 3. Natural Language Processing (NLP) Module:

[0743] The system analyzes the question content and converts it into a format suitable for generative artificial intelligence.

[0744] Processing flow

[0745] When a user enters a question using a terminal, the question is sent from the terminal to the server. The server analyzes the received question and passes it to a generative artificial intelligence (AI) through a natural language processing module. The generative AI generates an appropriate answer, which the server then receives.

[0746] The server further analyzes the user's emotions using an emotion analysis engine and adjusts the generated responses and suggestions according to that emotional state. For example, if the user is confused, it will provide more attentive support and supplementary information.

[0747] Based on this, formatted and adjusted answers and personalized product suggestions are sent to the user's device and displayed on it. The user can review the answers and ask additional questions.

[0748] Specific examples and prompt statements

[0749] Specific example:

[0750] If a user asks, "What is the battery life of this smartphone?", the generative artificial intelligence will generate the answer, "The battery life of this smartphone is approximately 24 hours." If the emotion analysis engine determines that the user's emotion is "interest," a "battery pack" will also be suggested as a related product.

[0751] Examples of prompts for a generative AI model:

[0752] Please generate the correct answer to the following question: "What is the battery life of this smartphone?"

[0753] This allows generative AI models to generate appropriate answers to questions.

[0754] In this way, this invention can provide personalized learning support and product suggestions that take user emotions into consideration, thereby improving the user experience.

[0755] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0756] Step 1:

[0757] The user enters a question from their device. The user uses a smartphone or tablet to enter a question and expects some kind of response. The entered data is sent in text format through the device's input interface.

[0758] Step 2:

[0759] The terminal sends the question to the server. The text entered by the user is sent to the server as an HTTP request by the terminal's application. The request also includes additional information such as the user ID and session ID.

[0760] Step 3:

[0761] The server analyzes the question and formats it for transmission to the generative artificial intelligence. The server analyzes the received HTTP request and extracts the question content. Next, it uses a natural language processing module to convert the data into a format that the AI ​​model can understand. The input is raw text data, and the output is structured data passed to the generative artificial intelligence model.

[0762] Step 4:

[0763] Generative artificial intelligence generates the answer. The generative AI on the server receives a formatted question and generates an answer using a trained model and knowledge database. For example, if the question is "What is the battery life of this smartphone?", it will generate the answer "The battery life of this smartphone is approximately 24 hours."

[0764] Step 5:

[0765] The sentiment analysis engine analyzes the user's emotions. Based on the generated response and the user's input text, the sentiment analysis engine determines the user's emotional state. For example, if the text indicates that the user is "confused," the sentiment analysis result will be labeled "confused." The input is text data, and the output is a label indicating the emotional state.

[0766] Step 6:

[0767] The server generates personalized suggestions based on the generated responses and sentiment analysis results. Taking the sentiment analysis results into account, the server adjusts the responses, including additional explanations and related products. For example, a user who is "confused" will be offered more detailed explanations and support options. The input is the generated responses and sentiment analysis results, and the output is the adjusted and formatted responses.

[0768] Step 7:

[0769] The server sends the formatted and refined response to the terminal. The refined response and suggestions are then sent back to the user's terminal as an HTTP response. The input is the formatted and refined response data, and the output is the HTTP response data.

[0770] Step 8:

[0771] The terminal displays the received response to the user. The user's terminal parses the received HTTP response and displays it on the screen as text data. The input is the HTTP response data, and the output is the text information displayed on the user's terminal's display.

[0772] Step 9:

[0773] The user enters additional questions or comments. The user reviews the displayed answers and enters further questions if they have any unclear points or additional questions. This process is repeated as needed. The input is new questions or comments, and the output is updated question data.

[0774] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0775] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0776] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0777] [Third Embodiment]

[0778] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0779] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0780] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0781] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0782] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0783] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0784] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0785] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0786] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0787] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0788] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0789] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0790] The educational chatbot system according to the present invention receives questions entered by the user, generates appropriate answers using generative artificial intelligence, and provides those answers to the user, thereby providing individually optimized learning support. The configuration for implementing this system is described in detail below.

[0791] 1. User enters question

[0792] Users input questions into the educational chatbot using their device. This device can be a variety of devices, including PCs, smartphones, and tablets. For example, a user might input, "I want to learn about Newton's laws of motion."

[0793] 2. Submit your question

[0794] The terminal receives the entered question and generates an HTTP request, along with additional information such as the user ID and session ID, which it sends to the server. This request includes the user's input text.

[0795] 3. Receiving and analyzing questions

[0796] The server analyzes the received request and extracts the question content. In doing so, it has a mechanism to extract the user's input text from the request parameters and convert it into a format suitable for passing to a generative artificial intelligence (AI) for natural language processing.

[0797] 4. Question analysis and answer generation

[0798] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to a question about "Newton's laws of motion," the AI ​​would generate the following answer: "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0799] 5. Preparing to submit your response

[0800] The server formats the responses received from the generative artificial intelligence into a user-friendly format (e.g., HTML or JSON). This ensures that the responses are organized and displayed appropriately.

[0801] 6. Submit your response

[0802] The server generates a formatted response as an HTTP response and sends it to the user's terminal.

[0803] 7. Display the answer

[0804] The device analyzes the HTTP response received from the server, extracts the answer, and displays it. The user can then read this and continue their learning. For example, the text "Newton's laws of motion include the following three..." might appear on the device screen.

[0805] 8. Additional learning support

[0806] If the user needs more detailed information, they can enter another question into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?"

[0807] In this case, the terminal sends a new question to the server, and the analysis and answer generation process is repeated. The generative artificial intelligence provides a concrete example, such as, "When a force of 10N is applied to an object with a mass of 1kg, the acceleration will be 10 m / s²."

[0808] 9. Proposal of an individualized learning plan

[0809] Generative artificial intelligence generates an optimal learning plan based on the user's learning history and level of understanding. For example, if a user asks multiple questions about mechanics, it will suggest additional learning materials and practice problems related to that topic.

[0810] The server sends this learning plan to the user's device. The device displays the learning plan to the user and provides further learning support.

[0811] In this way, the educational chatbot system according to the present invention provides appropriate answers to user questions and proposes individually optimized learning plans, thereby achieving effective learning support.

[0812] The following describes the processing flow.

[0813] Step 1:

[0814] The user enters a question into the chatbot interface from their device. For example, they might type, "I want to know about Newton's laws of motion."

[0815] Step 2:

[0816] The terminal receives user input and generates an HTTP request containing the question. This request may also include additional information such as the user ID and session ID.

[0817] Step 3:

[0818] The terminal generates an HTTP request and sends it to the server. This allows the server to receive the user's question.

[0819] Step 4:

[0820] The server parses the received request and extracts the question content. Specifically, it extracts the user's input text from the request parameters.

[0821] Step 5:

[0822] The server formats the extracted question content for transmission to a generative artificial intelligence (AI) for natural language processing. It converts it to an appropriate format.

[0823] Step 6:

[0824] Generative artificial intelligence analyzes questions received from a server. It understands the intent of the question and retrieves information from relevant knowledge databases and trained models.

[0825] Step 7:

[0826] The generative artificial intelligence generates an answer based on the analysis results. For example, it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0827] Step 8:

[0828] The server receives the generated response and formats it for transmission to the user, such as HTML or JSON.

[0829] Step 9:

[0830] The server generates a formatted response as an HTTP response and sends it to the user's terminal.

[0831] Step 10:

[0832] The terminal analyzes the HTTP response received from the server and extracts the response content. If necessary, it converts it to a display format.

[0833] Step 11:

[0834] The device displays the answer to the user. For example, the text "Newton's laws of motion include the following three..." might appear on the device screen.

[0835] Step 12:

[0836] If a user wants more detailed information or additional questions, they can enter their questions into the chatbot again. For example, they might type, "Can you give me a concrete example of the equations of motion?"

[0837] Step 13:

[0838] The terminal sends a new question to the server, and a similar process is repeated starting from step 4.

[0839] Step 14:

[0840] Generative artificial intelligence generates a personalized learning plan based on the user's learning history and level of understanding. For example, it may suggest additional learning materials or practice problems related to mechanics.

[0841] Step 15:

[0842] The server generates an individualized learning plan and sends it to the user's device.

[0843] Step 16:

[0844] The device displays a learning plan to the user. For example, it may suggest text materials and practice problems that the user needs.

[0845] (Example 1)

[0846] Next, we will describe Example 1. 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."

[0847] Conventional educational support systems have a problem in that they do not adequately provide personalized learning support in response to questions entered by users. Furthermore, because the generated answers are not optimized based on the user's level of understanding or learning history, effective learning is difficult to achieve.

[0848] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0849] In this invention, the server includes means for receiving questions entered by the user, means for transmitting the received questions from the terminal to the server, means for the server to analyze the questions and generate answers using generative artificial intelligence, means for transmitting the generated answers from the server to the user's terminal, means for displaying the generated answers on the user's terminal, and means for proposing individually optimized learning plans. This enables individually optimized learning support for the user, thereby achieving effective learning.

[0850] A "user" refers to an individual or group that uses the system to input questions and receive answers.

[0851] "Device" refers to any device used by a user to input questions or view generated answers. Specifically, this includes PCs, smartphones, and tablets.

[0852] A "server" refers to a central computer system that receives questions submitted by users, analyzes them, and generates answers.

[0853] "Means of acceptance" refers to the process or mechanism by which the system accepts questions entered by the user.

[0854] "Means of transmission" refers to the methods and technologies used to send questions received from users and generated answers to the appropriate recipients.

[0855] "Means of analyzing questions" refers to methods and technologies for understanding the content of questions entered by users and extracting the information necessary to generate appropriate answers.

[0856] "Generative artificial intelligence" refers to AI models used to generate appropriate answers to questions entered by users. It utilizes natural language processing technology.

[0857] "Means of generating answers" refers to the process or mechanism that uses AI to create answers in order to provide appropriate responses to user questions.

[0858] "Means of display" refers to methods and technologies for visually presenting the generated answers on a device.

[0859] "Means of proposing learning plans" refers to the process and system for suggesting the most suitable learning methods and materials based on the user's learning history and level of understanding.

[0860] The educational chatbot system according to the present invention receives questions entered by the user, generates appropriate answers using generative artificial intelligence, and provides those answers to the user, thereby providing individually optimized learning support. The configuration for implementing this system is described in detail below.

[0861] First, users input questions into the educational chatbot using devices such as PCs, smartphones, or tablets. These devices can communicate with the server via the internet. For example, a user might input, "I want to learn about Newton's laws of motion."

[0862] The terminal receives the entered question and generates an HTTP request along with the user ID and session ID. This request is sent to the server, for example, using the JavaScript fetch API executed in the browser. This request contains the user's input text.

[0863] The server parses the received HTTP request and extracts the question content. During this process, the server uses a Python script to convert the request data into JSON format, which is then formatted for use with a generative artificial intelligence (AI) for natural language processing. A specific AI model used might be OpenAI's GPT-3.

[0864] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to a question about "Newton's laws of motion," it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0865] Next, the server formats the generated response into a user-friendly format. For example, it might use a Python library or a template engine to assemble the response as HTML. The formatted response is then generated as an HTTP response and sent from the server to the user's terminal.

[0866] The device analyzes the HTTP response received from the server, extracts the answer, and displays it. For example, the device's browser can render HTML and display text such as, "Newton's laws of motion include the following three..." on the screen.

[0867] Furthermore, if the user needs more detailed information, they can enter another question into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?" In this case, the device similarly sends a new question to the server, and the generative artificial intelligence provides a concrete example. It might generate an example such as, "When a force of 10N is applied to an object with a mass of 1kg, the acceleration will be 10m / s²."

[0868] Finally, the generative artificial intelligence generates an optimal learning plan based on the user's learning history and level of understanding. For example, if the user asks several questions about mechanics, it will suggest additional learning materials and practice problems related to that topic. The server sends this learning plan to the user's device, which can then display the learning plan to the user, providing further learning support.

[0869] As a concrete example, in response to the input prompt "Please tell me about Newton's laws of motion," the generated answer "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)." can be presented.

[0870] As described above, the educational chatbot system according to the present invention provides appropriate answers to user questions and proposes individually optimized learning plans, thereby achieving effective learning support.

[0871] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0872] Step 1:

[0873] Users enter questions into the educational chatbot using devices such as PCs, smartphones, and tablets. The entered questions are displayed as text in the input field. For example, when entering a question, a user might type "I want to know about Newton's laws of motion." The input data consists of the user's question text.

[0874] Step 2:

[0875] The terminal receives the entered question, adds the user ID and session ID, and generates an HTTP request. This request is then sent to the server. Specifically, the HTTP request is generated and sent using the JavaScript fetch API. The input data includes the user's question text, user ID, and session ID. The output is a structured HTTP request to be sent to the server.

[0876] Step 3:

[0877] The server receives the incoming HTTP request and parses the request data. Using a Python script, the server extracts the user's input text, which has been converted to JSON format, and then converts it back into a format suitable for a generative artificial intelligence (AI) for natural language processing. At this point, the user's question text is converted into a format that can be input to the AI ​​model. The input data is the HTTP request, and the output is the converted question text.

[0878] Step 4:

[0879] Generative artificial intelligence analyzes a given question and generates an answer using a trained model and knowledge database. Examples of generative AI models used include OpenAI's GPT-3. The AI ​​model generates answers such as, "Newton's laws of motion include the first law (law of inertia), the second law (equations of motion), and the third law (law of action and reaction)." The input data is a formatted question text, and the output is the generated answer text.

[0880] Step 5:

[0881] The server formats the responses received from the generative artificial intelligence into a user-friendly format. Specifically, it uses a Python template engine to format the response text into HTML or JSON format. The input data is the generated response text, and the output is the formatted response in HTML or JSON format.

[0882] Step 6:

[0883] The server generates a formatted response as an HTTP response and sends it to the user's terminal. The technologies used include web frameworks such as Flask and Django. Input data is formatted HTML or JSON, and output is the generated HTTP response.

[0884] Step 7:

[0885] The terminal analyzes the HTTP response received from the server, extracts the answer, and displays it. At this time, the browser renders HTML, visually presenting the answer to the user. Text such as "Newton's laws of motion include the following three..." is displayed on the screen. The input data is the HTTP response, and the output is the displayable answer text.

[0886] Step 8:

[0887] If the user needs more detailed information, they can enter another question into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?" This question will be processed again from step 1. The input data will be the new question text, and the output will be the newly generated answer text.

[0888] Step 9:

[0889] Generative artificial intelligence generates an optimal learning plan based on the user's learning history and level of understanding. For example, if a user asks several questions about mechanics, it will suggest additional learning materials and practice problems related to that topic. The server sends this learning plan to the user's terminal, which then displays it. The input data consists of the user's learning history and level of understanding, and the output is the generated learning plan.

[0890] (Application Example 1)

[0891] Next, we will explain Application Example 1. In the following explanation, 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."

[0892] In modern online shopping, consumers face the challenge of selecting the best product from a vast amount of information. Therefore, there is a need for systems that efficiently answer consumer questions and recommend optimal products. Furthermore, there is a growing need for systems that can provide immediate and appropriate answers even when consumer questions are vague or when specific product information is requested.

[0893] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0894] In this invention, the server includes means for receiving questions entered by the user, means for analyzing the questions and generating answers using generative artificial intelligence, means for transmitting the generated answers to the user's terminal, and means for recommending the most suitable products and their information. This enables consumers to quickly obtain the most suitable product information.

[0895] "A means of receiving user-entered questions" refers to an interface that takes questions entered by the user using a terminal into the system and sends them to the server as the first step in processing.

[0896] "Means for sending received questions to the server" refers to a device or program that sends questions entered on the user terminal to the server in the form of an HTTP request or similar, and converts the data into a format that can be processed on the server side.

[0897] "A means by which a server analyzes a question and generates an answer using generative artificial intelligence" refers to a function in which a server analyzes a question received from a user through natural language processing and generates the optimal answer using generative artificial intelligence.

[0898] "Means of sending generated responses to the user's terminal" refers to a function that sends the responses generated on the server back to the user's terminal in the form of an HTTP response or similar, providing them in a format that the user can view.

[0899] "Means for displaying responses generated on the user's device" refers to an interface that displays responses received on the user's device in an easy-to-read format, allowing the user to confirm and use those responses.

[0900] "Means of proposing individually optimized learning plans" refers to a function that generates an individually optimized learning plan based on the user's learning history and question content, and then proposes it to the user.

[0901] "A means of analyzing product-related questions and recommending the most suitable products and their information" refers to a function that analyzes product-related questions entered by the user and uses generative artificial intelligence to recommend the most suitable products and related information for the user.

[0902] The intelligent purchasing assistant system for virtual stores according to the present invention generates appropriate answers to product-related questions entered by the user using generative artificial intelligence. The configuration for implementing this system is described in detail below.

[0903] 1. User enters question

[0904] Users use their smartphones to enter questions into an intelligent purchasing assistant app for a virtual store. These questions can include information about the category of product they want to buy or specific products. For example, a user might type, "Which laptop do you recommend?"

[0905] 2. Submit your question

[0906] The terminal receives the question entered by the user and generates an HTTP request, along with additional information such as the user ID and session ID, and sends it to the server. This request includes the user's input text. The software used here is a library for handling HTTP requests.

[0907] 3. Receiving and analyzing questions

[0908] The server parses the received request and extracts the question content. During this process, it has a means of extracting the user's input text from the request parameters and converting it into a format suitable for generative artificial intelligence (AI) for natural language processing. For example, the Python requests library can be used.

[0909] 4. Question analysis and answer generation

[0910] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to the question, "Which laptop do you recommend?", the AI ​​would generate the following answer: "We provide comparison information on products. Product name: Laptop A, Price: 80,000 yen, Review rating: 4.5."

[0911] 5. Preparing to submit your response

[0912] The server formats the responses received from the generative artificial intelligence into a user-friendly format (e.g., HTML or JSON). This ensures that the responses are organized and displayed appropriately.

[0913] 6. Submit your response

[0914] The server generates a formatted response as an HTTP response and sends it to the user's terminal.

[0915] 7. Display the answer

[0916] The terminal analyzes the HTTP response received from the server, extracts the answer, and displays it. The user can then view this information and select the most suitable product. For example, the terminal screen might display text such as "Product comparison information: Product name: Laptop A, Price: 80,000 yen, Review rating: 4.5."

[0917] 8. Additional Questions and Answers

[0918] If the user needs more detailed information, they can enter another question into the assistant app. For example, they might ask, "What are the features of laptop A?" In this case, the device sends the new question to the server, and the analysis and answer generation process is repeated. The generative artificial intelligence generates the answer, "The features of laptop A are its long battery life, high-resolution display, and fast processing speed."

[0919] 9. Individual Recommendations

[0920] Generative artificial intelligence suggests the most suitable products and plans for each user based on their past questions and purchase history. For example, if a user asks multiple questions about laptops, the system will suggest additional recommended products and promotional information related to that category. The server sends this recommendation information to the user's device. The device then displays the recommendations to the user, providing further options.

[0921] Example of a prompt

[0922] "Which laptop do you recommend?"

[0923] "What are the features of laptop A?"

[0924] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0925] Step 1:

[0926] Users access an intelligent purchasing assistant app for a virtual store using their smartphones and enter questions about the category of product they want to buy or specific products. This input is in text format, for example, "Which laptop do you recommend?"

[0927] Step 2:

[0928] The terminal receives the question entered by the user and generates an HTTP request, along with additional information such as the user ID and session ID, and sends it to the server. This request includes the user's input text. Specifically, the data obtained from the input form on the terminal is serialized using the json.dumps function and sent using the requests.post function.

[0929] Step 3:

[0930] The server parses the received HTTP request and extracts the user's question. Here, it extracts the user's input text from the request parameters and converts it into a format to be passed to a generative artificial intelligence for natural language processing. Specifically, it deserializes the request body using Python's json.loads function and extracts the text portion.

[0931] Step 4:

[0932] The server uses generative artificial intelligence to analyze user questions and generates answers using a trained model and knowledge database. For example, in response to the question, "Which laptop do you recommend?", the generative AI generates the answer, "We will provide comparison information on products. Product name: Laptop A, Price: 80,000 yen, Review rating: 4.5." In this process, the AI ​​model refers to a pre-trained dataset to predict the most appropriate answer.

[0933] Step 5:

[0934] The server formats the responses received from the generative artificial intelligence into a user-friendly format. Here, the response data is converted to HTML or JSON format so that it can be easily displayed on the user's device. Specifically, the generated responses are converted to the appropriate format using Python's HTML and JSON libraries.

[0935] Step 6:

[0936] The server generates a formatted response as an HTTP response and sends it to the user's device. Specifically, it creates a response object using the requests.post function and embeds the response data within it.

[0937] Step 7:

[0938] The terminal analyzes the HTTP response received from the server, extracts the generated response content, and displays it. The user can then view this and select the most suitable product. Specifically, the response body is deserialized and embedded into the corresponding HTML element.

[0939] Step 8:

[0940] If the user needs more detailed information, they can re-enter the question into the assistant app. For example, they might ask, "What are the features of laptop A?" The device sends the new question to the server, and the analysis and answer generation process is repeated.

[0941] Step 9:

[0942] Generative artificial intelligence suggests the most suitable products and plans for each user based on their past questions and purchase history. The server sends this recommendation information to the user's device, which then displays the recommendations to the user. Specifically, the AI ​​generates a recommendation model based on the user's interaction data and provides additional product and campaign information.

[0943] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0944] The educational chatbot system according to the present invention not only receives user questions, generates answers using generative artificial intelligence, displays the answers, and proposes individualized learning plans, but also recognizes the user's emotions and provides learning support. This system uses an emotion engine to analyze the user's emotions and provides an individually optimized learning experience.

[0945] 1. User enters question

[0946] The user enters their question into the chatbot interface from their device. For example, they might type, "I want to know about Newton's laws of motion."

[0947] 2. Submit your question

[0948] The terminal receives the entered question and generates an HTTP request containing the question content. This request may also include additional information such as the user ID and session ID.

[0949] 3. Receiving and analyzing questions

[0950] The server analyzes the received request and extracts the question content. During this process, it extracts the user's input text from the request parameters and converts it into a format suitable for generative artificial intelligence (AI) for natural language processing.

[0951] 4. Question analysis and answer generation

[0952] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to a question about "Newton's laws of motion," it might generate the answer, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0953] 5. Emotion analysis

[0954] The emotion engine analyzes the user's emotions based on their text input and conversation history. For example, if a user types "I'm confused and don't understand," the emotion engine recognizes that the user is confused.

[0955] 6. Preparing to submit your response

[0956] The server adjusts the generated responses based on the results of the emotion engine's analysis. For example, it can include clearer language and additional explanations for confused users.

[0957] 7. Submit your response

[0958] The server generates a formatted and adjusted response as an HTTP response and sends it to the user's terminal.

[0959] 8. Display the answer

[0960] The terminal analyzes the HTTP response received from the server, extracts the answer, and displays it. For example, it might display text such as, "Newton's laws of motion include the following three..."

[0961] 9. Additional learning support

[0962] If a user wants more detailed information or additional questions, they can enter their questions into the chatbot again. For example, they might ask, "Can you give me a concrete example of the equations of motion?"

[0963] 10. Proposal of an individualized learning plan

[0964] Generative artificial intelligence generates an optimal learning plan based on the user's learning history, understanding level, and the results of the emotion engine's analysis. For example, it may suggest additional learning materials or practice problems related to mechanics.

[0965] 11. Submitting and displaying your study plan

[0966] The server formats this learning plan and sends it to the user's device. The device displays it to the user and provides further learning support. For example, it may present the user with necessary text materials and practice problems.

[0967] The educational chatbot system according to the present invention enables efficient and effective learning by providing interactive learning support that also takes into account the user's emotions.

[0968] The following describes the processing flow.

[0969] Step 1:

[0970] The user enters a question into the chatbot interface from their device. For example, they might type, "I want to know about Newton's laws of motion."

[0971] Step 2:

[0972] The terminal receives user input and generates an HTTP request containing the question. This request also includes additional information such as the user ID and session ID.

[0973] Step 3:

[0974] The question is transmitted to the server by sending an HTTP request generated by the terminal to the server.

[0975] Step 4:

[0976] The server analyzes the received request and extracts the question content. It then extracts the user's input text from the request parameters and converts it into a format suitable for generative artificial intelligence (AI) for natural language processing.

[0977] Step 5:

[0978] Generative artificial intelligence analyzes questions received from the server and understands their intent. It then retrieves relevant information using a trained model and knowledge database.

[0979] Step 6:

[0980] Generative artificial intelligence generates appropriate answers. For example, it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[0981] Step 7:

[0982] The emotion engine analyzes the user's emotions based on their input text and conversation history. For example, if a user inputs "I'm confused and don't understand," the emotion engine recognizes that the user is confused.

[0983] Step 8:

[0984] The server adjusts the content and tone of the responses based on the generated responses and the results of the sentiment engine's analysis. For example, it adds clear and polite explanations to confused users.

[0985] Step 9:

[0986] The server generates the adjusted response as an HTTP response and sends it to the user's terminal.

[0987] Step 10:

[0988] The terminal analyzes the HTTP response received from the server and extracts the response content. It then converts it to a display format as needed.

[0989] Step 11:

[0990] The device displays the answer to the user. For example, the text "Newton's laws of motion include the following three..." is displayed on the screen.

[0991] Step 12:

[0992] If a user wants more detailed information or additional questions, they can simply type their question back into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?"

[0993] Step 13:

[0994] The terminal sends a new question to the server, and a similar process is repeated starting from step 4.

[0995] Step 14:

[0996] Generative artificial intelligence generates an optimal learning plan based on the user's learning history, understanding level, and the results of the emotion engine's analysis. For example, it may suggest additional learning materials or practice problems related to mechanics.

[0997] Step 15:

[0998] The server formats the individual learning plan and sends it to the user's device.

[0999] Step 16:

[1000] The device displays a learning plan to the user. For example, it might suggest necessary text materials and practice exercises.

[1001] This invention realizes learning support that also takes into account the user's emotions through the steps described above.

[1002] (Example 2)

[1003] Next, we will describe Example 2. 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."

[1004] Conventional educational chatbot systems only mechanically respond to user questions, failing to recognize and appropriately address user emotions or confusion. As a result, learning effectiveness is limited, and improving user comprehension and motivation is difficult. Furthermore, they lack the ability to propose individually optimized learning plans, preventing them from providing effective learning support tailored to individual users.

[1005] The specific processing performed by the specific 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 analyzing the user's question and generating an answer using generative artificial intelligence, means for analyzing the user's emotions, and means for adjusting the answer generated based on the emotion analysis results. This makes it possible to provide an optimal answer that takes the user's emotions into consideration and propose an individually optimized learning plan.

[1006] A "user" is an individual or organization that uses this system to enter a question.

[1007] A "means of receiving questions" refers to an input device or interface for receiving text entered by a user.

[1008] A "data processing device" is a server or computer system used for the purpose of analyzing questions and generating answers.

[1009] "Means of analysis" refer to algorithms and software used to understand the received question and generate an appropriate answer.

[1010] "Generative artificial intelligence" refers to machine learning models and AI technologies trained to generate appropriate answers to user questions.

[1011] "Means for generating answers" refers to processes or systems that use generative artificial intelligence to produce answers to user questions.

[1012] A "display device" is a display or screen that visually shows the generated answer to the user.

[1013] A "learning plan" is a personalized suggestion of learning materials and practice problems designed to maximize the user's learning effectiveness.

[1014] "Means of analyzing emotions" refer to engines or software that determine an emotional state based on user input and history.

[1015] "Means of adjustment" refer to processes or systems that adapt the generated responses, based on the results of sentiment analysis, to the user's emotions.

[1016] The educational chatbot system according to the present invention receives user questions, generates answers using generative artificial intelligence, and provides a personalized learning experience by recognizing the user's emotions. Specifically, this system is implemented using the following hardware and software.

[1017] Hardware to use

[1018] Server: As a high-performance data processing unit, it performs question analysis, answer generation, sentiment analysis, and proposes learning plans.

[1019] Terminal: A device that provides an interface for users to access (such as a PC, smartphone, or tablet).

[1020] Software to use

[1021] Chatbot interface: A graphical user interface (GUI) for users to input questions.

[1022] Generative artificial intelligence: Machine learning models for generating answers to questions (e.g., GPT-4).

[1023] Sentiment analysis engine: Software that analyzes user text and recognizes emotions (e.g., IBM Watson Tone Analyzer).

[1024] Overview of program processing

[1025] 1. User Question Input: The user enters a specific question into the chatbot interface. For example, they might type, "I want to know about Newton's laws of motion."

[1026] 2. Sending the Question: The terminal generates an HTTP request based on the question received from the user and sends it to the server.

[1027] 3. Question analysis on the server: The server analyzes the received request, extracts the question content, and converts it into a format for passing to the generative artificial intelligence.

[1028] 4. Answer Generation: Generative artificial intelligence uses a trained model to generate the best possible answer to a question. For example, it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[1029] 5. Sentiment Analysis: The sentiment analysis engine analyzes the user's emotions based on their text and conversation history. For example, if a user enters "I'm confused and don't understand," the sentiment engine recognizes that the user is confused.

[1030] 6. Adjusting and Sending Responses: The server adjusts the responses generated based on the sentiment analysis results and sends them to the device. If the user is confused, it can add clearer language or additional explanations.

[1031] 7. Displaying the answer: The terminal displays the answer received from the server to the user. For example, it might display text such as, "Newton's laws of motion include the following three..."

[1032] 8. Proposal of Personalized Learning Plans: Generative artificial intelligence generates an optimal learning plan, including additional learning materials and practice problems, based on the user's learning history, comprehension level, and sentiment analysis results.

[1033] 9. Displaying the learning plan: The server sends the generated learning plan to the terminal, which then displays it to the user. For example, additional practice problems related to mechanics might be presented.

[1034] This system allows for efficient and effective learning by providing appropriate answers and learning support while considering the user's emotions. Therefore, it offers a personalized learning experience, improving the user's understanding and motivation.

[1035] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1036] Step 1: User Question Input

[1037] The user opens the chatbot interface on their device and enters their question in the text input field. For example, they might type, "I want to know about Newton's laws of motion."

[1038] Input: User's question text

[1039] Output: The question text is displayed in the chatbot interface.

[1040] Specific action: The user types a question using the keyboard and clicks the submit button.

[1041] Step 2: Submit your question

[1042] The terminal retrieves the question text entered by the user, generates an HTTP request, and sends it to the server.

[1043] Input: Question text entered by the user, User ID, Session ID

[1044] Output: HTTP request sent to server

[1045] Specific operation: An HTTP request containing the question text "I want to know about Newton's laws of motion" is generated and sent to a specific URL on the server.

[1046] Step 3: Receiving and analyzing questions

[1047] The server receives an HTTP request sent from the terminal and extracts the question content from the request body. It then converts the extracted question content into a format suitable for natural language processing.

[1048] Input: HTTP Request

[1049] Output: The question content is converted into structured data such as JSON format.

[1050] Specific operation: The server parses the request body and converts the question text into JSON format.

[1051] Step 4: Question analysis and answer generation

[1052] Generative artificial intelligence analyzes questions received from a server and generates answers using a trained model.

[1053] Input: Structured question data

[1054] Output: Generated answer text

[1055] Specific operation: In response to the question "I want to know about Newton's laws of motion," it generates an answer such as "Newton's laws of motion include the first law, the second law, and the third law."

[1056] Step 5: Emotion Analysis

[1057] The emotion engine analyzes the user's emotions based on their text input and conversation history.

[1058] Input: User text input, conversation history

[1059] Output: Sentiment analysis result (e.g., confused)

[1060] Specific operation: If a user types "I'm confused and don't understand," the sentiment engine analyzes the tone of this text and determines that the user is confused.

[1061] Step 6: Prepare to submit your response

[1062] The server adjusts the response to match the user's emotions based on the generated response and the analysis results of the emotion engine.

[1063] Input: Generated response text, sentiment analysis results

[1064] Output: Adjusted answer text

[1065] Specific action: For confused users, the explanation will be formatted to be more helpful, such as "Newton's laws of motion consist of the following three..."

[1066] Step 7: Submit your response

[1067] The server generates the adjusted response as an HTTP response and sends it to the user's terminal.

[1068] Input: Adjusted response text

[1069] Output: HTTP response is sent to the terminal.

[1070] Specific operation: The server generates an HTTP response containing an answer such as "Newton's laws of motion include the following three..." and sends it to the terminal.

[1071] Step 8: Display the answer

[1072] The terminal analyzes the HTTP response received from the server, extracts the answer content, and displays it to the user.

[1073] Input: HTTP response

[1074] Output: The response will be displayed on the chatbot interface.

[1075] Specific action: The chatbot interface displays the following three statements: "Newton's laws of motion are..."

[1076] Step 9: Additional Learning Support

[1077] If the user has further questions or would like more information, they can enter their questions into the chatbot again.

[1078] Input: Request text

[1079] Output: The follow-up question text is sent to the server.

[1080] Specific action: The user enters a new question, "Please give me a concrete example of the equations of motion," and clicks the submit button.

[1081] Step 10: Proposing an Individualized Learning Plan

[1082] Generative artificial intelligence generates an optimal learning plan based on the user's learning history, level of understanding, and analysis results of the emotion engine.

[1083] Input: Learning history, comprehension level, sentiment analysis results

[1084] Output: Study plan

[1085] Specific operation: The generative artificial intelligence creates a learning plan that suggests additional learning materials and practice problems related to mechanics.

[1086] Step 11: Submit and view your study plan

[1087] The server formats the newly generated training plan and sends it to the user's terminal.

[1088] The device receives the learning plan and displays it to the user.

[1089] Input: Study plan

[1090] Output: The learning plan is displayed on the chatbot interface.

[1091] Specific operation: The learning plan sent from the server is displayed on the chatbot interface, and "additional learning materials and practice problems related to mechanics" are presented to the user.

[1092] (Application Example 2)

[1093] Next, we will explain application example 2. In the following explanation, 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."

[1094] Traditional educational chatbot systems and virtual store support systems often fail to adequately consider user emotions, leading to user confusion and unsatisfactory support. Furthermore, they lacked personalized suggestions and optimization tailored to specific user needs. This resulted in a diminished user experience and hindered the development of efficient and effective learning and purchasing experiences.

[1095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1096] In this invention, the server includes means for receiving questions entered by the user, means for analyzing the user's emotions, and means for proposing individually optimized learning plans or product suggestions. This enables the generation of emotionally conscious answers and personalized suggestions.

[1097] "A means of receiving questions entered by the user" refers to a function that receives the content of questions entered by the user using a device.

[1098] "Means of sending received questions to the server" refers to the function of transferring questions entered by the user to the server via the internet.

[1099] "A means by which a server analyzes a question and generates an answer using generative artificial intelligence" refers to a function in which a server analyzes a received question and uses generative artificial intelligence to generate an appropriate answer.

[1100] "Means of sending generated responses to the user's terminal" refers to a function that sends back the responses generated on the server to the terminal being operated by the user.

[1101] "Means for displaying the generated response on the user's device" refers to a function that displays the response sent from the server on the user's device screen.

[1102] "An emotion analysis tool for analyzing user emotions" refers to a function that analyzes the user's emotional state based on the user's input text and dialogue history.

[1103] "Means for generating personalized suggestions based on sentiment analysis results" refers to a function that generates suggestions optimized for the user based on the results of sentiment analysis.

[1104] "Means of suggesting individually optimized learning plans or product recommendations" refers to a function that suggests the most suitable learning plan or product for a user based on their learning history, purchase history, level of understanding, and emotional state.

[1105] The system according to this invention provides personalized support using emotion analysis and generative artificial intelligence to improve the user's shopping experience in virtual stores. The embodiments of this system are described in detail below.

[1106] Hardware configuration

[1107] 1. User's device:

[1108] Mobile devices that can connect to the internet, such as smartphones and tablets.

[1109] This function allows you to input questions and display the generated answers.

[1110] 2. Server:

[1111] Cloud servers or dedicated servers are used.

[1112] It performs processing that includes generative artificial intelligence and an emotion analysis engine.

[1113] Software Configuration

[1114] 1. Generative artificial intelligence:

[1115] An artificial intelligence model that analyzes the content of a question and generates an appropriate answer.

[1116] It runs on a server.

[1117] 2. Emotion analysis engine:

[1118] Software for analyzing user emotions.

[1119] The system determines the user's emotional state based on their input text and dialogue history.

[1120] 3. Natural Language Processing (NLP) Module:

[1121] The system analyzes the question content and converts it into a format suitable for generative artificial intelligence.

[1122] Processing flow

[1123] When a user enters a question using a terminal, the question is sent from the terminal to the server. The server analyzes the received question and passes it to a generative artificial intelligence (AI) through a natural language processing module. The generative AI generates an appropriate answer, which the server then receives.

[1124] The server further analyzes the user's emotions using an emotion analysis engine and adjusts the generated responses and suggestions according to that emotional state. For example, if the user is confused, it will provide more attentive support and supplementary information.

[1125] Based on this, formatted and adjusted answers and personalized product suggestions are sent to the user's device and displayed on it. The user can review the answers and ask additional questions.

[1126] Specific examples and prompt statements

[1127] Specific example:

[1128] If a user asks, "What is the battery life of this smartphone?", the generative artificial intelligence will generate the answer, "The battery life of this smartphone is approximately 24 hours." If the emotion analysis engine determines that the user's emotion is "interest," a "battery pack" will also be suggested as a related product.

[1129] Examples of prompts for a generative AI model:

[1130] Please generate the correct answer to the following question: "What is the battery life of this smartphone?"

[1131] This allows generative AI models to generate appropriate answers to questions.

[1132] In this way, this invention can provide personalized learning support and product suggestions that take user emotions into consideration, thereby improving the user experience.

[1133] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1134] Step 1:

[1135] The user enters a question from their device. The user uses a smartphone or tablet to enter a question and expects some kind of response. The entered data is sent in text format through the device's input interface.

[1136] Step 2:

[1137] The terminal sends the question to the server. The text entered by the user is sent to the server as an HTTP request by the terminal's application. The request also includes additional information such as the user ID and session ID.

[1138] Step 3:

[1139] The server analyzes the question and formats it for transmission to the generative artificial intelligence. The server analyzes the received HTTP request and extracts the question content. Next, it uses a natural language processing module to convert the data into a format that the AI ​​model can understand. The input is raw text data, and the output is structured data passed to the generative artificial intelligence model.

[1140] Step 4:

[1141] Generative artificial intelligence generates the answer. The generative AI on the server receives a formatted question and generates an answer using a trained model and knowledge database. For example, if the question is "What is the battery life of this smartphone?", it will generate the answer "The battery life of this smartphone is approximately 24 hours."

[1142] Step 5:

[1143] The sentiment analysis engine analyzes the user's emotions. Based on the generated response and the user's input text, the sentiment analysis engine determines the user's emotional state. For example, if the text indicates that the user is "confused," the sentiment analysis result will be labeled "confused." The input is text data, and the output is a label indicating the emotional state.

[1144] Step 6:

[1145] The server generates personalized suggestions based on the generated responses and sentiment analysis results. Taking the sentiment analysis results into account, the server adjusts the responses, including additional explanations and related products. For example, a user who is "confused" will be offered more detailed explanations and support options. The input is the generated responses and sentiment analysis results, and the output is the adjusted and formatted responses.

[1146] Step 7:

[1147] The server sends the formatted and refined response to the terminal. The refined response and suggestions are then sent back to the user's terminal as an HTTP response. The input is the formatted and refined response data, and the output is the HTTP response data.

[1148] Step 8:

[1149] The terminal displays the received response to the user. The user's terminal parses the received HTTP response and displays it on the screen as text data. The input is the HTTP response data, and the output is the text information displayed on the user's terminal's display.

[1150] Step 9:

[1151] The user enters additional questions or comments. The user reviews the displayed answers and enters further questions if they have any unclear points or additional questions. This process is repeated as needed. The input is new questions or comments, and the output is updated question data.

[1152] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1153] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1154] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1155] [Fourth Embodiment]

[1156] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1157] As shown in Figure 7, the 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.

[1158] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1159] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1160] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1161] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1162] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1163] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1164] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1165] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1166] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1167] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1168] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1169] The educational chatbot system according to the present invention receives questions entered by the user, generates appropriate answers using generative artificial intelligence, and provides those answers to the user, thereby providing individually optimized learning support. The configuration for implementing this system is described in detail below.

[1170] 1. User enters question

[1171] Users input questions into the educational chatbot using their device. This device can be a variety of devices, including PCs, smartphones, and tablets. For example, a user might input, "I want to learn about Newton's laws of motion."

[1172] 2. Submit your question

[1173] The terminal receives the entered question and generates an HTTP request, along with additional information such as the user ID and session ID, which it sends to the server. This request includes the user's input text.

[1174] 3. Receiving and analyzing questions

[1175] The server analyzes the received request and extracts the question content. In doing so, it has a mechanism to extract the user's input text from the request parameters and convert it into a format suitable for passing to a generative artificial intelligence (AI) for natural language processing.

[1176] 4. Question analysis and answer generation

[1177] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to a question about "Newton's laws of motion," the AI ​​would generate the following answer: "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[1178] 5. Preparing to submit your response

[1179] The server formats the responses received from the generative artificial intelligence into a user-friendly format (e.g., HTML or JSON). This ensures that the responses are organized and displayed appropriately.

[1180] 6. Submit your response

[1181] The server generates a formatted response as an HTTP response and sends it to the user's terminal.

[1182] 7. Display the answer

[1183] The device analyzes the HTTP response received from the server, extracts the answer, and displays it. The user can then read this and continue their learning. For example, the text "Newton's laws of motion include the following three..." might appear on the device screen.

[1184] 8. Additional learning support

[1185] If the user needs more detailed information, they can enter another question into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?"

[1186] In this case, the terminal sends a new question to the server, and the analysis and answer generation process is repeated. The generative artificial intelligence provides a concrete example, such as, "When a force of 10N is applied to an object with a mass of 1kg, the acceleration will be 10 m / s²."

[1187] 9. Proposal of an individualized learning plan

[1188] Generative artificial intelligence generates an optimal learning plan based on the user's learning history and level of understanding. For example, if a user asks multiple questions about mechanics, it will suggest additional learning materials and practice problems related to that topic.

[1189] The server sends this learning plan to the user's device. The device displays the learning plan to the user and provides further learning support.

[1190] In this way, the educational chatbot system according to the present invention provides appropriate answers to user questions and proposes individually optimized learning plans, thereby achieving effective learning support.

[1191] The following describes the processing flow.

[1192] Step 1:

[1193] The user enters a question into the chatbot interface from their device. For example, they might type, "I want to know about Newton's laws of motion."

[1194] Step 2:

[1195] The terminal receives user input and generates an HTTP request containing the question. This request may also include additional information such as the user ID and session ID.

[1196] Step 3:

[1197] The terminal generates an HTTP request and sends it to the server. This allows the server to receive the user's question.

[1198] Step 4:

[1199] The server parses the received request and extracts the question content. Specifically, it extracts the user's input text from the request parameters.

[1200] Step 5:

[1201] The server formats the extracted question content for transmission to a generative artificial intelligence (AI) for natural language processing. It converts it to an appropriate format.

[1202] Step 6:

[1203] Generative artificial intelligence analyzes questions received from a server. It understands the intent of the question and retrieves information from relevant knowledge databases and trained models.

[1204] Step 7:

[1205] The generative artificial intelligence generates an answer based on the analysis results. For example, it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[1206] Step 8:

[1207] The server receives the generated response and formats it for transmission to the user, such as HTML or JSON.

[1208] Step 9:

[1209] The server generates a formatted response as an HTTP response and sends it to the user's terminal.

[1210] Step 10:

[1211] The terminal analyzes the HTTP response received from the server and extracts the response content. If necessary, it converts it to a display format.

[1212] Step 11:

[1213] The device displays the answer to the user. For example, the text "Newton's laws of motion include the following three..." might appear on the device screen.

[1214] Step 12:

[1215] If a user wants more detailed information or additional questions, they can enter their questions into the chatbot again. For example, they might type, "Can you give me a concrete example of the equations of motion?"

[1216] Step 13:

[1217] The terminal sends a new question to the server, and a similar process is repeated starting from step 4.

[1218] Step 14:

[1219] Generative artificial intelligence generates a personalized learning plan based on the user's learning history and level of understanding. For example, it may suggest additional learning materials or practice problems related to mechanics.

[1220] Step 15:

[1221] The server generates an individualized learning plan and sends it to the user's device.

[1222] Step 16:

[1223] The device displays a learning plan to the user. For example, it may suggest text materials and practice problems that the user needs.

[1224] (Example 1)

[1225] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1226] Conventional educational support systems have a problem in that they do not adequately provide personalized learning support in response to questions entered by users. Furthermore, because the generated answers are not optimized based on the user's level of understanding or learning history, effective learning is difficult to achieve.

[1227] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1228] In this invention, the server includes means for receiving questions entered by the user, means for transmitting the received questions from the terminal to the server, means for the server to analyze the questions and generate answers using generative artificial intelligence, means for transmitting the generated answers from the server to the user's terminal, means for displaying the generated answers on the user's terminal, and means for proposing individually optimized learning plans. This enables individually optimized learning support for the user, thereby achieving effective learning.

[1229] A "user" refers to an individual or group that uses the system to input questions and receive answers.

[1230] "Device" refers to any device used by a user to input questions or view generated answers. Specifically, this includes PCs, smartphones, and tablets.

[1231] A "server" refers to a central computer system that receives questions submitted by users, analyzes them, and generates answers.

[1232] "Means of acceptance" refers to the process or mechanism by which the system accepts questions entered by the user.

[1233] "Means of transmission" refers to the methods and technologies used to send questions received from users and generated answers to the appropriate recipients.

[1234] "Means of analyzing questions" refers to methods and technologies for understanding the content of questions entered by users and extracting the information necessary to generate appropriate answers.

[1235] "Generative artificial intelligence" refers to AI models used to generate appropriate answers to questions entered by users. It utilizes natural language processing technology.

[1236] "Means of generating answers" refers to the process or mechanism that uses AI to create answers in order to provide appropriate responses to user questions.

[1237] "Means of display" refers to methods and technologies for visually presenting the generated answers on a device.

[1238] "Means of proposing learning plans" refers to the process and system for suggesting the most suitable learning methods and materials based on the user's learning history and level of understanding.

[1239] The educational chatbot system according to the present invention receives questions entered by the user, generates appropriate answers using generative artificial intelligence, and provides those answers to the user, thereby providing individually optimized learning support. The configuration for implementing this system is described in detail below.

[1240] First, users input questions into the educational chatbot using devices such as PCs, smartphones, or tablets. These devices can communicate with the server via the internet. For example, a user might input, "I want to learn about Newton's laws of motion."

[1241] The terminal receives the entered question and generates an HTTP request along with the user ID and session ID. This request is sent to the server, for example, using the JavaScript fetch API executed in the browser. This request contains the user's input text.

[1242] The server parses the received HTTP request and extracts the question content. During this process, the server uses a Python script to convert the request data into JSON format, which is then formatted for use with a generative artificial intelligence (AI) for natural language processing. A specific AI model used might be OpenAI's GPT-3.

[1243] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to a question about "Newton's laws of motion," it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[1244] Next, the server formats the generated response into a user-friendly format. For example, it might use a Python library or a template engine to assemble the response as HTML. The formatted response is then generated as an HTTP response and sent from the server to the user's terminal.

[1245] The device analyzes the HTTP response received from the server, extracts the answer, and displays it. For example, the device's browser can render HTML and display text such as, "Newton's laws of motion include the following three..." on the screen.

[1246] Furthermore, if the user needs more detailed information, they can enter another question into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?" In this case, the device similarly sends a new question to the server, and the generative artificial intelligence provides a concrete example. It might generate an example such as, "When a force of 10N is applied to an object with a mass of 1kg, the acceleration will be 10m / s²."

[1247] Finally, the generative artificial intelligence generates an optimal learning plan based on the user's learning history and level of understanding. For example, if the user asks several questions about mechanics, it will suggest additional learning materials and practice problems related to that topic. The server sends this learning plan to the user's device, which can then display the learning plan to the user, providing further learning support.

[1248] As a concrete example, in response to the input prompt "Please tell me about Newton's laws of motion," the generated answer "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)." can be presented.

[1249] As described above, the educational chatbot system according to the present invention provides appropriate answers to user questions and proposes individually optimized learning plans, thereby achieving effective learning support.

[1250] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1251] Step 1:

[1252] Users enter questions into the educational chatbot using devices such as PCs, smartphones, and tablets. The entered questions are displayed as text in the input field. For example, when entering a question, a user might type "I want to know about Newton's laws of motion." The input data consists of the user's question text.

[1253] Step 2:

[1254] The terminal receives the entered question, adds the user ID and session ID, and generates an HTTP request. This request is then sent to the server. Specifically, the HTTP request is generated and sent using the JavaScript fetch API. The input data includes the user's question text, user ID, and session ID. The output is a structured HTTP request to be sent to the server.

[1255] Step 3:

[1256] The server receives the incoming HTTP request and parses the request data. Using a Python script, the server extracts the user's input text, which has been converted to JSON format, and then converts it back into a format suitable for a generative artificial intelligence (AI) for natural language processing. At this point, the user's question text is converted into a format that can be input to the AI ​​model. The input data is the HTTP request, and the output is the converted question text.

[1257] Step 4:

[1258] Generative artificial intelligence analyzes a given question and generates an answer using a trained model and knowledge database. Examples of generative AI models used include OpenAI's GPT-3. The AI ​​model generates answers such as, "Newton's laws of motion include the first law (law of inertia), the second law (equations of motion), and the third law (law of action and reaction)." The input data is a formatted question text, and the output is the generated answer text.

[1259] Step 5:

[1260] The server formats the responses received from the generative artificial intelligence into a user-friendly format. Specifically, it uses a Python template engine to format the response text into HTML or JSON format. The input data is the generated response text, and the output is the formatted response in HTML or JSON format.

[1261] Step 6:

[1262] The server generates a formatted response as an HTTP response and sends it to the user's terminal. The technologies used include web frameworks such as Flask and Django. Input data is formatted HTML or JSON, and output is the generated HTTP response.

[1263] Step 7:

[1264] The terminal analyzes the HTTP response received from the server, extracts the answer, and displays it. At this time, the browser renders HTML, visually presenting the answer to the user. Text such as "Newton's laws of motion include the following three..." is displayed on the screen. The input data is the HTTP response, and the output is the displayable answer text.

[1265] Step 8:

[1266] If the user needs more detailed information, they can enter another question into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?" This question will be processed again from step 1. The input data will be the new question text, and the output will be the newly generated answer text.

[1267] Step 9:

[1268] Generative artificial intelligence generates an optimal learning plan based on the user's learning history and level of understanding. For example, if a user asks several questions about mechanics, it will suggest additional learning materials and practice problems related to that topic. The server sends this learning plan to the user's terminal, which then displays it. The input data consists of the user's learning history and level of understanding, and the output is the generated learning plan.

[1269] (Application Example 1)

[1270] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1271] In modern online shopping, consumers face the challenge of selecting the best product from a vast amount of information. Therefore, there is a need for systems that efficiently answer consumer questions and recommend optimal products. Furthermore, there is a growing need for systems that can provide immediate and appropriate answers even when consumer questions are vague or when specific product information is requested.

[1272] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1273] In this invention, the server includes means for receiving questions entered by the user, means for analyzing the questions and generating answers using generative artificial intelligence, means for transmitting the generated answers to the user's terminal, and means for recommending the most suitable products and their information. This enables consumers to quickly obtain the most suitable product information.

[1274] "A means of receiving user-entered questions" refers to an interface that takes questions entered by the user using a terminal into the system and sends them to the server as the first step in processing.

[1275] "Means for sending received questions to the server" refers to a device or program that sends questions entered on the user terminal to the server in the form of an HTTP request or similar, and converts the data into a format that can be processed on the server side.

[1276] "A means by which a server analyzes a question and generates an answer using generative artificial intelligence" refers to a function in which a server analyzes a question received from a user through natural language processing and generates the optimal answer using generative artificial intelligence.

[1277] "Means of sending generated responses to the user's terminal" refers to a function that sends the responses generated on the server back to the user's terminal in the form of an HTTP response or similar, providing them in a format that the user can view.

[1278] "Means for displaying responses generated on the user's device" refers to an interface that displays responses received on the user's device in an easy-to-read format, allowing the user to confirm and use those responses.

[1279] "Means of proposing individually optimized learning plans" refers to a function that generates an individually optimized learning plan based on the user's learning history and question content, and then proposes it to the user.

[1280] "A means of analyzing product-related questions and recommending the most suitable products and their information" refers to a function that analyzes product-related questions entered by the user and uses generative artificial intelligence to recommend the most suitable products and related information for the user.

[1281] The intelligent purchasing assistant system for virtual stores according to the present invention generates appropriate answers to product-related questions entered by the user using generative artificial intelligence. The configuration for implementing this system is described in detail below.

[1282] 1. User enters question

[1283] Users use their smartphones to enter questions into an intelligent purchasing assistant app for a virtual store. These questions can include information about the category of product they want to buy or specific products. For example, a user might type, "Which laptop do you recommend?"

[1284] 2. Submit your question

[1285] The terminal receives the question entered by the user and generates an HTTP request, along with additional information such as the user ID and session ID, and sends it to the server. This request includes the user's input text. The software used here is a library for handling HTTP requests.

[1286] 3. Receiving and analyzing questions

[1287] The server parses the received request and extracts the question content. During this process, it has a means of extracting the user's input text from the request parameters and converting it into a format suitable for generative artificial intelligence (AI) for natural language processing. For example, the Python requests library can be used.

[1288] 4. Question analysis and answer generation

[1289] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to the question, "Which laptop do you recommend?", the AI ​​would generate the following answer: "We provide comparison information on products. Product name: Laptop A, Price: 80,000 yen, Review rating: 4.5."

[1290] 5. Preparing to submit your response

[1291] The server formats the responses received from the generative artificial intelligence into a user-friendly format (e.g., HTML or JSON). This ensures that the responses are organized and displayed appropriately.

[1292] 6. Submit your response

[1293] The server generates a formatted response as an HTTP response and sends it to the user's terminal.

[1294] 7. Display the answer

[1295] The terminal analyzes the HTTP response received from the server, extracts the answer, and displays it. The user can then view this information and select the most suitable product. For example, the terminal screen might display text such as "Product comparison information: Product name: Laptop A, Price: 80,000 yen, Review rating: 4.5."

[1296] 8. Additional Questions and Answers

[1297] If the user needs more detailed information, they can enter another question into the assistant app. For example, they might ask, "What are the features of laptop A?" In this case, the device sends the new question to the server, and the analysis and answer generation process is repeated. The generative artificial intelligence generates the answer, "The features of laptop A are its long battery life, high-resolution display, and fast processing speed."

[1298] 9. Individual Recommendations

[1299] Generative artificial intelligence suggests the most suitable products and plans for each user based on their past questions and purchase history. For example, if a user asks multiple questions about laptops, the system will suggest additional recommended products and promotional information related to that category. The server sends this recommendation information to the user's device. The device then displays the recommendations to the user, providing further options.

[1300] Example of a prompt

[1301] "Which laptop do you recommend?"

[1302] "What are the features of laptop A?"

[1303] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1304] Step 1:

[1305] Users access an intelligent purchasing assistant app for a virtual store using their smartphones and enter questions about the category of product they want to buy or specific products. This input is in text format, for example, "Which laptop do you recommend?"

[1306] Step 2:

[1307] The terminal receives the question entered by the user and generates an HTTP request, along with additional information such as the user ID and session ID, and sends it to the server. This request includes the user's input text. Specifically, the data obtained from the input form on the terminal is serialized using the json.dumps function and sent using the requests.post function.

[1308] Step 3:

[1309] The server parses the received HTTP request and extracts the user's question. Here, it extracts the user's input text from the request parameters and converts it into a format to be passed to a generative artificial intelligence for natural language processing. Specifically, it deserializes the request body using Python's json.loads function and extracts the text portion.

[1310] Step 4:

[1311] The server uses generative artificial intelligence to analyze user questions and generates answers using a trained model and knowledge database. For example, in response to the question, "Which laptop do you recommend?", the generative AI generates the answer, "We will provide comparison information on products. Product name: Laptop A, Price: 80,000 yen, Review rating: 4.5." In this process, the AI ​​model refers to a pre-trained dataset to predict the most appropriate answer.

[1312] Step 5:

[1313] The server formats the responses received from the generative artificial intelligence into a user-friendly format. Here, the response data is converted to HTML or JSON format so that it can be easily displayed on the user's device. Specifically, the generated responses are converted to the appropriate format using Python's HTML and JSON libraries.

[1314] Step 6:

[1315] The server generates a formatted response as an HTTP response and sends it to the user's device. Specifically, it creates a response object using the requests.post function and embeds the response data within it.

[1316] Step 7:

[1317] The terminal analyzes the HTTP response received from the server, extracts the generated response content, and displays it. The user can then view this and select the most suitable product. Specifically, the response body is deserialized and embedded into the corresponding HTML element.

[1318] Step 8:

[1319] If the user needs more detailed information, they can re-enter the question into the assistant app. For example, they might ask, "What are the features of laptop A?" The device sends the new question to the server, and the analysis and answer generation process is repeated.

[1320] Step 9:

[1321] Generative artificial intelligence suggests the most suitable products and plans for each user based on their past questions and purchase history. The server sends this recommendation information to the user's device, which then displays the recommendations to the user. Specifically, the AI ​​generates a recommendation model based on the user's interaction data and provides additional product and campaign information.

[1322] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1323] The educational chatbot system according to the present invention not only receives user questions, generates answers using generative artificial intelligence, displays the answers, and proposes individualized learning plans, but also recognizes the user's emotions and provides learning support. This system uses an emotion engine to analyze the user's emotions and provides an individually optimized learning experience.

[1324] 1. User enters question

[1325] The user enters their question into the chatbot interface from their device. For example, they might type, "I want to know about Newton's laws of motion."

[1326] 2. Submit your question

[1327] The terminal receives the entered question and generates an HTTP request containing the question content. This request may also include additional information such as the user ID and session ID.

[1328] 3. Receiving and analyzing questions

[1329] The server analyzes the received request and extracts the question content. During this process, it extracts the user's input text from the request parameters and converts it into a format suitable for generative artificial intelligence (AI) for natural language processing.

[1330] 4. Question analysis and answer generation

[1331] Generative artificial intelligence analyzes acquired questions and generates answers using trained models and knowledge databases. For example, in response to a question about "Newton's laws of motion," it might generate the answer, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[1332] 5. Emotion analysis

[1333] The emotion engine analyzes the user's emotions based on their text input and conversation history. For example, if a user types "I'm confused and don't understand," the emotion engine recognizes that the user is confused.

[1334] 6. Preparing to submit your response

[1335] The server adjusts the generated responses based on the results of the emotion engine's analysis. For example, it can include clearer language and additional explanations for confused users.

[1336] 7. Submit your response

[1337] The server generates a formatted and adjusted response as an HTTP response and sends it to the user's terminal.

[1338] 8. Display the answer

[1339] The terminal analyzes the HTTP response received from the server, extracts the answer, and displays it. For example, it might display text such as, "Newton's laws of motion include the following three..."

[1340] 9. Additional learning support

[1341] If a user wants more detailed information or additional questions, they can enter their questions into the chatbot again. For example, they might ask, "Can you give me a concrete example of the equations of motion?"

[1342] 10. Proposal of an individualized learning plan

[1343] Generative artificial intelligence generates an optimal learning plan based on the user's learning history, understanding level, and the results of the emotion engine's analysis. For example, it may suggest additional learning materials or practice problems related to mechanics.

[1344] 11. Submitting and displaying your study plan

[1345] The server formats this learning plan and sends it to the user's device. The device displays it to the user and provides further learning support. For example, it may present the user with necessary text materials and practice problems.

[1346] The educational chatbot system according to the present invention enables efficient and effective learning by providing interactive learning support that also takes into account the user's emotions.

[1347] The following describes the processing flow.

[1348] Step 1:

[1349] The user enters a question into the chatbot interface from their device. For example, they might type, "I want to know about Newton's laws of motion."

[1350] Step 2:

[1351] The terminal receives user input and generates an HTTP request containing the question. This request also includes additional information such as the user ID and session ID.

[1352] Step 3:

[1353] The question is transmitted to the server by sending an HTTP request generated by the terminal to the server.

[1354] Step 4:

[1355] The server analyzes the received request and extracts the question content. It then extracts the user's input text from the request parameters and converts it into a format suitable for generative artificial intelligence (AI) for natural language processing.

[1356] Step 5:

[1357] Generative artificial intelligence analyzes questions received from the server and understands their intent. It then retrieves relevant information using a trained model and knowledge database.

[1358] Step 6:

[1359] Generative artificial intelligence generates appropriate answers. For example, it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[1360] Step 7:

[1361] The emotion engine analyzes the user's emotions based on their input text and conversation history. For example, if a user inputs "I'm confused and don't understand," the emotion engine recognizes that the user is confused.

[1362] Step 8:

[1363] The server adjusts the content and tone of the responses based on the generated responses and the results of the sentiment engine's analysis. For example, it adds clear and polite explanations to confused users.

[1364] Step 9:

[1365] The server generates the adjusted response as an HTTP response and sends it to the user's terminal.

[1366] Step 10:

[1367] The terminal analyzes the HTTP response received from the server and extracts the response content. It then converts it to a display format as needed.

[1368] Step 11:

[1369] The device displays the answer to the user. For example, the text "Newton's laws of motion include the following three..." is displayed on the screen.

[1370] Step 12:

[1371] If a user wants more detailed information or additional questions, they can simply type their question back into the chatbot. For example, they might ask, "Can you give me a concrete example of the equations of motion?"

[1372] Step 13:

[1373] The terminal sends a new question to the server, and a similar process is repeated starting from step 4.

[1374] Step 14:

[1375] Generative artificial intelligence generates an optimal learning plan based on the user's learning history, understanding level, and the results of the emotion engine's analysis. For example, it may suggest additional learning materials or practice problems related to mechanics.

[1376] Step 15:

[1377] The server formats the individual learning plan and sends it to the user's device.

[1378] Step 16:

[1379] The device displays a learning plan to the user. For example, it might suggest necessary text materials and practice exercises.

[1380] This invention realizes learning support that also takes into account the user's emotions through the steps described above.

[1381] (Example 2)

[1382] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1383] Conventional educational chatbot systems only mechanically respond to user questions, failing to recognize and appropriately address user emotions or confusion. As a result, learning effectiveness is limited, and improving user comprehension and motivation is difficult. Furthermore, they lack the ability to propose individually optimized learning plans, preventing them from providing effective learning support tailored to individual users.

[1384] The specific processing performed by the specific 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 analyzing the user's question and generating an answer using generative artificial intelligence, means for analyzing the user's emotions, and means for adjusting the answer generated based on the emotion analysis results. This makes it possible to provide an optimal answer that takes the user's emotions into consideration and propose an individually optimized learning plan.

[1385] A "user" is an individual or organization that uses this system to enter a question.

[1386] A "means of receiving questions" refers to an input device or interface for receiving text entered by a user.

[1387] A "data processing device" is a server or computer system used for the purpose of analyzing questions and generating answers.

[1388] "Means of analysis" refer to algorithms and software used to understand the received question and generate an appropriate answer.

[1389] "Generative artificial intelligence" refers to machine learning models and AI technologies trained to generate appropriate answers to user questions.

[1390] "Means for generating answers" refers to processes or systems that use generative artificial intelligence to produce answers to user questions.

[1391] A "display device" is a display or screen that visually shows the generated answer to the user.

[1392] A "learning plan" is a personalized suggestion of learning materials and practice problems designed to maximize the user's learning effectiveness.

[1393] "Means of analyzing emotions" refer to engines or software that determine an emotional state based on user input and history.

[1394] "Means of adjustment" refer to processes or systems that adapt the generated responses, based on the results of sentiment analysis, to the user's emotions.

[1395] The educational chatbot system according to the present invention receives user questions, generates answers using generative artificial intelligence, and provides a personalized learning experience by recognizing the user's emotions. Specifically, this system is implemented using the following hardware and software.

[1396] Hardware to use

[1397] Server: As a high-performance data processing unit, it performs question analysis, answer generation, sentiment analysis, and proposes learning plans.

[1398] Terminal: A device that provides an interface for users to access (such as a PC, smartphone, or tablet).

[1399] Software to use

[1400] Chatbot interface: A graphical user interface (GUI) for users to input questions.

[1401] Generative artificial intelligence: Machine learning models for generating answers to questions (e.g., GPT-4).

[1402] Sentiment analysis engine: Software that analyzes user text and recognizes emotions (e.g., IBM Watson Tone Analyzer).

[1403] Overview of program processing

[1404] 1. User Question Input: The user enters a specific question into the chatbot interface. For example, they might type, "I want to know about Newton's laws of motion."

[1405] 2. Sending the Question: The terminal generates an HTTP request based on the question received from the user and sends it to the server.

[1406] 3. Question analysis on the server: The server analyzes the received request, extracts the question content, and converts it into a format for passing to the generative artificial intelligence.

[1407] 4. Answer Generation: Generative artificial intelligence uses a trained model to generate the best possible answer to a question. For example, it might generate an answer such as, "Newton's laws of motion include the first law (law of inertia), the second law (equation of motion), and the third law (law of action and reaction)."

[1408] 5. Sentiment Analysis: The sentiment analysis engine analyzes the user's emotions based on their text and conversation history. For example, if a user enters "I'm confused and don't understand," the sentiment engine recognizes that the user is confused.

[1409] 6. Adjusting and Sending Responses: The server adjusts the responses generated based on the sentiment analysis results and sends them to the device. If the user is confused, it can add clearer language or additional explanations.

[1410] 7. Displaying the answer: The terminal displays the answer received from the server to the user. For example, it might display text such as, "Newton's laws of motion include the following three..."

[1411] 8. Proposal of Personalized Learning Plans: Generative artificial intelligence generates an optimal learning plan, including additional learning materials and practice problems, based on the user's learning history, comprehension level, and sentiment analysis results.

[1412] 9. Displaying the learning plan: The server sends the generated learning plan to the terminal, which then displays it to the user. For example, additional practice problems related to mechanics might be presented.

[1413] This system allows for efficient and effective learning by providing appropriate answers and learning support while considering the user's emotions. Therefore, it offers a personalized learning experience, improving the user's understanding and motivation.

[1414] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1415] Step 1: User Question Input

[1416] The user opens the chatbot interface on their device and enters their question in the text input field. For example, they might type, "I want to know about Newton's laws of motion."

[1417] Input: User's question text

[1418] Output: The question text is displayed in the chatbot interface.

[1419] Specific action: The user types a question using the keyboard and clicks the submit button.

[1420] Step 2: Submit your question

[1421] The terminal retrieves the question text entered by the user, generates an HTTP request, and sends it to the server.

[1422] Input: Question text entered by the user, User ID, Session ID

[1423] Output: HTTP request sent to server

[1424] Specific operation: An HTTP request containing the question text "I want to know about Newton's laws of motion" is generated and sent to a specific URL on the server.

[1425] Step 3: Receiving and analyzing questions

[1426] The server receives an HTTP request sent from the terminal and extracts the question content from the request body. It then converts the extracted question content into a format suitable for natural language processing.

[1427] Input: HTTP Request

[1428] Output: The question content is converted into structured data such as JSON format.

[1429] Specific operation: The server parses the request body and converts the question text into JSON format.

[1430] Step 4: Question analysis and answer generation

[1431] Generative artificial intelligence analyzes questions received from a server and generates answers using a trained model.

[1432] Input: Structured question data

[1433] Output: Generated answer text

[1434] Specific operation: In response to the question "I want to know about Newton's laws of motion," it generates an answer such as "Newton's laws of motion include the first law, the second law, and the third law."

[1435] Step 5: Emotion Analysis

[1436] The emotion engine analyzes the user's emotions based on their text input and conversation history.

[1437] Input: User text input, conversation history

[1438] Output: Sentiment analysis result (e.g., confused)

[1439] Specific operation: If a user types "I'm confused and don't understand," the sentiment engine analyzes the tone of this text and determines that the user is confused.

[1440] Step 6: Prepare to submit your response

[1441] The server adjusts the response to match the user's emotions based on the generated response and the analysis results of the emotion engine.

[1442] Input: Generated response text, sentiment analysis results

[1443] Output: Adjusted answer text

[1444] Specific action: For confused users, the explanation will be formatted to be more helpful, such as "Newton's laws of motion consist of the following three..."

[1445] Step 7: Submit your response

[1446] The server generates the adjusted response as an HTTP response and sends it to the user's terminal.

[1447] Input: Adjusted response text

[1448] Output: HTTP response is sent to the terminal.

[1449] Specific operation: The server generates an HTTP response containing an answer such as "Newton's laws of motion include the following three..." and sends it to the terminal.

[1450] Step 8: Display the answer

[1451] The terminal analyzes the HTTP response received from the server, extracts the answer content, and displays it to the user.

[1452] Input: HTTP response

[1453] Output: The response will be displayed on the chatbot interface.

[1454] Specific action: The chatbot interface displays the following three statements: "Newton's laws of motion are..."

[1455] Step 9: Additional Learning Support

[1456] If the user has further questions or would like more information, they can enter their questions into the chatbot again.

[1457] Input: Request text

[1458] Output: The follow-up question text is sent to the server.

[1459] Specific action: The user enters a new question, "Please give me a concrete example of the equations of motion," and clicks the submit button.

[1460] Step 10: Proposing an Individualized Learning Plan

[1461] Generative artificial intelligence generates an optimal learning plan based on the user's learning history, level of understanding, and analysis results of the emotion engine.

[1462] Input: Learning history, comprehension level, sentiment analysis results

[1463] Output: Study plan

[1464] Specific operation: The generative artificial intelligence creates a learning plan that suggests additional learning materials and practice problems related to mechanics.

[1465] Step 11: Submit and view your study plan

[1466] The server formats the newly generated training plan and sends it to the user's terminal.

[1467] The device receives the learning plan and displays it to the user.

[1468] Input: Study plan

[1469] Output: The learning plan is displayed on the chatbot interface.

[1470] Specific operation: The learning plan sent from the server is displayed on the chatbot interface, and "additional learning materials and practice problems related to mechanics" are presented to the user.

[1471] (Application Example 2)

[1472] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1473] Traditional educational chatbot systems and virtual store support systems often fail to adequately consider user emotions, leading to user confusion and unsatisfactory support. Furthermore, they lacked personalized suggestions and optimization tailored to specific user needs. This resulted in a diminished user experience and hindered the development of efficient and effective learning and purchasing experiences.

[1474] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1475] In this invention, the server includes means for receiving questions entered by the user, means for analyzing the user's emotions, and means for proposing individually optimized learning plans or product suggestions. This enables the generation of emotionally conscious answers and personalized suggestions.

[1476] "A means of receiving questions entered by the user" refers to a function that receives the content of questions entered by the user using a device.

[1477] "Means of sending received questions to the server" refers to the function of transferring questions entered by the user to the server via the internet.

[1478] "A means by which a server analyzes a question and generates an answer using generative artificial intelligence" refers to a function in which a server analyzes a received question and uses generative artificial intelligence to generate an appropriate answer.

[1479] "Means of sending generated responses to the user's terminal" refers to a function that sends back the responses generated on the server to the terminal being operated by the user.

[1480] "Means for displaying the generated response on the user's device" refers to a function that displays the response sent from the server on the user's device screen.

[1481] "An emotion analysis tool for analyzing user emotions" refers to a function that analyzes the user's emotional state based on the user's input text and dialogue history.

[1482] "Means for generating personalized suggestions based on sentiment analysis results" refers to a function that generates suggestions optimized for the user based on the results of sentiment analysis.

[1483] "Means of suggesting individually optimized learning plans or product recommendations" refers to a function that suggests the most suitable learning plan or product for a user based on their learning history, purchase history, level of understanding, and emotional state.

[1484] The system according to this invention provides personalized support using emotion analysis and generative artificial intelligence to improve the user's shopping experience in virtual stores. The embodiments of this system are described in detail below.

[1485] Hardware configuration

[1486] 1. User's device:

[1487] Mobile devices that can connect to the internet, such as smartphones and tablets.

[1488] This function allows you to input questions and display the generated answers.

[1489] 2. Server:

[1490] Cloud servers or dedicated servers are used.

[1491] It performs processing that includes generative artificial intelligence and an emotion analysis engine.

[1492] Software Configuration

[1493] 1. Generative artificial intelligence:

[1494] An artificial intelligence model that analyzes the content of a question and generates an appropriate answer.

[1495] It runs on a server.

[1496] 2. Emotion analysis engine:

[1497] Software for analyzing user emotions.

[1498] The system determines the user's emotional state based on their input text and dialogue history.

[1499] 3. Natural Language Processing (NLP) Module:

[1500] The system analyzes the question content and converts it into a format suitable for generative artificial intelligence.

[1501] Processing flow

[1502] When a user enters a question using a terminal, the question is sent from the terminal to the server. The server analyzes the received question and passes it to a generative artificial intelligence (AI) through a natural language processing module. The generative AI generates an appropriate answer, which the server then receives.

[1503] The server further analyzes the user's emotions using an emotion analysis engine and adjusts the generated responses and suggestions according to that emotional state. For example, if the user is confused, it will provide more attentive support and supplementary information.

[1504] Based on this, formatted and adjusted answers and personalized product suggestions are sent to the user's device and displayed on it. The user can review the answers and ask additional questions.

[1505] Specific examples and prompt statements

[1506] Specific example:

[1507] If a user asks, "What is the battery life of this smartphone?", the generative artificial intelligence will generate the answer, "The battery life of this smartphone is approximately 24 hours." If the emotion analysis engine determines that the user's emotion is "interest," a "battery pack" will also be suggested as a related product.

[1508] Examples of prompts for a generative AI model:

[1509] Please generate the correct answer to the following question: "What is the battery life of this smartphone?"

[1510] This allows generative AI models to generate appropriate answers to questions.

[1511] In this way, this invention can provide personalized learning support and product suggestions that take user emotions into consideration, thereby improving the user experience.

[1512] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1513] Step 1:

[1514] The user enters a question from their device. The user uses a smartphone or tablet to enter a question and expects some kind of response. The entered data is sent in text format through the device's input interface.

[1515] Step 2:

[1516] The terminal sends the question to the server. The text entered by the user is sent to the server as an HTTP request by the terminal's application. The request also includes additional information such as the user ID and session ID.

[1517] Step 3:

[1518] The server analyzes the question and formats it for transmission to the generative artificial intelligence. The server analyzes the received HTTP request and extracts the question content. Next, it uses a natural language processing module to convert the data into a format that the AI ​​model can understand. The input is raw text data, and the output is structured data passed to the generative artificial intelligence model.

[1519] Step 4:

[1520] Generative artificial intelligence generates the answer. The generative AI on the server receives a formatted question and generates an answer using a trained model and knowledge database. For example, if the question is "What is the battery life of this smartphone?", it will generate the answer "The battery life of this smartphone is approximately 24 hours."

[1521] Step 5:

[1522] The sentiment analysis engine analyzes the user's emotions. Based on the generated response and the user's input text, the sentiment analysis engine determines the user's emotional state. For example, if the text indicates that the user is "confused," the sentiment analysis result will be labeled "confused." The input is text data, and the output is a label indicating the emotional state.

[1523] Step 6:

[1524] The server generates personalized suggestions based on the generated responses and sentiment analysis results. Taking the sentiment analysis results into account, the server adjusts the responses, including additional explanations and related products. For example, a user who is "confused" will be offered more detailed explanations and support options. The input is the generated responses and sentiment analysis results, and the output is the adjusted and formatted responses.

[1525] Step 7:

[1526] The server sends the formatted and refined response to the terminal. The refined response and suggestions are then sent back to the user's terminal as an HTTP response. The input is the formatted and refined response data, and the output is the HTTP response data.

[1527] Step 8:

[1528] The terminal displays the received response to the user. The user's terminal parses the received HTTP response and displays it on the screen as text data. The input is the HTTP response data, and the output is the text information displayed on the user's terminal's display.

[1529] Step 9:

[1530] The user enters additional questions or comments. The user reviews the displayed answers and enters further questions if they have any unclear points or additional questions. This process is repeated as needed. The input is new questions or comments, and the output is updated question data.

[1531] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1532] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1533] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1534] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1535] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1536] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1537] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1538] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1539] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1540] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1541] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1542] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1543] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1544] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1545] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1546] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1547] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1548] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1549] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1550] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1551] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1552] The following is further disclosed regarding the embodiments described above.

[1553] (Claim 1)

[1554] A means of receiving questions entered by the user,

[1555] A means of sending the received question to the server,

[1556] A means by which a server analyzes a question and generates an answer using generative artificial intelligence,

[1557] A means of sending the generated response to the user's device,

[1558] A means of displaying the generated answer on the user's device,

[1559] A system that includes means for proposing individually optimized learning plans.

[1560] (Claim 2)

[1561] The system according to claim 1, further comprising means for analyzing received questions using natural language processing.

[1562] (Claim 3)

[1563] The system according to claim 1, further comprising means for providing additional information or examples related to the received questions.

[1564] "Example 1"

[1565] (Claim 1)

[1566] A means of receiving questions entered by the user,

[1567] A means of sending the received question from the terminal to the server,

[1568] A means by which a server analyzes a question and generates an answer using generative artificial intelligence,

[1569] A means of sending the generated response from the server to the user's terminal,

[1570] A means of displaying the generated answer on the user's device,

[1571] A system that includes means for proposing individually optimized learning plans.

[1572] (Claim 2)

[1573] The system according to claim 1, further comprising means for analyzing received questions using natural language processing.

[1574] (Claim 3)

[1575] The system according to claim 1, further comprising means for providing additional information or examples related to the received questions.

[1576] "Application Example 1"

[1577] (Claim 1)

[1578] A means of receiving questions entered by the user,

[1579] A means of sending the received question to the server,

[1580] A means by which a server analyzes a question and generates an answer using generative artificial intelligence,

[1581] A means of sending the generated response to the user's device,

[1582] A means of displaying the generated answer on the user's device,

[1583] A means of proposing individually optimized learning plans,

[1584] A system that analyzes questions about products and includes means to recommend the most suitable products and their information.

[1585] (Claim 2)

[1586] The system according to claim 1, further comprising means for analyzing received questions using natural language processing.

[1587] (Claim 3)

[1588] The system according to claim 1, further comprising means for providing additional information or examples related to the received questions.

[1589] "Example 2 of combining an emotion engine"

[1590] (Claim 1)

[1591] A means of receiving questions entered by the user,

[1592] A means for transmitting the received question to a data processing device,

[1593] A data processing device analyzes a question and generates an answer using generative artificial intelligence,

[1594] A means for transmitting the generated response to the user's display device,

[1595] A means for displaying the generated answer on the user's display device,

[1596] A means of proposing an individually optimized learning plan,

[1597] A means of analyzing user emotions,

[1598] A system that includes means for adjusting responses generated based on sentiment analysis results.

[1599] (Claim 2)

[1600] The system according to claim 1, further comprising means for analyzing received questions using natural language processing.

[1601] (Claim 3)

[1602] The system according to claim 1, further comprising means for providing additional information or specific examples related to the received question.

[1603] "Application example 2 when combining with an emotional engine"

[1604] (Claim 1)

[1605] A means of receiving questions entered by the user,

[1606] A means of sending the received question to the server,

[1607] A means by which a server analyzes a question and generates an answer using generative artificial intelligence,

[1608] A means of sending the generated response to the user's device,

[1609] A means of displaying the generated answer on the user's device,

[1610] A means of analyzing user emotions,

[1611] A means for generating personalized suggestions based on the results of sentiment analysis,

[1612] A system that includes means for proposing individually optimized learning plans or product recommendations.

[1613] (Claim 2)

[1614] The system according to claim 1, further comprising means for analyzing received questions using natural language processing.

[1615] (Claim 3)

[1616] The system according to claim 1, further comprising means for providing additional information, examples, or products related to the received questions. [Explanation of symbols]

[1617] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving questions entered by the user, A means of sending the received question to the server, A means by which a server analyzes a question and generates an answer using generative artificial intelligence, A means of sending the generated response to the user's device, A means of displaying the generated answer on the user's device, A system that includes means for proposing individually optimized learning plans.

2. The system according to claim 1, further comprising means for analyzing received questions using natural language processing.

3. The system according to claim 1, further comprising means for providing additional information or examples related to the received questions.

Images