System

Abstract

A system is provided.SOLUTION: A system comprising: a server means for communicating with a terminal for a user to practice a conversation; a database means for storing user's profile data and past conversation practice data; a generation means for generating a conversation scenario based on generative artificial intelligence; and a communication means for transmitting the generated conversation scenario and a feedback on the conversation to the user's terminal.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] Today, there is a lack of effective practice environments for aspiring floor ladies to improve their conversation skills. It is particularly difficult to hone conversation skills through simulations that closely resemble actual workplace environments. Another issue is that floor ladies often struggle to find the content of their conversations with customers, making it difficult to maintain natural conversations and build relationships. The present invention provides a system that solves these problems. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means. We propose a system including a server means for communicating with a terminal on which a user practices conversation, a database means for storing the user's profile data and past conversation practice data, a generation means for generating a conversation scenario based on a generation artificial intelligence, and a communication means for transmitting feedback on the generated conversation scenario and the conversation to the user's terminal. Furthermore, by further including a generation artificial intelligence means for analyzing conversation data input by the user and generating appropriate responses, and a feedback generation means for generating conversation feedback, the system effectively supports the improvement of the user's conversation skills. Furthermore, by including a personalization means for generating different scenarios based on the user's ID information and a scenario adjustment means for dynamically adjusting the conversation scenario based on past feedback, it is possible to provide training optimized for each individual user.

[0006] "User" refers to an individual person who uses the system to practice speaking.

[0007] "Terminal" refers to a device such as a computer, smartphone, or tablet that a user uses to access the system.

[0008] "Server" refers to a central system that communicates with user terminals, generates conversation scenarios, and manages user data.

[0009] "Database" refers to the storage system for storing and managing user profile data and past practice data.

[0010] "Generative AI" refers to algorithms and related technologies that analyze user input data and generate appropriate conversational content and feedback.

[0011] A "conversation scenario" refers to the flow and specific content of a conversation that is generated for practice.

[0012] "Communication means" refers to the technology and protocols for transmitting and receiving data between the server and the terminal.

[0013] "Feedback generation means" refers to a means for providing an evaluation of a conversation conducted by a user and suggestions for improvement.

[0014] "Personalization means" refers to technology that creates individual conversation scenarios based on the user's characteristics and past practice history.

[0015] "Scenario adjustment means" refers to a function that dynamically adjusts the optimal conversation scenario for the user based on past feedback. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention is a system that allows users to efficiently learn and improve the conversation skills required for floor ladies. This system consists of multiple components, such as a server, terminals, a database, and generative artificial intelligence (AI).

[0038] Overall system flow

[0039] 1. User Registration and Login

[0040] First, a user accesses the system using their own terminal and registers or logs in. The server stores the user's registration data in a database and authenticates the login information.

[0041] 2. Conversation scenario selection and generation

[0042] After logging in, the user selects a conversation practice via the terminal. The server retrieves the user's profile data and past practice data from the database and generates an appropriate conversation scenario based on the generative artificial intelligence. The scenario is sent to the terminal and displayed to the user.

[0043] 3. Conversation progression and feedback

[0044] When a user practices conversation, they interact with the generation AI via their device. The generation AI analyzes the user's input data and provides appropriate responses and methods for progressing the conversation. After the conversation is over, the server sends the conversation data to the generation AI, which generates detailed feedback. This allows the user to receive specific advice on how to improve their conversation skills.

[0045] Specific examples

[0046] User Registration and Login

[0047] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[0048] 2. The server sends a user registration form to the terminal, and the user enters the required information (name, email address, password).

[0049] 3. When the user clicks the "Submit" button, the terminal sends the data to the server. The server validates the data and stores it in the database. In addition, a registration completion message is displayed on the terminal.

[0050] 4. Next, when the user clicks the "Login" button, the server sends a login form to the terminal, where the user enters their email address and password and clicks "Submit."

[0051] 5. The server authenticates the data and initiates the user session.

[0052] Conversation scenario selection and generation

[0053] 1. The user selects the "Conversation Practice" menu on the device.

[0054] 2. The server retrieves the user's profile data and past practice data from the database.

[0055] 3. The generation AI generates an appropriate conversation scenario and sends it to the terminal via the server.

[0056] 4. The device displays the generated scenario and allows the user to start a conversation.

[0057] Conversation management and feedback

[0058] 1. The user types "Hello, how is your day going?" into the terminal.

[0059] 2. The device sends the input data to the server and requests the AI ​​to analyze it. The AI ​​then generates a response such as, "I'm having a great day. How about you?"

[0060] 3. The server receives the response from the AI ​​and sends it to the device, which displays the response to the user.

[0061] 4. After the conversation practice is completed, the server sends all the conversation data to the generation AI, which generates detailed feedback.

[0062] 5. The server sends the feedback data to the terminal so that the user can check it.

[0063] This allows users to effectively acquire and improve the conversation skills necessary for floor ladies. Furthermore, the system provides scenarios optimized for each user, enabling training tailored to individual needs.

[0064] The processing flow will be explained below.

[0065] User registration and login process steps

[0066] User Registration

[0067] Step 1:

[0068] The user clicks the "New Registration" button on the device.

[0069] The terminal displays a user registration form.

[0070] Step 2:

[0071] The user enters their name, email address, and password into the form and clicks the "Submit" button.

[0072] The terminal sends the input data to the server.

[0073] Step 3:

[0074] The server receives the input data and performs validation (e.g., checking for duplicate email addresses, matching passwords).

[0075] If the verification is successful, the server stores the user information in a database.

[0076] Step 4:

[0077] The server sends a registration completion message to the terminal.

[0078] The device will display a registration complete message.

[0079] Log in

[0080] Step 5:

[0081] The user clicks the "Login" button on the device.

[0082] The terminal displays a login form.

[0083] Step 6:

[0084] The user enters their email address and password and clicks the "Submit" button.

[0085] The terminal sends the input data to the server.

[0086] Step 7:

[0087] The server receives the input data and checks it against information in a database.

[0088] If the match is successful, the server starts the user session.

[0089] Processing steps for selecting and generating conversation scenarios

[0090] Step 8:

[0091] The user selects the "conversation practice" menu on the terminal.

[0092] The terminal transmits the selection data to the server.

[0093] Step 9:

[0094] The server retrieves the user's profile data and past practice data from the database.

[0095] The server sends this data to the generation AI and requests it to generate a conversation scenario.

[0096] Step 10:

[0097] Generative AI analyzes user data and generates appropriate conversation scenarios.

[0098] The generated scenario is sent back to the server.

[0099] Step 11:

[0100] The server sends the generated scenario to the terminal.

[0101] The terminal displays the scenario and prompts the user to start a conversation.

[0102] Steps for navigating the conversation and handling feedback

[0103] Step 12:

[0104] A user types into a terminal, "Hello, how is your day going?"

[0105] The terminal sends the input data to the server.

[0106] Step 13:

[0107] The server sends the input data to the generation AI.

[0108] Generative AI analyzes the data and generates appropriate responses.

[0109] Step 14:

[0110] The server sends the response data received from the generation AI to the terminal.

[0111] The terminal displays the reply message to the user.

[0112] Step 15:

[0113] The user makes a new input and the terminal again sends the data to the server.

[0114] The server sends data to the generating AI, which generates a response, and this process is repeated until the end of the conversation.

[0115] Step 16:

[0116] The user ends the conversation practice (e.g., clicks the "End" button).

[0117] The terminal sends a termination signal to the server.

[0118] Step 17:

[0119] The server sends all conversation data to the generation AI and asks it to generate an evaluation and feedback.

[0120] Generative AI analyzes the data and generates detailed feedback.

[0121] Step 18:

[0122] The server receives feedback data from the generated AI and sends it to the device.

[0123] The terminal displays a feedback message to the user.

[0124] Continual Skill Development Process Steps

[0125] Step 19:

[0126] The user selects the "Conversation Practice" menu again.

[0127] The terminal transmits the selection data to the server.

[0128] Step 20:

[0129] The server asks the generative AI to generate new conversation scenarios based on past feedback and learning history.

[0130] The generation AI generates an appropriate scenario and sends it back to the server.

[0131] Step 21:

[0132] The server sends the new scenario to the device.

[0133] The terminal displays the new scenario and prompts the user to start a conversation.

[0134] Through these processing steps, users can continually improve their speaking skills.

[0135] Example 1

[0136] 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."

[0137] Conventional conversation practice systems have struggled to generate optimal conversation scenarios for each user and provide immediate and appropriate feedback. This has prevented them from efficiently improving users' conversation skills. It has also been difficult to effectively utilize users' profile information and past practice data to generate personalized conversation scenarios.

[0138] 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.

[0139] In this invention, the server includes means for communicating with a terminal used by a user for conversation practice, means for storing the user's profile data and past conversation practice data, means for generating a conversation scenario based on a generative artificial intelligence model, and means for transmitting feedback on the generated conversation scenario and conversation to the user's terminal. This makes it possible to provide a conversation scenario optimized for each user and receive immediate and appropriate feedback. Furthermore, personalized scenarios can be generated based on the user's profile and past practice data, allowing users to effectively improve their skills through conversation practice based on the scenarios.

[0140] 1. "Server" means a central device that communicates with the terminals on which users practice conversation and processes data.

[0141] 2. "Terminal" means a computing device used by a user to practice speaking.

[0142] 3. "Profile Data" means basic information about a User, such as name, email address, and past practice history.

[0143] 4. "Past conversation practice data" refers to data that records the content and results of conversation practice sessions that the user has conducted in the past.

[0144] 5. "Database" refers to a system for storing and managing user profile data and past conversation practice data.

[0145] 6. "Generative AI model" refers to an AI technology that generates and analyzes conversation scenarios based on user data.

[0146] 7. "Generation means" means a process and system for generating conversation scenarios using a generative artificial intelligence model.

[0147] 8. "Personalization methods" are functions and technologies for generating different scenarios based on the user's ID.

[0148] 9. "Scenario adjustment means" refers to the functions and technologies for dynamically adjusting conversation scenarios based on past feedback.

[0149] 10. "Communication means" refers to the functions and technologies for transmitting the generated conversation scenario and feedback on the conversation to the user's device.

[0150] 11. "Feedback generation means" refers to the functions and technologies for generating detailed feedback based on user conversation data.

[0151] The present invention is a system for enabling users to efficiently learn and improve their conversation skills. This system is composed of multiple components, including a server, a terminal, a database, and a generative artificial intelligence model. The following describes how this system is specifically implemented.

[0152] First, a user accesses the system's webpage using their own device and registers or logs in. At this time, the server stores the user's input information, such as name, email address, and password, in a database and authenticates the login information. For example, the following specific operations are performed:

[0153] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[0154] 2. The server sends a user registration form to the terminal, and the user enters the required information (name, email address, password).

[0155] 3. When the user clicks the "Submit" button, the terminal sends the data to the server. The server validates the data and stores it in the database. In addition, a registration completion message is displayed on the terminal.

[0156] Next, after the user logs in, they select conversation practice. The server retrieves the user's profile data and past practice data from the database, and generates an appropriate conversation scenario based on a generative artificial intelligence model (e.g., GPT-3). The scenario is sent to the terminal and displayed to the user. The following specific operations are performed in this step:

[0157] 1. The user selects the "Conversation Practice" menu on the device.

[0158] 2. The server retrieves the user's profile data and past practice data from the database.

[0159] 3. The generative artificial intelligence model generates a conversation scenario based on the acquired data and sends it to the terminal via the server.

[0160] 4. The device displays the generated scenario and allows the user to start a conversation.

[0161] When a user practices a conversation, they interact with the Generative AI via their device. The Generative AI analyzes the user's input data and provides appropriate responses and methods for progressing the conversation. For example, if the user types, "Hello, how are you today?", the Generative AI will generate a response such as, "I'm having a great day. How about you?" The process proceeds as follows:

[0162] 1. The user types "Hello, how is your day going?" into the terminal.

[0163] 2. The terminal sends the input data to the server and requests the generative artificial intelligence model to analyze it.

[0164] 3. The generative artificial intelligence model generates a response and sends it to the terminal via the server.

[0165] 4. The terminal displays the response to the user.

[0166] After the conversation practice is completed, the server sends the conversation data to the generative AI model, which generates detailed feedback, including specific advice such as "It would be good to speed up the conversation." This feedback is then sent from the server to the device for the user to review.

[0167] This allows users to receive specific advice on how to improve their conversation skills. The system provides scenarios and feedback optimized for each user, enabling training tailored to individual needs.

[0168] For example, you might input the following prompt into a generator AI:

[0169] "What's your name?" "What are your hobbies?" "Hello, how are you today?"

[0170] Such a system allows users to efficiently acquire conversation skills and improve the techniques required for a floor lady.

[0171] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0172] Step 1:

[0173] User Registration and Login

[0174] input:

[0175] User registration request, name, email address, password

[0176] Login request, email address, password

[0177] Specific actions and data processing:

[0178] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[0179] 2. The server sends a user registration form to the device, which includes fields for entering name, email address, and password.

[0180] 3. The user enters the necessary information and presses the "Send" button. The terminal sends the input data to the server.

[0181] 4. The server verifies the data sent and stores it in the database if it is correct. If the information is invalid, it returns an error message to the terminal.

[0182] 5. When the user clicks the "Login" button, the server sends the login form to the terminal.

[0183] 6. The user enters their email address and password and clicks the "Submit" button. The device sends this information to the server.

[0184] 7. The server retrieves the email address from the database and verifies the password.

[0185] 8. If authentication is successful, the server starts the user session and redirects to the main menu, otherwise it displays an error message on the terminal.

[0186] output:

[0187] Registration completion message

[0188] Login success or failure message

[0189] Step 2:

[0190] Conversation scenario selection and generation

[0191] input:

[0192] User conversation practice menu selection

[0193] Profile Data

[0194] Past practice data

[0195] Specific actions and data processing:

[0196] 1. The user selects the "Conversation Practice" menu on the device.

[0197] 2. The server retrieves the user's profile data and past practice data from the database.

[0198] 3. The server passes this data to a generative artificial intelligence model (e.g., GPT-3) and requests it to generate a conversation scenario.

[0199] 4. The generative AI model generates a conversation scenario based on the data, and the scenario is created as a prompt sentence.

[0200] 5. The server sends the generated scenario to the terminal, which displays it to the user.

[0201] output:

[0202] Conversation scenario

[0203] Step 3:

[0204] Conversation management and feedback

[0205] input:

[0206] User conversation input data

[0207] System-generated conversation scenario

[0208] Dynamic feedback requests during conversations

[0209] Specific actions and data processing:

[0210] 1. The user enters the conversation content (e.g., "Hello, how are you doing today?") into the text box on the device and clicks the "Send" button.

[0211] 2. The device sends the input data to the server and requests the generative AI model to analyze it.

[0212] 3. The generative AI model generates a response based on the user's input and returns it to the server.

[0213] 4. The server sends the response to the terminal, which displays the response to the user.

[0214] 5. Once the conversation practice is completed, the server sends all the conversation data to the generative AI model and asks it to generate detailed feedback.

[0215] 6. The generative AI model analyzes the content of the conversation and the user's reactions, and generates feedback including specific advice and areas for improvement (e.g., "It would be better to speed up the conversation").

[0216] 7. The server sends the generated feedback to the device so that the user can view it.

[0217] output:

[0218] Responses generated by generative AI models

[0219] Detailed feedback after the conversation

[0220] (Application example 1)

[0221] 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."

[0222] In modern brick-and-mortar stores, improving the quality of customer service requires continuous improvement of the customer service skills of store clerks. However, conventional training methods make it difficult to acquire efficient conversational skills that meet individual needs, and it is also difficult to receive feedback in real time. The present invention aims to solve these problems and provide a system that allows store clerks to efficiently and effectively improve their customer service skills.

[0223] 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.

[0224] In this invention, the server includes server means for communicating with a device for user conversation practice, storage means for storing user attribute data and past conversation practice data, generation means for generating conversation scenarios based on a generative AI model, communication means for transmitting feedback on the generated conversation scenarios and conversations to the user's device, and a system used by users to improve their customer service skills. This allows store clerks to practice conversations optimally according to their individual needs and receive feedback in real time, thereby effectively improving their skills.

[0225] "User" refers to a person who uses the system to practice conversation, and in particular refers to a store clerk who aims to improve their customer service skills in a brick-and-mortar store.

[0226] "Device" refers to the hardware used to communicate with the server and practice conversation, and is primarily a portable computer such as a smartphone or tablet.

[0227] The "server means" is a device that executes processes for conversation practice and communicates with the user's terminal.

[0228] The "storage means" is a component that includes a database that stores user attribute data and past conversation practice data.

[0229] A "generative AI model" refers to an artificial intelligence program that generates a scenario for a user's conversation practice, analyzes conversation data, and generates appropriate responses.

[0230] A "generation means" is a component that has the function of automatically creating a conversation scenario using a generative AI model.

[0231] A "communication means" is a component that has the function of transmitting the generated conversation scenario and feedback to the user's device.

[0232] The "feedback generation means" is a component that has the function of creating detailed feedback based on the user's conversation data.

[0233] The "personalization means" is a component that has the function of generating different scenarios suited to individual users based on the user's identification information.

[0234] The "scenario adjustment means" is a component that has the function of dynamically changing the conversation scenario according to the user's past feedback.

[0235] A "prompt generation means" is a component that has the function of creating a prompt sentence to be input into a generative AI model.

[0236] This invention is a conversation practice system for enabling store clerks to efficiently improve their customer service skills, and is implemented using the following hardware and software.

[0237] Hardware

[0238] Server: Generates conversation scenarios, analyzes conversation data, and generates feedback.

[0239] Device: A device (smartphone, tablet, etc.) on which a user practices conversation.

[0240] software

[0241] Generative AI model: Generates conversation scenarios and analyzes user input data.

[0242] Storage means: A database that stores user attribute data and past conversation practice data.

[0243] Communication means: The server transmits conversation scenarios and feedback to the terminal.

[0244] The server communicates with a device on which the user practices conversation, and stores the user's attribute data and past conversation practice data in a storage means. It then generates a conversation scenario based on the generative AI model and transmits the scenario to the user's device via a communication means. The user practices conversation based on the generated scenario, and the conversation data is transmitted to the server. The server analyzes the received conversation data using the generative AI model, generates appropriate feedback, and provides it to the user.

[0245] This allows users to practice conversations optimally according to their individual needs and receive real-time feedback, effectively improving their skills. Furthermore, scenario generation and feedback take into account the user's identification information and past feedback, and the scenario is dynamically adjusted.

[0246] Specific operation example

[0247] 1. User Registration and Login

[0248] When a user uses the system for the first time, they enter their information to complete registration and then log in.

[0249] 2. Conversation scenario selection and generation

[0250] When the user selects the "conversation practice" menu, the server retrieves the user's attribute data and past practice data from an existing database.

[0251] A generative AI model generates appropriate conversation scenarios based on this data.

[0252] 3. Conversation practice and feedback

[0253] The user follows a scenario and practices conversation in an interactive format.

[0254] The server analyzes the user's input in real time and provides an appropriate response.

[0255] After completing the exercise, the server generates detailed feedback and sends it to the user.

[0256] Prompt Sentence Examples

[0257] The following prompt sentence is fed into the generative AI model:

[0258] "How can we keep you informed about promotions that might be of interest to you?"

[0259] "What are some examples of questions you can ask to accurately understand a customer's needs while serving them?"

[0260] The system of the present invention allows store staff in brick-and-mortar stores to continuously and effectively improve their customer service skills.

[0261] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0262] Step 1:

[0263] (User registration and login)

[0264] Input: The user enters their name, email address, and password.

[0265] Processing: The terminal sends the user input to the server, and the server stores the input data in a storage means and sends a registration completion message to the terminal.

[0266] Output: The user account is created and the user can log in to the system.

[0267] Specific operation: The user clicks the "New Registration" button, enters the required information in the registration form, and clicks the "Submit" button. The server verifies the validity of the data and saves it to the database.

[0268] Step 2:

[0269] (Selection and generation of conversation scenarios)

[0270] Input: The user selects the "Conversation Practice" menu.

[0271] Processing: The server retrieves the user's attribute data and past conversation practice data from the storage means, and generates an appropriate conversation scenario based on the generative AI model.

[0272] Output: The generated conversation scenario is sent to the terminal and displayed to the user.

[0273] Specific operation: When a user selects the "Conversation Practice" menu, the server retrieves the user's information from the database, and the generative AI model generates a scenario. The scenario is sent to the device and displayed on the user's screen.

[0274] Step 3:

[0275] (Conversation practice and feedback)

[0276] Input: The user inputs a conversation based on the scenario.

[0277] Processing: The device sends the user's input data to the server, the generative AI model generates an appropriate response, and the server sends the response to the device.

[0278] Output: A conversational exchange continues and feedback is generated after the practice session.

[0279] Specific operation: When the user enters text corresponding to the scenario displayed on the screen and clicks the send button, the data is sent to the server. The generative AI model analyzes the data, generates an appropriate response, and sends it back to the device. Once the conversation is over, the server analyzes the entire conversation data, generates feedback, and sends it to the device.

[0280] Step 4:

[0281] (Check feedback)

[0282] Input: User makes a request for feedback confirmation.

[0283] Processing: The server retrieves the generated feedback data from the storage means and transmits it to the terminal.

[0284] Output: Feedback is displayed on the user's device.

[0285] Specific operation: When a user selects a feedback menu and sends a request, the server retrieves the corresponding feedback data from the database, sends it to the terminal, and displays it to the user.

[0286] Step 5:

[0287] (Generate prompt sentence)

[0288] Input: User identity and past feedback data.

[0289] Processing: The server analyzes past feedback data and generates and sends prompt sentences to the generative AI model.

[0290] Output: The prompt sentence is sent to the generative AI model and used to generate new conversation scenarios.

[0291] Specific operation: The server analyzes past feedback data based on the user's identification information and generates a prompt such as, "Please tell us how we can provide you with campaign information that might interest you." The prompt is then sent to the generative AI model and used to generate new scenarios.

[0292] 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.

[0293] The present invention provides a system for enabling users to efficiently learn and improve the conversation skills required for floor ladies. The system includes a server, a terminal, a database, a generative artificial intelligence (AI), and an emotion engine.

[0294] Overall system flow

[0295] 1. User Registration and Login

[0296] First, a user accesses the system using their own terminal and registers or logs in. The server stores the user's registration data in a database and authenticates the login information.

[0297] 2. Conversation scenario selection and generation

[0298] After logging in, the user selects a conversation practice via the terminal. The server retrieves the user's profile data and past practice data from the database, and generates an appropriate conversation scenario based on the generative artificial intelligence and emotion engine. The scenario is sent to the terminal and displayed to the user.

[0299] 3. Conversation progression, emotion recognition, and feedback

[0300] When a user practices conversation, they interact with the generation AI via their device. The generation AI analyzes the user's input data, and its emotion engine recognizes their emotions. Based on this, it provides appropriate responses and methods for progressing the conversation. After the conversation ends, the server sends the conversation data and emotion data to the generation AI, which generates detailed feedback. This allows the user to receive specific advice on how to improve their conversation skills.

[0301] Specific examples

[0302] User Registration and Login

[0303] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[0304] 2. The server sends a user registration form to the terminal, and the user enters the required information (name, email address, password).

[0305] 3. When the user clicks the "Submit" button, the terminal sends the data to the server. The server validates the data and stores it in the database. In addition, a message indicating completion of registration is displayed on the terminal.

[0306] 4. Next, when the user clicks the "Login" button, the server sends a login form to the terminal, where the user enters their email address and password and clicks "Submit."

[0307] 5. The server authenticates the data and initiates the user session.

[0308] Conversation scenario selection and generation

[0309] 1. The user selects the "Conversation Practice" menu on the device.

[0310] 2. The server retrieves the user's profile data and past practice data from the database.

[0311] 3. Generative AI and emotion engine analyze user data and generate appropriate conversation scenarios.

[0312] 4. The generated scenario is sent to the terminal via the server and displayed to the user.

[0313] Conversation progression, emotion recognition, and feedback

[0314] 1. The user types "Hello, how is your day going?" into the terminal.

[0315] 2. The terminal sends the input data to the server.

[0316] 3. The server sends the input data to the generation AI, which analyzes the data.

[0317] 4. The emotion engine recognizes the user's emotions, and the generative AI generates an appropriate response based on that (e.g., "You look like you're having fun. Did something special happen today?").

[0318] 5. The server sends the response data received from the generation AI and emotion engine to the device, and the device displays the response message to the user.

[0319] 6. After the conversation practice is completed, the server sends all conversation data and emotion data to the generation AI and asks it to generate an evaluation and feedback.

[0320] 7. Generative AI analyzes the data and generates detailed feedback.

[0321] 8. The server sends feedback data to the device so that the user can review it (e.g., "I liked how natural the conversation was. Next time, try asking more open-ended questions. Also, you seemed a little nervous, so try practicing ways to relax.").

[0322] Continuous skill development

[0323] 1. The user selects the "Conversation Practice" menu again.

[0324] 2. The server asks the generative AI and emotion engine to generate new conversation scenarios based on past feedback and learning history.

[0325] 3. The generative AI and emotion engine generate an appropriate scenario and send it back to the server.

[0326] 4. The server sends the new scenario to the terminal, which displays the new scenario and prompts the user to start a conversation.

[0327] Through these processes, users can continuously improve their conversation skills and emotion recognition abilities. The system provides scenarios and feedback optimized for each user, allowing for personalized training.

[0328] The processing flow will be explained below.

[0329] User registration and login process steps

[0330] User Registration

[0331] Step 1:

[0332] The user clicks the "New Registration" button on the device.

[0333] The terminal displays a user registration form.

[0334] Step 2:

[0335] The user enters their name, email address, and password into the form and clicks the "Submit" button.

[0336] The terminal sends the input data to the server.

[0337] Step 3:

[0338] The server receives the input data and performs validation (e.g., checking for duplicate email addresses, matching passwords).

[0339] If the verification is successful, the server stores the user information in a database.

[0340] Step 4:

[0341] The server sends a registration completion message to the terminal.

[0342] The device will display a registration complete message.

[0343] Log in

[0344] Step 5:

[0345] The user clicks the "Login" button on the device.

[0346] The terminal displays a login form.

[0347] Step 6:

[0348] The user enters their email address and password and clicks the "Submit" button.

[0349] The terminal sends the input data to the server.

[0350] Step 7:

[0351] The server receives the input data and checks it against information in a database.

[0352] If the match is successful, the server starts the user session.

[0353] Processing steps for selecting and generating conversation scenarios

[0354] Step 8:

[0355] The user selects the "conversation practice" menu on the terminal.

[0356] The terminal transmits the selection data to the server.

[0357] Step 9:

[0358] The server retrieves the user's profile data and past practice data from the database.

[0359] The server sends this data to the generation AI and emotion engine, requesting them to generate a conversation scenario.

[0360] Step 10:

[0361] Generative AI and emotion engines analyze user data and generate appropriate conversation scenarios.

[0362] The generated scenario is sent back to the server.

[0363] Step 11:

[0364] The server sends the generated scenario to the terminal.

[0365] The terminal displays the scenario and prompts the user to start a conversation.

[0366] Conversation progression, emotion recognition, and feedback processing steps

[0367] Step 12:

[0368] A user types into a terminal, "Hello, how is your day going?"

[0369] The terminal sends the input data to the server.

[0370] Step 13:

[0371] The server sends the input data to the generative AI and emotion engine.

[0372] The generative AI analyzes the data and the emotion engine recognizes the emotion.

[0373] Step 14:

[0374] Based on the recognition results of the emotion engine, the generative AI generates an appropriate response (e.g., "I'm having a great day. How about you?").

[0375] Response data is sent from the generation AI and emotion engine to the server.

[0376] Step 15:

[0377] The server sends the response data to the terminal.

[0378] The terminal displays the reply message to the user.

[0379] Step 16:

[0380] The user makes a new input and the terminal again sends the data to the server.

[0381] The server sends data to the generative AI and emotion engine, which then responds and recognizes emotions. This process is repeated until the end of the conversation.

[0382] Step 17:

[0383] The user ends the conversation practice (e.g., clicks the "End" button).

[0384] The terminal sends a termination signal to the server.

[0385] Step 18:

[0386] The server sends all conversational and emotional data to the generative AI and emotion engine, asking them to generate ratings and feedback.

[0387] Generative AI and emotion engines analyze data and generate detailed feedback.

[0388] Step 19:

[0389] The server receives feedback data from the generation AI and emotion engine and sends it to the device.

[0390] The device displays a feedback message to the user (e.g., "I liked how natural the conversation was. Next time, try asking more open-ended questions. Also, you seemed a little nervous; try practicing some relaxation techniques.").

[0391] Continual Skill Development Process Steps

[0392] Step 20:

[0393] The user selects the "Conversation Practice" menu again.

[0394] The terminal transmits the selection data to the server.

[0395] Step 21:

[0396] The server requests the generative AI and emotion engine to generate new conversation scenarios based on past feedback and learning history.

[0397] The generative AI and emotion engine generate appropriate scenarios and send them back to the server.

[0398] Step 22:

[0399] The server sends the new scenario to the device.

[0400] The terminal displays the new scenario and prompts the user to start a conversation.

[0401] Through these processing steps, users can continuously improve their conversation skills and emotion recognition abilities, and the system provides optimized scenarios and feedback for each user, allowing for personalized training.

[0402] Example 2

[0403] 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."

[0404] Currently, systems that allow users to efficiently learn and improve their conversation skills struggle to recognize users' emotions and provide appropriate feedback. Furthermore, it is not sufficient to generate conversation scenarios optimized for individual users; flexible scenario generation and adjustment based on each user's learning progress and emotions is required. Furthermore, there is a lack of detailed evaluation methods for improving users' conversation skills through continuous feedback.

[0405] 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.

[0406] In this invention, the server includes server means for communicating with a terminal on which a user practices conversation, database means for storing user profile data and past conversation practice data, and generation means for generating conversation scenarios based on artificial intelligence. This makes it possible to recognize user emotions using emotion recognition and analysis means and to provide optimal conversation scenarios for each user using personalization means. Furthermore, by analyzing the conversation data and emotion data and generating detailed feedback using feedback generation means, it is possible to continuously improve the user's conversation skills.

[0407] The "server means" is a device that communicates with the terminal so that the user can practice conversation, and manages and processes various data.

[0408] The "database means" is a system that stores user profile data and past conversation practice data, and searches and updates them as needed.

[0409] The "generation means" is a device or program that generates a conversation scenario based on the generation artificial intelligence and creates learning materials for the user.

[0410] The "communication means" refers to a device or method for transmitting the generated conversation scenario and feedback to the user's terminal.

[0411] The "emotion engine means" is a device or program that analyzes the user's input data, recognizes the emotion, and reflects the results in other processes.

[0412] The "analysis means" is a device or program that analyzes conversation data and emotion data and provides an appropriate response to the user.

[0413] "Personalization means" refers to a device or program that generates conversation scenarios and feedback optimized for each user based on each user's profile data and past feedback.

[0414] The present invention is a system for enabling users to efficiently learn and improve their conversation skills. This system is mainly composed of a server, a terminal, a database, a generative artificial intelligence (generative AI), and an emotion engine.

[0415] The overall system flow is as follows:

[0416] First, a user accesses the system using their own device and performs new registration or login. At this time, the server saves the user's registration data in a database and authenticates the login information. As a concrete example, a user accesses a web page on their device, enters the required information (name, email address, password) in the new registration form, and submits it. This data is sent to the server and saved in the database.

[0417] After logging in, the user selects the conversation practice menu. At this time, the server retrieves the user's profile data and past practice data from the database and generates an appropriate conversation scenario based on the generative AI and emotion engine. The generated scenario is sent to the terminal via the server and displayed to the user. For example, when the user clicks the "Conversation Practice" button, the server retrieves data from the database, and the generative AI generates a conversation scenario that asks, "Hello, how are you doing today?" and sends it to the terminal.

[0418] When a user practices a conversation, they interact with the generation AI via their device. At this time, the generation AI analyzes the user's input data, and the emotion engine recognizes the emotion to provide a more appropriate response. For example, if a user inputs "Today was a great day," the generation AI analyzes the data, and the emotion engine recognizes it as "positive." As a result, the response "That's great. Did anything special happen?" is generated and sent from the server to the device.

[0419] Once the conversation is over, the server sends all conversation and emotion data to the AI ​​to generate detailed feedback. The generated feedback is sent to the device and displayed for the user to review. For example, feedback such as "The naturalness of the conversation was good. Next time, try asking more open-ended questions. Also, you seemed a little nervous, so try practicing ways to relax." may be displayed.

[0420] Examples of prompts include "Hello, how are you today?" or "Is there anything special happening today?"

[0421] Through these processes, users can continuously improve their conversation skills. The system provides optimized scenarios and personalized feedback, enabling optimal training for each user.

[0422] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0423] Step 1:

[0424] User Registration

[0425] A user accesses the system's web page on a terminal and clicks the "New Registration" button. The server generates a user registration form and sends it to the terminal. When the user enters their name, email address, and password and clicks the "Submit" button, the data is sent to the server. The server verifies this data and saves it in a database. The input is the user's registration information, and the output is the user information saved in the database.

[0426] Step 2:

[0427] User Authentication

[0428] When the user clicks the "Login" button on the terminal, the server generates a login form and sends it to the terminal. When the user enters an email address and password and clicks the "Submit" button, the data is sent to the server. The server collates the user information in the database and performs authentication. If authentication is successful, a session ID is generated and sent to the terminal. The input is the user's login information, and the output is the authentication result and session ID.

[0429] Step 3:

[0430] Conversation scenario generation

[0431] When a user selects the "Conversation Practice" menu on their device, the server retrieves the user's profile data and past practice data from the database. Using generative artificial intelligence and an emotion engine, the server analyzes the user's data and generates an optimal conversation scenario. The generated scenario is sent to the device via the server and displayed to the user. The input is the user's profile data and past practice data, and the output is the generated conversation scenario.

[0432] Step 4:

[0433] Conversation progression

[0434] The user initiates a dialogue according to the generated scenario. Data entered by the user into the device is sent to the server, which then sends it to the generation AI and emotion engine. The generation AI analyzes the input data, and the emotion engine recognizes emotions. Based on this, an appropriate response is generated, and the server sends the response to the device. The input is the user's dialogue input, and the output is the generated response.

[0435] Step 5:

[0436] Generate feedback

[0437] Once the conversation is over, the server sends all conversation data and emotion data to the AI ​​to generate detailed feedback. The generated feedback is sent to the device and displayed to the user. The input is the conversation data and emotion data, and the output is the generated feedback.

[0438] Step 6:

[0439] Continuous skill development

[0440] Each time the user selects the "Conversation Practice" menu again, the server requests the AI ​​and emotion engine to generate a new conversation scenario based on past feedback and learning history. The generated new scenario is sent to the device via the server, and the user practices conversation based on the new scenario. The input is past feedback and learning history, and the output is the new conversation scenario.

[0441] (Application example 2)

[0442] 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."

[0443] Traditional customer service training systems lack efficient and effective methods for supporting employee conversation skill improvement. In particular, they lack a system that provides real-time emotion recognition and feedback necessary for customer service in brick-and-mortar stores, making it difficult for employees to improve their skills on demand. Furthermore, they lack the ability to generate conversation scenarios optimized for individual employees or dynamically adjust scenarios based on past feedback, making it difficult to provide personalized training.

[0444] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0445] In this invention, the server includes server means for communicating with a terminal on which a user practices conversation, database means for storing user profile data and past conversation practice data, generation means for generating conversation scenarios based on a generation artificial intelligence, communication means for transmitting feedback on the generated conversation scenarios and conversations to the user's terminal, training means for providing training to store employees to improve their customer service skills, and emotion recognition means for recognizing user emotions using an emotion recognition engine. This enables employees to receive appropriate feedback based on emotion recognition in real time and receive personalized training based on their individual profiles and past practice data.

[0446] A "server" is a central computer system in the conversation practice system that communicates with users' terminals and manages profile data and conversation practice data.

[0447] A "terminal" is a device that a user uses to practice conversation, and includes devices such as smartphones, smart glasses, and head-mounted displays.

[0448] A "database" is a storage device for storing user profile data and past conversation practice data.

[0449] "Generative AI" refers to machine learning models and algorithms that analyze user data and generate conversation scenarios and responses.

[0450] "Communication means" refers to a network communication interface for transmitting and receiving data between the terminal and the server.

[0451] "Training Tools" is a feature that provides interactive training for store employees to improve their customer service skills.

[0452] An "emotion recognition engine" is an algorithm or software that analyzes the emotions expressed by a user in response to input data and recognizes those emotions.

[0453] The "feedback generation means" is a function that generates evaluations and advice for the user based on the progress of the conversation and emotional data.

[0454] "Personalization means" is a function that generates individually optimized conversation scenarios based on the user's ID information and past data.

[0455] The "scenario adjustment means" is a function that dynamically adjusts the conversation scenario based on past feedback.

[0456] To implement this invention, specific hardware and software must be used, including a terminal for users to practice conversation, a server for managing and processing conversation data, a database for storing data, a generative AI model for generating conversation scenarios, and an emotion recognition engine.

[0457] Hardware and Software Configuration

[0458] 1. Device: The user uses a smartphone, smart glasses, or head-mounted display, which allows the user to receive interactive training.

[0459] 2. Server: The server communicates with the user's device and manages profile data and past conversation data. It includes a web server and a database server.

[0460] 3. Database: A relational database is used to store user profile data and past conversation practice data.

[0461] 4. Generative AI models: Use machine learning models to generate conversation scenarios. An example is Hugging Face's Transformers library.

[0462] 5. Emotion Recognition Engine: To analyze the user's emotions, we use an emotion recognition model, which also uses the Transformers library from Hugging Face.

[0463] Processing flow

[0464] 1. User Registration and Login:

[0465] The user accesses the server using a terminal and performs new registration or login. The server stores the user's data in a database and performs authentication.

[0466] 2. Conversation scenario selection and generation:

[0467] After logging in, the user selects conversation practice. The server generates a conversation scenario using a generative AI model based on the user's profile data and past practice data, and sends it to the device.

[0468] 3. Conversation progression, emotion recognition, and feedback:

[0469] When a user practices a conversation, their input is sent to the server, and the generative AI model generates an appropriate response. At the same time, the emotion recognition engine analyzes emotions, and the server collects all conversation and emotion data to generate feedback.

[0470] Use of concrete examples and prompts

[0471] Examples:

[0472] When a store staff member says, "Hello, how are you today?", the emotion recognition model analyzes the user's emotions from the text and generates a response such as, "You seem happy. Did anything special happen today?" The generated feedback is then displayed as, "I liked the naturalness of the conversation. Next time, try asking more open-ended questions."

[0473] Example prompt sentence:

[0474] User profile: New staff member

[0475] Past data: In yesterday's scenario, there was feedback that "the customer service was quiet"

[0476] Generate new conversation scenario.

[0477] Using this format, employees can receive appropriate feedback based on real-time emotion recognition and personalized training based on their individual profile and past practice data.

[0478] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0479] Step 1:

[0480] A user accesses the server using a terminal to register or log in. The user's name, email address, and password are required as input, and an authentication success message or an error message is displayed as output. The server stores this data in a database and performs user authentication.

[0481] Step 2:

[0482] After logging in, the user selects the "Conversation Practice" menu on the terminal. As input, the user's selection is sent to the server, which retrieves the user's profile data and past practice data from the database. As output, an appropriate conversation scenario is generated.

[0483] Step 3:

[0484] The server inputs a prompt sentence containing the user's profile data and past practice data to the generative AI model. Based on the input data, the generative AI model generates a new conversation scenario. The output is a new conversation scenario.

[0485] Step 4:

[0486] The generated conversation scenario is sent from the server to the device and displayed to the user. The user then begins practicing on the device. As input, the user enters text according to the conversation scenario and sends it to the server. As output, an appropriate response is obtained from the generative AI model.

[0487] Step 5:

[0488] Once the user's input data is sent to the server, the emotion recognition engine analyzes the text for emotions. As input, the user's text is used, and as output, an emotion tag (e.g., joy, anger, sadness, etc.) is generated.

[0489] Step 6:

[0490] The server combines the results of the emotion recognition engine with the responses of the generative AI model to generate appropriate feedback. The server uses the user's conversational and emotional data as input, and generates detailed feedback as output.

[0491] Step 7:

[0492] The generated detailed feedback is sent from the server to the terminal and displayed to the user.As input, feedback data is sent from the server to the terminal and as output, it is visually displayed to the user.

[0493] Step 8:

[0494] The next time the user starts a conversation practice session, the server uses the generative AI model again to generate a new conversation scenario based on past feedback and learning history. Past feedback and learning history are used as input, and a new personalized scenario is generated as output.

[0495] Step 9:

[0496] The server sends the generated personalized scenario to the terminal, and the user practices conversation based on the new scenario. The user's profile and past scenario data are used as input, and the new conversation practice scenario is displayed to the user as output.

[0497] Through these processing steps, users can continuously improve their conversation skills and emotion recognition abilities, and the system provides personalized training for each user, resulting in more effective learning.

[0498] 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.

[0499] 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.

[0500] 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.

[0501] [Second embodiment]

[0502] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0503] 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.

[0504] 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).

[0505] 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.

[0506] 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.

[0507] 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).

[0508] 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.

[0509] 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.

[0510] 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.

[0511] 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.

[0512] 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.

[0513] 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."

[0514] This invention is a system that allows users to efficiently learn and improve the conversation skills required for floor ladies. This system consists of multiple components, such as a server, terminals, a database, and generative artificial intelligence (AI).

[0515] Overall system flow

[0516] 1. User Registration and Login

[0517] First, a user accesses the system using their own terminal and registers or logs in. The server stores the user's registration data in a database and authenticates the login information.

[0518] 2. Conversation scenario selection and generation

[0519] After logging in, the user selects a conversation practice via the terminal. The server retrieves the user's profile data and past practice data from the database and generates an appropriate conversation scenario based on the generative artificial intelligence. The scenario is sent to the terminal and displayed to the user.

[0520] 3. Conversation progression and feedback

[0521] When a user practices conversation, they interact with the generation AI via their device. The generation AI analyzes the user's input data and provides appropriate responses and methods for progressing the conversation. After the conversation is over, the server sends the conversation data to the generation AI, which generates detailed feedback. This allows the user to receive specific advice on how to improve their conversation skills.

[0522] Specific examples

[0523] User Registration and Login

[0524] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[0525] 2. The server sends a user registration form to the terminal, and the user enters the required information (name, email address, password).

[0526] 3. When the user clicks the "Submit" button, the terminal sends the data to the server. The server validates the data and stores it in the database. In addition, a message indicating completion of registration is displayed on the terminal.

[0527] 4. Next, when the user clicks the "Login" button, the server sends a login form to the terminal, where the user enters their email address and password and clicks "Submit."

[0528] 5. The server authenticates the data and initiates the user session.

[0529] Conversation scenario selection and generation

[0530] 1. The user selects the "Conversation Practice" menu on the device.

[0531] 2. The server retrieves the user's profile data and past practice data from the database.

[0532] 3. The generation AI generates an appropriate conversation scenario and sends it to the terminal via the server.

[0533] 4. The device displays the generated scenario and allows the user to start a conversation.

[0534] Conversation management and feedback

[0535] 1. The user types "Hello, how is your day going?" into the terminal.

[0536] 2. The device sends the input data to the server and requests the AI ​​to analyze it. The AI ​​then generates a response such as, "I'm having a great day. How about you?"

[0537] 3. The server receives the response from the AI ​​and sends it to the device, which displays the response to the user.

[0538] 4. After the conversation practice is completed, the server sends all the conversation data to the generation AI, which generates detailed feedback.

[0539] 5. The server sends the feedback data to the terminal so that the user can check it.

[0540] This allows users to effectively acquire and improve the conversation skills necessary for floor ladies. Furthermore, the system provides scenarios optimized for each user, enabling training tailored to individual needs.

[0541] The processing flow will be explained below.

[0542] User registration and login process steps

[0543] User Registration

[0544] Step 1:

[0545] The user clicks the "New Registration" button on the device.

[0546] The terminal displays a user registration form.

[0547] Step 2:

[0548] The user enters their name, email address, and password into the form and clicks the "Submit" button.

[0549] The terminal sends the input data to the server.

[0550] Step 3:

[0551] The server receives the input data and performs validation (e.g., checking for duplicate email addresses, matching passwords).

[0552] If the verification is successful, the server stores the user information in a database.

[0553] Step 4:

[0554] The server sends a registration completion message to the terminal.

[0555] The device will display a registration complete message.

[0556] Log in

[0557] Step 5:

[0558] The user clicks the "Login" button on the device.

[0559] The terminal displays a login form.

[0560] Step 6:

[0561] The user enters their email address and password and clicks the "Submit" button.

[0562] The terminal sends the input data to the server.

[0563] Step 7:

[0564] The server receives the input data and checks it against information in a database.

[0565] If the match is successful, the server starts the user session.

[0566] Processing steps for selecting and generating conversation scenarios

[0567] Step 8:

[0568] The user selects the "conversation practice" menu on the terminal.

[0569] The terminal transmits the selection data to the server.

[0570] Step 9:

[0571] The server retrieves the user's profile data and past practice data from the database.

[0572] The server sends this data to the generation AI and requests it to generate a conversation scenario.

[0573] Step 10:

[0574] Generative AI analyzes user data and generates appropriate conversation scenarios.

[0575] The generated scenario is sent back to the server.

[0576] Step 11:

[0577] The server sends the generated scenario to the terminal.

[0578] The terminal displays the scenario and prompts the user to start a conversation.

[0579] Steps for navigating the conversation and handling feedback

[0580] Step 12:

[0581] A user types into a terminal, "Hello, how is your day going?"

[0582] The terminal sends the input data to the server.

[0583] Step 13:

[0584] The server sends the input data to the generation AI.

[0585] Generative AI analyzes the data and generates appropriate responses.

[0586] Step 14:

[0587] The server sends the response data received from the generation AI to the terminal.

[0588] The terminal displays the reply message to the user.

[0589] Step 15:

[0590] The user makes a new input and the terminal again sends the data to the server.

[0591] The server sends data to the generating AI, which generates a response, and this process is repeated until the end of the conversation.

[0592] Step 16:

[0593] The user ends the conversation practice (e.g., clicks the "End" button).

[0594] The terminal sends a termination signal to the server.

[0595] Step 17:

[0596] The server sends all conversation data to the generation AI and asks it to generate an evaluation and feedback.

[0597] Generative AI analyzes the data and generates detailed feedback.

[0598] Step 18:

[0599] The server receives feedback data from the generated AI and sends it to the device.

[0600] The terminal displays a feedback message to the user.

[0601] Continual Skill Development Process Steps

[0602] Step 19:

[0603] The user selects the "Conversation Practice" menu again.

[0604] The terminal transmits the selection data to the server.

[0605] Step 20:

[0606] The server asks the generative AI to generate new conversation scenarios based on past feedback and learning history.

[0607] The generation AI generates an appropriate scenario and sends it back to the server.

[0608] Step 21:

[0609] The server sends the new scenario to the device.

[0610] The terminal displays the new scenario and prompts the user to start a conversation.

[0611] Through these processing steps, users can continually improve their speaking skills.

[0612] Example 1

[0613] 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."

[0614] Conventional conversation practice systems have struggled to generate optimal conversation scenarios for each user and provide immediate and appropriate feedback. This has prevented them from efficiently improving users' conversation skills. It has also been difficult to effectively utilize users' profile information and past practice data to generate personalized conversation scenarios.

[0615] 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.

[0616] In this invention, the server includes means for communicating with a terminal used by a user for conversation practice, means for storing the user's profile data and past conversation practice data, means for generating a conversation scenario based on a generative artificial intelligence model, and means for transmitting feedback on the generated conversation scenario and conversation to the user's terminal. This makes it possible to provide a conversation scenario optimized for each user and receive immediate and appropriate feedback. Furthermore, personalized scenarios can be generated based on the user's profile and past practice data, allowing users to effectively improve their skills through conversation practice based on the scenarios.

[0617] 1. "Server" means a central device that communicates with the terminals on which users practice conversation and processes data.

[0618] 2. "Terminal" means a computing device used by a user to practice speaking.

[0619] 3. "Profile Data" means basic information about a User, such as name, email address, and past practice history.

[0620] 4. "Past conversation practice data" refers to data that records the content and results of conversation practice sessions that the user has conducted in the past.

[0621] 5. "Database" refers to a system for storing and managing user profile data and past conversation practice data.

[0622] 6. "Generative AI model" refers to an AI technology that generates and analyzes conversation scenarios based on user data.

[0623] 7. "Generation means" means a process and system for generating conversation scenarios using a generative artificial intelligence model.

[0624] 8. "Personalization methods" are functions and technologies for generating different scenarios based on the user's ID.

[0625] 9. "Scenario adjustment means" refers to the functions and technologies for dynamically adjusting conversation scenarios based on past feedback.

[0626] 10. "Communication means" refers to the functions and technologies for transmitting the generated conversation scenario and feedback on the conversation to the user's device.

[0627] 11. "Feedback generation means" refers to the functions and technologies for generating detailed feedback based on user conversation data.

[0628] The present invention is a system for enabling users to efficiently learn and improve their conversation skills. This system is composed of multiple components, including a server, a terminal, a database, and a generative artificial intelligence model. The following describes how this system is specifically implemented.

[0629] First, a user accesses the system's webpage using their own device and registers or logs in. At this time, the server stores the user's input information, such as name, email address, and password, in a database and authenticates the login information. For example, the following specific operations are performed:

[0630] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[0631] 2. The server sends a user registration form to the terminal, and the user enters the required information (name, email address, password).

[0632] 3. When the user clicks the "Submit" button, the terminal sends the data to the server. The server validates the data and stores it in the database. In addition, a message indicating completion of registration is displayed on the terminal.

[0633] Next, after the user logs in, they select conversation practice. The server retrieves the user's profile data and past practice data from the database, and generates an appropriate conversation scenario based on a generative artificial intelligence model (e.g., GPT-3). The scenario is sent to the terminal and displayed to the user. The following specific operations are performed in this step:

[0634] 1. The user selects the "Conversation Practice" menu on the device.

[0635] 2. The server retrieves the user's profile data and past practice data from the database.

[0636] 3. The generative artificial intelligence model generates a conversation scenario based on the acquired data and sends it to the terminal via the server.

[0637] 4. The device displays the generated scenario and allows the user to start a conversation.

[0638] When a user practices a conversation, they interact with the Generative AI via their device. The Generative AI analyzes the user's input data and provides appropriate responses and methods for progressing the conversation. For example, if the user types, "Hello, how are you today?", the Generative AI will generate a response such as, "I'm having a great day. How about you?" The process proceeds as follows:

[0639] 1. The user types "Hello, how is your day going?" into the terminal.

[0640] 2. The terminal sends the input data to the server and requests the generative artificial intelligence model to analyze it.

[0641] 3. The generative artificial intelligence model generates a response and sends it to the terminal via the server.

[0642] 4. The terminal displays the response to the user.

[0643] After the conversation practice is completed, the server sends the conversation data to the generative AI model, which generates detailed feedback, including specific advice such as "It would be good to speed up the conversation." This feedback is then sent from the server to the device for the user to review.

[0644] This allows users to receive specific advice on how to improve their conversation skills. The system provides scenarios and feedback optimized for each user, enabling training tailored to individual needs.

[0645] For example, you might input the following prompt into a generator AI:

[0646] "What's your name?" "What are your hobbies?" "Hello, how are you today?"

[0647] Such a system allows users to efficiently acquire conversation skills and improve the techniques required for a floor lady.

[0648] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0649] Step 1:

[0650] User Registration and Login

[0651] input:

[0652] User registration request, name, email address, password

[0653] Login request, email address, password

[0654] Specific actions and data processing:

[0655] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[0656] 2. The server sends a user registration form to the device, which includes fields for entering name, email address, and password.

[0657] 3. The user enters the necessary information and presses the "Send" button. The terminal sends the input data to the server.

[0658] 4. The server verifies the data sent and stores it in the database if it is correct. If the information is invalid, it returns an error message to the terminal.

[0659] 5. When the user clicks the "Login" button, the server sends the login form to the terminal.

[0660] 6. The user enters their email address and password and clicks the "Submit" button. The device sends this information to the server.

[0661] 7. The server retrieves the email address from the database and verifies the password.

[0662] 8. If authentication is successful, the server starts the user session and redirects to the main menu, otherwise it displays an error message on the terminal.

[0663] output:

[0664] Registration completion message

[0665] Login success or failure message

[0666] Step 2:

[0667] Conversation scenario selection and generation

[0668] input:

[0669] User conversation practice menu selection

[0670] Profile Data

[0671] Past practice data

[0672] Specific actions and data processing:

[0673] 1. The user selects the "Conversation Practice" menu on the device.

[0674] 2. The server retrieves the user's profile data and past practice data from the database.

[0675] 3. The server passes this data to a generative artificial intelligence model (e.g., GPT-3) and requests it to generate a conversation scenario.

[0676] 4. The generative AI model generates a conversation scenario based on the data, and the scenario is created as a prompt sentence.

[0677] 5. The server sends the generated scenario to the terminal, which displays it to the user.

[0678] output:

[0679] Conversation scenario

[0680] Step 3:

[0681] Conversation management and feedback

[0682] input:

[0683] User conversation input data

[0684] System-generated conversation scenario

[0685] Dynamic feedback requests during conversations

[0686] Specific actions and data processing:

[0687] 1. The user enters the conversation content (e.g., "Hello, how are you doing today?") into the text box on the device and clicks the "Send" button.

[0688] 2. The device sends the input data to the server and requests the generative AI model to analyze it.

[0689] 3. The generative AI model generates a response based on the user's input and returns it to the server.

[0690] 4. The server sends the response to the terminal, which displays the response to the user.

[0691] 5. Once the conversation practice is completed, the server sends all the conversation data to the generative AI model and asks it to generate detailed feedback.

[0692] 6. The generative AI model analyzes the content of the conversation and the user's reactions, and generates feedback including specific advice and areas for improvement (e.g., "It would be better to speed up the conversation").

[0693] 7. The server sends the generated feedback to the device so that the user can view it.

[0694] output:

[0695] Responses generated by generative AI models

[0696] Detailed feedback after the conversation

[0697] (Application example 1)

[0698] 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."

[0699] In modern brick-and-mortar stores, improving the quality of customer service requires continuous improvement of the customer service skills of store clerks. However, conventional training methods make it difficult to acquire efficient conversational skills that meet individual needs, and it is also difficult to receive feedback in real time. The present invention aims to solve these problems and provide a system that allows store clerks to efficiently and effectively improve their customer service skills.

[0700] 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.

[0701] In this invention, the server includes server means for communicating with a device for user conversation practice, storage means for storing user attribute data and past conversation practice data, generation means for generating conversation scenarios based on a generative AI model, communication means for transmitting feedback on the generated conversation scenarios and conversations to the user's device, and a system used by users to improve their customer service skills. This allows store clerks to practice conversations optimally according to their individual needs and receive feedback in real time, thereby effectively improving their skills.

[0702] "User" refers to a person who uses the system to practice conversation, and in particular refers to a store clerk who aims to improve their customer service skills in a brick-and-mortar store.

[0703] "Device" refers to the hardware used to communicate with the server and practice conversation, and is primarily a portable computer such as a smartphone or tablet.

[0704] The "server means" is a device that executes processes for conversation practice and communicates with the user's terminal.

[0705] The "storage means" is a component that includes a database that stores user attribute data and past conversation practice data.

[0706] A "generative AI model" refers to an artificial intelligence program that generates a scenario for a user's conversation practice, analyzes conversation data, and generates appropriate responses.

[0707] A "generation means" is a component that has the function of automatically creating a conversation scenario using a generative AI model.

[0708] A "communication means" is a component that has the function of transmitting the generated conversation scenario and feedback to the user's device.

[0709] The "feedback generation means" is a component that has the function of creating detailed feedback based on the user's conversation data.

[0710] The "personalization means" is a component that has the function of generating different scenarios suited to individual users based on the user's identification information.

[0711] The "scenario adjustment means" is a component that has the function of dynamically changing the conversation scenario according to the user's past feedback.

[0712] A "prompt generation means" is a component that has the function of creating a prompt sentence to be input into a generative AI model.

[0713] This invention is a conversation practice system for enabling store clerks to efficiently improve their customer service skills, and is implemented using the following hardware and software.

[0714] Hardware

[0715] Server: Generates conversation scenarios, analyzes conversation data, and generates feedback.

[0716] Device: A device (smartphone, tablet, etc.) on which a user practices conversation.

[0717] software

[0718] Generative AI model: Generates conversation scenarios and analyzes user input data.

[0719] Storage means: A database that stores user attribute data and past conversation practice data.

[0720] Communication means: The server transmits conversation scenarios and feedback to the terminal.

[0721] The server communicates with a device on which the user practices conversation, and stores the user's attribute data and past conversation practice data in a storage means. It then generates a conversation scenario based on the generative AI model and transmits the scenario to the user's device via a communication means. The user practices conversation based on the generated scenario, and the conversation data is transmitted to the server. The server analyzes the received conversation data using the generative AI model, generates appropriate feedback, and provides it to the user.

[0722] This allows users to practice conversations optimally according to their individual needs and receive real-time feedback, effectively improving their skills. Furthermore, scenario generation and feedback take into account the user's identification information and past feedback, and the scenario is dynamically adjusted.

[0723] Specific operation example

[0724] 1. User Registration and Login

[0725] When a user uses the system for the first time, they enter their information to complete registration and then log in.

[0726] 2. Conversation scenario selection and generation

[0727] When the user selects the "conversation practice" menu, the server retrieves the user's attribute data and past practice data from an existing database.

[0728] A generative AI model generates appropriate conversation scenarios based on this data.

[0729] 3. Conversation practice and feedback

[0730] The user follows a scenario and practices conversation in an interactive format.

[0731] The server analyzes the user's input in real time and provides an appropriate response.

[0732] After completing the exercise, the server generates detailed feedback and sends it to the user.

[0733] Prompt Sentence Examples

[0734] The following prompt sentence is fed into the generative AI model:

[0735] "How can we keep you informed about promotions that might be of interest to you?"

[0736] "What are some examples of questions you can ask to accurately understand a customer's needs while serving them?"

[0737] The system of the present invention allows store staff in brick-and-mortar stores to continuously and effectively improve their customer service skills.

[0738] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0739] Step 1:

[0740] (User registration and login)

[0741] Input: The user enters their name, email address, and password.

[0742] Processing: The terminal sends the user input to the server, and the server stores the input data in a storage means and sends a registration completion message to the terminal.

[0743] Output: The user account is created and the user can log in to the system.

[0744] Specific operation: The user clicks the "New Registration" button, enters the required information in the registration form, and clicks the "Submit" button. The server verifies the validity of the data and saves it to the database.

[0745] Step 2:

[0746] (Selection and generation of conversation scenarios)

[0747] Input: The user selects the "Conversation Practice" menu.

[0748] Processing: The server retrieves the user's attribute data and past conversation practice data from the storage means, and generates an appropriate conversation scenario based on the generative AI model.

[0749] Output: The generated conversation scenario is sent to the terminal and displayed to the user.

[0750] Specific operation: When a user selects the "Conversation Practice" menu, the server retrieves the user's information from the database, and the generative AI model generates a scenario. The scenario is sent to the device and displayed on the user's screen.

[0751] Step 3:

[0752] (Conversation practice and feedback)

[0753] Input: The user inputs a conversation based on the scenario.

[0754] Processing: The device sends the user's input data to the server, the generative AI model generates an appropriate response, and the server sends the response to the device.

[0755] Output: A conversational exchange continues and feedback is generated after the practice session.

[0756] Specific operation: When the user enters text corresponding to the scenario displayed on the screen and clicks the send button, the data is sent to the server. The generative AI model analyzes the data, generates an appropriate response, and sends it back to the device. Once the conversation is over, the server analyzes the entire conversation data, generates feedback, and sends it to the device.

[0757] Step 4:

[0758] (Check feedback)

[0759] Input: User makes a request for feedback confirmation.

[0760] Processing: The server retrieves the generated feedback data from the storage means and transmits it to the terminal.

[0761] Output: Feedback is displayed on the user's device.

[0762] Specific operation: When a user selects a feedback menu and sends a request, the server retrieves the corresponding feedback data from the database, sends it to the terminal, and displays it to the user.

[0763] Step 5:

[0764] (Generate prompt sentence)

[0765] Input: User identity and past feedback data.

[0766] Processing: The server analyzes past feedback data and generates and sends prompt sentences to the generative AI model.

[0767] Output: The prompt sentence is sent to the generative AI model and used to generate new conversation scenarios.

[0768] Specific operation: The server analyzes past feedback data based on the user's identification information and generates a prompt such as, "Please tell us how we can provide you with campaign information that might interest you." The prompt is then sent to the generative AI model and used to generate new scenarios.

[0769] 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.

[0770] The present invention provides a system for enabling users to efficiently learn and improve the conversation skills required for floor ladies. The system includes a server, a terminal, a database, a generative artificial intelligence (AI), and an emotion engine.

[0771] Overall system flow

[0772] 1. User Registration and Login

[0773] First, a user accesses the system using their own terminal and registers or logs in. The server stores the user's registration data in a database and authenticates the login information.

[0774] 2. Conversation scenario selection and generation

[0775] After logging in, the user selects a conversation practice via the terminal. The server retrieves the user's profile data and past practice data from the database, and generates an appropriate conversation scenario based on the generative artificial intelligence and emotion engine. The scenario is sent to the terminal and displayed to the user.

[0776] 3. Conversation progression, emotion recognition, and feedback

[0777] When a user practices conversation, they interact with the generation AI via their device. The generation AI analyzes the user's input data, and its emotion engine recognizes their emotions. Based on this, it provides appropriate responses and methods for progressing the conversation. After the conversation ends, the server sends the conversation data and emotion data to the generation AI, which generates detailed feedback. This allows the user to receive specific advice on how to improve their conversation skills.

[0778] Specific examples

[0779] User Registration and Login

[0780] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[0781] 2. The server sends a user registration form to the terminal, and the user enters the required information (name, email address, password).

[0782] 3. When the user clicks the "Submit" button, the terminal sends the data to the server. The server validates the data and stores it in the database. In addition, a registration completion message is displayed on the terminal.

[0783] 4. Next, when the user clicks the "Login" button, the server sends a login form to the terminal, where the user enters their email address and password and clicks "Submit."

[0784] 5. The server authenticates the data and initiates the user session.

[0785] Conversation scenario selection and generation

[0786] 1. The user selects the "Conversation Practice" menu on the device.

[0787] 2. The server retrieves the user's profile data and past practice data from the database.

[0788] 3. Generative AI and emotion engine analyze user data and generate appropriate conversation scenarios.

[0789] 4. The generated scenario is sent to the terminal via the server and displayed to the user.

[0790] Conversation progression, emotion recognition, and feedback

[0791] 1. The user types "Hello, how is your day going?" into the terminal.

[0792] 2. The terminal sends the input data to the server.

[0793] 3. The server sends the input data to the generation AI, which analyzes the data.

[0794] 4. The emotion engine recognizes the user's emotions, and the generative AI generates an appropriate response based on that (e.g., "You look like you're having fun. Did something special happen today?").

[0795] 5. The server sends the response data received from the generation AI and emotion engine to the device, and the device displays the response message to the user.

[0796] 6. After the conversation practice is completed, the server sends all conversation data and emotion data to the generation AI and asks it to generate an evaluation and feedback.

[0797] 7. Generative AI analyzes the data and generates detailed feedback.

[0798] 8. The server sends feedback data to the device so that the user can review it (e.g., "I liked how natural the conversation was. Next time, try asking more open-ended questions. Also, you seemed a little nervous, so try practicing ways to relax.").

[0799] Continuous skill development

[0800] 1. The user selects the "Conversation Practice" menu again.

[0801] 2. The server asks the generative AI and emotion engine to generate new conversation scenarios based on past feedback and learning history.

[0802] 3. The generative AI and emotion engine generate an appropriate scenario and send it back to the server.

[0803] 4. The server sends the new scenario to the terminal, which displays the new scenario and prompts the user to start a conversation.

[0804] Through these processes, users can continuously improve their conversation skills and emotion recognition abilities. The system provides scenarios and feedback optimized for each user, allowing for personalized training.

[0805] The processing flow will be explained below.

[0806] User registration and login process steps

[0807] User Registration

[0808] Step 1:

[0809] The user clicks the "New Registration" button on the device.

[0810] The terminal displays a user registration form.

[0811] Step 2:

[0812] The user enters their name, email address, and password into the form and clicks the "Submit" button.

[0813] The terminal sends the input data to the server.

[0814] Step 3:

[0815] The server receives the input data and performs validation (e.g., checking for duplicate email addresses, matching passwords).

[0816] If the verification is successful, the server stores the user information in a database.

[0817] Step 4:

[0818] The server sends a registration completion message to the terminal.

[0819] The device will display a registration complete message.

[0820] Log in

[0821] Step 5:

[0822] The user clicks the "Login" button on the device.

[0823] The terminal displays a login form.

[0824] Step 6:

[0825] The user enters their email address and password and clicks the "Submit" button.

[0826] The terminal sends the input data to the server.

[0827] Step 7:

[0828] The server receives the input data and checks it against information in a database.

[0829] If the match is successful, the server starts the user session.

[0830] Processing steps for selecting and generating conversation scenarios

[0831] Step 8:

[0832] The user selects the "conversation practice" menu on the terminal.

[0833] The terminal transmits the selection data to the server.

[0834] Step 9:

[0835] The server retrieves the user's profile data and past practice data from the database.

[0836] The server sends this data to the generation AI and emotion engine, requesting them to generate a conversation scenario.

[0837] Step 10:

[0838] Generative AI and emotion engines analyze user data and generate appropriate conversation scenarios.

[0839] The generated scenario is sent back to the server.

[0840] Step 11:

[0841] The server sends the generated scenario to the terminal.

[0842] The terminal displays the scenario and prompts the user to start a conversation.

[0843] Conversation progression, emotion recognition, and feedback processing steps

[0844] Step 12:

[0845] A user types into a terminal, "Hello, how is your day going?"

[0846] The terminal sends the input data to the server.

[0847] Step 13:

[0848] The server sends the input data to the generative AI and emotion engine.

[0849] The generative AI analyzes the data and the emotion engine recognizes the emotion.

[0850] Step 14:

[0851] Based on the recognition results of the emotion engine, the generative AI generates an appropriate response (e.g., "I'm having a great day. How about you?").

[0852] Response data is sent from the generation AI and emotion engine to the server.

[0853] Step 15:

[0854] The server sends the response data to the terminal.

[0855] The terminal displays the reply message to the user.

[0856] Step 16:

[0857] The user makes a new input and the terminal again sends the data to the server.

[0858] The server sends data to the generative AI and emotion engine, which then responds and recognizes emotions. This process is repeated until the end of the conversation.

[0859] Step 17:

[0860] The user ends the conversation practice (e.g., clicks the "End" button).

[0861] The terminal sends a termination signal to the server.

[0862] Step 18:

[0863] The server sends all conversational and emotional data to the generative AI and emotion engine, asking them to generate ratings and feedback.

[0864] Generative AI and emotion engines analyze data and generate detailed feedback.

[0865] Step 19:

[0866] The server receives feedback data from the generation AI and emotion engine and sends it to the device.

[0867] The device displays a feedback message to the user (e.g., "I liked how natural the conversation was. Next time, try asking more open-ended questions. Also, you seemed a little nervous; try practicing some relaxation techniques.").

[0868] Continual Skill Development Process Steps

[0869] Step 20:

[0870] The user selects the "Conversation Practice" menu again.

[0871] The terminal transmits the selection data to the server.

[0872] Step 21:

[0873] The server requests the generative AI and emotion engine to generate new conversation scenarios based on past feedback and learning history.

[0874] The generative AI and emotion engine generate appropriate scenarios and send them back to the server.

[0875] Step 22:

[0876] The server sends the new scenario to the device.

[0877] The terminal displays the new scenario and prompts the user to start a conversation.

[0878] Through these processing steps, users can continuously improve their conversation skills and emotion recognition abilities, and the system provides optimized scenarios and feedback for each user, allowing for personalized training.

[0879] Example 2

[0880] 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."

[0881] Currently, systems that allow users to efficiently learn and improve their conversation skills struggle to recognize users' emotions and provide appropriate feedback. Furthermore, it is not sufficient to generate conversation scenarios optimized for individual users; flexible scenario generation and adjustment based on each user's learning progress and emotions is required. Furthermore, there is a lack of detailed evaluation methods for improving users' conversation skills through continuous feedback.

[0882] 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.

[0883] In this invention, the server includes server means for communicating with a terminal on which a user practices conversation, database means for storing user profile data and past conversation practice data, and generation means for generating conversation scenarios based on artificial intelligence. This makes it possible to recognize user emotions using emotion recognition and analysis means and to provide optimal conversation scenarios for each user using personalization means. Furthermore, by analyzing the conversation data and emotion data and generating detailed feedback using feedback generation means, it is possible to continuously improve the user's conversation skills.

[0884] The "server means" is a device that communicates with the terminal so that the user can practice conversation, and manages and processes various data.

[0885] The "database means" is a system that stores user profile data and past conversation practice data, and searches and updates them as needed.

[0886] The "generation means" is a device or program that generates a conversation scenario based on the generation artificial intelligence and creates learning materials for the user.

[0887] The "communication means" refers to a device or method for transmitting the generated conversation scenario and feedback to the user's terminal.

[0888] The "emotion engine means" is a device or program that analyzes the user's input data, recognizes the emotion, and reflects the results in other processes.

[0889] The "analysis means" is a device or program that analyzes conversation data and emotion data and provides an appropriate response to the user.

[0890] "Personalization means" refers to a device or program that generates conversation scenarios and feedback optimized for each user based on each user's profile data and past feedback.

[0891] The present invention is a system for enabling users to efficiently learn and improve their conversation skills. This system is mainly composed of a server, a terminal, a database, a generative artificial intelligence (generative AI), and an emotion engine.

[0892] The overall system flow is as follows:

[0893] First, a user accesses the system using their own device and performs new registration or login. At this time, the server saves the user's registration data in a database and authenticates the login information. As a concrete example, a user accesses a web page on their device, enters the required information (name, email address, password) in the new registration form, and submits it. This data is sent to the server and saved in the database.

[0894] After logging in, the user selects the conversation practice menu. At this time, the server retrieves the user's profile data and past practice data from the database and generates an appropriate conversation scenario based on the generative AI and emotion engine. The generated scenario is sent to the terminal via the server and displayed to the user. For example, when the user clicks the "Conversation Practice" button, the server retrieves data from the database, and the generative AI generates a conversation scenario that asks, "Hello, how are you doing today?" and sends it to the terminal.

[0895] When a user practices a conversation, they interact with the generation AI via their device. At this time, the generation AI analyzes the user's input data, and the emotion engine recognizes the emotion to provide a more appropriate response. For example, if a user inputs "Today was a great day," the generation AI analyzes the data, and the emotion engine recognizes it as "positive." As a result, the response "That's great. Did anything special happen?" is generated and sent from the server to the device.

[0896] Once the conversation is over, the server sends all conversation and emotion data to the AI ​​to generate detailed feedback. The generated feedback is sent to the device and displayed for the user to review. For example, feedback such as "The naturalness of the conversation was good. Next time, try asking more open-ended questions. Also, you seemed a little nervous, so try practicing ways to relax." may be displayed.

[0897] Examples of prompts include "Hello, how are you today?" or "Is there anything special happening today?"

[0898] Through these processes, users can continuously improve their conversation skills. The system provides optimized scenarios and personalized feedback, enabling optimal training for each user.

[0899] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0900] Step 1:

[0901] User Registration

[0902] A user accesses the system's web page on a terminal and clicks the "New Registration" button. The server generates a user registration form and sends it to the terminal. When the user enters their name, email address, and password and clicks the "Submit" button, the data is sent to the server. The server verifies this data and saves it in a database. The input is the user's registration information, and the output is the user information saved in the database.

[0903] Step 2:

[0904] User Authentication

[0905] When the user clicks the "Login" button on the terminal, the server generates a login form and sends it to the terminal. When the user enters an email address and password and clicks the "Submit" button, the data is sent to the server. The server collates the user information in the database and performs authentication. If authentication is successful, a session ID is generated and sent to the terminal. The input is the user's login information, and the output is the authentication result and session ID.

[0906] Step 3:

[0907] Conversation scenario generation

[0908] When a user selects the "Conversation Practice" menu on their device, the server retrieves the user's profile data and past practice data from the database. Using generative artificial intelligence and an emotion engine, the server analyzes the user's data and generates an optimal conversation scenario. The generated scenario is sent to the device via the server and displayed to the user. The input is the user's profile data and past practice data, and the output is the generated conversation scenario.

[0909] Step 4:

[0910] Conversation progression

[0911] The user initiates a dialogue according to the generated scenario. Data entered by the user into the device is sent to the server, which then sends it to the generation AI and emotion engine. The generation AI analyzes the input data, and the emotion engine recognizes emotions. Based on this, an appropriate response is generated, and the server sends the response to the device. The input is the user's dialogue input, and the output is the generated response.

[0912] Step 5:

[0913] Generate feedback

[0914] Once the conversation is over, the server sends all conversation data and emotion data to the AI ​​to generate detailed feedback. The generated feedback is sent to the device and displayed to the user. The input is the conversation data and emotion data, and the output is the generated feedback.

[0915] Step 6:

[0916] Continuous skill development

[0917] Each time the user selects the "Conversation Practice" menu again, the server requests the AI ​​and emotion engine to generate a new conversation scenario based on past feedback and learning history. The generated new scenario is sent to the device via the server, and the user practices conversation based on the new scenario. The input is past feedback and learning history, and the output is the new conversation scenario.

[0918] (Application example 2)

[0919] 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."

[0920] Traditional customer service training systems lack efficient and effective methods for supporting employee conversation skill improvement. In particular, they lack a system that provides real-time emotion recognition and feedback necessary for customer service in brick-and-mortar stores, making it difficult for employees to improve their skills on demand. Furthermore, they lack the ability to generate conversation scenarios optimized for individual employees or dynamically adjust scenarios based on past feedback, making it difficult to provide personalized training.

[0921] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0922] In this invention, the server includes server means for communicating with a terminal on which a user practices conversation, database means for storing user profile data and past conversation practice data, generation means for generating conversation scenarios based on a generation artificial intelligence, communication means for transmitting feedback on the generated conversation scenarios and conversations to the user's terminal, training means for providing training to store employees to improve their customer service skills, and emotion recognition means for recognizing user emotions using an emotion recognition engine. This enables employees to receive appropriate feedback based on emotion recognition in real time and receive personalized training based on their individual profiles and past practice data.

[0923] A "server" is a central computer system in the conversation practice system that communicates with users' terminals and manages profile data and conversation practice data.

[0924] A "terminal" is a device that a user uses to practice conversation, and includes devices such as smartphones, smart glasses, and head-mounted displays.

[0925] A "database" is a storage device for storing user profile data and past conversation practice data.

[0926] "Generative AI" refers to machine learning models and algorithms that analyze user data and generate conversation scenarios and responses.

[0927] "Communication means" refers to a network communication interface for transmitting and receiving data between the terminal and the server.

[0928] "Training Tools" is a feature that provides interactive training for store employees to improve their customer service skills.

[0929] An "emotion recognition engine" is an algorithm or software that analyzes the emotions expressed by a user in response to input data and recognizes those emotions.

[0930] The "feedback generation means" is a function that generates evaluations and advice for the user based on the progress of the conversation and emotional data.

[0931] "Personalization means" is a function that generates individually optimized conversation scenarios based on the user's ID information and past data.

[0932] The "scenario adjustment means" is a function that dynamically adjusts the conversation scenario based on past feedback.

[0933] To implement this invention, specific hardware and software must be used, including a terminal for users to practice conversation, a server for managing and processing conversation data, a database for storing data, a generative AI model for generating conversation scenarios, and an emotion recognition engine.

[0934] Hardware and Software Configuration

[0935] 1. Device: The user uses a smartphone, smart glasses, or head-mounted display, which allows the user to receive interactive training.

[0936] 2. Server: The server communicates with the user's device and manages profile data and past conversation data. It includes a web server and a database server.

[0937] 3. Database: A relational database is used to store user profile data and past conversation practice data.

[0938] 4. Generative AI models: Use machine learning models to generate conversation scenarios. An example is Hugging Face's Transformers library.

[0939] 5. Emotion Recognition Engine: To analyze the user's emotions, we use an emotion recognition model, which also uses the Transformers library from Hugging Face.

[0940] Processing flow

[0941] 1. User Registration and Login:

[0942] The user accesses the server using a terminal and performs new registration or login. The server stores the user's data in a database and performs authentication.

[0943] 2. Conversation scenario selection and generation:

[0944] After logging in, the user selects conversation practice. The server generates a conversation scenario using a generative AI model based on the user's profile data and past practice data, and sends it to the device.

[0945] 3. Conversation progression, emotion recognition, and feedback:

[0946] When a user practices a conversation, their input is sent to the server, and the generative AI model generates an appropriate response. At the same time, the emotion recognition engine analyzes emotions, and the server collects all conversation data and emotion data to generate feedback.

[0947] Use of concrete examples and prompts

[0948] Examples:

[0949] When a store staff member says, "Hello, how are you today?", the emotion recognition model analyzes the user's emotions from the text and generates a response such as, "You seem happy. Did anything special happen today?" The generated feedback is then displayed as, "I liked the naturalness of the conversation. Next time, try asking more open-ended questions."

[0950] Example prompt sentence:

[0951] User profile: New staff member

[0952] Past data: In yesterday's scenario, there was feedback that "the customer service was quiet"

[0953] Generate new conversation scenario.

[0954] Using this format, employees can receive appropriate feedback based on real-time emotion recognition and personalized training based on their individual profile and past practice data.

[0955] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0956] Step 1:

[0957] A user accesses the server using a terminal to register or log in. The user's name, email address, and password are required as input, and an authentication success message or an error message is displayed as output. The server stores this data in a database and performs user authentication.

[0958] Step 2:

[0959] After logging in, the user selects the "Conversation Practice" menu on the terminal. As input, the user's selection is sent to the server, which retrieves the user's profile data and past practice data from the database. As output, an appropriate conversation scenario is generated.

[0960] Step 3:

[0961] The server inputs a prompt sentence containing the user's profile data and past practice data to the generative AI model. Based on the input data, the generative AI model generates a new conversation scenario. The output is a new conversation scenario.

[0962] Step 4:

[0963] The generated conversation scenario is sent from the server to the device and displayed to the user. The user then begins practicing on the device. As input, the user enters text according to the conversation scenario and sends it to the server. As output, an appropriate response is obtained from the generative AI model.

[0964] Step 5:

[0965] Once the user's input data is sent to the server, the emotion recognition engine analyzes the text for emotions. As input, the user's text is used, and as output, an emotion tag (e.g., joy, anger, sadness, etc.) is generated.

[0966] Step 6:

[0967] The server combines the results of the emotion recognition engine with the responses of the generative AI model to generate appropriate feedback. The server uses the user's conversational and emotional data as input, and generates detailed feedback as output.

[0968] Step 7:

[0969] The generated detailed feedback is sent from the server to the terminal and displayed to the user.As input, feedback data is sent from the server to the terminal and as output, it is visually displayed to the user.

[0970] Step 8:

[0971] The next time the user starts a conversation practice session, the server uses the generative AI model again to generate a new conversation scenario based on past feedback and learning history. Past feedback and learning history are used as input, and a new personalized scenario is generated as output.

[0972] Step 9:

[0973] The server sends the generated personalized scenario to the terminal, and the user practices conversation based on the new scenario. The user's profile and past scenario data are used as input, and the new conversation practice scenario is displayed to the user as output.

[0974] Through these processing steps, users can continuously improve their conversation skills and emotion recognition abilities, and the system provides personalized training for each user, resulting in more effective learning.

[0975] 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.

[0976] 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.

[0977] 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.

[0978] [Third embodiment]

[0979] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0980] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0981] 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).

[0982] 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.

[0983] 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.

[0984] 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).

[0985] 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. 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.

[0986] 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.

[0987] 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.

[0988] 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.

[0989] 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.

[0990] 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."

[0991] This invention is a system that allows users to efficiently learn and improve the conversation skills required for floor ladies. This system consists of multiple components, such as a server, terminals, a database, and generative artificial intelligence (AI).

[0992] Overall system flow

[0993] 1. User Registration and Login

[0994] First, a user accesses the system using their own terminal and registers or logs in. The server stores the user's registration data in a database and authenticates the login information.

[0995] 2. Conversation scenario selection and generation

[0996] After logging in, the user selects a conversation practice via the terminal. The server retrieves the user's profile data and past practice data from the database and generates an appropriate conversation scenario based on the generative artificial intelligence. The scenario is sent to the terminal and displayed to the user.

[0997] 3. Conversation progression and feedback

[0998] When a user practices conversation, they interact with the generation AI via their device. The generation AI analyzes the user's input data and provides appropriate responses and methods for progressing the conversation. After the conversation is over, the server sends the conversation data to the generation AI, which generates detailed feedback. This allows the user to receive specific advice on how to improve their conversation skills.

[0999] Specific examples

[1000] User Registration and Login

[1001] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[1002] 2. The server sends a user registration form to the terminal, and the user enters the required information (name, email address, password).

[1003] 3. When the user clicks the "Submit" button, the terminal sends the data to the server. The server validates the data and stores it in the database. In addition, a registration completion message is displayed on the terminal.

[1004] 4. Next, when the user clicks the "Login" button, the server sends a login form to the terminal, where the user enters their email address and password and clicks "Submit."

[1005] 5. The server authenticates the data and initiates the user session.

[1006] Conversation scenario selection and generation

[1007] 1. The user selects the "Conversation Practice" menu on the device.

[1008] 2. The server retrieves the user's profile data and past practice data from the database.

[1009] 3. The generation AI generates an appropriate conversation scenario and sends it to the terminal via the server.

[1010] 4. The device displays the generated scenario and allows the user to start a conversation.

[1011] Conversation management and feedback

[1012] 1. The user types "Hello, how is your day going?" into the terminal.

[1013] 2. The device sends the input data to the server and requests the AI ​​to analyze it. The AI ​​then generates a response such as, "I'm having a great day. How about you?"

[1014] 3. The server receives the response from the AI ​​and sends it to the device, which displays the response to the user.

[1015] 4. After the conversation practice is completed, the server sends all the conversation data to the generation AI, which generates detailed feedback.

[1016] 5. The server sends the feedback data to the terminal so that the user can check it.

[1017] This allows users to effectively acquire and improve the conversation skills necessary for floor ladies. Furthermore, the system provides scenarios optimized for each user, enabling training tailored to individual needs.

[1018] The processing flow will be explained below.

[1019] User registration and login process steps

[1020] User Registration

[1021] Step 1:

[1022] The user clicks the "New Registration" button on the device.

[1023] The terminal displays a user registration form.

[1024] Step 2:

[1025] The user enters their name, email address, and password into the form and clicks the "Submit" button.

[1026] The terminal sends the input data to the server.

[1027] Step 3:

[1028] The server receives the input data and performs validation (e.g., checking for duplicate email addresses, matching passwords).

[1029] If the verification is successful, the server stores the user information in a database.

[1030] Step 4:

[1031] The server sends a registration completion message to the terminal.

[1032] The device will display a registration complete message.

[1033] Log in

[1034] Step 5:

[1035] The user clicks the "Login" button on the device.

[1036] The terminal displays a login form.

[1037] Step 6:

[1038] The user enters their email address and password and clicks the "Submit" button.

[1039] The terminal sends the input data to the server.

[1040] Step 7:

[1041] The server receives the input data and checks it against information in a database.

[1042] If the match is successful, the server starts the user session.

[1043] Processing steps for selecting and generating conversation scenarios

[1044] Step 8:

[1045] The user selects the "conversation practice" menu on the terminal.

[1046] The terminal transmits the selection data to the server.

[1047] Step 9:

[1048] The server retrieves the user's profile data and past practice data from the database.

[1049] The server sends this data to the generation AI and requests it to generate a conversation scenario.

[1050] Step 10:

[1051] Generative AI analyzes user data and generates appropriate conversation scenarios.

[1052] The generated scenario is sent back to the server.

[1053] Step 11:

[1054] The server sends the generated scenario to the terminal.

[1055] The terminal displays the scenario and prompts the user to start a conversation.

[1056] Steps for navigating the conversation and handling feedback

[1057] Step 12:

[1058] A user types into a terminal, "Hello, how is your day going?"

[1059] The terminal sends the input data to the server.

[1060] Step 13:

[1061] The server sends the input data to the generation AI.

[1062] Generative AI analyzes the data and generates appropriate responses.

[1063] Step 14:

[1064] The server sends the response data received from the generation AI to the terminal.

[1065] The terminal displays the reply message to the user.

[1066] Step 15:

[1067] The user makes a new input and the terminal again sends the data to the server.

[1068] The server sends data to the generating AI, which generates a response, and this process is repeated until the end of the conversation.

[1069] Step 16:

[1070] The user ends the conversation practice (e.g., clicks the "End" button).

[1071] The terminal sends a termination signal to the server.

[1072] Step 17:

[1073] The server sends all conversation data to the generation AI and asks it to generate an evaluation and feedback.

[1074] Generative AI analyzes the data and generates detailed feedback.

[1075] Step 18:

[1076] The server receives feedback data from the generated AI and sends it to the device.

[1077] The terminal displays a feedback message to the user.

[1078] Continual Skill Development Process Steps

[1079] Step 19:

[1080] The user selects the "Conversation Practice" menu again.

[1081] The terminal transmits the selection data to the server.

[1082] Step 20:

[1083] The server asks the generative AI to generate new conversation scenarios based on past feedback and learning history.

[1084] The generation AI generates an appropriate scenario and sends it back to the server.

[1085] Step 21:

[1086] The server sends the new scenario to the device.

[1087] The terminal displays the new scenario and prompts the user to start a conversation.

[1088] Through these processing steps, users can continually improve their speaking skills.

[1089] Example 1

[1090] 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."

[1091] Conventional conversation practice systems have struggled to generate optimal conversation scenarios for each user and provide immediate and appropriate feedback. This has prevented them from efficiently improving users' conversation skills. It has also been difficult to effectively utilize users' profile information and past practice data to generate personalized conversation scenarios.

[1092] 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.

[1093] In this invention, the server includes means for communicating with a terminal used by a user for conversation practice, means for storing the user's profile data and past conversation practice data, means for generating a conversation scenario based on a generative artificial intelligence model, and means for transmitting feedback on the generated conversation scenario and conversation to the user's terminal. This makes it possible to provide a conversation scenario optimized for each user and receive immediate and appropriate feedback. Furthermore, personalized scenarios can be generated based on the user's profile and past practice data, allowing users to effectively improve their skills through conversation practice based on the scenarios.

[1094] 1. "Server" means a central device that communicates with the terminals on which users practice conversation and processes data.

[1095] 2. "Terminal" means a computing device used by a user to practice speaking.

[1096] 3. "Profile Data" means basic information about a User, such as name, email address, and past practice history.

[1097] 4. "Past conversation practice data" refers to data that records the content and results of conversation practice sessions that the user has conducted in the past.

[1098] 5. "Database" refers to a system for storing and managing user profile data and past conversation practice data.

[1099] 6. "Generative AI model" refers to an AI technology that generates and analyzes conversation scenarios based on user data.

[1100] 7. "Generation means" means a process and system for generating conversation scenarios using a generative artificial intelligence model.

[1101] 8. "Personalization methods" are functions and technologies for generating different scenarios based on the user's ID.

[1102] 9. "Scenario adjustment means" refers to the functions and technologies for dynamically adjusting conversation scenarios based on past feedback.

[1103] 10. "Communication means" refers to the functions and technologies for transmitting the generated conversation scenario and feedback on the conversation to the user's device.

[1104] 11. "Feedback generation means" refers to the functions and technologies for generating detailed feedback based on user conversation data.

[1105] The present invention is a system for enabling users to efficiently learn and improve their conversation skills. This system is composed of multiple components, including a server, a terminal, a database, and a generative artificial intelligence model. The following describes how this system is specifically implemented.

[1106] First, a user accesses the system's webpage using their own device and registers or logs in. At this time, the server stores the user's input information, such as name, email address, and password, in a database and authenticates the login information. For example, the following specific operations are performed:

[1107] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[1108] 2. The server sends a user registration form to the terminal, and the user enters the required information (name, email address, password).

[1109] 3. When the user clicks the "Submit" button, the terminal sends the data to the server. The server validates the data and stores it in the database. In addition, a registration completion message is displayed on the terminal.

[1110] Next, after the user logs in, they select conversation practice. The server retrieves the user's profile data and past practice data from the database, and generates an appropriate conversation scenario based on a generative artificial intelligence model (e.g., GPT-3). The scenario is sent to the terminal and displayed to the user. The following specific operations are performed in this step:

[1111] 1. The user selects the "Conversation Practice" menu on the device.

[1112] 2. The server retrieves the user's profile data and past practice data from the database.

[1113] 3. The generative artificial intelligence model generates a conversation scenario based on the acquired data and sends it to the terminal via the server.

[1114] 4. The device displays the generated scenario and allows the user to start a conversation.

[1115] When a user practices a conversation, they interact with the Generative AI via their device. The Generative AI analyzes the user's input data and provides appropriate responses and methods for progressing the conversation. For example, if the user types, "Hello, how are you today?", the Generative AI will generate a response such as, "I'm having a great day. How about you?" The process proceeds as follows:

[1116] 1. The user types "Hello, how is your day going?" into the terminal.

[1117] 2. The terminal sends the input data to the server and requests the generative artificial intelligence model to analyze it.

[1118] 3. The generative artificial intelligence model generates a response and sends it to the terminal via the server.

[1119] 4. The terminal displays the response to the user.

[1120] After the conversation practice is completed, the server sends the conversation data to the generative AI model, which generates detailed feedback, including specific advice such as "It would be good to speed up the conversation." This feedback is then sent from the server to the device for the user to review.

[1121] This allows users to receive specific advice on how to improve their conversation skills. The system provides scenarios and feedback optimized for each user, enabling training tailored to individual needs.

[1122] For example, you might input the following prompt into a generator AI:

[1123] "What's your name?" "What are your hobbies?" "Hello, how are you today?"

[1124] Such a system allows users to efficiently acquire conversation skills and improve the techniques required for a floor lady.

[1125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1126] Step 1:

[1127] User Registration and Login

[1128] input:

[1129] User registration request, name, email address, password

[1130] Login request, email address, password

[1131] Specific actions and data processing:

[1132] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[1133] 2. The server sends a user registration form to the device, which includes fields for entering name, email address, and password.

[1134] 3. The user enters the necessary information and presses the "Send" button. The terminal sends the input data to the server.

[1135] 4. The server verifies the data sent and stores it in the database if it is correct. If the information is invalid, it returns an error message to the terminal.

[1136] 5. When the user clicks the "Login" button, the server sends the login form to the terminal.

[1137] 6. The user enters their email address and password and clicks the "Submit" button. The device sends this information to the server.

[1138] 7. The server retrieves the email address from the database and verifies the password.

[1139] 8. If authentication is successful, the server starts the user session and redirects to the main menu, otherwise it displays an error message on the terminal.

[1140] output:

[1141] Registration completion message

[1142] Login success or failure message

[1143] Step 2:

[1144] Conversation scenario selection and generation

[1145] input:

[1146] User conversation practice menu selection

[1147] Profile Data

[1148] Past practice data

[1149] Specific actions and data processing:

[1150] 1. The user selects the "Conversation Practice" menu on the device.

[1151] 2. The server retrieves the user's profile data and past practice data from the database.

[1152] 3. The server passes this data to a generative artificial intelligence model (e.g., GPT-3) and requests it to generate a conversation scenario.

[1153] 4. The generative AI model generates a conversation scenario based on the data, and the scenario is created as a prompt sentence.

[1154] 5. The server sends the generated scenario to the terminal, which displays it to the user.

[1155] output:

[1156] Conversation scenario

[1157] Step 3:

[1158] Conversation management and feedback

[1159] input:

[1160] User conversation input data

[1161] System-generated conversation scenario

[1162] Dynamic feedback requests during conversations

[1163] Specific actions and data processing:

[1164] 1. The user enters the conversation content (e.g., "Hello, how are you doing today?") into the text box on the device and clicks the "Send" button.

[1165] 2. The device sends the input data to the server and requests the generative AI model to analyze it.

[1166] 3. The generative AI model generates a response based on the user's input and returns it to the server.

[1167] 4. The server sends the response to the terminal, which displays the response to the user.

[1168] 5. Once the conversation practice is completed, the server sends all the conversation data to the generative AI model and asks it to generate detailed feedback.

[1169] 6. The generative AI model analyzes the content of the conversation and the user's responses, and generates feedback including specific advice and areas for improvement (e.g., "It would be better to speed up the conversation").

[1170] 7. The server sends the generated feedback to the device so that the user can view it.

[1171] output:

[1172] Responses generated by generative AI models

[1173] Detailed feedback after the conversation

[1174] (Application example 1)

[1175] 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."

[1176] In modern brick-and-mortar stores, improving the quality of customer service requires continuous improvement of the customer service skills of store clerks. However, conventional training methods make it difficult to acquire efficient conversational skills that meet individual needs, and it is also difficult to receive feedback in real time. The present invention aims to solve these problems and provide a system that allows store clerks to efficiently and effectively improve their customer service skills.

[1177] 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.

[1178] In this invention, the server includes server means for communicating with a device for user conversation practice, storage means for storing user attribute data and past conversation practice data, generation means for generating conversation scenarios based on a generative AI model, communication means for transmitting feedback on the generated conversation scenarios and conversations to the user's device, and a system used by users to improve their customer service skills. This allows store clerks to practice conversations optimally according to their individual needs and receive feedback in real time, thereby effectively improving their skills.

[1179] "User" refers to a person who uses the system to practice conversation, and in particular to a store clerk who aims to improve their customer service skills in a brick-and-mortar store.

[1180] "Device" refers to the hardware used to communicate with the server and practice conversation, and is primarily a portable computer such as a smartphone or tablet.

[1181] The "server means" is a device that executes processes for conversation practice and communicates with the user's terminal.

[1182] The "storage means" is a component that includes a database that stores user attribute data and past conversation practice data.

[1183] A "generative AI model" refers to an artificial intelligence program that generates a scenario for a user's conversation practice, analyzes conversation data, and generates appropriate responses.

[1184] A "generation means" is a component that has the function of automatically creating a conversation scenario using a generative AI model.

[1185] A "communication means" is a component that has the function of transmitting the generated conversation scenario and feedback to the user's device.

[1186] The "feedback generation means" is a component that has the function of creating detailed feedback based on the user's conversation data.

[1187] The "personalization means" is a component that has the function of generating different scenarios suited to individual users based on the user's identification information.

[1188] The "scenario adjustment means" is a component that has the function of dynamically changing the conversation scenario according to the user's past feedback.

[1189] A "prompt generation means" is a component that has the function of creating a prompt sentence to be input into a generative AI model.

[1190] This invention is a conversation practice system for enabling store clerks to efficiently improve their customer service skills, and is implemented using the following hardware and software.

[1191] Hardware

[1192] Server: Generates conversation scenarios, analyzes conversation data, and generates feedback.

[1193] Device: A device (smartphone, tablet, etc.) on which a user practices conversation.

[1194] software

[1195] Generative AI model: Generates conversation scenarios and analyzes user input data.

[1196] Storage means: A database that stores user attribute data and past conversation practice data.

[1197] Communication means: The server transmits conversation scenarios and feedback to the terminal.

[1198] The server communicates with a device on which the user practices conversation, and stores the user's attribute data and past conversation practice data in a storage means. It then generates a conversation scenario based on the generative AI model and transmits the scenario to the user's device via a communication means. The user practices conversation based on the generated scenario, and the conversation data is transmitted to the server. The server analyzes the received conversation data using the generative AI model, generates appropriate feedback, and provides it to the user.

[1199] This allows users to practice conversations optimally according to their individual needs and receive real-time feedback, effectively improving their skills. Furthermore, scenario generation and feedback take into account the user's identification information and past feedback, and the scenario is dynamically adjusted.

[1200] Specific operation example

[1201] 1. User Registration and Login

[1202] When a user uses the system for the first time, they enter their information to complete registration and then log in.

[1203] 2. Conversation scenario selection and generation

[1204] When the user selects the "conversation practice" menu, the server retrieves the user's attribute data and past practice data from an existing database.

[1205] A generative AI model generates appropriate conversation scenarios based on this data.

[1206] 3. Conversation practice and feedback

[1207] The user follows a scenario and practices conversation in an interactive format.

[1208] The server analyzes the user's input in real time and provides an appropriate response.

[1209] After completing the exercise, the server generates detailed feedback and sends it to the user.

[1210] Prompt Sentence Examples

[1211] The following prompt sentence is fed into the generative AI model:

[1212] "How can we keep you informed about promotions that might be of interest to you?"

[1213] "What are some examples of questions you can ask to accurately understand a customer's needs while serving them?"

[1214] The system of the present invention allows store staff in brick-and-mortar stores to continuously and effectively improve their customer service skills.

[1215] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1216] Step 1:

[1217] (User registration and login)

[1218] Input: The user enters their name, email address, and password.

[1219] Processing: The terminal sends the user input to the server, and the server stores the input data in a storage means and sends a registration completion message to the terminal.

[1220] Output: The user account is created and the user can log in to the system.

[1221] Specific operation: The user clicks the "New Registration" button, enters the required information in the registration form, and clicks the "Submit" button. The server verifies the validity of the data and saves it to the database.

[1222] Step 2:

[1223] (Selection and generation of conversation scenarios)

[1224] Input: The user selects the "Conversation Practice" menu.

[1225] Processing: The server retrieves the user's attribute data and past conversation practice data from the storage means, and generates an appropriate conversation scenario based on the generative AI model.

[1226] Output: The generated conversation scenario is sent to the terminal and displayed to the user.

[1227] Specific operation: When a user selects the "Conversation Practice" menu, the server retrieves the user's information from the database, and the generative AI model generates a scenario. The scenario is sent to the device and displayed on the user's screen.

[1228] Step 3:

[1229] (Conversation practice and feedback)

[1230] Input: The user inputs a conversation based on the scenario.

[1231] Processing: The device sends the user's input data to the server, the generative AI model generates an appropriate response, and the server sends the response to the device.

[1232] Output: A conversational exchange continues and feedback is generated after the practice session.

[1233] Specific operation: When the user enters text corresponding to the scenario displayed on the screen and clicks the send button, the data is sent to the server. The generative AI model analyzes the data, generates an appropriate response, and sends it back to the device. Once the conversation is over, the server analyzes the entire conversation data, generates feedback, and sends it to the device.

[1234] Step 4:

[1235] (Check feedback)

[1236] Input: User makes a request for feedback confirmation.

[1237] Processing: The server retrieves the generated feedback data from the storage means and transmits it to the terminal.

[1238] Output: Feedback is displayed on the user's device.

[1239] Specific operation: When a user selects a feedback menu and sends a request, the server retrieves the corresponding feedback data from the database, sends it to the terminal, and displays it to the user.

[1240] Step 5:

[1241] (Generate prompt sentence)

[1242] Input: User identity and past feedback data.

[1243] Processing: The server analyzes past feedback data and generates and sends prompt sentences to the generative AI model.

[1244] Output: The prompt sentence is sent to the generative AI model and used to generate new conversation scenarios.

[1245] Specific operation: The server analyzes past feedback data based on the user's identification information and generates a prompt such as, "Please tell us how we can provide you with campaign information that might interest you." The prompt is then sent to the generative AI model and used to generate new scenarios.

[1246] 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.

[1247] The present invention provides a system for enabling users to efficiently learn and improve the conversation skills required for floor ladies. The system includes a server, a terminal, a database, a generative artificial intelligence (AI), and an emotion engine.

[1248] Overall system flow

[1249] 1. User Registration and Login

[1250] First, a user accesses the system using their own terminal and registers or logs in. The server stores the user's registration data in a database and authenticates the login information.

[1251] 2. Conversation scenario selection and generation

[1252] After logging in, the user selects a conversation practice via the terminal. The server retrieves the user's profile data and past practice data from the database, and generates an appropriate conversation scenario based on the generative artificial intelligence and emotion engine. The scenario is sent to the terminal and displayed to the user.

[1253] 3. Conversation progression, emotion recognition, and feedback

[1254] When a user practices conversation, they interact with the generation AI via their device. The generation AI analyzes the user's input data, and its emotion engine recognizes their emotions. Based on this, it provides appropriate responses and methods for progressing the conversation. After the conversation ends, the server sends the conversation data and emotion data to the generation AI, which generates detailed feedback. This allows the user to receive specific advice on how to improve their conversation skills.

[1255] Specific examples

[1256] User Registration and Login

[1257] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[1258] 2. The server sends a user registration form to the terminal, and the user enters the required information (name, email address, password).

[1259] 3. When the user clicks the "Submit" button, the terminal sends the data to the server. The server validates the data and stores it in the database. In addition, a message indicating completion of registration is displayed on the terminal.

[1260] 4. Next, when the user clicks the "Login" button, the server sends a login form to the terminal, where the user enters their email address and password and clicks "Submit."

[1261] 5. The server authenticates the data and initiates the user session.

[1262] Conversation scenario selection and generation

[1263] 1. The user selects the "Conversation Practice" menu on the device.

[1264] 2. The server retrieves the user's profile data and past practice data from the database.

[1265] 3. Generative AI and emotion engine analyze user data and generate appropriate conversation scenarios.

[1266] 4. The generated scenario is sent to the terminal via the server and displayed to the user.

[1267] Conversation progression, emotion recognition, and feedback

[1268] 1. The user types "Hello, how is your day going?" into the terminal.

[1269] 2. The terminal sends the input data to the server.

[1270] 3. The server sends the input data to the generation AI, which analyzes the data.

[1271] 4. The emotion engine recognizes the user's emotions, and the generative AI generates an appropriate response based on that (e.g., "You look like you're having fun. Did something special happen today?").

[1272] 5. The server sends the response data received from the generation AI and emotion engine to the device, and the device displays the response message to the user.

[1273] 6. After the conversation practice is completed, the server sends all conversation data and emotion data to the generation AI and asks it to generate an evaluation and feedback.

[1274] 7. Generative AI analyzes the data and generates detailed feedback.

[1275] 8. The server sends feedback data to the device so that the user can review it (e.g., "I liked how natural the conversation was. Next time, try asking more open-ended questions. Also, you seemed a little nervous, so try practicing ways to relax.").

[1276] Continuous skill development

[1277] 1. The user selects the "Conversation Practice" menu again.

[1278] 2. The server asks the generative AI and emotion engine to generate new conversation scenarios based on past feedback and learning history.

[1279] 3. The generative AI and emotion engine generate an appropriate scenario and send it back to the server.

[1280] 4. The server sends the new scenario to the terminal, which displays the new scenario and prompts the user to start a conversation.

[1281] Through these processes, users can continuously improve their conversation skills and emotion recognition abilities. The system provides scenarios and feedback optimized for each user, allowing for personalized training.

[1282] The processing flow will be explained below.

[1283] User registration and login process steps

[1284] User Registration

[1285] Step 1:

[1286] The user clicks the "New Registration" button on the device.

[1287] The terminal displays a user registration form.

[1288] Step 2:

[1289] The user enters their name, email address, and password into the form and clicks the "Submit" button.

[1290] The terminal sends the input data to the server.

[1291] Step 3:

[1292] The server receives the input data and performs validation (e.g., checking for duplicate email addresses, matching passwords).

[1293] If the verification is successful, the server stores the user information in a database.

[1294] Step 4:

[1295] The server sends a registration completion message to the terminal.

[1296] The device will display a registration complete message.

[1297] Log in

[1298] Step 5:

[1299] The user clicks the "Login" button on the device.

[1300] The terminal displays a login form.

[1301] Step 6:

[1302] The user enters their email address and password and clicks the "Submit" button.

[1303] The terminal sends the input data to the server.

[1304] Step 7:

[1305] The server receives the input data and checks it against information in a database.

[1306] If the match is successful, the server starts the user session.

[1307] Processing steps for selecting and generating conversation scenarios

[1308] Step 8:

[1309] The user selects the "conversation practice" menu on the terminal.

[1310] The terminal transmits the selection data to the server.

[1311] Step 9:

[1312] The server retrieves the user's profile data and past practice data from the database.

[1313] The server sends this data to the generation AI and emotion engine, requesting them to generate a conversation scenario.

[1314] Step 10:

[1315] Generative AI and emotion engines analyze user data and generate appropriate conversation scenarios.

[1316] The generated scenario is sent back to the server.

[1317] Step 11:

[1318] The server sends the generated scenario to the terminal.

[1319] The terminal displays the scenario and prompts the user to start a conversation.

[1320] Conversation progression, emotion recognition, and feedback processing steps

[1321] Step 12:

[1322] A user types into a terminal, "Hello, how is your day going?"

[1323] The terminal sends the input data to the server.

[1324] Step 13:

[1325] The server sends the input data to the generative AI and emotion engine.

[1326] The generative AI analyzes the data and the emotion engine recognizes the emotion.

[1327] Step 14:

[1328] Based on the recognition results of the emotion engine, the generative AI generates an appropriate response (e.g., "I'm having a great day. How about you?").

[1329] Response data is sent from the generation AI and emotion engine to the server.

[1330] Step 15:

[1331] The server sends the response data to the terminal.

[1332] The terminal displays the reply message to the user.

[1333] Step 16:

[1334] The user makes a new input and the terminal again sends the data to the server.

[1335] The server sends data to the generative AI and emotion engine, which then responds and recognizes emotions. This process is repeated until the end of the conversation.

[1336] Step 17:

[1337] The user ends the conversation practice (e.g., clicks the "End" button).

[1338] The terminal sends a termination signal to the server.

[1339] Step 18:

[1340] The server sends all conversational and emotional data to the generative AI and emotion engine, asking them to generate ratings and feedback.

[1341] Generative AI and emotion engines analyze data and generate detailed feedback.

[1342] Step 19:

[1343] The server receives feedback data from the generation AI and emotion engine and sends it to the device.

[1344] The device displays a feedback message to the user (e.g., "I liked how natural the conversation was. Next time, try asking more open-ended questions. Also, you seemed a little nervous; try practicing some relaxation techniques.").

[1345] Continual Skill Development Process Steps

[1346] Step 20:

[1347] The user selects the "Conversation Practice" menu again.

[1348] The terminal transmits the selection data to the server.

[1349] Step 21:

[1350] The server requests the generative AI and emotion engine to generate new conversation scenarios based on past feedback and learning history.

[1351] The generative AI and emotion engine generate appropriate scenarios and send them back to the server.

[1352] Step 22:

[1353] The server sends the new scenario to the device.

[1354] The terminal displays the new scenario and prompts the user to start a conversation.

[1355] Through these processing steps, users can continuously improve their conversation skills and emotion recognition abilities, and the system provides optimized scenarios and feedback for each user, allowing for personalized training.

[1356] Example 2

[1357] 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."

[1358] Currently, systems that allow users to efficiently learn and improve their conversation skills struggle to recognize users' emotions and provide appropriate feedback. Furthermore, it is not sufficient to generate conversation scenarios optimized for individual users; flexible scenario generation and adjustment based on each user's learning progress and emotions is required. Furthermore, there is a lack of detailed evaluation methods for improving users' conversation skills through continuous feedback.

[1359] 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.

[1360] In this invention, the server includes server means for communicating with a terminal on which a user practices conversation, database means for storing user profile data and past conversation practice data, and generation means for generating conversation scenarios based on artificial intelligence. This makes it possible to recognize user emotions using emotion recognition and analysis means and to provide optimal conversation scenarios for each user using personalization means. Furthermore, by analyzing the conversation data and emotion data and generating detailed feedback using feedback generation means, it is possible to continuously improve the user's conversation skills.

[1361] The "server means" is a device that communicates with the terminal so that the user can practice conversation, and manages and processes various data.

[1362] The "database means" is a system that stores user profile data and past conversation practice data, and searches and updates them as needed.

[1363] The "generation means" is a device or program that generates a conversation scenario based on the generation artificial intelligence and creates learning materials for the user.

[1364] The "communication means" refers to a device or method for transmitting the generated conversation scenario and feedback to the user's terminal.

[1365] The "emotion engine means" is a device or program that analyzes the user's input data, recognizes the emotion, and reflects the results in other processes.

[1366] The "analysis means" is a device or program that analyzes conversation data and emotion data and provides an appropriate response to the user.

[1367] "Personalization means" refers to a device or program that generates conversation scenarios and feedback optimized for each user based on each user's profile data and past feedback.

[1368] The present invention is a system for enabling users to efficiently learn and improve their conversation skills. This system is mainly composed of a server, a terminal, a database, a generative artificial intelligence (generative AI), and an emotion engine.

[1369] The overall system flow is as follows:

[1370] First, a user accesses the system using their own device and performs new registration or login. At this time, the server saves the user's registration data in a database and authenticates the login information. As a concrete example, a user accesses a web page on their device, enters the required information (name, email address, password) in the new registration form, and submits it. This data is sent to the server and saved in the database.

[1371] After logging in, the user selects the conversation practice menu. At this time, the server retrieves the user's profile data and past practice data from the database and generates an appropriate conversation scenario based on the generative AI and emotion engine. The generated scenario is sent to the terminal via the server and displayed to the user. For example, when the user clicks the "Conversation Practice" button, the server retrieves data from the database, and the generative AI generates a conversation scenario that asks, "Hello, how are you doing today?" and sends it to the terminal.

[1372] When a user practices a conversation, they interact with the generation AI via their device. At this time, the generation AI analyzes the user's input data, and the emotion engine recognizes the emotion to provide a more appropriate response. For example, if a user inputs "Today was a great day," the generation AI analyzes the data, and the emotion engine recognizes it as "positive." As a result, the response "That's great. Did anything special happen?" is generated and sent from the server to the device.

[1373] Once the conversation is over, the server sends all conversation and emotion data to the AI ​​to generate detailed feedback. The generated feedback is sent to the device and displayed for the user to review. For example, feedback such as "The naturalness of the conversation was good. Next time, try asking more open-ended questions. Also, you seemed a little nervous, so try practicing ways to relax." may be displayed.

[1374] Examples of prompts include "Hello, how are you today?" or "Is there anything special happening today?"

[1375] Through these processes, users can continuously improve their conversation skills. The system provides optimized scenarios and personalized feedback, enabling optimal training for each user.

[1376] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1377] Step 1:

[1378] User Registration

[1379] A user accesses the system's web page on a terminal and clicks the "New Registration" button. The server generates a user registration form and sends it to the terminal. When the user enters their name, email address, and password and clicks the "Submit" button, the data is sent to the server. The server verifies this data and saves it in a database. The input is the user's registration information, and the output is the user information saved in the database.

[1380] Step 2:

[1381] User Authentication

[1382] When the user clicks the "Login" button on the terminal, the server generates a login form and sends it to the terminal. When the user enters an email address and password and clicks the "Submit" button, the data is sent to the server. The server collates the user information in the database and performs authentication. If authentication is successful, a session ID is generated and sent to the terminal. The input is the user's login information, and the output is the authentication result and session ID.

[1383] Step 3:

[1384] Conversation scenario generation

[1385] When a user selects the "Conversation Practice" menu on their device, the server retrieves the user's profile data and past practice data from the database. Using generative artificial intelligence and an emotion engine, the server analyzes the user's data and generates an optimal conversation scenario. The generated scenario is sent to the device via the server and displayed to the user. The input is the user's profile data and past practice data, and the output is the generated conversation scenario.

[1386] Step 4:

[1387] Conversation progression

[1388] The user initiates a dialogue according to the generated scenario. Data entered by the user into the device is sent to the server, which then sends it to the generation AI and emotion engine. The generation AI analyzes the input data, and the emotion engine recognizes emotions. Based on this, an appropriate response is generated, and the server sends the response to the device. The input is the user's dialogue input, and the output is the generated response.

[1389] Step 5:

[1390] Generate feedback

[1391] Once the conversation is over, the server sends all conversation data and emotion data to the AI ​​to generate detailed feedback. The generated feedback is sent to the device and displayed to the user. The input is the conversation data and emotion data, and the output is the generated feedback.

[1392] Step 6:

[1393] Continuous skill development

[1394] Each time the user selects the "Conversation Practice" menu again, the server requests the AI ​​and emotion engine to generate a new conversation scenario based on past feedback and learning history. The generated new scenario is sent to the device via the server, and the user practices conversation based on the new scenario. The input is past feedback and learning history, and the output is the new conversation scenario.

[1395] (Application example 2)

[1396] 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."

[1397] Traditional customer service training systems lack efficient and effective methods for supporting employee conversation skill improvement. In particular, they lack a system that provides real-time emotion recognition and feedback necessary for customer service in brick-and-mortar stores, making it difficult for employees to improve their skills on demand. Furthermore, they lack the ability to generate conversation scenarios optimized for individual employees or dynamically adjust scenarios based on past feedback, making it difficult to provide personalized training.

[1398] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1399] In this invention, the server includes server means for communicating with a terminal on which a user practices conversation, database means for storing user profile data and past conversation practice data, generation means for generating conversation scenarios based on a generation artificial intelligence, communication means for transmitting feedback on the generated conversation scenarios and conversations to the user's terminal, training means for providing training to store employees to improve their customer service skills, and emotion recognition means for recognizing user emotions using an emotion recognition engine. This enables employees to receive appropriate feedback based on emotion recognition in real time and receive personalized training based on their individual profiles and past practice data.

[1400] A "server" is a central computer system in the conversation practice system that communicates with users' terminals and manages profile data and conversation practice data.

[1401] A "terminal" is a device that a user uses to practice conversation, and includes devices such as smartphones, smart glasses, and head-mounted displays.

[1402] A "database" is a storage device for storing user profile data and past conversation practice data.

[1403] "Generative AI" refers to machine learning models and algorithms that analyze user data and generate conversation scenarios and responses.

[1404] "Communication means" refers to a network communication interface for transmitting and receiving data between the terminal and the server.

[1405] "Training Tools" is a feature that provides interactive training for store employees to improve their customer service skills.

[1406] An "emotion recognition engine" is an algorithm or software that analyzes the emotions expressed by a user in response to input data and recognizes those emotions.

[1407] The "feedback generation means" is a function that generates evaluations and advice for the user based on the progress of the conversation and emotional data.

[1408] "Personalization means" is a function that generates individually optimized conversation scenarios based on the user's ID information and past data.

[1409] The "scenario adjustment means" is a function that dynamically adjusts the conversation scenario based on past feedback.

[1410] To implement this invention, specific hardware and software must be used, including a terminal for users to practice conversation, a server for managing and processing conversation data, a database for storing data, a generative AI model for generating conversation scenarios, and an emotion recognition engine.

[1411] Hardware and Software Configuration

[1412] 1. Device: The user uses a smartphone, smart glasses, or head-mounted display, which allows the user to receive interactive training.

[1413] 2. Server: The server communicates with the user's device and manages profile data and past conversation data. It includes a web server and a database server.

[1414] 3. Database: A relational database is used to store user profile data and past conversation practice data.

[1415] 4. Generative AI models: Use machine learning models to generate conversation scenarios. An example is Hugging Face's Transformers library.

[1416] 5. Emotion Recognition Engine: To analyze the user's emotions, we use an emotion recognition model, which also uses the Transformers library from Hugging Face.

[1417] Processing flow

[1418] 1. User Registration and Login:

[1419] The user accesses the server using a terminal to register or log in. The server stores the user's data in a database and performs authentication.

[1420] 2. Conversation scenario selection and generation:

[1421] After logging in, the user selects conversation practice. The server generates a conversation scenario using a generative AI model based on the user's profile data and past practice data, and sends it to the device.

[1422] 3. Conversation progression, emotion recognition, and feedback:

[1423] When a user practices a conversation, their input is sent to the server, and the generative AI model generates an appropriate response. At the same time, the emotion recognition engine analyzes emotions, and the server collects all conversation and emotion data to generate feedback.

[1424] Use of concrete examples and prompts

[1425] Examples:

[1426] When a store staff member says, "Hello, how are you today?", the emotion recognition model analyzes the user's emotions from the text and generates a response such as, "You seem happy. Did anything special happen today?" The generated feedback is then displayed as, "I liked the naturalness of the conversation. Next time, try asking more open-ended questions."

[1427] Example prompt sentence:

[1428] User profile: New staff member

[1429] Past data: In yesterday's scenario, there was feedback that "the customer service was quiet"

[1430] Generate new conversation scenario.

[1431] Using this format, employees can receive appropriate feedback based on real-time emotion recognition and personalized training based on their individual profile and past practice data.

[1432] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1433] Step 1:

[1434] A user accesses the server using a terminal to register or log in. The user's name, email address, and password are required as input, and an authentication success message or an error message is displayed as output. The server stores this data in a database and performs user authentication.

[1435] Step 2:

[1436] After logging in, the user selects the "Conversation Practice" menu on the terminal. As input, the user's selection is sent to the server, which retrieves the user's profile data and past practice data from the database. As output, an appropriate conversation scenario is generated.

[1437] Step 3:

[1438] The server inputs a prompt sentence containing the user's profile data and past practice data to the generative AI model. Based on the input data, the generative AI model generates a new conversation scenario. The output is a new conversation scenario.

[1439] Step 4:

[1440] The generated conversation scenario is sent from the server to the device and displayed to the user. The user then begins practicing on the device. As input, the user enters text according to the conversation scenario and sends it to the server. As output, an appropriate response is obtained from the generative AI model.

[1441] Step 5:

[1442] Once the user's input data is sent to the server, the emotion recognition engine analyzes the text for emotions. As input, the user's text is used, and as output, an emotion tag (e.g., joy, anger, sadness, etc.) is generated.

[1443] Step 6:

[1444] The server combines the results of the emotion recognition engine with the responses of the generative AI model to generate appropriate feedback. The server uses the user's conversational and emotional data as input, and generates detailed feedback as output.

[1445] Step 7:

[1446] The generated detailed feedback is sent from the server to the terminal and displayed to the user.As input, feedback data is sent from the server to the terminal and as output, it is visually displayed to the user.

[1447] Step 8:

[1448] The next time the user starts a conversation practice session, the server uses the generative AI model again to generate a new conversation scenario based on past feedback and learning history. Past feedback and learning history are used as input, and a new personalized scenario is generated as output.

[1449] Step 9:

[1450] The server sends the generated personalized scenario to the terminal, and the user practices conversation based on the new scenario. The user's profile and past scenario data are used as input, and the new conversation practice scenario is displayed to the user as output.

[1451] Through these processing steps, users can continuously improve their conversation skills and emotion recognition abilities, and the system provides personalized training for each user, resulting in more effective learning.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] [Fourth embodiment]

[1456] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1457] 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.

[1458] 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).

[1459] 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.

[1460] 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.

[1461] 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).

[1462] 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. 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.

[1463] 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.

[1464] 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.

[1465] 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.

[1466] 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.

[1467] 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.

[1468] 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."

[1469] This invention is a system that allows users to efficiently learn and improve the conversation skills required for floor ladies. This system consists of multiple components, such as a server, terminals, a database, and generative artificial intelligence (AI).

[1470] Overall system flow

[1471] 1. User Registration and Login

[1472] First, a user accesses the system using their own terminal and registers or logs in. The server stores the user's registration data in a database and authenticates the login information.

[1473] 2. Conversation scenario selection and generation

[1474] After logging in, the user selects a conversation practice via the terminal. The server retrieves the user's profile data and past practice data from the database and generates an appropriate conversation scenario based on the generative artificial intelligence. The scenario is sent to the terminal and displayed to the user.

[1475] 3. Conversation progression and feedback

[1476] When a user practices conversation, they interact with the generation AI via their device. The generation AI analyzes the user's input data and provides appropriate responses and methods for progressing the conversation. After the conversation is over, the server sends the conversation data to the generation AI, which generates detailed feedback. This allows the user to receive specific advice on how to improve their conversation skills.

[1477] Specific examples

[1478] User Registration and Login

[1479] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[1480] 2. The server sends a user registration form to the terminal, and the user enters the required information (name, email address, password).

[1481] 3. When the user clicks the "Submit" button, the terminal sends the data to the server. The server validates the data and stores it in the database. In addition, a registration completion message is displayed on the terminal.

[1482] 4. Next, when the user clicks the "Login" button, the server sends a login form to the terminal, where the user enters their email address and password and clicks "Submit."

[1483] 5. The server authenticates the data and initiates the user session.

[1484] Conversation scenario selection and generation

[1485] 1. The user selects the "Conversation Practice" menu on the device.

[1486] 2. The server retrieves the user's profile data and past practice data from the database.

[1487] 3. The generation AI generates an appropriate conversation scenario and sends it to the terminal via the server.

[1488] 4. The device displays the generated scenario and allows the user to start a conversation.

[1489] Conversation management and feedback

[1490] 1. The user types "Hello, how is your day going?" into the terminal.

[1491] 2. The device sends the input data to the server and requests the AI ​​to analyze it. The AI ​​then generates a response such as, "I'm having a great day. How about you?"

[1492] 3. The server receives the response from the AI ​​and sends it to the device, which displays the response to the user.

[1493] 4. After the conversation practice is completed, the server sends all the conversation data to the generation AI, which generates detailed feedback.

[1494] 5. The server sends the feedback data to the terminal so that the user can check it.

[1495] This allows users to effectively acquire and improve the conversation skills necessary for floor ladies. Furthermore, the system provides scenarios optimized for each user, enabling training tailored to individual needs.

[1496] The processing flow will be explained below.

[1497] User registration and login process steps

[1498] User Registration

[1499] Step 1:

[1500] The user clicks the "New Registration" button on the device.

[1501] The terminal displays a user registration form.

[1502] Step 2:

[1503] The user enters their name, email address, and password into the form and clicks the "Submit" button.

[1504] The terminal sends the input data to the server.

[1505] Step 3:

[1506] The server receives the input data and performs validation (e.g., checking for duplicate email addresses, matching passwords).

[1507] If the verification is successful, the server stores the user information in a database.

[1508] Step 4:

[1509] The server sends a registration completion message to the terminal.

[1510] The device will display a registration complete message.

[1511] Log in

[1512] Step 5:

[1513] The user clicks the "Login" button on the device.

[1514] The terminal displays a login form.

[1515] Step 6:

[1516] The user enters their email address and password and clicks the "Submit" button.

[1517] The terminal sends the input data to the server.

[1518] Step 7:

[1519] The server receives the input data and checks it against information in a database.

[1520] If the match is successful, the server starts the user session.

[1521] Processing steps for selecting and generating conversation scenarios

[1522] Step 8:

[1523] The user selects the "conversation practice" menu on the terminal.

[1524] The terminal transmits the selection data to the server.

[1525] Step 9:

[1526] The server retrieves the user's profile data and past practice data from the database.

[1527] The server sends this data to the generation AI and requests it to generate a conversation scenario.

[1528] Step 10:

[1529] Generative AI analyzes user data and generates appropriate conversation scenarios.

[1530] The generated scenario is sent back to the server.

[1531] Step 11:

[1532] The server sends the generated scenario to the terminal.

[1533] The terminal displays the scenario and prompts the user to start a conversation.

[1534] Steps for navigating the conversation and handling feedback

[1535] Step 12:

[1536] A user types into a terminal, "Hello, how is your day going?"

[1537] The terminal sends the input data to the server.

[1538] Step 13:

[1539] The server sends the input data to the generation AI.

[1540] Generative AI analyzes the data and generates appropriate responses.

[1541] Step 14:

[1542] The server sends the response data received from the generation AI to the terminal.

[1543] The terminal displays the reply message to the user.

[1544] Step 15:

[1545] The user makes a new input and the terminal again sends the data to the server.

[1546] The server sends data to the generating AI, which generates a response, and this process is repeated until the end of the conversation.

[1547] Step 16:

[1548] The user ends the conversation practice (e.g., clicks the "End" button).

[1549] The terminal sends a termination signal to the server.

[1550] Step 17:

[1551] The server sends all conversation data to the generation AI and asks it to generate an evaluation and feedback.

[1552] Generative AI analyzes the data and generates detailed feedback.

[1553] Step 18:

[1554] The server receives feedback data from the generated AI and sends it to the device.

[1555] The terminal displays a feedback message to the user.

[1556] Continual Skill Development Process Steps

[1557] Step 19:

[1558] The user selects the "Conversation Practice" menu again.

[1559] The terminal transmits the selection data to the server.

[1560] Step 20:

[1561] The server asks the generative AI to generate new conversation scenarios based on past feedback and learning history.

[1562] The generation AI generates an appropriate scenario and sends it back to the server.

[1563] Step 21:

[1564] The server sends the new scenario to the device.

[1565] The terminal displays the new scenario and prompts the user to start a conversation.

[1566] Through these processing steps, users can continually improve their speaking skills.

[1567] Example 1

[1568] 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."

[1569] Conventional conversation practice systems have struggled to generate optimal conversation scenarios for each user and provide immediate and appropriate feedback. This has prevented them from efficiently improving users' conversation skills. It has also been difficult to effectively utilize users' profile information and past practice data to generate personalized conversation scenarios.

[1570] 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.

[1571] In this invention, the server includes means for communicating with a terminal used by a user for conversation practice, means for storing the user's profile data and past conversation practice data, means for generating a conversation scenario based on a generative artificial intelligence model, and means for transmitting feedback on the generated conversation scenario and conversation to the user's terminal. This makes it possible to provide a conversation scenario optimized for each user and receive immediate and appropriate feedback. Furthermore, personalized scenarios can be generated based on the user's profile and past practice data, allowing users to effectively improve their skills through conversation practice based on the scenarios.

[1572] 1. "Server" means a central device that communicates with the terminals on which users practice conversation and processes data.

[1573] 2. "Terminal" means a computing device used by a user to practice speaking.

[1574] 3. "Profile Data" means basic information about a User, such as name, email address, and past practice history.

[1575] 4. "Past conversation practice data" refers to data that records the content and results of conversation practice sessions that the user has conducted in the past.

[1576] 5. "Database" refers to a system for storing and managing user profile data and past conversation practice data.

[1577] 6. "Generative AI model" refers to an AI technology that generates and analyzes conversation scenarios based on user data.

[1578] 7. "Generation means" means a process and system for generating conversation scenarios using a generative artificial intelligence model.

[1579] 8. "Personalization methods" are functions and technologies for generating different scenarios based on the user's ID.

[1580] 9. "Scenario adjustment means" refers to the functions and technologies for dynamically adjusting conversation scenarios based on past feedback.

[1581] 10. "Communication means" refers to the functions and technologies for transmitting the generated conversation scenario and feedback on the conversation to the user's device.

[1582] 11. "Feedback generation means" refers to the functions and technologies for generating detailed feedback based on user conversation data.

[1583] The present invention is a system for enabling users to efficiently learn and improve their conversation skills. This system is composed of multiple components, including a server, a terminal, a database, and a generative artificial intelligence model. The following describes how this system is specifically implemented.

[1584] First, a user accesses the system's webpage using their own device and registers or logs in. At this time, the server stores the user's input information, such as name, email address, and password, in a database and authenticates the login information. For example, the following specific operations are performed:

[1585] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[1586] 2. The server sends a user registration form to the terminal, and the user enters the required information (name, email address, password).

[1587] 3. When the user clicks the "Submit" button, the terminal sends the data to the server. The server validates the data and stores it in the database. In addition, a registration completion message is displayed on the terminal.

[1588] Next, after the user logs in, they select conversation practice. The server retrieves the user's profile data and past practice data from the database, and generates an appropriate conversation scenario based on a generative artificial intelligence model (e.g., GPT-3). The scenario is sent to the terminal and displayed to the user. The following specific operations are performed in this step:

[1589] 1. The user selects the "Conversation Practice" menu on the device.

[1590] 2. The server retrieves the user's profile data and past practice data from the database.

[1591] 3. The generative artificial intelligence model generates a conversation scenario based on the acquired data and sends it to the terminal via the server.

[1592] 4. The device displays the generated scenario and allows the user to start a conversation.

[1593] When a user practices a conversation, they interact with the Generative AI via their device. The Generative AI analyzes the user's input data and provides appropriate responses and methods for progressing the conversation. For example, if the user types, "Hello, how are you today?", the Generative AI will generate a response such as, "I'm having a great day. How about you?" The process proceeds as follows:

[1594] 1. The user types "Hello, how is your day going?" into the terminal.

[1595] 2. The terminal sends the input data to the server and requests the generative artificial intelligence model to analyze it.

[1596] 3. The generative artificial intelligence model generates a response and sends it to the terminal via the server.

[1597] 4. The terminal displays the response to the user.

[1598] After the conversation practice is completed, the server sends the conversation data to the generative AI model, which generates detailed feedback, including specific advice such as "It would be good to speed up the conversation." This feedback is then sent from the server to the device for the user to review.

[1599] This allows users to receive specific advice on how to improve their conversation skills. The system provides scenarios and feedback optimized for each user, enabling training tailored to individual needs.

[1600] For example, you might input the following prompt into a generator AI:

[1601] "What's your name?" "What are your hobbies?" "Hello, how are you today?"

[1602] Such a system allows users to efficiently acquire conversation skills and improve the techniques required for a floor lady.

[1603] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1604] Step 1:

[1605] User Registration and Login

[1606] input:

[1607] User registration request, name, email address, password

[1608] Login request, email address, password

[1609] Specific actions and data processing:

[1610] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[1611] 2. The server sends a user registration form to the device, which includes fields for entering name, email address, and password.

[1612] 3. The user enters the necessary information and presses the "Send" button. The terminal sends the input data to the server.

[1613] 4. The server verifies the data sent and stores it in the database if it is correct. If the information is invalid, it returns an error message to the terminal.

[1614] 5. When the user clicks the "Login" button, the server sends the login form to the terminal.

[1615] 6. The user enters their email address and password and clicks the "Submit" button. The device sends this information to the server.

[1616] 7. The server retrieves the email address from the database and verifies the password.

[1617] 8. If authentication is successful, the server starts the user session and redirects to the main menu, otherwise it displays an error message on the terminal.

[1618] output:

[1619] Registration completion message

[1620] Login success or failure message

[1621] Step 2:

[1622] Conversation scenario selection and generation

[1623] input:

[1624] User conversation practice menu selection

[1625] Profile Data

[1626] Past practice data

[1627] Specific actions and data processing:

[1628] 1. The user selects the "Conversation Practice" menu on the device.

[1629] 2. The server retrieves the user's profile data and past practice data from the database.

[1630] 3. The server passes this data to a generative artificial intelligence model (e.g., GPT-3) and requests it to generate a conversation scenario.

[1631] 4. The generative AI model generates a conversation scenario based on the data, and the scenario is created as a prompt sentence.

[1632] 5. The server sends the generated scenario to the terminal, which displays it to the user.

[1633] output:

[1634] Conversation scenario

[1635] Step 3:

[1636] Conversation management and feedback

[1637] input:

[1638] User conversation input data

[1639] System-generated conversation scenario

[1640] Dynamic feedback requests during conversations

[1641] Specific actions and data processing:

[1642] 1. The user enters the conversation content (e.g., "Hello, how are you doing today?") into the text box on the device and clicks the "Send" button.

[1643] 2. The device sends the input data to the server and requests the generative AI model to analyze it.

[1644] 3. The generative AI model generates a response based on the user's input and returns it to the server.

[1645] 4. The server sends the response to the terminal, which displays the response to the user.

[1646] 5. Once the conversation practice is completed, the server sends all the conversation data to the generative AI model and asks it to generate detailed feedback.

[1647] 6. The generative AI model analyzes the content of the conversation and the user's responses, and generates feedback including specific advice and areas for improvement (e.g., "It would be better to speed up the conversation").

[1648] 7. The server sends the generated feedback to the device so that the user can view it.

[1649] output:

[1650] Responses generated by generative AI models

[1651] Detailed feedback after the conversation

[1652] (Application example 1)

[1653] 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."

[1654] In modern brick-and-mortar stores, improving the quality of customer service requires continuous improvement of the customer service skills of store clerks. However, conventional training methods make it difficult to acquire efficient conversational skills that meet individual needs, and it is also difficult to receive feedback in real time. The present invention aims to solve these problems and provide a system that allows store clerks to efficiently and effectively improve their customer service skills.

[1655] 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.

[1656] In this invention, the server includes server means for communicating with a device for user conversation practice, storage means for storing user attribute data and past conversation practice data, generation means for generating conversation scenarios based on a generative AI model, communication means for transmitting feedback on the generated conversation scenarios and conversations to the user's device, and a system used by users to improve their customer service skills. This allows store clerks to practice conversations optimally according to their individual needs and receive feedback in real time, thereby effectively improving their skills.

[1657] "User" refers to a person who uses the system to practice conversation, and in particular to a store clerk who aims to improve their customer service skills in a brick-and-mortar store.

[1658] "Device" refers to the hardware used to communicate with the server and practice conversation, and is primarily a portable computer such as a smartphone or tablet.

[1659] The "server means" is a device that executes processes for conversation practice and communicates with the user's terminal.

[1660] The "storage means" is a component that includes a database that stores user attribute data and past conversation practice data.

[1661] A "generative AI model" refers to an artificial intelligence program that generates a scenario for a user's conversation practice, analyzes conversation data, and generates appropriate responses.

[1662] A "generation means" is a component that has the function of automatically creating a conversation scenario using a generative AI model.

[1663] A "communication means" is a component that has the function of transmitting the generated conversation scenario and feedback to the user's device.

[1664] The "feedback generation means" is a component that has the function of creating detailed feedback based on the user's conversation data.

[1665] The "personalization means" is a component that has the function of generating different scenarios suited to individual users based on the user's identification information.

[1666] The "scenario adjustment means" is a component that has the function of dynamically changing the conversation scenario according to the user's past feedback.

[1667] A "prompt generation means" is a component that has the function of creating a prompt sentence to be input into a generative AI model.

[1668] This invention is a conversation practice system for enabling store clerks to efficiently improve their customer service skills, and is implemented using the following hardware and software.

[1669] Hardware

[1670] Server: Generates conversation scenarios, analyzes conversation data, and generates feedback.

[1671] Device: A device (smartphone, tablet, etc.) on which a user practices conversation.

[1672] software

[1673] Generative AI model: Generates conversation scenarios and analyzes user input data.

[1674] Storage means: A database that stores user attribute data and past conversation practice data.

[1675] Communication means: The server transmits conversation scenarios and feedback to the terminal.

[1676] The server communicates with a device on which the user practices conversation, and stores the user's attribute data and past conversation practice data in a storage means. It then generates a conversation scenario based on the generative AI model and transmits the scenario to the user's device via a communication means. The user practices conversation based on the generated scenario, and the conversation data is transmitted to the server. The server analyzes the received conversation data using the generative AI model, generates appropriate feedback, and provides it to the user.

[1677] This allows users to practice conversations optimally according to their individual needs and receive real-time feedback, effectively improving their skills. Furthermore, scenario generation and feedback take into account the user's identification information and past feedback, and the scenario is dynamically adjusted.

[1678] Specific operation example

[1679] 1. User Registration and Login

[1680] When a user uses the system for the first time, they enter their information to complete registration and then log in.

[1681] 2. Conversation scenario selection and generation

[1682] When the user selects the "conversation practice" menu, the server retrieves the user's attribute data and past practice data from an existing database.

[1683] A generative AI model generates appropriate conversation scenarios based on this data.

[1684] 3. Conversation practice and feedback

[1685] The user follows a scenario and practices conversation in an interactive format.

[1686] The server analyzes the user's input in real time and provides an appropriate response.

[1687] After completing the exercise, the server generates detailed feedback and sends it to the user.

[1688] Prompt Sentence Examples

[1689] The following prompt sentence is fed into the generative AI model:

[1690] "How can we keep you informed about promotions that might be of interest to you?"

[1691] "What are some examples of questions you can ask to accurately understand a customer's needs while serving them?"

[1692] The system of the present invention allows store staff in brick-and-mortar stores to continuously and effectively improve their customer service skills.

[1693] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1694] Step 1:

[1695] (User registration and login)

[1696] Input: The user enters their name, email address, and password.

[1697] Processing: The terminal sends the user input to the server, and the server stores the input data in a storage means and sends a registration completion message to the terminal.

[1698] Output: The user account is created and the user can log in to the system.

[1699] Specific operation: The user clicks the "New Registration" button, enters the required information in the registration form, and clicks the "Submit" button. The server verifies the validity of the data and saves it to the database.

[1700] Step 2:

[1701] (Selection and generation of conversation scenarios)

[1702] Input: The user selects the "Conversation Practice" menu.

[1703] Processing: The server retrieves the user's attribute data and past conversation practice data from the storage means, and generates an appropriate conversation scenario based on the generative AI model.

[1704] Output: The generated conversation scenario is sent to the terminal and displayed to the user.

[1705] Specific operation: When a user selects the "Conversation Practice" menu, the server retrieves the user's information from the database, and the generative AI model generates a scenario. The scenario is sent to the device and displayed on the user's screen.

[1706] Step 3:

[1707] (Conversation practice and feedback)

[1708] Input: The user inputs a conversation based on the scenario.

[1709] Processing: The device sends the user's input data to the server, the generative AI model generates an appropriate response, and the server sends the response to the device.

[1710] Output: A conversational exchange continues and feedback is generated after the practice session.

[1711] Specific operation: When the user enters text corresponding to the scenario displayed on the screen and clicks the send button, the data is sent to the server. The generative AI model analyzes the data, generates an appropriate response, and sends it back to the device. Once the conversation is over, the server analyzes the entire conversation data, generates feedback, and sends it to the device.

[1712] Step 4:

[1713] (Check feedback)

[1714] Input: User makes a request for feedback confirmation.

[1715] Processing: The server retrieves the generated feedback data from the storage means and transmits it to the terminal.

[1716] Output: Feedback is displayed on the user's device.

[1717] Specific operation: When a user selects a feedback menu and sends a request, the server retrieves the corresponding feedback data from the database, sends it to the terminal, and displays it to the user.

[1718] Step 5:

[1719] (Generate prompt sentence)

[1720] Input: User identity and past feedback data.

[1721] Processing: The server analyzes past feedback data and generates and sends prompt sentences to the generative AI model.

[1722] Output: The prompt sentence is sent to the generative AI model and used to generate new conversation scenarios.

[1723] Specific operation: The server analyzes past feedback data based on the user's identification information and generates a prompt such as, "Please tell us how we can provide you with campaign information that might interest you." The prompt is then sent to the generative AI model and used to generate new scenarios.

[1724] 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.

[1725] The present invention provides a system for enabling users to efficiently learn and improve the conversation skills required for floor ladies. The system includes a server, a terminal, a database, a generative artificial intelligence (AI), and an emotion engine.

[1726] Overall system flow

[1727] 1. User Registration and Login

[1728] First, a user accesses the system using their own terminal and registers or logs in. The server stores the user's registration data in a database and authenticates the login information.

[1729] 2. Conversation scenario selection and generation

[1730] After logging in, the user selects a conversation practice via the terminal. The server retrieves the user's profile data and past practice data from the database, and generates an appropriate conversation scenario based on the generative artificial intelligence and emotion engine. The scenario is sent to the terminal and displayed to the user.

[1731] 3. Conversation progression, emotion recognition, and feedback

[1732] When a user practices conversation, they interact with the generation AI via their device. The generation AI analyzes the user's input data, and its emotion engine recognizes their emotions. Based on this, it provides appropriate responses and methods for progressing the conversation. After the conversation ends, the server sends the conversation data and emotion data to the generation AI, which generates detailed feedback. This allows the user to receive specific advice on how to improve their conversation skills.

[1733] Specific examples

[1734] User Registration and Login

[1735] 1. The user accesses the system's web page on their device and clicks the "New Registration" button.

[1736] 2. The server sends a user registration form to the terminal, and the user enters the required information (name, email address, password).

[1737] 3. When the user clicks the "Submit" button, the terminal sends the data to the server. The server validates the data and stores it in the database. In addition, a message indicating completion of registration is displayed on the terminal.

[1738] 4. Next, when the user clicks the "Login" button, the server sends a login form to the terminal, where the user enters their email address and password and clicks "Submit."

[1739] 5. The server authenticates the data and initiates the user session.

[1740] Conversation scenario selection and generation

[1741] 1. The user selects the "Conversation Practice" menu on the device.

[1742] 2. The server retrieves the user's profile data and past practice data from the database.

[1743] 3. Generative AI and emotion engine analyze user data and generate appropriate conversation scenarios.

[1744] 4. The generated scenario is sent to the terminal via the server and displayed to the user.

[1745] Conversation progression, emotion recognition, and feedback

[1746] 1. The user types "Hello, how is your day going?" into the terminal.

[1747] 2. The terminal sends the input data to the server.

[1748] 3. The server sends the input data to the generation AI, which analyzes the data.

[1749] 4. The emotion engine recognizes the user's emotions, and the generative AI generates an appropriate response based on that (e.g., "You look like you're having fun. Did something special happen today?").

[1750] 5. The server sends the response data received from the generation AI and emotion engine to the device, and the device displays the response message to the user.

[1751] 6. After the conversation practice is completed, the server sends all conversation data and emotion data to the generation AI and asks it to generate an evaluation and feedback.

[1752] 7. Generative AI analyzes the data and generates detailed feedback.

[1753] 8. The server sends feedback data to the device so that the user can review it (e.g., "I liked how natural the conversation was. Next time, try asking more open-ended questions. Also, you seemed a little nervous, so try practicing ways to relax.").

[1754] Continuous skill development

[1755] 1. The user selects the "Conversation Practice" menu again.

[1756] 2. The server asks the generative AI and emotion engine to generate new conversation scenarios based on past feedback and learning history.

[1757] 3. The generative AI and emotion engine generate an appropriate scenario and send it back to the server.

[1758] 4. The server sends the new scenario to the terminal, which displays the new scenario and prompts the user to start a conversation.

[1759] Through these processes, users can continuously improve their conversation skills and emotion recognition abilities. The system provides scenarios and feedback optimized for each user, allowing for personalized training.

[1760] The processing flow will be explained below.

[1761] User registration and login process steps

[1762] User Registration

[1763] Step 1:

[1764] The user clicks the "New Registration" button on the device.

[1765] The terminal displays a user registration form.

[1766] Step 2:

[1767] The user enters their name, email address, and password into the form and clicks the "Submit" button.

[1768] The terminal sends the input data to the server.

[1769] Step 3:

[1770] The server receives the input data and performs validation (e.g., checking for duplicate email addresses, matching passwords).

[1771] If the verification is successful, the server stores the user information in a database.

[1772] Step 4:

[1773] The server sends a registration completion message to the terminal.

[1774] The device will display a registration complete message.

[1775] Log in

[1776] Step 5:

[1777] The user clicks the "Login" button on the device.

[1778] The terminal displays a login form.

[1779] Step 6:

[1780] The user enters their email address and password and clicks the "Submit" button.

[1781] The terminal sends the input data to the server.

[1782] Step 7:

[1783] The server receives the input data and checks it against information in a database.

[1784] If the match is successful, the server starts the user session.

[1785] Processing steps for selecting and generating conversation scenarios

[1786] Step 8:

[1787] The user selects the "conversation practice" menu on the terminal.

[1788] The terminal transmits the selection data to the server.

[1789] Step 9:

[1790] The server retrieves the user's profile data and past practice data from the database.

[1791] The server sends this data to the generation AI and emotion engine, requesting them to generate a conversation scenario.

[1792] Step 10:

[1793] Generative AI and emotion engines analyze user data and generate appropriate conversation scenarios.

[1794] The generated scenario is sent back to the server.

[1795] Step 11:

[1796] The server sends the generated scenario to the terminal.

[1797] The terminal displays the scenario and prompts the user to start a conversation.

[1798] Conversation progression, emotion recognition, and feedback processing steps

[1799] Step 12:

[1800] A user types into a terminal, "Hello, how is your day going?"

[1801] The terminal sends the input data to the server.

[1802] Step 13:

[1803] The server sends the input data to the generative AI and emotion engine.

[1804] The generative AI analyzes the data and the emotion engine recognizes the emotion.

[1805] Step 14:

[1806] Based on the recognition results of the emotion engine, the generative AI generates an appropriate response (e.g., "I'm having a great day. How about you?").

[1807] Response data is sent from the generation AI and emotion engine to the server.

[1808] Step 15:

[1809] The server sends the response data to the terminal.

[1810] The terminal displays the reply message to the user.

[1811] Step 16:

[1812] The user makes a new input and the terminal again sends the data to the server.

[1813] The server sends data to the generative AI and emotion engine, which then responds and recognizes emotions. This process is repeated until the end of the conversation.

[1814] Step 17:

[1815] The user ends the conversation practice (e.g., clicks the "End" button).

[1816] The terminal sends a termination signal to the server.

[1817] Step 18:

[1818] The server sends all conversational and emotional data to the generative AI and emotion engine, asking them to generate ratings and feedback.

[1819] Generative AI and emotion engines analyze data and generate detailed feedback.

[1820] Step 19:

[1821] The server receives feedback data from the generation AI and emotion engine and sends it to the device.

[1822] The device displays a feedback message to the user (e.g., "I liked how natural the conversation was. Next time, try asking more open-ended questions. Also, you seemed a little nervous; try practicing some relaxation techniques.").

[1823] Continual Skill Development Process Steps

[1824] Step 20:

[1825] The user selects the "Conversation Practice" menu again.

[1826] The terminal transmits the selection data to the server.

[1827] Step 21:

[1828] The server requests the generative AI and emotion engine to generate new conversation scenarios based on past feedback and learning history.

[1829] The generative AI and emotion engine generate appropriate scenarios and send them back to the server.

[1830] Step 22:

[1831] The server sends the new scenario to the device.

[1832] The terminal displays the new scenario and prompts the user to start a conversation.

[1833] Through these processing steps, users can continuously improve their conversation skills and emotion recognition abilities, and the system provides optimized scenarios and feedback for each user, allowing for personalized training.

[1834] Example 2

[1835] 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."

[1836] Currently, systems that allow users to efficiently learn and improve their conversation skills struggle to recognize users' emotions and provide appropriate feedback. Furthermore, it is not sufficient to generate conversation scenarios optimized for individual users; flexible scenario generation and adjustment based on each user's learning progress and emotions is required. Furthermore, there is a lack of detailed evaluation methods for improving users' conversation skills through continuous feedback.

[1837] 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.

[1838] In this invention, the server includes server means for communicating with a terminal on which a user practices conversation, database means for storing user profile data and past conversation practice data, and generation means for generating conversation scenarios based on artificial intelligence. This makes it possible to recognize user emotions using emotion recognition and analysis means and to provide optimal conversation scenarios for each user using personalization means. Furthermore, by analyzing the conversation data and emotion data and generating detailed feedback using feedback generation means, it is possible to continuously improve the user's conversation skills.

[1839] The "server means" is a device that communicates with the terminal so that the user can practice conversation, and manages and processes various data.

[1840] The "database means" is a system that stores user profile data and past conversation practice data, and searches and updates them as needed.

[1841] The "generation means" is a device or program that generates a conversation scenario based on the generation artificial intelligence and creates learning materials for the user.

[1842] The "communication means" refers to a device or method for transmitting the generated conversation scenario and feedback to the user's terminal.

[1843] The "emotion engine means" is a device or program that analyzes the user's input data, recognizes the emotion, and reflects the results in other processes.

[1844] The "analysis means" is a device or program that analyzes conversation data and emotion data and provides an appropriate response to the user.

[1845] "Personalization means" refers to a device or program that generates conversation scenarios and feedback optimized for each user based on each user's profile data and past feedback.

[1846] The present invention is a system for enabling users to efficiently learn and improve their conversation skills. This system is mainly composed of a server, a terminal, a database, a generative artificial intelligence (generative AI), and an emotion engine.

[1847] The overall system flow is as follows:

[1848] First, a user accesses the system using their own device and performs new registration or login. At this time, the server saves the user's registration data in a database and authenticates the login information. As a concrete example, a user accesses a web page on their device, enters the required information (name, email address, password) in the new registration form, and submits it. This data is sent to the server and saved in the database.

[1849] After logging in, the user selects the conversation practice menu. At this time, the server retrieves the user's profile data and past practice data from the database and generates an appropriate conversation scenario based on the generative AI and emotion engine. The generated scenario is sent to the terminal via the server and displayed to the user. For example, when the user clicks the "Conversation Practice" button, the server retrieves data from the database, and the generative AI generates a conversation scenario that asks, "Hello, how are you doing today?" and sends it to the terminal.

[1850] When a user practices a conversation, they interact with the generation AI via their device. At this time, the generation AI analyzes the user's input data, and the emotion engine recognizes the emotion to provide a more appropriate response. For example, if a user inputs "Today was a great day," the generation AI analyzes the data, and the emotion engine recognizes it as "positive." As a result, the response "That's great. Did anything special happen?" is generated and sent from the server to the device.

[1851] Once the conversation is over, the server sends all conversation and emotion data to the AI ​​to generate detailed feedback. The generated feedback is sent to the device and displayed for the user to review. For example, feedback such as "The naturalness of the conversation was good. Next time, try asking more open-ended questions. Also, you seemed a little nervous, so try practicing ways to relax." may be displayed.

[1852] Examples of prompts include "Hello, how are you today?" or "Is there anything special happening today?"

[1853] Through these processes, users can continuously improve their conversation skills. The system provides optimized scenarios and personalized feedback, enabling optimal training for each user.

[1854] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1855] Step 1:

[1856] User Registration

[1857] A user accesses the system's web page on a terminal and clicks the "New Registration" button. The server generates a user registration form and sends it to the terminal. When the user enters their name, email address, and password and clicks the "Submit" button, the data is sent to the server. The server verifies this data and saves it in a database. The input is the user's registration information, and the output is the user information saved in the database.

[1858] Step 2:

[1859] User Authentication

[1860] When the user clicks the "Login" button on the terminal, the server generates a login form and sends it to the terminal. When the user enters an email address and password and clicks the "Submit" button, the data is sent to the server. The server collates the user information in the database and performs authentication. If authentication is successful, a session ID is generated and sent to the terminal. The input is the user's login information, and the output is the authentication result and session ID.

[1861] Step 3:

[1862] Conversation scenario generation

[1863] When a user selects the "Conversation Practice" menu on their device, the server retrieves the user's profile data and past practice data from the database. Using generative artificial intelligence and an emotion engine, the server analyzes the user's data and generates an optimal conversation scenario. The generated scenario is sent to the device via the server and displayed to the user. The input is the user's profile data and past practice data, and the output is the generated conversation scenario.

[1864] Step 4:

[1865] Conversation progression

[1866] The user initiates a dialogue according to the generated scenario. Data entered by the user into the device is sent to the server, which then sends it to the generation AI and emotion engine. The generation AI analyzes the input data, and the emotion engine recognizes emotions. Based on this, an appropriate response is generated, and the server sends the response to the device. The input is the user's dialogue input, and the output is the generated response.

[1867] Step 5:

[1868] Generate feedback

[1869] Once the conversation is over, the server sends all conversation data and emotion data to the AI ​​to generate detailed feedback. The generated feedback is sent to the device and displayed to the user. The input is the conversation data and emotion data, and the output is the generated feedback.

[1870] Step 6:

[1871] Continuous skill development

[1872] Each time the user selects the "Conversation Practice" menu again, the server requests the AI ​​and emotion engine to generate a new conversation scenario based on past feedback and learning history. The generated new scenario is sent to the device via the server, and the user practices conversation based on the new scenario. The input is past feedback and learning history, and the output is the new conversation scenario.

[1873] (Application example 2)

[1874] 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."

[1875] Traditional customer service training systems lack efficient and effective methods for supporting employee conversation skill improvement. In particular, they lack a system that provides real-time emotion recognition and feedback necessary for customer service in brick-and-mortar stores, making it difficult for employees to improve their skills on demand. Furthermore, they lack the ability to generate conversation scenarios optimized for individual employees or dynamically adjust scenarios based on past feedback, making it difficult to provide personalized training.

[1876] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1877] In this invention, the server includes server means for communicating with a terminal on which a user practices conversation, database means for storing user profile data and past conversation practice data, generation means for generating conversation scenarios based on a generation artificial intelligence, communication means for transmitting feedback on the generated conversation scenarios and conversations to the user's terminal, training means for providing training to store employees to improve their customer service skills, and emotion recognition means for recognizing user emotions using an emotion recognition engine. This enables employees to receive appropriate feedback based on emotion recognition in real time and receive personalized training based on their individual profiles and past practice data.

[1878] A "server" is a central computer system in the conversation practice system that communicates with users' terminals and manages profile data and conversation practice data.

[1879] A "terminal" is a device that a user uses to practice conversation, and includes devices such as smartphones, smart glasses, and head-mounted displays.

[1880] A "database" is a storage device for storing user profile data and past conversation practice data.

[1881] "Generative AI" refers to machine learning models and algorithms that analyze user data and generate conversation scenarios and responses.

[1882] "Communication means" refers to a network communication interface for transmitting and receiving data between the terminal and the server.

[1883] "Training Tools" is a feature that provides interactive training for store employees to improve their customer service skills.

[1884] An "emotion recognition engine" is an algorithm or software that analyzes the emotions expressed by a user in response to input data and recognizes those emotions.

[1885] The "feedback generation means" is a function that generates evaluations and advice for the user based on the progress of the conversation and emotional data.

[1886] "Personalization means" is a function that generates individually optimized conversation scenarios based on the user's ID information and past data.

[1887] The "scenario adjustment means" is a function that dynamically adjusts the conversation scenario based on past feedback.

[1888] To implement this invention, specific hardware and software must be used, including a terminal for users to practice conversation, a server for managing and processing conversation data, a database for storing data, a generative AI model for generating conversation scenarios, and an emotion recognition engine.

[1889] Hardware and Software Configuration

[1890] 1. Device: The user uses a smartphone, smart glasses, or head-mounted display, which allows the user to receive interactive training.

[1891] 2. Server: The server communicates with the user's device and manages profile data and past conversation data. It includes a web server and a database server.

[1892] 3. Database: A relational database is used to store user profile data and past conversation practice data.

[1893] 4. Generative AI models: Use machine learning models to generate conversation scenarios. An example is Hugging Face's Transformers library.

[1894] 5. Emotion Recognition Engine: To analyze the user's emotions, we use an emotion recognition model, which also uses the Transformers library from Hugging Face.

[1895] Processing flow

[1896] 1. User Registration and Login:

[1897] The user accesses the server using a terminal and performs new registration or login. The server stores the user's data in a database and performs authentication.

[1898] 2. Conversation scenario selection and generation:

[1899] After logging in, the user selects conversation practice. The server generates a conversation scenario using a generative AI model based on the user's profile data and past practice data, and sends it to the device.

[1900] 3. Conversation progression, emotion recognition, and feedback:

[1901] When a user practices a conversation, their input is sent to the server, and the generative AI model generates an appropriate response. At the same time, the emotion recognition engine analyzes emotions, and the server collects all conversation data and emotion data to generate feedback.

[1902] Use of concrete examples and prompts

[1903] Examples:

[1904] When a store staff member says, "Hello, how are you today?", the emotion recognition model analyzes the user's emotions from the text and generates a response such as, "You seem happy. Did anything special happen today?" The generated feedback is then displayed as, "I liked the naturalness of the conversation. Next time, try asking more open-ended questions."

[1905] Example prompt sentence:

[1906] User profile: New staff member

[1907] Past data: In yesterday's scenario, there was feedback that "the customer service was quiet"

[1908] Generate new conversation scenario.

[1909] Using this format, employees can receive appropriate feedback based on real-time emotion recognition and personalized training based on their individual profile and past practice data.

[1910] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1911] Step 1:

[1912] A user accesses the server using a terminal to register or log in. The user's name, email address, and password are required as input, and an authentication success message or an error message is displayed as output. The server stores this data in a database and performs user authentication.

[1913] Step 2:

[1914] After logging in, the user selects the "Conversation Practice" menu on the terminal. As input, the user's selection is sent to the server, which retrieves the user's profile data and past practice data from the database. As output, an appropriate conversation scenario is generated.

[1915] Step 3:

[1916] The server inputs a prompt sentence containing the user's profile data and past practice data to the generative AI model. Based on the input data, the generative AI model generates a new conversation scenario. The output is a new conversation scenario.

[1917] Step 4:

[1918] The generated conversation scenario is sent from the server to the device and displayed to the user. The user then begins practicing on the device. As input, the user enters text according to the conversation scenario and sends it to the server. As output, an appropriate response is obtained from the generative AI model.

[1919] Step 5:

[1920] Once the user's input data is sent to the server, the emotion recognition engine analyzes the text for emotions. As input, the user's text is used, and as output, an emotion tag (e.g., joy, anger, sadness, etc.) is generated.

[1921] Step 6:

[1922] The server combines the results of the emotion recognition engine with the responses of the generative AI model to generate appropriate feedback. The server uses the user's conversational and emotional data as input, and generates detailed feedback as output.

[1923] Step 7:

[1924] The generated detailed feedback is sent from the server to the terminal and displayed to the user.As input, feedback data is sent from the server to the terminal and as output, it is visually displayed to the user.

[1925] Step 8:

[1926] The next time the user starts a conversation practice session, the server uses the generative AI model again to generate a new conversation scenario based on past feedback and learning history. Past feedback and learning history are used as input, and a new personalized scenario is generated as output.

[1927] Step 9:

[1928] The server sends the generated personalized scenario to the terminal, and the user practices conversation based on the new scenario. The user's profile and past scenario data are used as input, and the new conversation practice scenario is displayed to the user as output.

[1929] Through these processing steps, users can continuously improve their conversation skills and emotion recognition abilities, and the system provides personalized training for each user, resulting in more effective learning.

[1930] 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.

[1931] 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.

[1932] 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.

[1933] 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.

[1934] 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.

[1935] 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.

[1936] 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).

[1937] 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.

[1938] 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."

[1939] 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.

[1940] 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).

[1941] 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.

[1942] 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.

[1943] 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.

[1944] 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.

[1945] 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.

[1946] 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.

[1947] 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.

[1948] 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.

[1949] 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.

[1950] 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.

[1951] The following is further disclosed regarding the above embodiment.

[1952] (Claim 1)

[1953] a server means for communicating with a terminal for user conversation practice;

[1954] a database means for storing user profile data and past conversation practice data;

[1955] a generating means for generating a conversation scenario based on a generating artificial intelligence;

[1956] a communication means for transmitting the generated conversation scenario and feedback on the conversation to a user's terminal;

[1957] A system including:

[1958] (Claim 2)

[1959] a generation artificial intelligence means for analyzing conversation data input by a user and generating an appropriate response;

[1960] feedback generation means for generating conversational feedback;

[1961] The system of claim 1 further comprising:

[1962] (Claim 3)

[1963] a personalization means for generating different scenarios based on user ID information;

[1964] a scenario adjustment means for dynamically adjusting a conversation scenario based on past feedback;

[1965] The system of claim 1 further comprising:

[1966] "Example 1"

[1967] (Claim 1)

[1968] a server means for communicating with a terminal for user conversation practice;

[1969] a database means for storing user profile data and past conversation practice data;

[1970] a generating means for generating a conversation scenario based on a generative artificial intelligence model;

[1971] a communication means for transmitting the generated conversation scenario and feedback on the conversation to a user's terminal;

[1972] A system including:

[1973] (Claim 2)

[1974] a generation artificial intelligence means for analyzing conversation data input by a user and generating an appropriate response;

[1975] feedback generation means for generating conversational feedback;

[1976] A means for analyzing input data sent from the terminal via a server;

[1977] The system of claim 1 further comprising:

[1978] (Claim 3)

[1979] a personalization means for generating different scenarios based on the user's ID;

[1980] a scenario adjustment means for dynamically adjusting a conversation scenario based on past feedback;

[1981] a means for enabling a user to respond to a conversation scenario displayed on the terminal;

[1982] The system of claim 1 further comprising:

[1983] "Application Example 1"

[1984] (Claim 1)

[1985] a server means for communicating with the device for user conversation practice;

[1986] a storage means for storing user attribute data and past conversation practice data;

[1987] A generation means for generating a conversation scenario based on a generative AI model;

[1988] a communication means for transmitting the generated conversation scenario and feedback on the conversation to a user's device;

[1989] It is characterized in that it is used by users for the purpose of improving their customer service skills.

[1990] A system including:

[1991] (Claim 2)

[1992] A generation AI model means for analyzing conversation data input by a user and generating an appropriate response;

[1993] feedback generation means for generating conversational feedback;

[1994] It is characterized by simulating actual conversations with customers.

[1995] 10. The system of claim 1.

[1996] (Claim 3)

[1997] a personalization means for generating different scenarios based on the user's identification information;

[1998] a scenario adjustment means for dynamically adjusting a conversation scenario based on past feedback;

[1999] a prompt generation means for generating a prompt sentence to be input to the generative AI model;

[2000] 2. The system of claim 1, comprising:

[2001] "Example 2: Combining Emotion Engines"

[2002] (Claim 1)

[2003] a server means for communicating with a terminal for user conversation practice;

[2004] a database means for storing user profile data and past conversation practice data;

[2005] a generating means for generating a conversation scenario based on a generating artificial intelligence;

[2006] a communication means for transmitting the generated conversation scenario and feedback on the conversation to a user's terminal;

[2007] emotion engine means for analyzing user input data and recognizing emotions;

[2008] analysis means for analyzing the conversation data and emotion data and providing an appropriate response to the user;

[2009] A personalization method that optimizes conversation scenarios and feedback for each user;

[2010] A system including:

[2011] (Claim 2)

[2012] a generation artificial intelligence means for analyzing conversation data input by a user and generating an appropriate response;

[2013] feedback generation means for generating conversational feedback;

[2014] A means for analyzing user input data based on an emotion engine and reflecting the recognition results in a response;

[2015] The system of claim 1 further comprising:

[2016] (Claim 3)

[2017] a personalization means for generating different scenarios based on user ID information;

[2018] a scenario adjustment means for dynamically adjusting a conversation scenario based on past feedback;

[2019] means for analyzing the conversation data and emotion data to generate detailed feedback after the conversation has concluded;

[2020] The system of claim 1 further comprising:

[2021] "Application example 2 when combining emotion engines"

[2022] (Claim 1)

[2023] a server means for communicating with a terminal for user conversation practice;

[2024] a database means for storing user profile data and past conversation practice data;

[2025] a generating means for generating a conversation scenario based on a generating artificial intelligence;

[2026] a communication means for transmitting the generated conversation scenario and feedback on the conversation to a user's terminal;

[2027] Training methods to provide training for brick-and-mortar store employees to improve their customer service skills;

[2028] emotion recognition means for recognizing an emotion of a user using an emotion recognition engine;

[2029] A system including:

[2030] (Claim 2)

[2031] a generation artificial intelligence means for analyzing conversation data input by a user and generating an appropriate response;

[2032] feedback generation means for generating conversational feedback;

[2033] The system of claim 1 further comprising:

[2034] (Claim 3)

[2035] a personalization means for generating different scenarios based on user ID information;

[2036] a scenario adjustment means for dynamically adjusting a conversation scenario based on past feedback;

[2037] The system of claim 1 further comprising: [Explanation of symbols]

[2038] 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 server means for communicating with a terminal for user conversation practice; a database means for storing user profile data and past conversation practice data; a generating means for generating a conversation scenario based on a generating artificial intelligence; a communication means for transmitting the generated conversation scenario and feedback on the conversation to a user's terminal; A system including:

2. a generation artificial intelligence means for analyzing conversation data input by a user and generating an appropriate response; feedback generation means for generating conversational feedback; The system of claim 1 further comprising:

3. a personalization means for generating different scenarios based on user ID information; a scenario adjustment means for dynamically adjusting a conversation scenario based on past feedback; The system of claim 1 further comprising:

Images