System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving question content input by a user; means for generating an appropriate answer using a generative model that analyzes the received question content; and means for transmitting and displaying the generated answer to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Users have difficulty obtaining prompt and accurate answers to their smartphone-related questions. This can lead to lower user satisfaction and negatively impact a company's image. Furthermore, the need to assign personnel with specialized knowledge to provide appropriate answers creates a cost problem. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system that includes a means for accepting a question entered by a user, a means for generating an appropriate answer using a generative model that analyzes the accepted question, and a means for transmitting and displaying the generated answer to the user. This system includes a server that accepts the question and then transmits the question to the generative model, and a terminal that displays the answer received from the server to the user. The system also includes a means for recording the generated answer in a database and using it to improve subsequent questions, thereby improving the accuracy and efficiency of the entire system. This allows users to receive quick and accurate answers, improving the company's image and increasing user satisfaction.

[0006] A "user" is an entity that uses a terminal to input questions and receive answers.

[0007] A "terminal" is a device used by a user, and is an electronic device that has the function of inputting questions and displaying answers.

[0008] The "question content" is the specific content of an inquiry about the smartphone that the user inputs through the terminal.

[0009] The "accepting means" is a mechanism by which the terminal acquires the content of the question from the user in an input format and stores it.

[0010] A "generative model" is an artificial intelligence technology that analyzes questions in natural language similar to that used by humans and generates appropriate answers.

[0011] A "server" is a device or system that receives questions sent from terminals, analyzes them using a generative model, and generates answers.

[0012] An "answer" is an appropriate response generated by a generative model in response to a question.

[0013] "Means for sending" refers to the mechanism by which the server transfers the response it has generated to the terminal.

[0014] The "display means" is a function that visually presents the answer received by the terminal from the server to the user.

[0015] A "database" is a recording device that stores generated answers and other related information for reference and refinement of subsequent questions.

[0016] The "means of recording" is a mechanism for storing the generated answers in a database for subsequent use.

[0017] "Means used for improvement" are methods and processes for improving the accuracy and efficiency of the system based on the response information recorded in the database. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

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

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] The present invention relates to a system for providing quick and accurate answers to questions about smartphones in real time. Specific embodiments will be described in detail below.

[0040] This system is comprised of a device used by the user, a server that analyzes the question and generates an answer, and a generative model. The user uses the device to input a question about a smartphone. For example, the user can input, "How can I extend the battery life of my iPhone?"

[0041] The device receives the question entered by the user and sends it to the server. The server passes the received question to the generative model, which analyzes the question and generates an appropriate answer. The generated answer is formatted by the server and sent back to the device. The device displays the received answer to the user.

[0042] This will be explained with specific examples.

[0043] Example 1: iPhone battery life question

[0044] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[0045] 2. The device sends this question to the server.

[0046] 3. The server passes the question to the generative model, which generates an answer such as "Adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[0047] 4. The server sends the generated answer to the terminal, which displays it to the user.

[0048] 5. The user checks the displayed answers.

[0049] Next, the processing flow of the program of the present invention will be explained in natural language.

[0050] 1. Questions

[0051] The user launches a dedicated application on the device and inputs a question, such as "What is SoftBank's latest pricing plan?"

[0052] The terminal displays the question on the confirmation screen, and the user presses the "Send" button.

[0053] 2. Submit a question

[0054] The terminal sends the question entered by the user to the server as an HTTP request.

[0055] 3. Question analysis

[0056] The server receives the HTTP request and passes the question to the generative model.

[0057] The generative model analyzes the question and creates an appropriate answer.

[0058] 4. Answer generation

[0059] The generative model generates an answer such as, "The latest SoftBank pricing plans include the 5G GREEN Plan and the Super Pocket Plan. Please check the official website for details."

[0060] The server formats the generated response for delivery to the device.

[0061] 5. Submit your response

[0062] The server formats the answer and sends it to the terminal as an HTTP response.

[0063] 6. Answer display

[0064] The terminal receives the HTTP response, analyzes it, and displays it in the user interface.

[0065] The user checks the answer.

[0066] The system records the generated answers in a database and has a mechanism to improve the accuracy of answers based on past data, which is expected to result in quick and accurate responses to subsequent questions.

[0067] In this way, the present system quickly provides users with the information they need, improving the company's image and customer satisfaction.

[0068] The processing flow will be explained below.

[0069] Step 1: Ask a question

[0070] The user launches a dedicated application on the device.

[0071] A user types a smartphone question into an in-app form, for example, "How can I extend my iPhone's battery life?"

[0072] The device obtains the user's input and displays it on a confirmation screen.

[0073] The user checks the information entered on the confirmation screen and presses the "Submit" button.

[0074] Step 2: Submit your question

[0075] The terminal sends the question entered by the user to the server as an HTTP request.

[0076] The terminal confirms the success of the transmission and notifies the user of the completion of the transmission.

[0077] Step 3: Question acceptance (server side)

[0078] The server receives the HTTP request and analyzes the question.

[0079] The server stores the question content as a log in a database.

[0080] Step 4: Question Analysis

[0081] The server passes the received question to the generative model.

[0082] The generative model analyzes the question and prepares to generate an appropriate answer.

[0083] Step 5: Answer Generation

[0084] The generative model references the corresponding database or knowledge base based on the question.

[0085] The generative model creates an appropriate answer in natural language based on the reference results.

[0086] The server receives and formats the generated response.

[0087] Step 6: Submit your response

[0088] The server prepares the answer and sends it to the terminal as an HTTP response.

[0089] The server acknowledges and logs the successful transmission of the response.

[0090] Step 7: View Answers

[0091] The terminal analyzes the response received from the server.

[0092] The terminal analyzes the answer and displays it on the user interface.

[0093] The user checks the answer displayed on the device screen.

[0094] Step 8: Feedback (optional)

[0095] The user enters feedback on the displayed answer.

[0096] The terminal obtains the user's feedback and sends it to the server.

[0097] The server receives the feedback and records it in a database to help improve subsequent questions.

[0098] Through these processing steps, users can get fast and accurate answers to their smartphone-related questions, improving the company's image and increasing user satisfaction.

[0099] Example 1

[0100] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0101] Conventional systems have difficulty providing fast and accurate answers to smartphone-related questions. Since users often input a wide range of questions, ensuring the accuracy and speed of the answers is crucial. Furthermore, the quality of the answers is questionable due to a lack of a feedback mechanism for improving the generated answers over the long term. This can result in reduced user satisfaction.

[0102] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0103] In this invention, the server includes a means for accepting questions entered by users, a means for analyzing the accepted questions and creating appropriate answers using a generative AI model, and a means for formatting the generated answers and sending them to the user for display. This enables quick and accurate answers to questions entered by users. The server also includes a means for recording the generated answers in a database and using them to improve future questions. This improves the quality and accuracy of answers and increases user satisfaction.

[0104] "User" refers to an entity that uses the system to enter questions and receive answers.

[0105] "Question content" refers to information or questions entered by the user, which are the subject of analysis and answer generation.

[0106] "Means for accepting" refers to the means by which the terminal or server checks the content of the question entered by the user and converts it into a format that can be used within the system.

[0107] A "generative AI model" refers to an artificial intelligence algorithm that analyzes a question and creates an appropriate answer.

[0108] "Means of analysis" refers to the mechanism that processes the received question to understand it and provide an answer.

[0109] "Means for creating answers" refers to the function of creating appropriate answers based on the question content analyzed using a generative AI model.

[0110] "Formatting" refers to the process of converting the answers obtained from a generative AI model into a format that is easy to read for display to the user.

[0111] "Means for transmitting and displaying" refers to a function for transmitting the generated answer from the server to the terminal and for the terminal to display it to the user.

[0112] "Server" refers to the computer system that receives the question and analyzes it using a generative AI model.

[0113] "Terminal" refers to a device through which a user can enter questions and receive answers. Examples include smartphones and tablets.

[0114] "Database" means a collection of information that stores generated answers and questions and is recorded in an accessible format for future use.

[0115] "Improvement measures" refers to the process of using information recorded in the database to improve the quality of answers to future questions.

[0116] The present invention is a system that provides quick and accurate answers in real time to questions about smartphones entered by users. This system consists of the following components:

[0117] System Configuration

[0118] 1. Terminal

[0119] A terminal is a device on which a user inputs questions and receives answers, such as a smartphone or tablet.

[0120] The device provides a dedicated application for users to input questions. This application has the function of inputting, confirming, and sending questions through a user interface.

[0121] 2. Server

[0122] The server receives the question sent from the terminal, analyzes it, and generates an answer.

[0123] The server passes the question to the generative AI model, formats the results, and sends them to the device.

[0124] The server also records the generated answers in a database to help improve the quality of answers to future questions.

[0125] 3. Generative AI Models

[0126] The generative AI model is an artificial intelligence algorithm that analyzes the question content passed from the server and generates an appropriate answer.

[0127] The model performs contextual understanding, tokenization, and syntax analysis to generate the answer the user expects.

[0128] Data processing flow

[0129] 1. Questions

[0130] The user launches a dedicated application on the device and enters a question, for example, "What is SoftBank's latest pricing plan?"

[0131] The terminal displays the question on the confirmation screen, and the user presses the "Send" button.

[0132] 2. Submit a question

[0133] When the user presses the "Send" button, the device converts the question into JSON format and sends it to the server as an HTTP request.

[0134] 3. Question analysis

[0135] The server receives the HTTP request and passes the question to the generative AI model.

[0136] 4. Answer generation

[0137] The generative AI model analyzes the question and generates an appropriate answer, such as, "SoftBank's latest pricing plans include the 5G GREEN Plan and the Super Pocket Plan. Please check the official website for details."

[0138] The server formats the generated response and prepares it for transmission to the terminal.

[0139] 5. Submitting and Displaying Answers

[0140] The server then sends the formatted answer to the terminal as an HTTP response.

[0141] The terminal receives the HTTP response, parses it, and displays it in the user interface. The user confirms the displayed answer.

[0142] Specific examples

[0143] (Example 1: Question about iPhone battery life)

[0144] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[0145] 2. The device sends this question to the server.

[0146] 3. The server passes the question to the generative AI model, which then generates an answer such as "adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[0147] 4. The server sends the generated answer to the terminal, which displays it to the user.

[0148] 5. The user checks the displayed answers.

[0149] An example of a prompt is as follows:

[0150] "How can I extend my iPhone's battery life?"

[0151] "What is SoftBank's latest pricing plan?"

[0152] "Tell me about your smartphone's security settings."

[0153] This system allows users to enter questions with confidence and receive prompt and accurate answers. The generated answers are recorded in a database, which is expected to improve the accuracy of answers to future questions and increase user satisfaction.

[0154] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0155] Step 1: Enter and confirm your questions

[0156] User enters a question: The user starts a dedicated application on their smartphone and enters a question in the input field on the screen. For example, the user might enter, "What is SoftBank's latest pricing plan?"

[0157] Input: Text entered by the user (e.g., "What are SoftBank's latest pricing plans?")

[0158] Output: Input contents displayed on the confirmation screen

[0159] The device displays the question on the confirmation screen: The device displays the entered question on the confirmation screen, and a "Send" button is provided. When the user presses the Send button, the question is ready to be sent to the server.

[0160] Input: What the user types

[0161] Output: What the user sees on the screen

[0162] Step 2: Submit your question

[0163] The terminal converts the question content into JSON format and sends it to the server: When the user presses the "Send" button, the terminal converts the question content into JSON format and sends it to the server as an HTTP request.

[0164] Input: Confirmed question

[0165] Output: Question data in JSON format, HTTP request

[0166] Step 3: Receiving and parsing the question

[0167] The server receives the question and prepares it to be passed to the generative AI model: The server receives the HTTP request sent from the device and extracts the question. The extracted question is passed to the generative AI model.

[0168] Input: HTTP request, question data in JSON format

[0169] Output: Cleaned and pre-processed data to feed into a generative AI model

[0170] Step 4: Generate an answer

[0171] The generative AI model analyzes the question and generates an appropriate answer: The generative AI model analyzes the question and generates an appropriate answer. For example, it generates an answer such as, "SoftBank's latest pricing plans include the 5G GREEN Plan and the Super Pocket Plan. Please check the official website for details."

[0172] Input: Preprocessed query data

[0173] Output: Generated answer text

[0174] The server formats the generated answer and prepares it for transmission: The server formats the generated answer in a format that is easy for the user to view and prepares it for transmission to the terminal.

[0175] Input: Answer text from the generative AI model

[0176] Output: Formatted answer text, HTTP response data

[0177] Step 5: Submit your response

[0178] The server formats the answer and sends it to the terminal: The server formats the answer and sends it to the terminal as an HTTP response.

[0179] Input: Formatted answer text, HTTP response data

[0180] Output: HTTP response

[0181] Step 6: View your answers

[0182] The terminal receives the HTTP response, parses it, and displays it on the user interface: The terminal receives the HTTP response from the server, parses it, and displays it on the user interface.

[0183] Input: HTTP response

[0184] Output: The answer displayed in the user interface

[0185] The user checks the displayed answer: The user checks the answer displayed on the device screen.

[0186] Input: The answer displayed in the user interface

[0187] Output: User confirmation action

[0188] (Application example 1)

[0189] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0190] With conventional food delivery services, it is difficult for users to receive prompt and accurate answers when they have questions about orders or delivery. Furthermore, inquiries about delivery status or order changes cannot be responded to appropriately, which can lead to a decrease in customer satisfaction. There is a need to solve these problems and provide better services to users.

[0191] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0192] In this invention, the server includes means for accepting questions entered by users, means for generating appropriate answers using a generative model that analyzes the accepted questions, means for transmitting and displaying the generated answers to the users, and means for processing inquiries about food delivery services and providing answers in real time, thereby enabling users to obtain prompt and accurate answers to their questions about food delivery.

[0193] "User" refers to an individual or corporation who uses this system to enter questions and obtain answers.

[0194] The "question content" refers to the specific content entered by the user regarding the information they want to know or the problem they want to solve.

[0195] The "receiving means" is an interface that has the function of receiving the question content input by the user and sending it to the server.

[0196] An "analytical generative model" refers to an algorithm or machine learning model that analyzes the content of the question received and generates an appropriate answer. Specifically, it is a model that uses natural language processing technology.

[0197] The "means for generating an answer" is a function that generates an appropriate answer to the question content using the generative model to be analyzed.

[0198] The "means for transmitting and displaying" is a mechanism that has the function of transmitting the generated answer to the user and displaying the answer on the user's interface.

[0199] A "server" is a computer system that manages the entire process of receiving a question, passing it to a generative model to generate an answer, and then sending it back to the user.

[0200] A "terminal" is an electronic device that allows a user to input questions and receive answers. Specifically, this includes smartphones and tablets.

[0201] A "food delivery service" is a service that delivers food ordered by a user to a specified location.

[0202] "Means for providing answers in real time" refers to technologies and mechanisms for generating and transmitting answers to questions from users in real time.

[0203] The "database" is an information management system that records and stores the generated answers and questions, and uses them to improve subsequent questions.

[0204] The system for realizing this invention mainly consists of a user terminal, a server, a generative model, and a database. The system allows users to input questions about food delivery using the terminal, analyzes the questions in real time, and provides appropriate answers. Specific embodiments are described below.

[0205] System configuration

[0206] 1. User Device

[0207] An electronic device that allows users to enter questions, such as a smartphone or tablet.

[0208] After the question is entered, it has the function of sending it to the server as an HTTP request.

[0209] 2. Server

[0210] It is a central control unit that receives the query content and passes it to the generative model for analysis.

[0211] It uses generative AI models such as OpenAI's GPT-4 to analyze questions and generate appropriate answers.

[0212] It has the function of formatting the generated answer and sending it to the terminal.

[0213] 3. Generative Model

[0214] This model analyzes the content of the received question and creates an appropriate answer, using natural language processing technology.

[0215] For example, it generates real-time answers to food delivery questions about delivery status and order details.

[0216] 4. Database

[0217] The generated answers and questions are recorded and used to improve subsequent questions.

[0218] It acts as a database for learning whether questions and answers are appropriate.

[0219] Data processing and calculation

[0220] When a user types and sends a question into their device, the question is sent to the server as an HTTP request. The server receives the question and passes it to a generative model. This generative model analyzes the question using natural language processing technology and has the means to process inquiries about food delivery services and provide answers in real time. The generated answer is formatted by the server and sent to the user's device as an HTTP response. The user's device can receive and display this answer.

[0221] Specific examples

[0222] A user types a question into the app: "Does the salad I ordered include dressing?"

[0223] Example prompt sentence:

[0224] User: "Does the salad I ordered include dressing?"

[0225] System: "Your current order includes dressing. Depending on the salad type, French dressing is standard. If you need other options, you can add them from your order history."

[0226] In this way, users can receive appropriate answers in real time through the app, which will increase customer satisfaction and improve the reliability of food delivery services.

[0227] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0228] Step 1:

[0229] The user launches the "Delivers Assistant" app and enters a question. The entered question is displayed as text in the app.

[0230] Step 2:

[0231] When the user presses the send button, the terminal sends the question to the server as an HTTP request. The input is the user's question text, and the output is the HTTP request sent to the server.

[0232] Step 3:

[0233] The server receives an HTTP request and passes it to the generative model to analyze the question. The input is the text data received as the HTTP request, and the output is the input data to the generative model.

[0234] Step 4:

[0235] A generative model (e.g., OpenAI's GPT-4) analyzes the question and generates an appropriate answer. The input is the text data of the question, and the output is the text data of the generated answer.

[0236] Step 5:

[0237] The server receives the generated answer, formats it, and generates an HTTP response. The input is the answer data from the generative model, and the output is an HTTP response containing the formatted answer data.

[0238] Step 6:

[0239] The server sends an HTTP response to the terminal. The input is the formatted response data, and the output is the HTTP response sent to the terminal.

[0240] Step 7:

[0241] The terminal receives the HTTP response, parses the response, and displays it in a user interface. The input is the received HTTP response, and the output is the response text that is displayed to the user.

[0242] Step 8:

[0243] The user confirms the displayed answer. Specifically, they read the answer displayed on the smartphone screen and enter additional questions if necessary. The input is the answer text that the user confirms, and the output is the next action depending on the situation.

[0244] Through these steps, users can get quick and accurate answers to their food delivery questions.

[0245] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0246] The present invention relates to a system that allows users to input questions about smartphones and provides real-time and accurate answers to those questions. Furthermore, this system is equipped with an emotion engine that recognizes the user's emotions and generates optimal answers based on the user's emotions.

[0247] This system is composed of a device used by the user, a server that analyzes the content of the question and generates an answer, and a generative model and emotion engine at its core. The user uses the device to input a question about their smartphone. For example, they can input, "How can I extend the battery life of my iPhone?"

[0248] The device receives the question entered by the user and sends it to the server. The server uses an emotion engine to analyze the question as well as the emotional data at the time of the user's input. The server passes the received question and emotional data to a generative model, which uses these to generate an appropriate answer. This generated answer is formatted by the server and sent back to the device. The device displays the received answer to the user. The emotional data recognized by the emotion engine is also recorded in a database and used to improve subsequent questions.

[0249] This will be explained with specific examples.

[0250] Example 1: iPhone battery life question

[0251] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[0252] 2. Using the device's built-in camera and microphone, the emotion engine recognizes emotional data such as the user's facial expressions and tone of voice.

[0253] 3. The device sends the question and emotion data to the server.

[0254] 4. The server passes the question and emotion data to the generative model, which then generates an answer such as "adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[0255] 5. If the emotion engine detects that the user is frustrated, the generative model adjusts the tone of the response to be more toned down.

[0256] 6. The server sends the generated answer to the terminal, which displays it to the user.

[0257] 7. The user checks the displayed answers.

[0258] 8. The user's emotion data recognized by the emotion engine is recorded in a database and used to improve the accuracy of subsequent questions.

[0259] Next, the processing flow of the program of the present invention will be explained in natural language.

[0260] 1. Questions

[0261] The user launches a dedicated application on the device and inputs a question, such as "What is SoftBank's latest pricing plan?"

[0262] The device collects the user's emotional data, displays it on a confirmation screen, and the user presses the "send" button.

[0263] 2. Submit a question

[0264] The device sends the question entered by the user and emotional data to the server as an HTTP request.

[0265] 3. Question reception (server side)

[0266] The server receives the HTTP request and analyzes the question content and sentiment data.

[0267] The server passes these to a generative model to generate an appropriate answer.

[0268] 4. Answer generation

[0269] A generative model generates appropriate answers based on the question, and an emotion engine adjusts the tone and content of the answers based on the user's emotional data.

[0270] The server receives and formats the generated response.

[0271] 5. Submit your response

[0272] The server prepares the answer and sends it to the terminal as an HTTP response.

[0273] 6. Answer display

[0274] The terminal analyzes the response received from the server and displays it on the user interface.

[0275] The user checks the answer.

[0276] The user's emotional data is recorded in a database and used to improve subsequent questions.

[0277] This system provides an appropriate response according to the user's emotions, thereby realizing a better user experience, improving the company's image, and increasing user satisfaction.

[0278] The processing flow will be explained below.

[0279] Step 1: Ask a question

[0280] The user launches a dedicated application on the device.

[0281] A user types a smartphone question into an in-app form, for example, "How can I extend my iPhone's battery life?"

[0282] The device obtains the user's input and displays it on a confirmation screen.

[0283] The user checks the information entered on the confirmation screen and presses the "Submit" button.

[0284] Step 2: Obtaining emotion data

[0285] The emotion engine uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice.

[0286] The emotion engine collects the user's emotion data and returns the analysis results to the device.

[0287] Step 3: Submit your question

[0288] The device sends the question entered by the user and emotional data to the server as an HTTP request.

[0289] The terminal confirms the success of the transmission and notifies the user of the completion of the transmission.

[0290] Step 4: Question acceptance (server side)

[0291] The server receives the HTTP request and analyzes the question content and sentiment data.

[0292] The server stores the question content and emotion data in a database as a log.

[0293] Step 5: Question Analysis

[0294] The server passes the received question and emotion data to the generative model.

[0295] The generative model analyzes the question and prepares to generate an appropriate answer.

[0296] Step 6: Reflecting emotional data

[0297] The generative model adjusts the tone and content of the response based on the question and sentiment data.

[0298] For example, if the user is annoyed, provide the answer in a calmer tone.

[0299] Step 7: Answer Generation

[0300] A generative model creates an appropriate answer based on the question and sentiment data.

[0301] The server receives and formats the generated response.

[0302] Step 8: Submit your response

[0303] The server prepares the answer and sends it to the terminal as an HTTP response.

[0304] The server acknowledges and logs the successful transmission of the response.

[0305] Step 9: View Answers

[0306] The terminal analyzes the response received from the server.

[0307] The terminal analyzes the answer and displays it on the user interface.

[0308] The user checks the answer displayed on the device screen.

[0309] Step 10: Feedback (Optional)

[0310] The user enters feedback on the displayed answer.

[0311] The terminal obtains the user's feedback and sends it to the server.

[0312] The server receives the feedback and records it in a database.

[0313] Through these specific processing steps, users can get fast and accurate answers to their smartphone-related questions. This system provides appropriate responses based on the user's emotions, improving the company's image and increasing user satisfaction.

[0314] Example 2

[0315] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0316] Conventional question-answering systems provide answers without considering the user's emotions, which can result in a poor user experience. Furthermore, it is difficult to understand the relationship between the content of the question entered by the user and the user's emotions and provide an accurate answer. This leads to the problem of not being able to provide the information the user is looking for quickly and appropriately.

[0317] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0318] In this invention, the server includes means for accepting a question entered by a user, means for collecting emotion data related to the question, means for generating an appropriate answer using a generative model that analyzes the accepted question and the emotion data, means for adjusting the generated answer in accordance with the user's emotion, means for sending and displaying the adjusted answer to the user, and means for recording the emotion data in a database and using it to improve subsequent questions. This allows for the provision of an appropriate response in accordance with the user's emotion, thereby improving the user experience and satisfaction.

[0319] "Question content" refers to the specific questions or requests that the user inputs to the system.

[0320] "Emotion data" refers to data relating to the user's emotional state obtained from facial expressions, tone of voice, and the like.

[0321] A "generative model" refers to an algorithm or machine learning model that generates appropriate answers based on the input question and emotional data.

[0322] The "server" refers to a central processing unit that receives the question content and emotion data, generates an answer using a generative model, and transmits it to the user after adjustment.

[0323] "Terminal" refers to a device through which a user can enter questions and receive and display generated answers.

[0324] An "emotion engine" refers to software or hardware that analyzes a user's emotions from their facial expressions and tone of voice and outputs the results as data.

[0325] "Database" refers to an information management system that stores the generated emotional data and answers and uses them to improve the accuracy of answers to subsequent questions.

[0326] "HTTP request" refers to the communication protocol that allows a device to send question content and emotional data to a server.

[0327] "HTTP response" refers to a communication protocol that allows a server to send a generated response to a terminal.

[0328] "Formatting" refers to the process of adjusting the generated answers into a form that is easy for the user to understand.

[0329] MODE FOR CARRYING OUT THE INVENTION

[0330] This invention relates to a system that allows users to input questions about smartphones and provides accurate answers in real time. Furthermore, this system is equipped with an emotion engine that recognizes the user's emotions and generates optimal answers based on the user's emotions. The system is comprised of a device used by the user, a server that analyzes the question content and generates answers, and a generative model and emotion engine at its core.

[0331] A user uses a device to input a question about their smartphone. For example, they can input a question such as, "How can I extend the battery life of my iPhone?" The device receives the question input by the user and sends it to the server. At the same time, the emotion engine recognizes emotional data such as the user's facial expressions and tone of voice using the device's built-in camera and microphone. The recognized emotional data is also sent to the server.

[0332] The server receives and analyzes the emotional data along with the question content. The question content and emotional data extracted through the analysis are passed to a generative AI model. The generative AI model analyzes the question content using, for example, natural language processing (NLP) technology and generates an appropriate answer based on that analysis. Furthermore, the emotion engine refers to the emotional data analyzed and adjusts the tone and content to match the user's emotions.

[0333] The generated answer is formatted by the server and sent back to the device, where it is displayed to the user. The emotion data recognized by the emotion engine is also recorded in a database and used to improve subsequent questions.

[0334] Specific examples are shown below.

[0335] Example 1: iPhone battery life question

[0336] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[0337] 2. Using the device's built-in camera and microphone, the emotion engine recognizes emotional data such as the user's facial expressions and tone of voice.

[0338] 3. The device sends the question and emotion data to the server.

[0339] 4. The server passes the question and emotion data to the generative model, which then generates an answer such as "adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[0340] 5. The server formats the generated response and sends it back to the terminal.

[0341] 6. The terminal displays the received answer to the user.

[0342] 7. The emotional data recognized by the emotion engine is recorded in a database and used to improve subsequent questions.

[0343] The system improves the user experience by recognizing the user's emotions using an emotion engine and providing optimal responses. The collected emotion data is also analyzed and used to improve the quality of future responses.

[0344] For example, examples of prompt sentences to input into a generative AI model include the following:

[0345] "How to extend iPhone battery life?"

[0346] "Please tell me about SoftBank's latest pricing plans."

[0347] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0348] Step 1: Ask a question

[0349] The user launches a dedicated application on the device and inputs a question. For example, they might input, "What is SoftBank's latest pricing plan?" The input question is displayed by the device's UI. The input is the user's question, and the output is the user's question displayed on a confirmation screen.

[0350] Step 2: Collecting Emotional Data

[0351] The device uses its built-in camera and microphone to detect the user's facial expressions and tone of voice. The emotion engine analyzes this data and recognizes the user's emotional state. Specifically, it uses facial expression images captured by the camera and voice recorded by the microphone as input and outputs emotional data.

[0352] Step 3: Submit your question

[0353] The device sends the question and emotion data entered by the user to the server as an HTTP request. The input is the question and emotion data, and the output is an HTTP request that includes them.

[0354] Step 4: Parse the questions and sentiment data

[0355] The server analyzes the received HTTP request and extracts the question content and emotional data. The server then passes this data to the generative AI model. Specifically, it extracts the question content and emotional data from the request and provides them to the generative AI model. The input is the HTTP request, and the output is the analysis results of the question content and emotional data.

[0356] Step 5: Answer Generation

[0357] The generative AI model generates an appropriate answer based on the question. At this time, it also takes emotional data into consideration to adjust the tone and content of the answer. For example, it generates an answer such as, "SoftBank's latest plan costs XX yen and includes XX GB of data." The input is the question and emotional data, and the output is an appropriately adjusted answer.

[0358] Step 6: Formatting your answers

[0359] The server receives the generated answer and formats it in a way that is easy for the user to understand. The tone is adjusted to a calm tone based on data from the emotion engine. The input is the answer from the generative AI model, and the output is the formatted answer.

[0360] Step 7: Submit your response

[0361] The server formats the answer and sends it to the terminal as an HTTP response, where the input is the formatted answer and the output is the generated HTTP response.

[0362] Step 8: View Answers

[0363] The terminal analyzes the response received from the server and displays it on the user interface. The user confirms the presented answer. The input is the HTTP response, and the output is the answer displayed on the user interface.

[0364] Step 9: Record and use emotional data

[0365] The emotion engine recognizes the user's emotion data and stores it in a database for future question answering. Specifically, the emotion data is recorded in the database and used to analyze and generate subsequent questions. The input is emotion data, and the output is a saved database entry.

[0366] (Application example 2)

[0367] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0368] In today's security services, there is a need to provide fast, accurate information in real time. However, there is a lack of means to quickly resolve the uncertainties and anxieties that security guards face while on patrol. Furthermore, systems that do not properly recognize and respond to user emotions increase the risk of misjudging the situation, resulting in increased security risks. To solve these issues, a system that takes user emotions into account and provides appropriate response instructions in real time is needed.

[0369] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting a question entered by a user, means for generating an appropriate answer using a generative model that analyzes the accepted question, means for sending and displaying the generated answer to the user, and means having an emotion engine that recognizes the user's emotion and adjusts the tone and content of the answer based on the emotion data. This makes it possible for security guards to receive appropriate advice in real time according to their emotions, even if they have questions or feel anxious while patrolling.

[0370] The "means for accepting the question content input by the user" is an interface for acquiring the question content input by the user through the terminal and transmitting it for subsequent processing.

[0371] A "generative model that analyzes received questions" is a machine learning model that analyzes received questions and generates appropriate answers to the questions.

[0372] The "means for transmitting and displaying the generated answer to the user" is an interface for transmitting the answer generated by the generative model to the user's terminal and displaying it.

[0373] "Means with an emotion engine that recognizes a user's emotions and adjusts the tone and content of responses based on the emotion data" refers to algorithms and functions that recognize a user's facial expressions, tone of voice, and other emotional indicators and adjust the tone and content of the generated responses based on them.

[0374] The "server that receives the question content and then transmits the question content and emotion data to the generative model" is a computer system that transmits the question content and emotion data received from the user to the generative model for analysis and answer generation.

[0375] The "terminal that displays the answer received from the server to the user" is a device that receives the answer generated by the server and displays it so that the user can confirm it visually or audibly.

[0376] "Means for recording the generated answers in a database and using them to improve answers to subsequent questions" refers to a system that stores answers generated by a generative model in a database and uses them to improve and optimize the accuracy of answers to future questions.

[0377] To implement this invention, it is necessary to build a system that accepts questions entered by users, generates appropriate answers, and transmits and displays the answers to the users. This system consists of a terminal used by the user, a server that analyzes the questions and emotion data, a generative model, and an emotion engine.

[0378] First, a user inputs a question using a device such as smart glasses. The device's camera captures the user's face, and the emotion engine recognizes the user's emotion. This emotion data is then sent to the server along with the question.

[0379] The server then passes the received question and emotion data to a generative model, which then generates an appropriate answer. The generative model uses machine learning to analyze the question and generates an optimal answer. Furthermore, the tone and content of the answer are adjusted based on the user's emotion as recognized by the emotion engine.

[0380] The generated answer is formatted by the server and sent back to the user's device. The device displays the received answer to the user for confirmation. The emotion data is also recorded in a database and used to improve the accuracy of answers for subsequent questions.

[0381] As a concrete example, consider the case where a security guard using smart glasses while patrolling inputs a question such as, "If there is suspicious activity in this area, how should I respond?" The camera in the smart glasses captures the user's facial expression, and the emotion engine detects "anxiety." This question and emotion data are sent to the server, and the generative model generates the answer, "First, remain calm, immediately avoid contact with suspicious individuals, and contact backup." The emotion engine adjusts the tone of the answer, providing the user with a calm tone.

[0382] An example prompt for a generative AI model might take the form:

[0383] Question: "If there is suspicious activity in this area, how should I respond?"

[0384] Emotion data: "Impatience"

[0385] Tone of generated answer: "Calm"

[0386] In this way, the present invention realizes a system in the field of security services that provides appropriate responses in real time according to the user's emotions and supports the work of security guards.

[0387] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0388] Step 1:

[0389] The system accepts questions entered by the user. The user enters the question using the voice input function of the smart glasses. The inputs are the question text and an image of the user's facial expression.

[0390] Step 2:

[0391] The device captures the user's face and recognizes the user's emotions using an emotion engine. The input is the captured facial image, and the output is emotion data such as "impatience" or "anger." Emotion data is extracted based on an analysis of the user's facial expressions.

[0392] Step 3:

[0393] The device sends the question and emotion data to the server. The input is the question text and emotion data, which are sent to the server as an HTTP request.

[0394] Step 4:

[0395] The server receives the question content and emotion data. The input is an HTTP request sent from the device. The server analyzes this data and converts it into an input format for the generative model.

[0396] Step 5:

[0397] The server passes the received data to a generative model to generate an answer. The input is the question text and sentiment data, which the generative AI model analyzes to generate an appropriate answer. The output is the generated answer.

[0398] Step 6:

[0399] The server passes the generated answer to the emotion engine, which adjusts the tone and content of the answer based on the emotion data. The input is the generated answer and emotion data, and the output is the adjusted answer. The tone is adjusted according to the emotion.

[0400] Step 7:

[0401] The server formats the adjusted answer and sends it to the device. The input is the adjusted answer and the output is sent to the device as an HTTP response.

[0402] Step 8:

[0403] The terminal displays the answer received from the server. The input is the answer text sent from the server, and the output is displayed in a format that the user can confirm visually or audibly. The user confirms the displayed answer.

[0404] Step 9:

[0405] The emotion data collected by the emotion engine is recorded in a database. The input is the emotion data recognized by the emotion engine, and the output is the emotion data stored in the database. This is used to improve the accuracy of answers to subsequent questions.

[0406] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0407] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0408] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0409] [Second embodiment]

[0410] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0411] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0412] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0413] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0414] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0415] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0416] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0417] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0418] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0419] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0420] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0421] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0422] The present invention relates to a system for providing quick and accurate answers to questions about smartphones in real time. Specific embodiments will be described in detail below.

[0423] This system is comprised of a device used by the user, a server that analyzes the question and generates an answer, and a generative model. The user uses the device to input a question about a smartphone. For example, the user can input, "How can I extend the battery life of my iPhone?"

[0424] The device receives the question entered by the user and sends it to the server. The server passes the received question to the generative model, which analyzes the question and generates an appropriate answer. The generated answer is formatted by the server and sent back to the device. The device displays the received answer to the user.

[0425] This will be explained with specific examples.

[0426] Example 1: iPhone battery life question

[0427] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[0428] 2. The device sends this question to the server.

[0429] 3. The server passes the question to the generative model, which generates an answer such as "Adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[0430] 4. The server sends the generated answer to the terminal, which displays it to the user.

[0431] 5. The user checks the displayed answers.

[0432] Next, the processing flow of the program of the present invention will be explained in natural language.

[0433] 1. Questions

[0434] The user launches a dedicated application on the device and inputs a question, such as "What is SoftBank's latest pricing plan?"

[0435] The terminal displays the question on the confirmation screen, and the user presses the "Send" button.

[0436] 2. Submit a question

[0437] The terminal sends the question entered by the user to the server as an HTTP request.

[0438] 3. Question analysis

[0439] The server receives the HTTP request and passes the question to the generative model.

[0440] The generative model analyzes the question and creates an appropriate answer.

[0441] 4. Answer generation

[0442] The generative model generates an answer such as, "The latest SoftBank pricing plans include the 5G GREEN Plan and the Super Pocket Plan. Please check the official website for details."

[0443] The server formats the generated response for delivery to the device.

[0444] 5. Submit your response

[0445] The server formats the answer and sends it to the terminal as an HTTP response.

[0446] 6. Answer display

[0447] The terminal receives the HTTP response, analyzes it, and displays it in the user interface.

[0448] The user checks the answer.

[0449] The system records the generated answers in a database and has a mechanism to improve the accuracy of answers based on past data, which is expected to result in quick and accurate responses to subsequent questions.

[0450] In this way, the present system quickly provides users with the information they need, improving the company's image and customer satisfaction.

[0451] The processing flow will be explained below.

[0452] Step 1: Ask a question

[0453] The user launches a dedicated application on the device.

[0454] A user types a smartphone question into an in-app form, for example, "How can I extend my iPhone's battery life?"

[0455] The device obtains the user's input and displays it on a confirmation screen.

[0456] The user checks the information entered on the confirmation screen and presses the "Submit" button.

[0457] Step 2: Submit your question

[0458] The terminal sends the question entered by the user to the server as an HTTP request.

[0459] The terminal confirms the success of the transmission and notifies the user of the completion of the transmission.

[0460] Step 3: Question acceptance (server side)

[0461] The server receives the HTTP request and analyzes the question.

[0462] The server stores the question content as a log in a database.

[0463] Step 4: Question Analysis

[0464] The server passes the received question to the generative model.

[0465] The generative model analyzes the question and prepares to generate an appropriate answer.

[0466] Step 5: Answer Generation

[0467] The generative model references the corresponding database or knowledge base based on the question.

[0468] The generative model creates an appropriate answer in natural language based on the reference results.

[0469] The server receives and formats the generated response.

[0470] Step 6: Submit your response

[0471] The server prepares the answer and sends it to the terminal as an HTTP response.

[0472] The server acknowledges and logs the successful transmission of the response.

[0473] Step 7: View Answers

[0474] The terminal analyzes the response received from the server.

[0475] The terminal analyzes the answer and displays it on the user interface.

[0476] The user checks the answer displayed on the device screen.

[0477] Step 8: Feedback (optional)

[0478] The user enters feedback on the displayed answer.

[0479] The terminal obtains the user's feedback and sends it to the server.

[0480] The server receives the feedback and records it in a database to help improve subsequent questions.

[0481] Through these processing steps, users can get fast and accurate answers to their smartphone-related questions, improving the company's image and increasing user satisfaction.

[0482] Example 1

[0483] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0484] Conventional systems have difficulty providing fast and accurate answers to smartphone-related questions. Since users often input a wide range of questions, ensuring the accuracy and speed of the answers is crucial. Furthermore, the quality of the answers is questionable due to a lack of a feedback mechanism for improving the generated answers over the long term. This can result in reduced user satisfaction.

[0485] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0486] In this invention, the server includes a means for accepting questions entered by users, a means for analyzing the accepted questions and creating appropriate answers using a generative AI model, and a means for formatting the generated answers and sending them to the user for display. This enables quick and accurate answers to questions entered by users. The server also includes a means for recording the generated answers in a database and using them to improve future questions. This improves the quality and accuracy of answers and increases user satisfaction.

[0487] "User" refers to an entity that uses the system to enter questions and receive answers.

[0488] "Question content" refers to information or questions entered by the user, which are the subject of analysis and answer generation.

[0489] "Means for accepting" refers to the means by which the terminal or server checks the content of the question entered by the user and converts it into a format that can be used within the system.

[0490] A "generative AI model" refers to an artificial intelligence algorithm that analyzes a question and creates an appropriate answer.

[0491] "Means of analysis" refers to the mechanism that processes the received question to understand it and provide an answer.

[0492] "Means for creating answers" refers to the function of creating appropriate answers based on the question content analyzed using a generative AI model.

[0493] "Formatting" refers to the process of converting the answers obtained from a generative AI model into a format that is easy to read for display to the user.

[0494] "Means for transmitting and displaying" refers to a function for transmitting the generated answer from the server to the terminal and for the terminal to display it to the user.

[0495] "Server" refers to the computer system that receives the question and analyzes it using a generative AI model.

[0496] "Terminal" refers to a device through which a user can enter questions and receive answers. Examples include smartphones and tablets.

[0497] "Database" means a collection of information that stores generated answers and questions and is recorded in an accessible format for future use.

[0498] "Improvement measures" refers to the process of using information recorded in the database to improve the quality of answers to future questions.

[0499] The present invention is a system that provides quick and accurate answers in real time to questions about smartphones entered by users. This system consists of the following components:

[0500] System Configuration

[0501] 1. Terminal

[0502] A terminal is a device on which a user inputs questions and receives answers, such as a smartphone or tablet.

[0503] The device provides a dedicated application for users to input questions. This application has the function of inputting, confirming, and sending questions through a user interface.

[0504] 2. Server

[0505] The server receives the question sent from the terminal, analyzes it, and generates an answer.

[0506] The server passes the question to the generative AI model, formats the results, and sends them to the device.

[0507] The server also records the generated answers in a database to help improve the quality of answers to future questions.

[0508] 3. Generative AI Models

[0509] The generative AI model is an artificial intelligence algorithm that analyzes the question content passed from the server and generates an appropriate answer.

[0510] The model performs contextual understanding, tokenization, and syntax analysis to generate the answer the user expects.

[0511] Data processing flow

[0512] 1. Questions

[0513] The user launches a dedicated application on the device and enters a question, for example, "What is SoftBank's latest pricing plan?"

[0514] The terminal displays the question on the confirmation screen, and the user presses the "Send" button.

[0515] 2. Submit a question

[0516] When the user presses the "Send" button, the device converts the question into JSON format and sends it to the server as an HTTP request.

[0517] 3. Question analysis

[0518] The server receives the HTTP request and passes the question to the generative AI model.

[0519] 4. Answer generation

[0520] The generative AI model analyzes the question and generates an appropriate answer, such as, "SoftBank's latest pricing plans include the 5G GREEN Plan and the Super Pocket Plan. Please check the official website for details."

[0521] The server formats the generated response and prepares it for transmission to the terminal.

[0522] 5. Submitting and Displaying Answers

[0523] The server then sends the formatted answer to the terminal as an HTTP response.

[0524] The terminal receives the HTTP response, parses it, and displays it in the user interface. The user confirms the displayed answer.

[0525] Specific examples

[0526] (Example 1: Question about iPhone battery life)

[0527] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[0528] 2. The device sends this question to the server.

[0529] 3. The server passes the question to the generative AI model, which then generates an answer such as "adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[0530] 4. The server sends the generated answer to the terminal, which displays it to the user.

[0531] 5. The user checks the displayed answers.

[0532] An example of a prompt is as follows:

[0533] "How can I extend my iPhone's battery life?"

[0534] "What is SoftBank's latest pricing plan?"

[0535] "Tell me about your smartphone's security settings."

[0536] This system allows users to enter questions with confidence and receive prompt and accurate answers. The generated answers are recorded in a database, which is expected to improve the accuracy of answers to future questions and increase user satisfaction.

[0537] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0538] Step 1: Enter and confirm your questions

[0539] User enters a question: The user starts a dedicated application on their smartphone and enters a question in the input field on the screen. For example, the user might enter, "What is SoftBank's latest pricing plan?"

[0540] Input: Text entered by the user (e.g., "What are SoftBank's latest pricing plans?")

[0541] Output: Input contents displayed on the confirmation screen

[0542] The device displays the question on the confirmation screen: The device displays the entered question on the confirmation screen, and a "Send" button is provided. When the user presses the Send button, the question is ready to be sent to the server.

[0543] Input: What the user types

[0544] Output: What the user sees on the screen

[0545] Step 2: Submit your question

[0546] The terminal converts the question content into JSON format and sends it to the server: When the user presses the "Send" button, the terminal converts the question content into JSON format and sends it to the server as an HTTP request.

[0547] Input: Confirmed question

[0548] Output: Question data in JSON format, HTTP request

[0549] Step 3: Receiving and parsing the question

[0550] The server receives the question and prepares it to be passed to the generative AI model: The server receives the HTTP request sent from the device and extracts the question. The extracted question is passed to the generative AI model.

[0551] Input: HTTP request, question data in JSON format

[0552] Output: Cleaned and pre-processed data to feed into a generative AI model

[0553] Step 4: Generate an answer

[0554] The generative AI model analyzes the question and generates an appropriate answer: The generative AI model analyzes the question and generates an appropriate answer. For example, it generates an answer such as, "SoftBank's latest pricing plans include the 5G GREEN Plan and the Super Pocket Plan. Please check the official website for details."

[0555] Input: Preprocessed query data

[0556] Output: Generated answer text

[0557] The server formats the generated answer and prepares it for transmission: The server formats the generated answer in a format that is easy for the user to view and prepares it for transmission to the terminal.

[0558] Input: Answer text from the generative AI model

[0559] Output: Formatted answer text, HTTP response data

[0560] Step 5: Submit your response

[0561] The server formats the answer and sends it to the terminal: The server formats the answer and sends it to the terminal as an HTTP response.

[0562] Input: Formatted answer text, HTTP response data

[0563] Output: HTTP response

[0564] Step 6: View your answers

[0565] The terminal receives the HTTP response, parses it, and displays it on the user interface: The terminal receives the HTTP response from the server, parses it, and displays it on the user interface.

[0566] Input: HTTP response

[0567] Output: The answer displayed in the user interface

[0568] The user checks the displayed answer: The user checks the answer displayed on the device screen.

[0569] Input: The answer displayed in the user interface

[0570] Output: User confirmation action

[0571] (Application example 1)

[0572] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0573] With conventional food delivery services, it is difficult for users to receive prompt and accurate answers when they have questions about orders or delivery. Furthermore, inquiries about delivery status or order changes cannot be responded to appropriately, which can lead to a decrease in customer satisfaction. There is a need to solve these problems and provide better services to users.

[0574] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0575] In this invention, the server includes means for accepting questions entered by users, means for generating appropriate answers using a generative model that analyzes the accepted questions, means for transmitting and displaying the generated answers to the users, and means for processing inquiries about food delivery services and providing answers in real time, thereby enabling users to obtain prompt and accurate answers to their questions about food delivery.

[0576] "User" refers to an individual or corporation who uses this system to enter questions and obtain answers.

[0577] The "question content" refers to the specific content entered by the user regarding the information they want to know or the problem they want to solve.

[0578] The "receiving means" is an interface that has the function of receiving the question content input by the user and sending it to the server.

[0579] An "analytical generative model" refers to an algorithm or machine learning model that analyzes the content of the question received and generates an appropriate answer. Specifically, it is a model that uses natural language processing technology.

[0580] The "means for generating an answer" is a function that generates an appropriate answer to the question content using the generative model to be analyzed.

[0581] The "means for transmitting and displaying" is a mechanism that has the function of transmitting the generated answer to the user and displaying the answer on the user's interface.

[0582] A "server" is a computer system that manages the entire process of receiving a question, passing it to a generative model to generate an answer, and then sending it back to the user.

[0583] A "terminal" is an electronic device that allows a user to input questions and receive answers. Specifically, this includes smartphones and tablets.

[0584] A "food delivery service" is a service that delivers food ordered by a user to a specified location.

[0585] "Means for providing answers in real time" refers to technologies and mechanisms for generating and transmitting answers to questions from users in real time.

[0586] The "database" is an information management system that records and stores the generated answers and questions, and uses them to improve subsequent questions.

[0587] The system for realizing this invention mainly consists of a user terminal, a server, a generative model, and a database. The system allows users to input questions about food delivery using the terminal, analyzes the questions in real time, and provides appropriate answers. Specific embodiments are described below.

[0588] System configuration

[0589] 1. User Device

[0590] An electronic device that allows users to enter questions, such as a smartphone or tablet.

[0591] After the question is entered, it has the function of sending it to the server as an HTTP request.

[0592] 2. Server

[0593] It is a central control unit that receives the query content and passes it to the generative model for analysis.

[0594] It uses generative AI models such as OpenAI's GPT-4 to analyze questions and generate appropriate answers.

[0595] It has the function of formatting the generated answer and sending it to the terminal.

[0596] 3. Generative Model

[0597] This model analyzes the content of the received question and creates an appropriate answer, using natural language processing technology.

[0598] For example, it generates real-time answers to food delivery questions about delivery status and order details.

[0599] 4. Database

[0600] The generated answers and questions are recorded and used to improve subsequent questions.

[0601] It acts as a database for learning whether questions and answers are appropriate.

[0602] Data processing and calculation

[0603] When a user types and sends a question into their device, the question is sent to the server as an HTTP request. The server receives the question and passes it to a generative model. This generative model analyzes the question using natural language processing technology and has the means to process inquiries about food delivery services and provide answers in real time. The generated answer is formatted by the server and sent to the user's device as an HTTP response. The user's device can receive and display this answer.

[0604] Specific examples

[0605] A user types a question into the app: "Does the salad I ordered include dressing?"

[0606] Example prompt sentence:

[0607] User: "Does the salad I ordered include dressing?"

[0608] System: "Your current order includes dressing. Depending on the salad type, French dressing is standard. If you need other options, you can add them from your order history."

[0609] In this way, users can receive appropriate answers in real time through the app, which will increase customer satisfaction and improve the reliability of food delivery services.

[0610] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0611] Step 1:

[0612] The user launches the "Delivers Assistant" app and enters a question. The entered question is displayed as text in the app.

[0613] Step 2:

[0614] When the user presses the send button, the terminal sends the question to the server as an HTTP request. The input is the user's question text, and the output is the HTTP request sent to the server.

[0615] Step 3:

[0616] The server receives an HTTP request and passes it to the generative model to analyze the question. The input is the text data received as the HTTP request, and the output is the input data to the generative model.

[0617] Step 4:

[0618] A generative model (e.g., OpenAI's GPT-4) analyzes the question and generates an appropriate answer. The input is the text data of the question, and the output is the text data of the generated answer.

[0619] Step 5:

[0620] The server receives the generated answer, formats it, and generates an HTTP response. The input is the answer data from the generative model, and the output is an HTTP response containing the formatted answer data.

[0621] Step 6:

[0622] The server sends an HTTP response to the terminal. The input is the formatted response data, and the output is the HTTP response sent to the terminal.

[0623] Step 7:

[0624] The terminal receives the HTTP response, parses the response, and displays it in a user interface. The input is the received HTTP response, and the output is the response text that is displayed to the user.

[0625] Step 8:

[0626] The user confirms the displayed answer. Specifically, they read the answer displayed on the smartphone screen and enter additional questions if necessary. The input is the answer text that the user confirms, and the output is the next action depending on the situation.

[0627] Through these steps, users can get quick and accurate answers to their food delivery questions.

[0628] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0629] The present invention relates to a system that allows users to input questions about smartphones and provides real-time and accurate answers to those questions. Furthermore, this system is equipped with an emotion engine that recognizes the user's emotions and generates optimal answers based on the user's emotions.

[0630] This system is composed of a device used by the user, a server that analyzes the content of the question and generates an answer, and a generative model and emotion engine at its core. The user uses the device to input a question about their smartphone. For example, they can input, "How can I extend the battery life of my iPhone?"

[0631] The device receives the question entered by the user and sends it to the server. The server uses an emotion engine to analyze the question as well as the emotional data at the time of the user's input. The server passes the received question and emotional data to a generative model, which uses these to generate an appropriate answer. This generated answer is formatted by the server and sent back to the device. The device displays the received answer to the user. The emotional data recognized by the emotion engine is also recorded in a database and used to improve subsequent questions.

[0632] This will be explained with specific examples.

[0633] Example 1: iPhone battery life question

[0634] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[0635] 2. Using the device's built-in camera and microphone, the emotion engine recognizes emotional data such as the user's facial expressions and tone of voice.

[0636] 3. The device sends the question and emotion data to the server.

[0637] 4. The server passes the question and emotion data to the generative model, which then generates an answer such as "adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[0638] 5. If the emotion engine detects that the user is frustrated, the generative model adjusts the tone of the response to be more toned down.

[0639] 6. The server sends the generated answer to the terminal, which displays it to the user.

[0640] 7. The user checks the displayed answers.

[0641] 8. The user's emotion data recognized by the emotion engine is recorded in a database and used to improve the accuracy of subsequent questions.

[0642] Next, the processing flow of the program of the present invention will be explained in natural language.

[0643] 1. Questions

[0644] The user launches a dedicated application on the device and inputs a question, such as "What is SoftBank's latest pricing plan?"

[0645] The device collects the user's emotional data, displays it on a confirmation screen, and the user presses the "send" button.

[0646] 2. Submit a question

[0647] The device sends the question entered by the user and emotional data to the server as an HTTP request.

[0648] 3. Question reception (server side)

[0649] The server receives the HTTP request and analyzes the question content and sentiment data.

[0650] The server passes these to a generative model to generate an appropriate answer.

[0651] 4. Answer generation

[0652] A generative model generates appropriate answers based on the question, and an emotion engine adjusts the tone and content of the answers based on the user's emotional data.

[0653] The server receives and formats the generated response.

[0654] 5. Submit your response

[0655] The server prepares the answer and sends it to the terminal as an HTTP response.

[0656] 6. Answer display

[0657] The terminal analyzes the response received from the server and displays it on the user interface.

[0658] The user checks the answer.

[0659] The user's emotional data is recorded in a database and used to improve subsequent questions.

[0660] This system provides an appropriate response according to the user's emotions, thereby realizing a better user experience, improving the company's image, and increasing user satisfaction.

[0661] The processing flow will be explained below.

[0662] Step 1: Ask a question

[0663] The user launches a dedicated application on the device.

[0664] A user types a smartphone question into an in-app form, for example, "How can I extend my iPhone's battery life?"

[0665] The device obtains the user's input and displays it on a confirmation screen.

[0666] The user checks the information entered on the confirmation screen and presses the "Submit" button.

[0667] Step 2: Obtaining emotion data

[0668] The emotion engine uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice.

[0669] The emotion engine collects the user's emotion data and returns the analysis results to the device.

[0670] Step 3: Submit your question

[0671] The device sends the question entered by the user and emotional data to the server as an HTTP request.

[0672] The terminal confirms the success of the transmission and notifies the user of the completion of the transmission.

[0673] Step 4: Question acceptance (server side)

[0674] The server receives the HTTP request and analyzes the question content and sentiment data.

[0675] The server stores the question content and emotion data in a database as a log.

[0676] Step 5: Question Analysis

[0677] The server passes the received question and emotion data to the generative model.

[0678] The generative model analyzes the question and prepares to generate an appropriate answer.

[0679] Step 6: Reflecting emotional data

[0680] The generative model adjusts the tone and content of the response based on the question and sentiment data.

[0681] For example, if the user is annoyed, provide the answer in a calmer tone.

[0682] Step 7: Answer Generation

[0683] A generative model creates an appropriate answer based on the question and sentiment data.

[0684] The server receives and formats the generated response.

[0685] Step 8: Submit your response

[0686] The server prepares the answer and sends it to the terminal as an HTTP response.

[0687] The server acknowledges and logs the successful transmission of the response.

[0688] Step 9: View Answers

[0689] The terminal analyzes the response received from the server.

[0690] The terminal analyzes the answer and displays it on the user interface.

[0691] The user checks the answer displayed on the device screen.

[0692] Step 10: Feedback (Optional)

[0693] The user enters feedback on the displayed answer.

[0694] The terminal obtains the user's feedback and sends it to the server.

[0695] The server receives the feedback and records it in a database.

[0696] Through these specific processing steps, users can get fast and accurate answers to their smartphone-related questions. This system provides appropriate responses based on the user's emotions, improving the company's image and increasing user satisfaction.

[0697] Example 2

[0698] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0699] Conventional question-answering systems provide answers without considering the user's emotions, which can result in a poor user experience. Furthermore, it is difficult to understand the relationship between the content of the question entered by the user and the user's emotions and provide an accurate answer. This leads to the problem of not being able to provide the information the user is looking for quickly and appropriately.

[0700] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0701] In this invention, the server includes means for accepting a question entered by a user, means for collecting emotion data related to the question, means for generating an appropriate answer using a generative model that analyzes the accepted question and the emotion data, means for adjusting the generated answer in accordance with the user's emotion, means for sending and displaying the adjusted answer to the user, and means for recording the emotion data in a database and using it to improve subsequent questions. This allows for the provision of an appropriate response in accordance with the user's emotion, thereby improving the user experience and satisfaction.

[0702] "Question content" refers to the specific questions or requests that the user inputs to the system.

[0703] "Emotion data" refers to data relating to the user's emotional state obtained from facial expressions, tone of voice, and the like.

[0704] A "generative model" refers to an algorithm or machine learning model that generates appropriate answers based on the input question and emotional data.

[0705] The "server" refers to a central processing unit that receives the question content and emotion data, generates an answer using a generative model, and transmits it to the user after adjustment.

[0706] "Terminal" refers to a device through which a user can enter questions and receive and display generated answers.

[0707] An "emotion engine" refers to software or hardware that analyzes a user's emotions from their facial expressions and tone of voice and outputs the results as data.

[0708] "Database" refers to an information management system that stores the generated emotional data and answers and uses them to improve the accuracy of answers to subsequent questions.

[0709] "HTTP request" refers to the communication protocol that allows a device to send question content and emotional data to a server.

[0710] "HTTP response" refers to a communication protocol that allows a server to send a generated response to a terminal.

[0711] "Formatting" refers to the process of adjusting the generated answers into a form that is easy for the user to understand.

[0712] MODE FOR CARRYING OUT THE INVENTION

[0713] This invention relates to a system that allows users to input questions about smartphones and provides accurate answers in real time. Furthermore, this system is equipped with an emotion engine that recognizes the user's emotions and generates optimal answers based on the user's emotions. The system is comprised of a device used by the user, a server that analyzes the question content and generates answers, and a generative model and emotion engine at its core.

[0714] A user uses a device to input a question about their smartphone. For example, they can input a question such as, "How can I extend the battery life of my iPhone?" The device receives the question input by the user and sends it to the server. At the same time, the emotion engine recognizes emotional data such as the user's facial expressions and tone of voice using the device's built-in camera and microphone. The recognized emotional data is also sent to the server.

[0715] The server receives and analyzes the emotional data along with the question content. The question content and emotional data extracted through the analysis are passed to a generative AI model. The generative AI model analyzes the question content using, for example, natural language processing (NLP) technology and generates an appropriate answer based on that analysis. Furthermore, the emotion engine refers to the emotional data analyzed and adjusts the tone and content to match the user's emotions.

[0716] The generated answer is formatted by the server and sent back to the device, where it is displayed to the user. The emotion data recognized by the emotion engine is also recorded in a database and used to improve subsequent questions.

[0717] Specific examples are shown below.

[0718] Example 1: iPhone battery life question

[0719] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[0720] 2. Using the device's built-in camera and microphone, the emotion engine recognizes emotional data such as the user's facial expressions and tone of voice.

[0721] 3. The device sends the question and emotion data to the server.

[0722] 4. The server passes the question and emotion data to the generative model, which then generates an answer such as "adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[0723] 5. The server formats the generated response and sends it back to the terminal.

[0724] 6. The terminal displays the received answer to the user.

[0725] 7. The emotional data recognized by the emotion engine is recorded in a database and used to improve subsequent questions.

[0726] The system improves the user experience by recognizing the user's emotions using an emotion engine and providing optimal responses. The collected emotion data is also analyzed and used to improve the quality of future responses.

[0727] For example, examples of prompt sentences to input into a generative AI model include the following:

[0728] "How to extend iPhone battery life?"

[0729] "Please tell me about SoftBank's latest pricing plans."

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

[0731] Step 1: Ask a question

[0732] The user launches a dedicated application on the device and inputs a question. For example, they might input, "What is SoftBank's latest pricing plan?" The input question is displayed by the device's UI. The input is the user's question, and the output is the user's question displayed on a confirmation screen.

[0733] Step 2: Collecting Emotional Data

[0734] The device uses its built-in camera and microphone to detect the user's facial expressions and tone of voice. The emotion engine analyzes this data and recognizes the user's emotional state. Specifically, it uses facial expression images captured by the camera and voice recorded by the microphone as input and outputs emotional data.

[0735] Step 3: Submit your question

[0736] The device sends the question and emotion data entered by the user to the server as an HTTP request. The input is the question and emotion data, and the output is an HTTP request that includes them.

[0737] Step 4: Parse the questions and sentiment data

[0738] The server analyzes the received HTTP request and extracts the question content and emotional data. The server then passes this data to the generative AI model. Specifically, it extracts the question content and emotional data from the request and provides them to the generative AI model. The input is the HTTP request, and the output is the analysis results of the question content and emotional data.

[0739] Step 5: Answer Generation

[0740] The generative AI model generates an appropriate answer based on the question. At this time, it also takes emotional data into consideration to adjust the tone and content of the answer. For example, it generates an answer such as, "SoftBank's latest plan costs XX yen and includes XX GB of data." The input is the question and emotional data, and the output is an appropriately adjusted answer.

[0741] Step 6: Formatting your answers

[0742] The server receives the generated answer and formats it in a way that is easy for the user to understand. The tone is adjusted to a calm tone based on data from the emotion engine. The input is the answer from the generative AI model, and the output is the formatted answer.

[0743] Step 7: Submit your response

[0744] The server formats the answer and sends it to the terminal as an HTTP response, where the input is the formatted answer and the output is the generated HTTP response.

[0745] Step 8: View Answers

[0746] The terminal analyzes the response received from the server and displays it on the user interface. The user confirms the presented answer. The input is the HTTP response, and the output is the answer displayed on the user interface.

[0747] Step 9: Record and use emotional data

[0748] The emotion engine recognizes the user's emotion data and stores it in a database for future question answering. Specifically, the emotion data is recorded in the database and used to analyze and generate subsequent questions. The input is emotion data, and the output is a saved database entry.

[0749] (Application example 2)

[0750] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0751] In today's security services, there is a need to provide fast, accurate information in real time. However, there is a lack of means to quickly resolve the uncertainties and anxieties that security guards face while on patrol. Furthermore, systems that do not properly recognize and respond to user emotions increase the risk of misjudging the situation, resulting in increased security risks. To solve these issues, a system that takes user emotions into account and provides appropriate response instructions in real time is needed.

[0752] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting a question entered by a user, means for generating an appropriate answer using a generative model that analyzes the accepted question, means for sending and displaying the generated answer to the user, and means having an emotion engine that recognizes the user's emotion and adjusts the tone and content of the answer based on the emotion data. This makes it possible for security guards to receive appropriate advice in real time according to their emotions, even if they have questions or feel anxious while patrolling.

[0753] The "means for accepting the question content input by the user" is an interface for acquiring the question content input by the user through the terminal and transmitting it for subsequent processing.

[0754] A "generative model that analyzes received questions" is a machine learning model that analyzes received questions and generates appropriate answers to the questions.

[0755] The "means for transmitting and displaying the generated answer to the user" is an interface for transmitting the answer generated by the generative model to the user's terminal and displaying it.

[0756] "Means with an emotion engine that recognizes a user's emotions and adjusts the tone and content of responses based on the emotion data" refers to algorithms and functions that recognize a user's facial expressions, tone of voice, and other emotional indicators and adjust the tone and content of the generated responses based on them.

[0757] The "server that receives the question content and then transmits the question content and emotion data to the generative model" is a computer system that transmits the question content and emotion data received from the user to the generative model for analysis and answer generation.

[0758] The "terminal that displays the answer received from the server to the user" is a device that receives the answer generated by the server and displays it so that the user can confirm it visually or audibly.

[0759] "Means for recording the generated answers in a database and using them to improve answers to subsequent questions" refers to a system that stores answers generated by a generative model in a database and uses them to improve and optimize the accuracy of answers to future questions.

[0760] To implement this invention, it is necessary to build a system that accepts questions entered by users, generates appropriate answers, and transmits and displays the answers to the users. This system consists of a terminal used by the user, a server that analyzes the questions and emotion data, a generative model, and an emotion engine.

[0761] First, a user inputs a question using a device such as smart glasses. The device's camera captures the user's face, and the emotion engine recognizes the user's emotion. This emotion data is then sent to the server along with the question.

[0762] The server then passes the received question and emotion data to a generative model, which then generates an appropriate answer. The generative model uses machine learning to analyze the question and generates an optimal answer. Furthermore, the tone and content of the answer are adjusted based on the user's emotion as recognized by the emotion engine.

[0763] The generated answer is formatted by the server and sent back to the user's device. The device displays the received answer to the user for confirmation. The emotion data is also recorded in a database and used to improve the accuracy of answers for subsequent questions.

[0764] As a concrete example, consider the case where a security guard using smart glasses while patrolling inputs a question such as, "If there is suspicious activity in this area, how should I respond?" The camera in the smart glasses captures the user's facial expression, and the emotion engine detects "anxiety." This question and emotion data are sent to the server, and the generative model generates the answer, "First, remain calm, immediately avoid contact with suspicious individuals, and contact backup." The emotion engine adjusts the tone of the answer, providing the user with a calm tone.

[0765] An example prompt for a generative AI model might take the form:

[0766] Question: "If there is suspicious activity in this area, how should I respond?"

[0767] Emotion data: "Impatience"

[0768] Tone of generated answer: "Calm"

[0769] In this way, the present invention realizes a system in the field of security services that provides appropriate responses in real time according to the user's emotions and supports the work of security guards.

[0770] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0771] Step 1:

[0772] The system accepts questions entered by the user. The user enters the question using the voice input function of the smart glasses. The inputs are the question text and an image of the user's facial expression.

[0773] Step 2:

[0774] The device captures the user's face and recognizes the user's emotions using an emotion engine. The input is the captured facial image, and the output is emotion data such as "impatience" or "anger." Emotion data is extracted based on an analysis of the user's facial expressions.

[0775] Step 3:

[0776] The device sends the question and emotion data to the server. The input is the question text and emotion data, which are sent to the server as an HTTP request.

[0777] Step 4:

[0778] The server receives the question content and emotion data. The input is an HTTP request sent from the device. The server analyzes this data and converts it into an input format for the generative model.

[0779] Step 5:

[0780] The server passes the received data to a generative model to generate an answer. The input is the question text and sentiment data, which the generative AI model analyzes to generate an appropriate answer. The output is the generated answer.

[0781] Step 6:

[0782] The server passes the generated answer to the emotion engine, which adjusts the tone and content of the answer based on the emotion data. The input is the generated answer and emotion data, and the output is the adjusted answer. The tone is adjusted according to the emotion.

[0783] Step 7:

[0784] The server formats the adjusted answer and sends it to the device. The input is the adjusted answer and the output is sent to the device as an HTTP response.

[0785] Step 8:

[0786] The terminal displays the answer received from the server. The input is the answer text sent from the server, and the output is displayed in a format that the user can confirm visually or audibly. The user confirms the displayed answer.

[0787] Step 9:

[0788] The emotion data collected by the emotion engine is recorded in a database. The input is the emotion data recognized by the emotion engine, and the output is the emotion data stored in the database. This is used to improve the accuracy of answers to subsequent questions.

[0789] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0790] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0791] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0792] [Third embodiment]

[0793] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0794] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0795] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0796] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0797] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0798] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0799] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0800] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0801] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0802] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0803] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0804] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0805] The present invention relates to a system for providing quick and accurate answers to questions about smartphones in real time. Specific embodiments will be described in detail below.

[0806] This system is comprised of a device used by the user, a server that analyzes the question and generates an answer, and a generative model. The user uses the device to input a question about a smartphone. For example, the user can input, "How can I extend the battery life of my iPhone?"

[0807] The device receives the question entered by the user and sends it to the server. The server passes the received question to the generative model, which analyzes the question and generates an appropriate answer. The generated answer is formatted by the server and sent back to the device. The device displays the received answer to the user.

[0808] This will be explained with specific examples.

[0809] Example 1: iPhone battery life question

[0810] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[0811] 2. The device sends this question to the server.

[0812] 3. The server passes the question to the generative model, which generates an answer such as "Adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[0813] 4. The server sends the generated answer to the terminal, which displays it to the user.

[0814] 5. The user checks the displayed answers.

[0815] Next, the processing flow of the program of the present invention will be explained in natural language.

[0816] 1. Questions

[0817] The user launches a dedicated application on the device and inputs a question, such as "What is SoftBank's latest pricing plan?"

[0818] The terminal displays the question on the confirmation screen, and the user presses the "Send" button.

[0819] 2. Submit a question

[0820] The terminal sends the question entered by the user to the server as an HTTP request.

[0821] 3. Question analysis

[0822] The server receives the HTTP request and passes the question to the generative model.

[0823] The generative model analyzes the question and creates an appropriate answer.

[0824] 4. Answer generation

[0825] The generative model generates an answer such as, "The latest SoftBank pricing plans include the 5G GREEN Plan and the Super Pocket Plan. Please check the official website for details."

[0826] The server formats the generated response for delivery to the device.

[0827] 5. Submit your response

[0828] The server formats the answer and sends it to the terminal as an HTTP response.

[0829] 6. Answer display

[0830] The terminal receives the HTTP response, analyzes it, and displays it in the user interface.

[0831] The user checks the answer.

[0832] The system records the generated answers in a database and has a mechanism to improve the accuracy of answers based on past data, which is expected to result in quick and accurate responses to subsequent questions.

[0833] In this way, the present system quickly provides users with the information they need, improving the company's image and customer satisfaction.

[0834] The processing flow will be explained below.

[0835] Step 1: Ask a question

[0836] The user launches a dedicated application on the device.

[0837] A user types a smartphone question into an in-app form, for example, "How can I extend my iPhone's battery life?"

[0838] The device obtains the user's input and displays it on a confirmation screen.

[0839] The user checks the information entered on the confirmation screen and presses the "Submit" button.

[0840] Step 2: Submit your question

[0841] The terminal sends the question entered by the user to the server as an HTTP request.

[0842] The terminal confirms the success of the transmission and notifies the user of the completion of the transmission.

[0843] Step 3: Question acceptance (server side)

[0844] The server receives the HTTP request and analyzes the question.

[0845] The server stores the question content as a log in a database.

[0846] Step 4: Question Analysis

[0847] The server passes the received question to the generative model.

[0848] The generative model analyzes the question and prepares to generate an appropriate answer.

[0849] Step 5: Answer Generation

[0850] The generative model references the corresponding database or knowledge base based on the question.

[0851] The generative model creates an appropriate answer in natural language based on the reference results.

[0852] The server receives and formats the generated response.

[0853] Step 6: Submit your response

[0854] The server prepares the answer and sends it to the terminal as an HTTP response.

[0855] The server acknowledges and logs the successful transmission of the response.

[0856] Step 7: View Answers

[0857] The terminal analyzes the response received from the server.

[0858] The terminal analyzes the answer and displays it on the user interface.

[0859] The user checks the answer displayed on the device screen.

[0860] Step 8: Feedback (optional)

[0861] The user enters feedback on the displayed answer.

[0862] The terminal obtains the user's feedback and sends it to the server.

[0863] The server receives the feedback and records it in a database to help improve subsequent questions.

[0864] Through these processing steps, users can get fast and accurate answers to their smartphone-related questions, improving the company's image and increasing user satisfaction.

[0865] Example 1

[0866] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0867] Conventional systems have difficulty providing fast and accurate answers to smartphone-related questions. Since users often input a wide range of questions, ensuring the accuracy and speed of the answers is crucial. Furthermore, the quality of the answers is questionable due to a lack of a feedback mechanism for improving the generated answers over the long term. This can result in reduced user satisfaction.

[0868] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0869] In this invention, the server includes a means for accepting questions entered by users, a means for analyzing the accepted questions and creating appropriate answers using a generative AI model, and a means for formatting the generated answers and sending them to the user for display. This enables quick and accurate answers to questions entered by users. The server also includes a means for recording the generated answers in a database and using them to improve future questions. This improves the quality and accuracy of answers and increases user satisfaction.

[0870] "User" refers to an entity that uses the system to enter questions and receive answers.

[0871] "Question content" refers to information or questions entered by the user, which are the subject of analysis and answer generation.

[0872] "Means for accepting" refers to the means by which the terminal or server checks the content of the question entered by the user and converts it into a format that can be used within the system.

[0873] A "generative AI model" refers to an artificial intelligence algorithm that analyzes a question and creates an appropriate answer.

[0874] "Means of analysis" refers to the mechanism that processes the received question to understand it and provide an answer.

[0875] "Means for creating answers" refers to the function of creating appropriate answers based on the question content analyzed using a generative AI model.

[0876] "Formatting" refers to the process of converting the answers obtained from a generative AI model into a format that is easy to read for display to the user.

[0877] "Means for transmitting and displaying" refers to a function for transmitting the generated answer from the server to the terminal and for the terminal to display it to the user.

[0878] "Server" refers to the computer system that receives the question and analyzes it using a generative AI model.

[0879] "Terminal" refers to a device through which a user can enter questions and receive answers. Examples include smartphones and tablets.

[0880] "Database" means a collection of information that stores generated answers and questions and is recorded in an accessible format for future use.

[0881] "Improvement measures" refers to the process of using information recorded in the database to improve the quality of answers to future questions.

[0882] The present invention is a system that provides quick and accurate answers in real time to questions about smartphones entered by users. This system consists of the following components:

[0883] System Configuration

[0884] 1. Terminal

[0885] A terminal is a device on which a user inputs questions and receives answers, such as a smartphone or tablet.

[0886] The device provides a dedicated application for users to input questions. This application has the function of inputting, confirming, and sending questions through a user interface.

[0887] 2. Server

[0888] The server receives the question sent from the terminal, analyzes it, and generates an answer.

[0889] The server passes the question to the generative AI model, formats the results, and sends them to the device.

[0890] The server also records the generated answers in a database to help improve the quality of answers to future questions.

[0891] 3. Generative AI Models

[0892] The generative AI model is an artificial intelligence algorithm that analyzes the question content passed from the server and generates an appropriate answer.

[0893] The model performs contextual understanding, tokenization, and syntax analysis to generate the answer the user expects.

[0894] Data processing flow

[0895] 1. Questions

[0896] The user launches a dedicated application on the device and enters a question, for example, "What is SoftBank's latest pricing plan?"

[0897] The terminal displays the question on the confirmation screen, and the user presses the "Send" button.

[0898] 2. Submit a question

[0899] When the user presses the "Send" button, the device converts the question into JSON format and sends it to the server as an HTTP request.

[0900] 3. Question analysis

[0901] The server receives the HTTP request and passes the question to the generative AI model.

[0902] 4. Answer generation

[0903] The generative AI model analyzes the question and generates an appropriate answer, such as, "SoftBank's latest pricing plans include the 5G GREEN Plan and the Super Pocket Plan. Please check the official website for details."

[0904] The server formats the generated response and prepares it for transmission to the terminal.

[0905] 5. Submitting and Displaying Answers

[0906] The server then sends the formatted answer to the terminal as an HTTP response.

[0907] The terminal receives the HTTP response, parses it, and displays it in the user interface. The user confirms the displayed answer.

[0908] Specific examples

[0909] (Example 1: Question about iPhone battery life)

[0910] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[0911] 2. The device sends this question to the server.

[0912] 3. The server passes the question to the generative AI model, which then generates an answer such as "adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[0913] 4. The server sends the generated answer to the terminal, which displays it to the user.

[0914] 5. The user checks the displayed answers.

[0915] An example of a prompt is as follows:

[0916] "How can I extend my iPhone's battery life?"

[0917] "What is SoftBank's latest pricing plan?"

[0918] "Tell me about your smartphone's security settings."

[0919] This system allows users to enter questions with confidence and receive prompt and accurate answers. The generated answers are recorded in a database, which is expected to improve the accuracy of answers to future questions and increase user satisfaction.

[0920] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0921] Step 1: Enter and confirm your questions

[0922] User enters a question: The user starts a dedicated application on their smartphone and enters a question in the input field on the screen. For example, the user might enter, "What is SoftBank's latest pricing plan?"

[0923] Input: Text entered by the user (e.g., "What are SoftBank's latest pricing plans?")

[0924] Output: Input contents displayed on the confirmation screen

[0925] The device displays the question on the confirmation screen: The device displays the entered question on the confirmation screen, and a "Send" button is provided. When the user presses the Send button, the question is ready to be sent to the server.

[0926] Input: What the user types

[0927] Output: What the user sees on the screen

[0928] Step 2: Submit your question

[0929] The terminal converts the question content into JSON format and sends it to the server: When the user presses the "Send" button, the terminal converts the question content into JSON format and sends it to the server as an HTTP request.

[0930] Input: Confirmed question

[0931] Output: Question data in JSON format, HTTP request

[0932] Step 3: Receiving and parsing the question

[0933] The server receives the question and prepares it to be passed to the generative AI model: The server receives the HTTP request sent from the device and extracts the question. The extracted question is passed to the generative AI model.

[0934] Input: HTTP request, question data in JSON format

[0935] Output: Cleaned and pre-processed data to feed into a generative AI model

[0936] Step 4: Generate an answer

[0937] The generative AI model analyzes the question and generates an appropriate answer: The generative AI model analyzes the question and generates an appropriate answer. For example, it generates an answer such as, "SoftBank's latest pricing plans include the 5G GREEN Plan and the Super Pocket Plan. Please check the official website for details."

[0938] Input: Preprocessed query data

[0939] Output: Generated answer text

[0940] The server formats the generated answer and prepares it for transmission: The server formats the generated answer in a format that is easy for the user to view and prepares it for transmission to the terminal.

[0941] Input: Answer text from the generative AI model

[0942] Output: Formatted answer text, HTTP response data

[0943] Step 5: Submit your response

[0944] The server formats the answer and sends it to the terminal: The server formats the answer and sends it to the terminal as an HTTP response.

[0945] Input: Formatted answer text, HTTP response data

[0946] Output: HTTP response

[0947] Step 6: View your answers

[0948] The terminal receives the HTTP response, parses it, and displays it on the user interface: The terminal receives the HTTP response from the server, parses it, and displays it on the user interface.

[0949] Input: HTTP response

[0950] Output: The answer displayed in the user interface

[0951] The user checks the displayed answer: The user checks the answer displayed on the device screen.

[0952] Input: The answer displayed in the user interface

[0953] Output: User confirmation action

[0954] (Application example 1)

[0955] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0956] With conventional food delivery services, it is difficult for users to receive prompt and accurate answers when they have questions about orders or delivery. Furthermore, inquiries about delivery status or order changes cannot be responded to appropriately, which can lead to a decrease in customer satisfaction. There is a need to solve these problems and provide better services to users.

[0957] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0958] In this invention, the server includes means for accepting questions entered by users, means for generating appropriate answers using a generative model that analyzes the accepted questions, means for transmitting and displaying the generated answers to the users, and means for processing inquiries about food delivery services and providing answers in real time, thereby enabling users to obtain prompt and accurate answers to their questions about food delivery.

[0959] "User" refers to an individual or corporation who uses this system to enter questions and obtain answers.

[0960] The "question content" refers to the specific content entered by the user regarding the information they want to know or the problem they want to solve.

[0961] The "receiving means" is an interface that has the function of receiving the question content input by the user and sending it to the server.

[0962] An "analytical generative model" refers to an algorithm or machine learning model that analyzes the content of the question received and generates an appropriate answer. Specifically, it is a model that uses natural language processing technology.

[0963] The "means for generating an answer" is a function that generates an appropriate answer to the question content using the generative model to be analyzed.

[0964] The "means for transmitting and displaying" is a mechanism that has the function of transmitting the generated answer to the user and displaying the answer on the user's interface.

[0965] A "server" is a computer system that manages the entire process of receiving a question, passing it to a generative model to generate an answer, and then sending it back to the user.

[0966] A "terminal" is an electronic device that allows a user to input questions and receive answers. Specifically, this includes smartphones and tablets.

[0967] A "food delivery service" is a service that delivers food ordered by a user to a specified location.

[0968] "Means for providing answers in real time" refers to technologies and mechanisms for generating and transmitting answers to questions from users in real time.

[0969] The "database" is an information management system that records and stores the generated answers and questions, and uses them to improve subsequent questions.

[0970] The system for realizing this invention mainly consists of a user terminal, a server, a generative model, and a database. The system allows users to input questions about food delivery using the terminal, analyzes the questions in real time, and provides appropriate answers. Specific embodiments are described below.

[0971] System configuration

[0972] 1. User Device

[0973] An electronic device that allows users to enter questions, such as a smartphone or tablet.

[0974] After the question is entered, it has the function of sending it to the server as an HTTP request.

[0975] 2. Server

[0976] It is a central control unit that receives the query content and passes it to the generative model for analysis.

[0977] It uses generative AI models such as OpenAI's GPT-4 to analyze questions and generate appropriate answers.

[0978] It has the function of formatting the generated answer and sending it to the terminal.

[0979] 3. Generative Model

[0980] This model analyzes the content of the received question and creates an appropriate answer, using natural language processing technology.

[0981] For example, it generates real-time answers to food delivery questions about delivery status and order details.

[0982] 4. Database

[0983] The generated answers and questions are recorded and used to improve subsequent questions.

[0984] It acts as a database for learning whether questions and answers are appropriate.

[0985] Data processing and calculation

[0986] When a user types and sends a question into their device, the question is sent to the server as an HTTP request. The server receives the question and passes it to a generative model. This generative model analyzes the question using natural language processing technology and has the means to process inquiries about food delivery services and provide answers in real time. The generated answer is formatted by the server and sent to the user's device as an HTTP response. The user's device can receive and display this answer.

[0987] Specific examples

[0988] A user types a question into the app: "Does the salad I ordered include dressing?"

[0989] Example prompt sentence:

[0990] User: "Does the salad I ordered include dressing?"

[0991] System: "Your current order includes dressing. Depending on the salad type, French dressing is standard. If you need other options, you can add them from your order history."

[0992] In this way, users can receive appropriate answers in real time through the app, which will increase customer satisfaction and improve the reliability of food delivery services.

[0993] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0994] Step 1:

[0995] The user launches the "Delivers Assistant" app and enters a question. The entered question is displayed as text in the app.

[0996] Step 2:

[0997] When the user presses the send button, the terminal sends the question to the server as an HTTP request. The input is the user's question text, and the output is the HTTP request sent to the server.

[0998] Step 3:

[0999] The server receives an HTTP request and passes it to the generative model to analyze the question. The input is the text data received as the HTTP request, and the output is the input data to the generative model.

[1000] Step 4:

[1001] A generative model (e.g., OpenAI's GPT-4) analyzes the question and generates an appropriate answer. The input is the text data of the question, and the output is the text data of the generated answer.

[1002] Step 5:

[1003] The server receives the generated answer, formats it, and generates an HTTP response. The input is the answer data from the generative model, and the output is an HTTP response containing the formatted answer data.

[1004] Step 6:

[1005] The server sends an HTTP response to the terminal. The input is the formatted response data, and the output is the HTTP response sent to the terminal.

[1006] Step 7:

[1007] The terminal receives the HTTP response, parses the response, and displays it in a user interface. The input is the received HTTP response, and the output is the response text that is displayed to the user.

[1008] Step 8:

[1009] The user confirms the displayed answer. Specifically, they read the answer displayed on the smartphone screen and enter additional questions if necessary. The input is the answer text that the user confirms, and the output is the next action depending on the situation.

[1010] Through these steps, users can get quick and accurate answers to their food delivery questions.

[1011] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1012] The present invention relates to a system that allows users to input questions about smartphones and provides real-time and accurate answers to those questions. Furthermore, this system is equipped with an emotion engine that recognizes the user's emotions and generates optimal answers based on the user's emotions.

[1013] This system is composed of a device used by the user, a server that analyzes the content of the question and generates an answer, and a generative model and emotion engine at its core. The user uses the device to input a question about their smartphone. For example, they can input, "How can I extend the battery life of my iPhone?"

[1014] The device receives the question entered by the user and sends it to the server. The server uses an emotion engine to analyze the question as well as the emotional data at the time of the user's input. The server passes the received question and emotional data to a generative model, which uses these to generate an appropriate answer. This generated answer is formatted by the server and sent back to the device. The device displays the received answer to the user. The emotional data recognized by the emotion engine is also recorded in a database and used to improve subsequent questions.

[1015] This will be explained with specific examples.

[1016] Example 1: iPhone battery life question

[1017] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[1018] 2. Using the device's built-in camera and microphone, the emotion engine recognizes emotional data such as the user's facial expressions and tone of voice.

[1019] 3. The device sends the question and emotion data to the server.

[1020] 4. The server passes the question and emotion data to the generative model, which then generates an answer such as "adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[1021] 5. If the emotion engine detects that the user is frustrated, the generative model adjusts the tone of the response to be more toned down.

[1022] 6. The server sends the generated answer to the terminal, which displays it to the user.

[1023] 7. The user checks the displayed answers.

[1024] 8. The user's emotion data recognized by the emotion engine is recorded in a database and used to improve the accuracy of subsequent questions.

[1025] Next, the processing flow of the program of the present invention will be explained in natural language.

[1026] 1. Questions

[1027] The user launches a dedicated application on the device and inputs a question, such as "What is SoftBank's latest pricing plan?"

[1028] The device collects the user's emotional data, displays it on a confirmation screen, and the user presses the "send" button.

[1029] 2. Submit a question

[1030] The device sends the question entered by the user and emotional data to the server as an HTTP request.

[1031] 3. Question reception (server side)

[1032] The server receives the HTTP request and analyzes the question content and sentiment data.

[1033] The server passes these to a generative model to generate an appropriate answer.

[1034] 4. Answer generation

[1035] A generative model generates appropriate answers based on the question, and an emotion engine adjusts the tone and content of the answers based on the user's emotional data.

[1036] The server receives and formats the generated response.

[1037] 5. Submit your response

[1038] The server prepares the answer and sends it to the terminal as an HTTP response.

[1039] 6. Answer display

[1040] The terminal analyzes the response received from the server and displays it on the user interface.

[1041] The user checks the answer.

[1042] The user's emotional data is recorded in a database and used to improve subsequent questions.

[1043] This system provides an appropriate response according to the user's emotions, thereby realizing a better user experience, improving the company's image, and increasing user satisfaction.

[1044] The processing flow will be explained below.

[1045] Step 1: Ask a question

[1046] The user launches a dedicated application on the device.

[1047] A user types a smartphone question into an in-app form, for example, "How can I extend my iPhone's battery life?"

[1048] The device obtains the user's input and displays it on a confirmation screen.

[1049] The user checks the information entered on the confirmation screen and presses the "Submit" button.

[1050] Step 2: Obtaining emotion data

[1051] The emotion engine uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice.

[1052] The emotion engine collects the user's emotion data and returns the analysis results to the device.

[1053] Step 3: Submit your question

[1054] The device sends the question entered by the user and emotional data to the server as an HTTP request.

[1055] The terminal confirms the success of the transmission and notifies the user of the completion of the transmission.

[1056] Step 4: Question acceptance (server side)

[1057] The server receives the HTTP request and analyzes the question content and sentiment data.

[1058] The server stores the question content and emotion data in a database as a log.

[1059] Step 5: Question Analysis

[1060] The server passes the received question and emotion data to the generative model.

[1061] The generative model analyzes the question and prepares to generate an appropriate answer.

[1062] Step 6: Reflecting emotional data

[1063] The generative model adjusts the tone and content of the response based on the question and sentiment data.

[1064] For example, if the user is annoyed, provide the answer in a calmer tone.

[1065] Step 7: Answer Generation

[1066] A generative model creates an appropriate answer based on the question and sentiment data.

[1067] The server receives and formats the generated response.

[1068] Step 8: Submit your response

[1069] The server prepares the answer and sends it to the terminal as an HTTP response.

[1070] The server acknowledges and logs the successful transmission of the response.

[1071] Step 9: View Answers

[1072] The terminal analyzes the response received from the server.

[1073] The terminal analyzes the answer and displays it on the user interface.

[1074] The user checks the answer displayed on the device screen.

[1075] Step 10: Feedback (Optional)

[1076] The user enters feedback on the displayed answer.

[1077] The terminal obtains the user's feedback and sends it to the server.

[1078] The server receives the feedback and records it in a database.

[1079] Through these specific processing steps, users can get fast and accurate answers to their smartphone-related questions. This system provides appropriate responses based on the user's emotions, improving the company's image and increasing user satisfaction.

[1080] Example 2

[1081] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1082] Conventional question-answering systems provide answers without considering the user's emotions, which can result in a poor user experience. Furthermore, it is difficult to understand the relationship between the content of the question entered by the user and the user's emotions and provide an accurate answer. This leads to the problem of not being able to provide the information the user is looking for quickly and appropriately.

[1083] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1084] In this invention, the server includes means for accepting a question entered by a user, means for collecting emotion data related to the question, means for generating an appropriate answer using a generative model that analyzes the accepted question and the emotion data, means for adjusting the generated answer in accordance with the user's emotion, means for sending and displaying the adjusted answer to the user, and means for recording the emotion data in a database and using it to improve subsequent questions. This allows for the provision of an appropriate response in accordance with the user's emotion, thereby improving the user experience and satisfaction.

[1085] "Question content" refers to the specific questions or requests that the user inputs to the system.

[1086] "Emotion data" refers to data relating to the user's emotional state obtained from facial expressions, tone of voice, and the like.

[1087] A "generative model" refers to an algorithm or machine learning model that generates appropriate answers based on the input question and emotional data.

[1088] The "server" refers to a central processing unit that receives the question content and emotion data, generates an answer using a generative model, and transmits it to the user after adjustment.

[1089] "Terminal" refers to a device through which a user can enter questions and receive and display generated answers.

[1090] An "emotion engine" refers to software or hardware that analyzes a user's emotions from their facial expressions and tone of voice and outputs the results as data.

[1091] "Database" refers to an information management system that stores the generated emotional data and answers and uses them to improve the accuracy of answers to subsequent questions.

[1092] "HTTP request" refers to the communication protocol that allows a device to send question content and emotional data to a server.

[1093] "HTTP response" refers to a communication protocol that allows a server to send a generated response to a terminal.

[1094] "Formatting" refers to the process of adjusting the generated answers into a form that is easy for the user to understand.

[1095] MODE FOR CARRYING OUT THE INVENTION

[1096] This invention relates to a system that allows users to input questions about smartphones and provides accurate answers in real time. Furthermore, this system is equipped with an emotion engine that recognizes the user's emotions and generates optimal answers based on the user's emotions. The system is comprised of a device used by the user, a server that analyzes the question content and generates answers, and a generative model and emotion engine at its core.

[1097] A user uses a device to input a question about their smartphone. For example, they can input a question such as, "How can I extend the battery life of my iPhone?" The device receives the question input by the user and sends it to the server. At the same time, the emotion engine recognizes emotional data such as the user's facial expressions and tone of voice using the device's built-in camera and microphone. The recognized emotional data is also sent to the server.

[1098] The server receives and analyzes the emotional data along with the question content. The question content and emotional data extracted through the analysis are passed to a generative AI model. The generative AI model analyzes the question content using, for example, natural language processing (NLP) technology and generates an appropriate answer based on that analysis. Furthermore, the emotion engine refers to the emotional data analyzed and adjusts the tone and content to match the user's emotions.

[1099] The generated answer is formatted by the server and sent back to the device, where it is displayed to the user. The emotion data recognized by the emotion engine is also recorded in a database and used to improve subsequent questions.

[1100] Specific examples are shown below.

[1101] Example 1: iPhone battery life question

[1102] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[1103] 2. Using the device's built-in camera and microphone, the emotion engine recognizes emotional data such as the user's facial expressions and tone of voice.

[1104] 3. The device sends the question and emotion data to the server.

[1105] 4. The server passes the question and emotion data to the generative model, which then generates an answer such as "adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[1106] 5. The server formats the generated response and sends it back to the terminal.

[1107] 6. The terminal displays the received answer to the user.

[1108] 7. The emotional data recognized by the emotion engine is recorded in a database and used to improve subsequent questions.

[1109] The system improves the user experience by recognizing the user's emotions using an emotion engine and providing optimal responses. The collected emotion data is also analyzed and used to improve the quality of future responses.

[1110] For example, examples of prompt sentences to input into a generative AI model include the following:

[1111] "How to extend iPhone battery life?"

[1112] "Please tell me about SoftBank's latest pricing plans."

[1113] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1114] Step 1: Ask a question

[1115] The user launches a dedicated application on the device and inputs a question. For example, they might input, "What is SoftBank's latest pricing plan?" The input question is displayed by the device's UI. The input is the user's question, and the output is the user's question displayed on a confirmation screen.

[1116] Step 2: Collecting Emotional Data

[1117] The device uses its built-in camera and microphone to detect the user's facial expressions and tone of voice. The emotion engine analyzes this data and recognizes the user's emotional state. Specifically, it uses facial expression images captured by the camera and voice recorded by the microphone as input and outputs emotional data.

[1118] Step 3: Submit your question

[1119] The device sends the question and emotion data entered by the user to the server as an HTTP request. The input is the question and emotion data, and the output is an HTTP request that includes them.

[1120] Step 4: Parse the questions and sentiment data

[1121] The server analyzes the received HTTP request and extracts the question content and emotional data. The server then passes this data to the generative AI model. Specifically, it extracts the question content and emotional data from the request and provides them to the generative AI model. The input is the HTTP request, and the output is the analysis results of the question content and emotional data.

[1122] Step 5: Answer Generation

[1123] The generative AI model generates an appropriate answer based on the question. At this time, it also takes emotional data into consideration to adjust the tone and content of the answer. For example, it generates an answer such as, "SoftBank's latest plan costs XX yen and includes XX GB of data." The input is the question and emotional data, and the output is an appropriately adjusted answer.

[1124] Step 6: Formatting your answers

[1125] The server receives the generated answer and formats it in a way that is easy for the user to understand. The tone is adjusted to a calm tone based on data from the emotion engine. The input is the answer from the generative AI model, and the output is the formatted answer.

[1126] Step 7: Submit your response

[1127] The server formats the answer and sends it to the terminal as an HTTP response, where the input is the formatted answer and the output is the generated HTTP response.

[1128] Step 8: View Answers

[1129] The terminal analyzes the response received from the server and displays it on the user interface. The user confirms the presented answer. The input is the HTTP response, and the output is the answer displayed on the user interface.

[1130] Step 9: Record and use emotional data

[1131] The emotion engine recognizes the user's emotion data and stores it in a database for future question answering. Specifically, the emotion data is recorded in the database and used to analyze and generate subsequent questions. The input is emotion data, and the output is a saved database entry.

[1132] (Application example 2)

[1133] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1134] In today's security services, there is a need to provide fast, accurate information in real time. However, there is a lack of means to quickly resolve the uncertainties and anxieties that security guards face while on patrol. Furthermore, systems that do not properly recognize and respond to user emotions increase the risk of misjudging the situation, resulting in increased security risks. To solve these issues, a system that takes user emotions into account and provides appropriate response instructions in real time is needed.

[1135] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting a question entered by a user, means for generating an appropriate answer using a generative model that analyzes the accepted question, means for sending and displaying the generated answer to the user, and means having an emotion engine that recognizes the user's emotion and adjusts the tone and content of the answer based on the emotion data. This makes it possible for security guards to receive appropriate advice in real time according to their emotions, even if they have questions or feel anxious while patrolling.

[1136] The "means for accepting the question content input by the user" is an interface for acquiring the question content input by the user through the terminal and transmitting it for subsequent processing.

[1137] A "generative model that analyzes received questions" is a machine learning model that analyzes received questions and generates appropriate answers to the questions.

[1138] The "means for transmitting and displaying the generated answer to the user" is an interface for transmitting the answer generated by the generative model to the user's terminal and displaying it.

[1139] "Means with an emotion engine that recognizes a user's emotions and adjusts the tone and content of responses based on the emotion data" refers to algorithms and functions that recognize a user's facial expressions, tone of voice, and other emotional indicators and adjust the tone and content of the generated responses based on them.

[1140] The "server that receives the question content and then transmits the question content and emotion data to the generative model" is a computer system that transmits the question content and emotion data received from the user to the generative model for analysis and answer generation.

[1141] The "terminal that displays the answer received from the server to the user" is a device that receives the answer generated by the server and displays it so that the user can confirm it visually or audibly.

[1142] "Means for recording the generated answers in a database and using them to improve answers to subsequent questions" refers to a system that stores answers generated by a generative model in a database and uses them to improve and optimize the accuracy of answers to future questions.

[1143] To implement this invention, it is necessary to build a system that accepts questions entered by users, generates appropriate answers, and transmits and displays the answers to the users. This system consists of a terminal used by the user, a server that analyzes the questions and emotion data, a generative model, and an emotion engine.

[1144] First, a user inputs a question using a device such as smart glasses. The device's camera captures the user's face, and the emotion engine recognizes the user's emotion. This emotion data is then sent to the server along with the question.

[1145] The server then passes the received question and emotion data to a generative model, which then generates an appropriate answer. The generative model uses machine learning to analyze the question and generates an optimal answer. Furthermore, the tone and content of the answer are adjusted based on the user's emotion as recognized by the emotion engine.

[1146] The generated answer is formatted by the server and sent back to the user's device. The device displays the received answer to the user for confirmation. The emotion data is also recorded in a database and used to improve the accuracy of answers for subsequent questions.

[1147] As a concrete example, consider the case where a security guard using smart glasses while patrolling inputs a question such as, "If there is suspicious activity in this area, how should I respond?" The camera in the smart glasses captures the user's facial expression, and the emotion engine detects "anxiety." This question and emotion data are sent to the server, and the generative model generates the answer, "First, remain calm, immediately avoid contact with suspicious individuals, and contact backup." The emotion engine adjusts the tone of the answer, providing the user with a calm tone.

[1148] An example prompt for a generative AI model might take the form:

[1149] Question: "If there is suspicious activity in this area, how should I respond?"

[1150] Emotion data: "Impatience"

[1151] Tone of generated answer: "Calm"

[1152] In this way, the present invention realizes a system in the field of security services that provides appropriate responses in real time according to the user's emotions and supports the work of security guards.

[1153] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1154] Step 1:

[1155] The system accepts questions entered by the user. The user enters the question using the voice input function of the smart glasses. The inputs are the question text and an image of the user's facial expression.

[1156] Step 2:

[1157] The device captures the user's face and recognizes the user's emotions using an emotion engine. The input is the captured facial image, and the output is emotion data such as "impatience" or "anger." Emotion data is extracted based on an analysis of the user's facial expressions.

[1158] Step 3:

[1159] The device sends the question and emotion data to the server. The input is the question text and emotion data, which are sent to the server as an HTTP request.

[1160] Step 4:

[1161] The server receives the question content and emotion data. The input is an HTTP request sent from the device. The server analyzes this data and converts it into an input format for the generative model.

[1162] Step 5:

[1163] The server passes the received data to a generative model to generate an answer. The input is the question text and sentiment data, which the generative AI model analyzes to generate an appropriate answer. The output is the generated answer.

[1164] Step 6:

[1165] The server passes the generated answer to the emotion engine, which adjusts the tone and content of the answer based on the emotion data. The input is the generated answer and emotion data, and the output is the adjusted answer. The tone is adjusted according to the emotion.

[1166] Step 7:

[1167] The server formats the adjusted answer and sends it to the device. The input is the adjusted answer and the output is sent to the device as an HTTP response.

[1168] Step 8:

[1169] The terminal displays the answer received from the server. The input is the answer text sent from the server, and the output is displayed in a format that the user can confirm visually or audibly. The user confirms the displayed answer.

[1170] Step 9:

[1171] The emotion data collected by the emotion engine is recorded in a database. The input is the emotion data recognized by the emotion engine, and the output is the emotion data stored in the database. This is used to improve the accuracy of answers to subsequent questions.

[1172] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1173] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1174] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1175] [Fourth embodiment]

[1176] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1177] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1178] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1179] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1180] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1181] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1182] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1183] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1184] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1185] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1186] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1187] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1188] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1189] The present invention relates to a system for providing quick and accurate answers to questions about smartphones in real time. Specific embodiments will be described in detail below.

[1190] This system is comprised of a device used by the user, a server that analyzes the question and generates an answer, and a generative model. The user uses the device to input a question about a smartphone. For example, the user can input, "How can I extend the battery life of my iPhone?"

[1191] The device receives the question entered by the user and sends it to the server. The server passes the received question to the generative model, which analyzes the question and generates an appropriate answer. The generated answer is formatted by the server and sent back to the device. The device displays the received answer to the user.

[1192] This will be explained with specific examples.

[1193] Example 1: iPhone battery life question

[1194] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[1195] 2. The device sends this question to the server.

[1196] 3. The server passes the question to the generative model, which generates an answer such as "Adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[1197] 4. The server sends the generated answer to the terminal, which displays it to the user.

[1198] 5. The user checks the displayed answers.

[1199] Next, the processing flow of the program of the present invention will be explained in natural language.

[1200] 1. Questions

[1201] The user launches a dedicated application on the device and inputs a question, such as "What is SoftBank's latest pricing plan?"

[1202] The terminal displays the question on the confirmation screen, and the user presses the "Send" button.

[1203] 2. Submit a question

[1204] The terminal sends the question entered by the user to the server as an HTTP request.

[1205] 3. Question analysis

[1206] The server receives the HTTP request and passes the question to the generative model.

[1207] The generative model analyzes the question and creates an appropriate answer.

[1208] 4. Answer generation

[1209] The generative model generates an answer such as, "The latest SoftBank pricing plans include the 5G GREEN Plan and the Super Pocket Plan. Please check the official website for details."

[1210] The server formats the generated response for delivery to the device.

[1211] 5. Submit your response

[1212] The server formats the answer and sends it to the terminal as an HTTP response.

[1213] 6. Answer display

[1214] The terminal receives the HTTP response, analyzes it, and displays it in the user interface.

[1215] The user checks the answer.

[1216] The system records the generated answers in a database and has a mechanism to improve the accuracy of answers based on past data, which is expected to result in quick and accurate responses to subsequent questions.

[1217] In this way, the present system quickly provides users with the information they need, improving the company's image and customer satisfaction.

[1218] The processing flow will be explained below.

[1219] Step 1: Ask a question

[1220] The user launches a dedicated application on the device.

[1221] A user types a smartphone question into an in-app form, for example, "How can I extend my iPhone's battery life?"

[1222] The device obtains the user's input and displays it on a confirmation screen.

[1223] The user checks the information entered on the confirmation screen and presses the "Submit" button.

[1224] Step 2: Submit your question

[1225] The terminal sends the question entered by the user to the server as an HTTP request.

[1226] The terminal confirms the success of the transmission and notifies the user of the completion of the transmission.

[1227] Step 3: Question acceptance (server side)

[1228] The server receives the HTTP request and analyzes the question.

[1229] The server stores the question content as a log in a database.

[1230] Step 4: Question Analysis

[1231] The server passes the received question to the generative model.

[1232] The generative model analyzes the question and prepares to generate an appropriate answer.

[1233] Step 5: Answer Generation

[1234] The generative model references the corresponding database or knowledge base based on the question.

[1235] The generative model creates an appropriate answer in natural language based on the reference results.

[1236] The server receives and formats the generated response.

[1237] Step 6: Submit your response

[1238] The server prepares the answer and sends it to the terminal as an HTTP response.

[1239] The server acknowledges and logs the successful transmission of the response.

[1240] Step 7: View Answers

[1241] The terminal analyzes the response received from the server.

[1242] The terminal analyzes the answer and displays it on the user interface.

[1243] The user checks the answer displayed on the device screen.

[1244] Step 8: Feedback (optional)

[1245] The user enters feedback on the displayed answer.

[1246] The terminal obtains the user's feedback and sends it to the server.

[1247] The server receives the feedback and records it in a database to help improve subsequent questions.

[1248] Through these processing steps, users can get fast and accurate answers to their smartphone-related questions, improving the company's image and increasing user satisfaction.

[1249] Example 1

[1250] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1251] Conventional systems have difficulty providing fast and accurate answers to smartphone-related questions. Since users often input a wide range of questions, ensuring the accuracy and speed of the answers is crucial. Furthermore, the quality of the answers is questionable due to a lack of a feedback mechanism for improving the generated answers over the long term. This can result in reduced user satisfaction.

[1252] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1253] In this invention, the server includes a means for accepting questions entered by users, a means for analyzing the accepted questions and creating appropriate answers using a generative AI model, and a means for formatting the generated answers and sending them to the user for display. This enables quick and accurate answers to questions entered by users. The server also includes a means for recording the generated answers in a database and using them to improve future questions. This improves the quality and accuracy of answers and increases user satisfaction.

[1254] "User" refers to an entity that uses the system to enter questions and receive answers.

[1255] "Question content" refers to information or questions entered by the user, which are the subject of analysis and answer generation.

[1256] "Means for accepting" refers to the means by which the terminal or server checks the content of the question entered by the user and converts it into a format that can be used within the system.

[1257] A "generative AI model" refers to an artificial intelligence algorithm that analyzes a question and creates an appropriate answer.

[1258] "Means of analysis" refers to the mechanism that processes the received question to understand it and provide an answer.

[1259] "Means for creating answers" refers to the function of creating appropriate answers based on the question content analyzed using a generative AI model.

[1260] "Formatting" refers to the process of converting the answers obtained from a generative AI model into a format that is easy to read for display to the user.

[1261] "Means for transmitting and displaying" refers to a function for transmitting the generated answer from the server to the terminal and for the terminal to display it to the user.

[1262] "Server" refers to the computer system that receives the question and analyzes it using a generative AI model.

[1263] "Terminal" refers to a device through which a user can enter questions and receive answers. Examples include smartphones and tablets.

[1264] "Database" means a collection of information that stores generated answers and questions and is recorded in an accessible format for future use.

[1265] "Improvement measures" refers to the process of using information recorded in the database to improve the quality of answers to future questions.

[1266] The present invention is a system that provides quick and accurate answers in real time to questions about smartphones entered by users. This system consists of the following components:

[1267] System Configuration

[1268] 1. Terminal

[1269] A terminal is a device on which a user inputs questions and receives answers, such as a smartphone or tablet.

[1270] The device provides a dedicated application for users to input questions. This application has the function of inputting, confirming, and sending questions through a user interface.

[1271] 2. Server

[1272] The server receives the question sent from the terminal, analyzes it, and generates an answer.

[1273] The server passes the question to the generative AI model, formats the results, and sends them to the device.

[1274] The server also records the generated answers in a database to help improve the quality of answers to future questions.

[1275] 3. Generative AI Models

[1276] The generative AI model is an artificial intelligence algorithm that analyzes the question content passed from the server and generates an appropriate answer.

[1277] The model performs contextual understanding, tokenization, and syntax analysis to generate the answer the user expects.

[1278] Data processing flow

[1279] 1. Questions

[1280] The user launches a dedicated application on the device and enters a question, for example, "What is SoftBank's latest pricing plan?"

[1281] The terminal displays the question on the confirmation screen, and the user presses the "Send" button.

[1282] 2. Submit a question

[1283] When the user presses the "Send" button, the device converts the question into JSON format and sends it to the server as an HTTP request.

[1284] 3. Question analysis

[1285] The server receives the HTTP request and passes the question to the generative AI model.

[1286] 4. Answer generation

[1287] The generative AI model analyzes the question and generates an appropriate answer, such as, "SoftBank's latest pricing plans include the 5G GREEN Plan and the Super Pocket Plan. Please check the official website for details."

[1288] The server formats the generated response and prepares it for transmission to the terminal.

[1289] 5. Submitting and Displaying Answers

[1290] The server then sends the formatted answer to the terminal as an HTTP response.

[1291] The terminal receives the HTTP response, parses it, and displays it in the user interface. The user confirms the displayed answer.

[1292] Specific examples

[1293] (Example 1: Question about iPhone battery life)

[1294] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[1295] 2. The device sends this question to the server.

[1296] 3. The server passes the question to the generative AI model, which then generates an answer such as "adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[1297] 4. The server sends the generated answer to the terminal, which displays it to the user.

[1298] 5. The user checks the displayed answers.

[1299] An example of a prompt is as follows:

[1300] "How can I extend my iPhone's battery life?"

[1301] "What is SoftBank's latest pricing plan?"

[1302] "Tell me about your smartphone's security settings."

[1303] This system allows users to enter questions with confidence and receive prompt and accurate answers. The generated answers are recorded in a database, which is expected to improve the accuracy of answers to future questions and increase user satisfaction.

[1304] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1305] Step 1: Enter and confirm your questions

[1306] User enters a question: The user starts a dedicated application on their smartphone and enters a question in the input field on the screen. For example, the user might enter, "What is SoftBank's latest pricing plan?"

[1307] Input: Text entered by the user (e.g., "What are SoftBank's latest pricing plans?")

[1308] Output: Input contents displayed on the confirmation screen

[1309] The device displays the question on the confirmation screen: The device displays the entered question on the confirmation screen, and a "Send" button is provided. When the user presses the Send button, the question is ready to be sent to the server.

[1310] Input: What the user types

[1311] Output: What the user sees on the screen

[1312] Step 2: Submit your question

[1313] The terminal converts the question content into JSON format and sends it to the server: When the user presses the "Send" button, the terminal converts the question content into JSON format and sends it to the server as an HTTP request.

[1314] Input: Confirmed question

[1315] Output: Question data in JSON format, HTTP request

[1316] Step 3: Receiving and parsing the question

[1317] The server receives the question and prepares it to be passed to the generative AI model: The server receives the HTTP request sent from the device and extracts the question. The extracted question is passed to the generative AI model.

[1318] Input: HTTP request, question data in JSON format

[1319] Output: Cleaned and pre-processed data to feed into a generative AI model

[1320] Step 4: Generate an answer

[1321] The generative AI model analyzes the question and generates an appropriate answer: The generative AI model analyzes the question and generates an appropriate answer. For example, it generates an answer such as, "SoftBank's latest pricing plans include the 5G GREEN Plan and the Super Pocket Plan. Please check the official website for details."

[1322] Input: Preprocessed query data

[1323] Output: Generated answer text

[1324] The server formats the generated answer and prepares it for transmission: The server formats the generated answer in a format that is easy for the user to view and prepares it for transmission to the terminal.

[1325] Input: Answer text from the generative AI model

[1326] Output: Formatted answer text, HTTP response data

[1327] Step 5: Submit your response

[1328] The server formats the answer and sends it to the terminal: The server formats the answer and sends it to the terminal as an HTTP response.

[1329] Input: Formatted answer text, HTTP response data

[1330] Output: HTTP response

[1331] Step 6: View your answers

[1332] The terminal receives the HTTP response, parses it, and displays it on the user interface: The terminal receives the HTTP response from the server, parses it, and displays it on the user interface.

[1333] Input: HTTP response

[1334] Output: The answer displayed in the user interface

[1335] The user checks the displayed answer: The user checks the answer displayed on the device screen.

[1336] Input: The answer displayed in the user interface

[1337] Output: User confirmation action

[1338] (Application example 1)

[1339] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1340] With conventional food delivery services, it is difficult for users to receive prompt and accurate answers when they have questions about orders or delivery. Furthermore, inquiries about delivery status or order changes cannot be responded to appropriately, which can lead to a decrease in customer satisfaction. There is a need to solve these problems and provide better services to users.

[1341] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1342] In this invention, the server includes means for accepting questions entered by users, means for generating appropriate answers using a generative model that analyzes the accepted questions, means for transmitting and displaying the generated answers to the users, and means for processing inquiries about food delivery services and providing answers in real time, thereby enabling users to obtain prompt and accurate answers to their questions about food delivery.

[1343] "User" refers to an individual or corporation who uses this system to enter questions and obtain answers.

[1344] The "question content" refers to the specific content entered by the user regarding the information they want to know or the problem they want to solve.

[1345] The "receiving means" is an interface that has the function of receiving the question content input by the user and sending it to the server.

[1346] An "analytical generative model" refers to an algorithm or machine learning model that analyzes the content of the question received and generates an appropriate answer. Specifically, it is a model that uses natural language processing technology.

[1347] The "means for generating an answer" is a function that generates an appropriate answer to the question content using the generative model to be analyzed.

[1348] The "means for transmitting and displaying" is a mechanism that has the function of transmitting the generated answer to the user and displaying the answer on the user's interface.

[1349] A "server" is a computer system that manages the entire process of receiving a question, passing it to a generative model to generate an answer, and then sending it back to the user.

[1350] A "terminal" is an electronic device that allows a user to input questions and receive answers. Specifically, this includes smartphones and tablets.

[1351] A "food delivery service" is a service that delivers food ordered by a user to a specified location.

[1352] "Means for providing answers in real time" refers to technologies and mechanisms for generating and transmitting answers to questions from users in real time.

[1353] The "database" is an information management system that records and stores the generated answers and questions, and uses them to improve subsequent questions.

[1354] The system for realizing this invention mainly consists of a user terminal, a server, a generative model, and a database. The system allows users to input questions about food delivery using the terminal, analyzes the questions in real time, and provides appropriate answers. Specific embodiments are described below.

[1355] System configuration

[1356] 1. User Device

[1357] An electronic device that allows users to enter questions, such as a smartphone or tablet.

[1358] After the question is entered, it has the function of sending it to the server as an HTTP request.

[1359] 2. Server

[1360] It is a central control unit that receives the query content and passes it to the generative model for analysis.

[1361] It uses generative AI models such as OpenAI's GPT-4 to analyze questions and generate appropriate answers.

[1362] It has the function of formatting the generated answer and sending it to the terminal.

[1363] 3. Generative Model

[1364] This model analyzes the content of the received question and creates an appropriate answer, using natural language processing technology.

[1365] For example, it generates real-time answers to food delivery questions about delivery status and order details.

[1366] 4. Database

[1367] The generated answers and questions are recorded and used to improve subsequent questions.

[1368] It acts as a database for learning whether questions and answers are appropriate.

[1369] Data processing and calculation

[1370] When a user types and sends a question into their device, the question is sent to the server as an HTTP request. The server receives the question and passes it to a generative model. This generative model analyzes the question using natural language processing technology and has the means to process inquiries about food delivery services and provide answers in real time. The generated answer is formatted by the server and sent to the user's device as an HTTP response. The user's device can receive and display this answer.

[1371] Specific examples

[1372] A user types a question into the app: "Does the salad I ordered include dressing?"

[1373] Example prompt sentence:

[1374] User: "Does the salad I ordered include dressing?"

[1375] System: "Your current order includes dressing. Depending on the salad type, French dressing is standard. If you need other options, you can add them from your order history."

[1376] In this way, users can receive appropriate answers in real time through the app, which will increase customer satisfaction and improve the reliability of food delivery services.

[1377] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1378] Step 1:

[1379] The user launches the "Delivers Assistant" app and enters a question. The entered question is displayed as text in the app.

[1380] Step 2:

[1381] When the user presses the send button, the terminal sends the question to the server as an HTTP request. The input is the user's question text, and the output is the HTTP request sent to the server.

[1382] Step 3:

[1383] The server receives an HTTP request and passes it to the generative model to analyze the question. The input is the text data received as the HTTP request, and the output is the input data to the generative model.

[1384] Step 4:

[1385] A generative model (e.g., OpenAI's GPT-4) analyzes the question and generates an appropriate answer. The input is the text data of the question, and the output is the text data of the generated answer.

[1386] Step 5:

[1387] The server receives the generated answer, formats it, and generates an HTTP response. The input is the answer data from the generative model, and the output is an HTTP response containing the formatted answer data.

[1388] Step 6:

[1389] The server sends an HTTP response to the terminal. The input is the formatted response data, and the output is the HTTP response sent to the terminal.

[1390] Step 7:

[1391] The terminal receives the HTTP response, parses the response, and displays it in a user interface. The input is the received HTTP response, and the output is the response text that is displayed to the user.

[1392] Step 8:

[1393] The user confirms the displayed answer. Specifically, they read the answer displayed on the smartphone screen and enter additional questions if necessary. The input is the answer text that the user confirms, and the output is the next action depending on the situation.

[1394] Through these steps, users can get quick and accurate answers to their food delivery questions.

[1395] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1396] The present invention relates to a system that allows users to input questions about smartphones and provides real-time and accurate answers to those questions. Furthermore, this system is equipped with an emotion engine that recognizes the user's emotions and generates optimal answers based on the user's emotions.

[1397] This system is composed of a device used by the user, a server that analyzes the content of the question and generates an answer, and a generative model and emotion engine at its core. The user uses the device to input a question about their smartphone. For example, they can input, "How can I extend the battery life of my iPhone?"

[1398] The device receives the question entered by the user and sends it to the server. The server uses an emotion engine to analyze the question as well as the emotional data at the time of the user's input. The server passes the received question and emotional data to a generative model, which uses these to generate an appropriate answer. This generated answer is formatted by the server and sent back to the device. The device displays the received answer to the user. The emotional data recognized by the emotion engine is also recorded in a database and used to improve subsequent questions.

[1399] This will be explained with specific examples.

[1400] Example 1: iPhone battery life question

[1401] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[1402] 2. Using the device's built-in camera and microphone, the emotion engine recognizes emotional data such as the user's facial expressions and tone of voice.

[1403] 3. The device sends the question and emotion data to the server.

[1404] 4. The server passes the question and emotion data to the generative model, which then generates an answer such as "adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[1405] 5. If the emotion engine detects that the user is frustrated, the generative model adjusts the tone of the response to be more toned down.

[1406] 6. The server sends the generated answer to the terminal, which displays it to the user.

[1407] 7. The user checks the displayed answers.

[1408] 8. The user's emotion data recognized by the emotion engine is recorded in a database and used to improve the accuracy of subsequent questions.

[1409] Next, the processing flow of the program of the present invention will be explained in natural language.

[1410] 1. Questions

[1411] The user launches a dedicated application on the device and inputs a question, such as "What is SoftBank's latest pricing plan?"

[1412] The device collects the user's emotional data, displays it on a confirmation screen, and the user presses the "send" button.

[1413] 2. Submit a question

[1414] The device sends the question entered by the user and emotional data to the server as an HTTP request.

[1415] 3. Question reception (server side)

[1416] The server receives the HTTP request and analyzes the question content and sentiment data.

[1417] The server passes these to a generative model to generate an appropriate answer.

[1418] 4. Answer generation

[1419] A generative model generates appropriate answers based on the question, and an emotion engine adjusts the tone and content of the answers based on the user's emotional data.

[1420] The server receives and formats the generated response.

[1421] 5. Submit your response

[1422] The server prepares the answer and sends it to the terminal as an HTTP response.

[1423] 6. Answer display

[1424] The terminal analyzes the response received from the server and displays it on the user interface.

[1425] The user checks the answer.

[1426] The user's emotional data is recorded in a database and used to improve subsequent questions.

[1427] This system provides an appropriate response according to the user's emotions, thereby realizing a better user experience, improving the company's image, and increasing user satisfaction.

[1428] The processing flow will be explained below.

[1429] Step 1: Ask a question

[1430] The user launches a dedicated application on the device.

[1431] A user types a smartphone question into an in-app form, for example, "How can I extend my iPhone's battery life?"

[1432] The device obtains the user's input and displays it on a confirmation screen.

[1433] The user checks the information entered on the confirmation screen and presses the "Submit" button.

[1434] Step 2: Obtaining emotion data

[1435] The emotion engine uses the device's built-in camera and microphone to analyze the user's facial expressions and tone of voice.

[1436] The emotion engine collects the user's emotion data and returns the analysis results to the device.

[1437] Step 3: Submit your question

[1438] The device sends the question entered by the user and emotional data to the server as an HTTP request.

[1439] The terminal confirms the success of the transmission and notifies the user of the completion of the transmission.

[1440] Step 4: Question acceptance (server side)

[1441] The server receives the HTTP request and analyzes the question content and sentiment data.

[1442] The server stores the question content and emotion data in a database as a log.

[1443] Step 5: Question Analysis

[1444] The server passes the received question and emotion data to the generative model.

[1445] The generative model analyzes the question and prepares to generate an appropriate answer.

[1446] Step 6: Reflecting emotional data

[1447] The generative model adjusts the tone and content of the response based on the question and sentiment data.

[1448] For example, if the user is annoyed, provide the answer in a calmer tone.

[1449] Step 7: Answer Generation

[1450] A generative model creates an appropriate answer based on the question and sentiment data.

[1451] The server receives and formats the generated response.

[1452] Step 8: Submit your response

[1453] The server prepares the answer and sends it to the terminal as an HTTP response.

[1454] The server acknowledges and logs the successful transmission of the response.

[1455] Step 9: View Answers

[1456] The terminal analyzes the response received from the server.

[1457] The terminal analyzes the answer and displays it on the user interface.

[1458] The user checks the answer displayed on the device screen.

[1459] Step 10: Feedback (Optional)

[1460] The user enters feedback on the displayed answer.

[1461] The terminal obtains the user's feedback and sends it to the server.

[1462] The server receives the feedback and records it in a database.

[1463] Through these specific processing steps, users can get fast and accurate answers to their smartphone-related questions. This system provides appropriate responses based on the user's emotions, improving the company's image and increasing user satisfaction.

[1464] Example 2

[1465] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1466] Conventional question-answering systems provide answers without considering the user's emotions, which can result in a poor user experience. Furthermore, it is difficult to understand the relationship between the content of the question entered by the user and the user's emotions and provide an accurate answer. This leads to the problem of not being able to provide the information the user is looking for quickly and appropriately.

[1467] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1468] In this invention, the server includes means for accepting a question entered by a user, means for collecting emotion data related to the question, means for generating an appropriate answer using a generative model that analyzes the accepted question and the emotion data, means for adjusting the generated answer in accordance with the user's emotion, means for sending and displaying the adjusted answer to the user, and means for recording the emotion data in a database and using it to improve subsequent questions. This allows for the provision of an appropriate response in accordance with the user's emotion, thereby improving the user experience and satisfaction.

[1469] "Question content" refers to the specific questions or requests that the user inputs to the system.

[1470] "Emotion data" refers to data relating to the user's emotional state obtained from facial expressions, tone of voice, and the like.

[1471] A "generative model" refers to an algorithm or machine learning model that generates appropriate answers based on the input question and emotional data.

[1472] The "server" refers to a central processing unit that receives the question content and emotion data, generates an answer using a generative model, and transmits it to the user after adjustment.

[1473] "Terminal" refers to a device through which a user can enter questions and receive and display generated answers.

[1474] An "emotion engine" refers to software or hardware that analyzes a user's emotions from their facial expressions and tone of voice and outputs the results as data.

[1475] "Database" refers to an information management system that stores the generated emotional data and answers and uses them to improve the accuracy of answers to subsequent questions.

[1476] "HTTP request" refers to the communication protocol that allows a device to send question content and emotional data to a server.

[1477] "HTTP response" refers to a communication protocol that allows a server to send a generated response to a terminal.

[1478] "Formatting" refers to the process of adjusting the generated answers into a form that is easy for the user to understand.

[1479] MODE FOR CARRYING OUT THE INVENTION

[1480] This invention relates to a system that allows users to input questions about smartphones and provides accurate answers in real time. Furthermore, this system is equipped with an emotion engine that recognizes the user's emotions and generates optimal answers based on the user's emotions. The system is comprised of a device used by the user, a server that analyzes the question content and generates answers, and a generative model and emotion engine at its core.

[1481] A user uses a device to input a question about their smartphone. For example, they can input a question such as, "How can I extend the battery life of my iPhone?" The device receives the question input by the user and sends it to the server. At the same time, the emotion engine recognizes emotional data such as the user's facial expressions and tone of voice using the device's built-in camera and microphone. The recognized emotional data is also sent to the server.

[1482] The server receives and analyzes the emotional data along with the question content. The question content and emotional data extracted through the analysis are passed to a generative AI model. The generative AI model analyzes the question content using, for example, natural language processing (NLP) technology and generates an appropriate answer based on that analysis. Furthermore, the emotion engine refers to the emotional data analyzed and adjusts the tone and content to match the user's emotions.

[1483] The generated answer is formatted by the server and sent back to the device, where it is displayed to the user. The emotion data recognized by the emotion engine is also recorded in a database and used to improve subsequent questions.

[1484] Specific examples are shown below.

[1485] Example 1: iPhone battery life question

[1486] 1. A user types "How do I extend my iPhone's battery life?" into their device.

[1487] 2. Using the device's built-in camera and microphone, the emotion engine recognizes emotional data such as the user's facial expressions and tone of voice.

[1488] 3. The device sends the question and emotion data to the server.

[1489] 4. The server passes the question and emotion data to the generative model, which then generates an answer such as "adjust the screen brightness appropriately, prevent unnecessary apps from running in the background, and use battery optimization features."

[1490] 5. The server formats the generated response and sends it back to the terminal.

[1491] 6. The terminal displays the received answer to the user.

[1492] 7. The emotional data recognized by the emotion engine is recorded in a database and used to improve subsequent questions.

[1493] The system improves the user experience by recognizing the user's emotions using an emotion engine and providing optimal responses. The collected emotion data is also analyzed and used to improve the quality of future responses.

[1494] For example, examples of prompt sentences to input into a generative AI model include the following:

[1495] "How to extend iPhone battery life?"

[1496] "Please tell me about SoftBank's latest pricing plans."

[1497] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1498] Step 1: Ask a question

[1499] The user launches a dedicated application on the device and inputs a question. For example, they might input, "What is SoftBank's latest pricing plan?" The input question is displayed by the device's UI. The input is the user's question, and the output is the user's question displayed on a confirmation screen.

[1500] Step 2: Collecting Emotional Data

[1501] The device uses its built-in camera and microphone to detect the user's facial expressions and tone of voice. The emotion engine analyzes this data and recognizes the user's emotional state. Specifically, it uses facial expression images captured by the camera and voice recorded by the microphone as input and outputs emotional data.

[1502] Step 3: Submit your question

[1503] The device sends the question and emotion data entered by the user to the server as an HTTP request. The input is the question and emotion data, and the output is an HTTP request that includes them.

[1504] Step 4: Parse the questions and sentiment data

[1505] The server analyzes the received HTTP request and extracts the question content and emotional data. The server then passes this data to the generative AI model. Specifically, it extracts the question content and emotional data from the request and provides them to the generative AI model. The input is the HTTP request, and the output is the analysis results of the question content and emotional data.

[1506] Step 5: Answer Generation

[1507] The generative AI model generates an appropriate answer based on the question. At this time, it also takes emotional data into consideration to adjust the tone and content of the answer. For example, it generates an answer such as, "SoftBank's latest plan costs XX yen and includes XX GB of data." The input is the question and emotional data, and the output is an appropriately adjusted answer.

[1508] Step 6: Formatting your answers

[1509] The server receives the generated answer and formats it in a way that is easy for the user to understand. The tone is adjusted to a calm tone based on data from the emotion engine. The input is the answer from the generative AI model, and the output is the formatted answer.

[1510] Step 7: Submit your response

[1511] The server formats the answer and sends it to the terminal as an HTTP response, where the input is the formatted answer and the output is the generated HTTP response.

[1512] Step 8: View Answers

[1513] The terminal analyzes the response received from the server and displays it on the user interface. The user confirms the presented answer. The input is the HTTP response, and the output is the answer displayed on the user interface.

[1514] Step 9: Record and use emotional data

[1515] The emotion engine recognizes the user's emotion data and stores it in a database for future question answering. Specifically, the emotion data is recorded in the database and used to analyze and generate subsequent questions. The input is emotion data, and the output is a saved database entry.

[1516] (Application example 2)

[1517] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1518] In today's security services, there is a need to provide fast, accurate information in real time. However, there is a lack of means to quickly resolve the uncertainties and anxieties that security guards face while on patrol. Furthermore, systems that do not properly recognize and respond to user emotions increase the risk of misjudging the situation, resulting in increased security risks. To solve these issues, a system that takes user emotions into account and provides appropriate response instructions in real time is needed.

[1519] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting a question entered by a user, means for generating an appropriate answer using a generative model that analyzes the accepted question, means for sending and displaying the generated answer to the user, and means having an emotion engine that recognizes the user's emotion and adjusts the tone and content of the answer based on the emotion data. This makes it possible for security guards to receive appropriate advice in real time according to their emotions, even if they have questions or feel anxious while patrolling.

[1520] The "means for accepting the question content input by the user" is an interface for acquiring the question content input by the user through the terminal and transmitting it for subsequent processing.

[1521] A "generative model that analyzes received questions" is a machine learning model that analyzes received questions and generates appropriate answers to the questions.

[1522] The "means for transmitting and displaying the generated answer to the user" is an interface for transmitting the answer generated by the generative model to the user's terminal and displaying it.

[1523] "Means with an emotion engine that recognizes a user's emotions and adjusts the tone and content of responses based on the emotion data" refers to algorithms and functions that recognize a user's facial expressions, tone of voice, and other emotional indicators and adjust the tone and content of the generated responses based on them.

[1524] The "server that receives the question content and then transmits the question content and emotion data to the generative model" is a computer system that transmits the question content and emotion data received from the user to the generative model for analysis and answer generation.

[1525] The "terminal that displays the answer received from the server to the user" is a device that receives the answer generated by the server and displays it so that the user can confirm it visually or audibly.

[1526] "Means for recording the generated answers in a database and using them to improve answers to subsequent questions" refers to a system that stores answers generated by a generative model in a database and uses them to improve and optimize the accuracy of answers to future questions.

[1527] To implement this invention, it is necessary to build a system that accepts questions entered by users, generates appropriate answers, and transmits and displays the answers to the users. This system consists of a terminal used by the user, a server that analyzes the questions and emotion data, a generative model, and an emotion engine.

[1528] First, a user inputs a question using a device such as smart glasses. The device's camera captures the user's face, and the emotion engine recognizes the user's emotion. This emotion data is then sent to the server along with the question.

[1529] The server then passes the received question and emotion data to a generative model, which then generates an appropriate answer. The generative model uses machine learning to analyze the question and generates an optimal answer. Furthermore, the tone and content of the answer are adjusted based on the user's emotion as recognized by the emotion engine.

[1530] The generated answer is formatted by the server and sent back to the user's device. The device displays the received answer to the user for confirmation. The emotion data is also recorded in a database and used to improve the accuracy of answers for subsequent questions.

[1531] As a concrete example, consider the case where a security guard using smart glasses while patrolling inputs a question such as, "If there is suspicious activity in this area, how should I respond?" The camera in the smart glasses captures the user's facial expression, and the emotion engine detects "anxiety." This question and emotion data are sent to the server, and the generative model generates the answer, "First, remain calm, immediately avoid contact with suspicious individuals, and contact backup." The emotion engine adjusts the tone of the answer, providing the user with a calm tone.

[1532] An example prompt for a generative AI model might take the form:

[1533] Question: "If there is suspicious activity in this area, how should I respond?"

[1534] Emotion data: "Impatience"

[1535] Tone of generated answer: "Calm"

[1536] In this way, the present invention realizes a system in the field of security services that provides appropriate responses in real time according to the user's emotions and supports the work of security guards.

[1537] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1538] Step 1:

[1539] The system accepts questions entered by the user. The user enters the question using the voice input function of the smart glasses. The inputs are the question text and an image of the user's facial expression.

[1540] Step 2:

[1541] The device captures the user's face and recognizes the user's emotions using an emotion engine. The input is the captured facial image, and the output is emotion data such as "impatience" or "anger." Emotion data is extracted based on an analysis of the user's facial expressions.

[1542] Step 3:

[1543] The device sends the question and emotion data to the server. The input is the question text and emotion data, which are sent to the server as an HTTP request.

[1544] Step 4:

[1545] The server receives the question content and emotion data. The input is an HTTP request sent from the device. The server analyzes this data and converts it into an input format for the generative model.

[1546] Step 5:

[1547] The server passes the received data to a generative model to generate an answer. The input is the question text and sentiment data, which the generative AI model analyzes to generate an appropriate answer. The output is the generated answer.

[1548] Step 6:

[1549] The server passes the generated answer to the emotion engine, which adjusts the tone and content of the answer based on the emotion data. The input is the generated answer and emotion data, and the output is the adjusted answer. The tone is adjusted according to the emotion.

[1550] Step 7:

[1551] The server formats the adjusted answer and sends it to the device. The input is the adjusted answer and the output is sent to the device as an HTTP response.

[1552] Step 8:

[1553] The terminal displays the answer received from the server. The input is the answer text sent from the server, and the output is displayed in a format that the user can confirm visually or audibly. The user confirms the displayed answer.

[1554] Step 9:

[1555] The emotion data collected by the emotion engine is recorded in a database. The input is the emotion data recognized by the emotion engine, and the output is the emotion data stored in the database. This is used to improve the accuracy of answers to subsequent questions.

[1556] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1557] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1558] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1559] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1560] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1561] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1562] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1563] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1564] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1565] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1566] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1567] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1568] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1569] 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.

[1570] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1571] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1572] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1573] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1574] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1575] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1576] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1577] The following is further disclosed regarding the above embodiment.

[1578] (Claim 1)

[1579] A means for accepting a question input by a user;

[1580] A means for generating an appropriate answer using a generative model that analyzes the content of the received question;

[1581] means for transmitting and displaying the generated answers to the user;

[1582] A system including:

[1583] (Claim 2)

[1584] a server that receives a question and then transmits the question to a generative model;

[1585] Contains a terminal that displays the answer received from the server to the user

[1586] 10. The system of claim 1.

[1587] (Claim 3)

[1588] Includes a means to record generated answers in a database and use them to improve subsequent questions.

[1589] 10. The system of claim 1.

[1590] "Example 1"

[1591] (Claim 1)

[1592] A means for accepting a question input by a user;

[1593] A means of analyzing the content of received questions and creating appropriate answers using generative AI models;

[1594] means for formatting the generated answer and transmitting it to the user for display;

[1595] A system including:

[1596] (Claim 2)

[1597] A server that receives the question and then sends the question to the generative AI model;

[1598] Contains a terminal that displays the answer received from the server to the user

[1599] 10. The system of claim 1.

[1600] (Claim 3)

[1601] Includes a means to record generated answers in a database and use them to improve future questions.

[1602] 10. The system of claim 1.

[1603] "Application Example 1"

[1604] (Claim 1)

[1605] A means for accepting a question input by a user;

[1606] A means for generating an appropriate answer using a generative model that analyzes the content of the received question;

[1607] means for transmitting and displaying the generated answers to the user;

[1608] A means of processing inquiries about food delivery services and providing answers in real time;

[1609] A system including:

[1610] (Claim 2)

[1611] a server that receives a question and then transmits the question to a generative model;

[1612] Contains a terminal that displays the answer received from the server to the user

[1613] 10. The system of claim 1.

[1614] (Claim 3)

[1615] Includes a means to record generated answers in a database and use them to improve subsequent questions.

[1616] 10. The system of claim 1.

[1617] "Example 2: Combining Emotion Engines"

[1618] (Claim 1)

[1619] A means for accepting a question input by a user;

[1620] a means for collecting emotional data related to the question;

[1621] A means for generating an appropriate answer using a generative model that analyzes the received question content and sentiment data;

[1622] means for adjusting the generated answers according to the user's emotions;

[1623] means for transmitting and displaying the adjusted answers to the user;

[1624] a means for recording the emotion data in a database and using it to improve subsequent questions;

[1625] A system including:

[1626] (Claim 2)

[1627] a server that receives a question and then transmits the question to a generative model;

[1628] Contains a terminal that displays the answer received from the server to the user

[1629] 10. The system of claim 1.

[1630] (Claim 3)

[1631] Includes a means to record generated answers in a database and use them to improve subsequent questions.

[1632] 10. The system of claim 1.

[1633] "Application example 2 when combining emotion engines"

[1634] (Claim 1)

[1635] A means for accepting a question input by a user;

[1636] A means for generating an appropriate answer using a generative model that analyzes the content of the received question;

[1637] means for transmitting and displaying the generated answers to the user;

[1638] means for recognizing a user's emotions and adjusting the tone and content of responses based on the emotion data;

[1639] A system including:

[1640] (Claim 2)

[1641] a server that receives the question and then transmits the question and emotion data to the generative model;

[1642] Contains a terminal that displays the answer received from the server to the user

[1643] 10. The system of claim 1.

[1644] (Claim 3)

[1645] Includes a means to record generated answers in a database and use them to improve subsequent questions.

[1646] 10. The system of claim 1. [Explanation of symbols]

[1647] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for accepting a question input by a user; A means for generating an appropriate answer using a generative model that analyzes the content of the received question; means for transmitting and displaying the generated answers to the user; A system including:

2. a server that receives a question and then transmits the question to a generative model; Contains a terminal that displays the answer received from the server to the user The system of claim 1 .

3. Includes a means to record generated answers in a database and use them to improve subsequent questions. The system of claim 1 .

Images