System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting and storing basic information of a user; means for performing a telephone call with the user by using generative artificial intelligence; and means for storing contents of a past conversation of the user and reflecting the contents in a next conversation.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] People today often feel stressed in their busy daily lives and feel that they lack someone to talk to casually. They also face the problem of not being able to find someone to talk to at certain times, such as late at night. This can increase mental stress and reduce quality of life. Therefore, there is a need to provide someone to talk to who can provide appropriate responses regardless of time or place. [Means for solving the problem]

[0005] To solve this problem, we provide a system that includes a means for inputting and saving basic user information, a means for using generative AI to communicate with the user, and a means for storing the content of the user's past conversations and reflecting it in the next conversation. Furthermore, by providing a means for selecting a specific model from among multiple AI models based on the user's selection and a means for receiving feedback from the user and using it to improve the AI ​​model, we can provide a meaningful and personalized conversation experience for the user.

[0006] "Basic user information" refers to personal information such as name, age, email address, and hobbies that a user enters when using an application.

[0007] "Generative AI" is AI that generates appropriate responses in natural language based on input from the user.

[0008] "Means for making a call" is a function that allows the user and the generative artificial intelligence to communicate through voice calls or text chat.

[0009] "Means for remembering the content of the conversation and reflecting it in the next conversation" refers to a function that stores the conversation between the user and the AI ​​in a database and uses that information to generate a response that is in line with the context during the next call.

[0010] "Multiple AI models" are types of generative AI with different algorithms and settings to fulfill different roles (e.g., chat, consultation, learning support, etc.) depending on the user's needs.

[0011] "Means of receiving feedback and using it to improve the AI ​​model" is a function that collects user feedback and evaluations and uses them to improve the quality of the AI's responses. [Brief explanation of the drawings]

[0012] [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

[0013] 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.

[0014] First, the terms used in the following description will be explained.

[0015] 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).

[0016] 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.

[0017] 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.

[0018] 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.

[0019] 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."

[0020] [First embodiment]

[0021] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] The present invention is a system that allows users to easily find someone to talk to through a call with a generative AI of their choice. Specifically, the system inputs and saves basic information about the user, uses the generative AI to talk to the user, and also has the ability to remember the content of past conversations and reflect it in the next conversation.

[0034] System Overview

[0035] The system mainly consists of a user device, a server, and a generative artificial intelligence (ChatGPT). Users install and launch the app using their smartphone or tablet.

[0036] User registration and profile settings

[0037] User:

[0038] Users install and launch the app and enter basic information such as their name, age, and hobbies, which allows the application to set up a personalized profile for the user.

[0039] Device:

[0040] The terminal transmits the information entered by the user to the server and stores it as profile data.

[0041] server:

[0042] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[0043] AI selection and call initiation

[0044] User:

[0045] From the app's home screen, users can choose from chat AI, consultation AI, or learning support AI, and then tap the "Start Call" button to begin the call.

[0046] Device:

[0047] The terminal sends the selected AI information and a call start request to the server and prepares to establish a call session.

[0048] server:

[0049] The server loads the appropriate generative artificial intelligence model based on the selected AI information, establishes a call session, and loads the user's profile data and past conversation records.

[0050] Conversation progression and data recording

[0051] Generative AI (ChatGPT):

[0052] Generative AI generates appropriate responses in real time based on user input, allowing users to easily find someone to talk to.

[0053] server:

[0054] The server records all conversations in real time and stores them in a database, which can be used in subsequent calls.

[0055] Specific examples

[0056] Let's say a user is suffering from insomnia in the middle of the night. The user opens the app, selects the consultation AI, and starts a call.

[0057] User:

[0058] "Work has been so stressful lately that I can't sleep."

[0059] Generative AI:

[0060] "That's tough. What exactly is stressing you out?"

[0061] server:

[0062] The server records this conversation and stores it for reference during the next call.

[0063] Ending a call and feedback

[0064] User:

[0065] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed.

[0066] Device:

[0067] The terminal sends a termination request and feedback information to the server.

[0068] server:

[0069] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model.

[0070] As a result, the system based on the present invention functions as a friend that can provide appropriate responses to the user 24 hours a day, 365 days a year, thereby reducing the user's mental burden and improving their quality of life.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] User:

[0074] The user installs the app on their smartphone or tablet and launches it.

[0075] Step 2:

[0076] User:

[0077] Users enter basic information such as their name, age, and email address on the account creation screen and tap the "Sign up" button.

[0078] Step 3:

[0079] Device:

[0080] The terminal transmits the input basic information to the server.

[0081] Step 4:

[0082] server:

[0083] The server verifies the received information and, if there are no problems, stores the user's basic information in a database.

[0084] The server will send a confirmation email to the user to complete the account creation.

[0085] Step 5:

[0086] User:

[0087] The user clicks on the link in the confirmation email they receive to complete their account registration.

[0088] Step 6:

[0089] User:

[0090] Users enter additional information such as hobbies, interests, and goals in the app's profile settings screen.

[0091] Step 7:

[0092] Device:

[0093] The terminal transmits the input profile information to the server.

[0094] Step 8:

[0095] server:

[0096] The server stores the received profile information in a database and generates a detailed profile for the user.

[0097] Step 9:

[0098] User:

[0099] On the home screen, users can select the AI ​​they want to talk to from among the chat AI, consultation AI, and learning support AI.

[0100] Step 10:

[0101] Device:

[0102] The device sends the selected AI information to the server and requests a call session.

[0103] Step 11:

[0104] server:

[0105] The server receives the request and loads the generative artificial intelligence model according to the selected AI, as well as the user's profile data and past conversation records.

[0106] Step 12:

[0107] User:

[0108] The user taps the "Start Call" button.

[0109] Step 13:

[0110] Device:

[0111] The terminal sends a call initiation request to the server.

[0112] Step 14:

[0113] server:

[0114] The server establishes the call session, initializes the generative AI (ChatGPT), and prepares to receive user input in real time.

[0115] Step 15:

[0116] Generative AI (ChatGPT):

[0117] Generative AI generates appropriate responses based on input from the user and replies to the user.

[0118] Step 16:

[0119] server:

[0120] The server records all conversations in real time and stores them in a database, allowing past conversation data to be accumulated and used for the next conversation.

[0121] Step 17:

[0122] User:

[0123] When the user finishes the call, he taps the "end call" button.

[0124] Step 18:

[0125] Device:

[0126] The terminal sends a call termination request to the server.

[0127] Step 19:

[0128] server:

[0129] The server terminates the call session and stores the termination information in a database.

[0130] Step 20:

[0131] User:

[0132] The user enters their thoughts and feedback on the call on the post-call screen.

[0133] Step 21:

[0134] Device:

[0135] The terminal transmits the feedback information to the server.

[0136] Step 22:

[0137] server:

[0138] The server receives the feedback and stores it in a database. The feedback information is analyzed and used to improve the generative AI model.

[0139] The above are the specific processing steps of the present invention.

[0140] Example 1

[0141] 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."

[0142] Conventional communication systems have the problem that it is difficult to provide a conversation partner in real time and lack the functionality to effectively reflect the user's past conversation content, which hinders the improvement of the user experience. Furthermore, there is no mechanism for reflecting user feedback in the AI ​​model, making it difficult to maintain and improve call quality.

[0143] 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.

[0144] In this invention, the server includes means for inputting and saving basic user information, means for using generative artificial intelligence to conduct phone calls with the user, and means for storing the content of the user's past conversations and incorporating it into the next conversation. This allows the user to find someone to talk to in real time, and the content of the past conversations can be used for the next call, improving the user experience. The server also includes means for establishing a call with a generative artificial intelligence model selected by the user, means for recording the content of the call in real time and saving it in a format that can be referenced later, and means for receiving feedback from the user after the call ends and using it to improve the artificial intelligence model. This allows the feedback to be incorporated into the artificial intelligence model, enabling the maintenance and improvement of call quality.

[0145] "Basic information" is data entered by the user for personal identification and individualization, such as name, age, hobbies, etc.

[0146] "Generative AI" is an AI system that generates responses in natural language in response to input from a user.

[0147] "Call" refers to interactive communication with a user via generative artificial intelligence.

[0148] "Profile data" is a data set that includes basic information about a user and the contents of past conversations.

[0149] A "call session" is a continuous process of interaction with a user conducted using generative artificial intelligence.

[0150] "Real-time" refers to interactions being processed and reacted to the instant they are sent or received.

[0151] "Feedback" refers to information such as evaluations, impressions, and requests for improvement provided by users after a call has ended.

[0152] A "database" is an information repository where user profile data and conversations are stored.

[0153] "Model improvement" is the process of improving the response accuracy and quality of generative artificial intelligence based on feedback from users.

[0154] The "selected generative artificial intelligence model" is the generative artificial intelligence algorithm that is most suitable for the application specified by the user.

[0155] The present invention is a system that allows users to easily find someone to talk to using a generative AI selected by the user. This system consists of a user terminal, a server, and a generative AI (e.g., ChatGPT). The following describes the specific steps and operation methods for implementing the present invention.

[0156] User registration and profile settings

[0157] User:

[0158] Users install and launch the dedicated app on their smartphone or tablet and enter basic information such as their name, age, hobbies, etc. For example, a user may say their name is "Taro," their age is "30," and their hobby is "reading."

[0159] Device:

[0160] The terminal transmits the information entered by the user to the server, including the user's name, age, and hobbies.

[0161] server:

[0162] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[0163] AI selection and call initiation

[0164] User:

[0165] From the app's home screen, users can select one of the following AIs: chat AI, consultation AI, or learning support AI, and then tap the "Start Call" button. For example, select "Consultation AI."

[0166] Device:

[0167] The terminal sends the selected AI information and a call start request to the server. The user ID and AI type are sent.

[0168] server:

[0169] The server loads the appropriate generative AI model (e.g., ChatGPT) based on the selected AI information and establishes the call session, along with the user's profile data and past conversation records.

[0170] Conversation progression and data recording

[0171] User:

[0172] The user can freely converse with the generative AI. For example, the user can input, "I've been stressed out at work lately and I can't sleep."

[0173] Generative AI (ChatGPT):

[0174] The generative AI responds, "That's tough. What exactly is stressing you out?" and generates an appropriate response in real time.

[0175] server:

[0176] The server records all conversations in real time and stores them in a database, allowing this information to be used in future calls.

[0177] Ending a call and feedback

[0178] User:

[0179] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed. For example, they can enter feedback such as "That was very helpful."

[0180] Device:

[0181] The terminal sends a termination request and feedback information to the server.

[0182] server:

[0183] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model.

[0184] Examples of concrete examples and prompts

[0185] Specific examples

[0186] Consider a situation where a user is suffering from insomnia in the middle of the night. The user opens the app, selects the consultation AI, and starts a call.

[0187] User:

[0188] "Work has been so stressful lately that I can't sleep."

[0189] Generative AI (ChatGPT):

[0190] "That's tough. What exactly is stressing you out?"

[0191] server:

[0192] The server records this conversation and stores it for reference during the next call.

[0193] Prompt Sentence Examples

[0194] "Recently, I've been having trouble sleeping because of stress at work. What can I do to make myself feel a little better?"

[0195] Through this prompt, the user can receive appropriate advice from the generative artificial intelligence.

[0196] According to the above procedures and operation methods, the system based on the present invention can function as a friend who is available to the user 24 hours a day, 365 days a year, reducing the user's mental burden and improving the quality of life.

[0197] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0198] Step 1:

[0199] User registration and profile settings

[0200] User:

[0201] Users install and launch the app and enter basic information (name, age, hobbies, etc.).

[0202] Input: User's name, age, hobbies

[0203] Output: Data sent from the basic information input screen

[0204] Device:

[0205] The device sends the information entered by the user to the server, including the user's name, age, and hobbies.

[0206] Input: Data entered by the user

[0207] Output: Data sent to the server

[0208] server:

[0209] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[0210] Input: Basic user information sent from the device

[0211] Output: User profile data stored in a database

[0212] Step 2:

[0213] AI selection and call initiation

[0214] User:

[0215] From the app's home screen, users select one of the chat AI, consultation AI, or learning support AI and tap the "Start Call" button.

[0216] Input: User's AI selection and call start request

[0217] Output: AI selection instructions and call start request

[0218] Device:

[0219] The terminal sends the selected AI information and a call start request to the server. Specifically, the AI ​​type and user ID are sent.

[0220] Input: User's AI selection information and call start request

[0221] Output: The request data sent to the server

[0222] server:

[0223] The server loads the appropriate generative artificial intelligence model based on the selected AI and establishes the call session, as well as the user's profile data and past conversation records.

[0224] Input: AI selection information and call start request sent from the device

[0225] Output: A loaded generative AI model, an established call session

[0226] Step 3:

[0227] Conversation progression and data recording

[0228] User:

[0229] The user can freely converse with the generative AI, for example, by inputting, "I've been so stressed out at work lately that I can't sleep."

[0230] Input: User spoken input

[0231] Output: prompts for generative AI

[0232] Generative AI (ChatGPT):

[0233] Based on user input, generative AI generates appropriate responses in real time, such as, "That's tough. What exactly is stressing you out?"

[0234] Input: Prompt from user

[0235] Output: The generated response

[0236] server:

[0237] The server records all conversations in real time and stores them in a database, allowing this information to be used in future calls.

[0238] Input: Conversation data between the generative AI and the user

[0239] Output: Conversation transcript stored in database

[0240] Step 4:

[0241] Ending a call and feedback

[0242] User:

[0243] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed. For example, they can enter feedback such as "That was very helpful."

[0244] Input: Tap the end call button, feedback

[0245] Output: Call termination request, feedback data

[0246] Device:

[0247] The terminal sends a termination request and feedback information to the server.

[0248] Input: User end call request, feedback

[0249] Output: Finished request and feedback data sent to the server

[0250] server:

[0251] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model.

[0252] Input: End call request sent from the device, feedback

[0253] Output: Call termination information stored in a database, feedback data for model improvement

[0254] (Application example 1)

[0255] 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."

[0256] In today's world, when users purchase products online, they need a lot of information, and if they do not receive appropriate support, their motivation to purchase decreases. Furthermore, if customers cannot resolve specific questions about a product, they risk missing out on a purchasing opportunity. Furthermore, online stores face the challenge of finding personalized product recommendations and support for each individual customer.

[0257] 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.

[0258] In this invention, the server includes means for inputting and saving basic information about the user, means for using generative artificial intelligence to communicate with the user, means for storing the content of past conversations with the user and reflecting this in the next conversation, means for using generative artificial intelligence selected by the user to provide product-related questions and advice in real time within a virtual store, means for recommending optimal products to the user based on their purchase history and the content of past conversations, and means for collecting feedback and improving support quality. This allows users to receive prompt and accurate support in real time when making online purchases, increasing their desire to purchase and enabling optimal product recommendations.

[0259] "Basic user information" refers to information necessary to form an individual profile, such as the user's name, age, and purchase history.

[0260] "Generative AI" is an AI system that generates appropriate responses in real time based on user input.

[0261] "Means for making calls" refers to a means of communication that allows the generative artificial intelligence and the user to interact in real time.

[0262] "Means for remembering the content of past conversations and reflecting it in the next conversation" refers to a means for providing continuous support by saving the content of the previous conversation and referring to it in the next conversation.

[0263] A "virtual store" is an online shopping environment used via the Internet where users can browse and purchase products.

[0264] The "means for providing product-related questions and advice in real time" is an interactive support system that can answer questions about products and how to use them on the spot when users ask questions within the virtual store.

[0265] "Purchase history" is a record of products that a user has purchased in the past.

[0266] "Means for recommending optimal products to users based on past conversation content" refers to a system that suggests products that meet individual user needs based on the user's past conversations and behavioral history.

[0267] "Means for collecting feedback and improving support quality" refers to a means for incorporating user evaluations and opinions into the system and using them to improve the performance and response accuracy of the generative artificial intelligence.

[0268] This invention is a system that provides optimal support to users in a virtual store by inputting and saving basic information about the user, using generative artificial intelligence to communicate with the user, and storing the content of past conversations and reflecting it in the next conversation. Specific embodiments for implementing this invention are described below.

[0269] System configuration

[0270] The system consists of the following main components:

[0271] 1. User Device

[0272] Using mobile devices such as smartphones and tablets, users can access virtual stores and talk to AI.

[0273] 2. Server

[0274] A high-performance database server is used to store and manage basic user information, purchase history, past conversations, etc. A cloud-based database such as AWS RDS is suitable for the server.

[0275] 3. Generative Artificial Intelligence

[0276] Using OpenAI's ChatGPT API, the system generates responses to users' real-time questions. This AI generates appropriate responses based on user input, maintaining the continuity of the conversation.

[0277] Processing Flow

[0278] 1. User Registration and Profile Settings

[0279] The application is installed on the user's device and launched. The user enters basic information such as name, age, hobbies, and purchasing history. This data is sent to the server and stored in a database.

[0280] 2. AI selection and call initiation

[0281] The user selects "Customer Support" from the application's home screen and taps the "Start Call" button. The server loads the user's profile data and loads the appropriate generative artificial intelligence model.

[0282] 3. Conversation management and data recording

[0283] The generative artificial intelligence (ChatGPT) responds to user questions and requests in real time. For example, if a user asks, "What are the features of this smartphone?", the AI ​​will respond, "This smartphone is equipped with a high-resolution camera, a state-of-the-art processor, and boasts a long battery life. It is also waterproof."

[0284] 4. Call End and Feedback

[0285] When the user finishes the call, they tap the "End Call" button and the call ends. After the call ends, the user enters feedback, which is sent to the server. The server collects the feedback and uses it to improve the AI ​​model.

[0286] Explanation of program processing

[0287] The server first stores the user's basic information in a database. Then, when the user sends a request to talk to a specific AI, the server loads the user's past conversations and launches the appropriate generative AI model. During the call, the server records the AI's responses and the user's input in real time, making them available for reference in the next conversation.

[0288] For hardware, smartphones and tablets are used as user devices, and cloud-based solutions such as AWS RDS are used as database servers. For software, OpenAI's ChatGPT API is used for generative artificial intelligence, and React Native is used for application development.

[0289] Prompt Sentence Examples

[0290] Examples of specific prompts include:

[0291] "User: Tell me about the new features on your smartphone these days. Generative AI:"

[0292] "User: What's the best way to use this camera? Generative AI:"

[0293] This allows users to receive prompt and accurate support in real time when making online purchases, which increases purchasing motivation and enables optimal product recommendations.

[0294] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0295] Step 1:

[0296] The user enters basic information

[0297] Input: Users enter basic information such as name, age, hobbies, and purchase history into an application on their smartphone or tablet.

[0298] Data processing: The terminal formats the entered user information and converts it into a format that can be sent to the server.

[0299] Output: The formatted user information is sent to the server.

[0300] Specific actions: Enter user information into the application form and tap the "Submit" button.

[0301] Step 2:

[0302] The server stores basic information

[0303] Input: Basic information of the user sent from the device.

[0304] Data Calculation: The server verifies the received user information and stores it in the database.

[0305] Output: A confirmation message that the save was successful is returned to the terminal.

[0306] Specific operation: The server checks the integrity of the received data and saves the information to the MySQL database using an INSERT statement.

[0307] Step 3:

[0308] The user selects the generative AI

[0309] Input: The user selects "Customer Support" or another AI model from the application home screen.

[0310] Data processing: The device generates a request to send information about the selected AI model to the server.

[0311] Output: The generated request is sent to the server.

[0312] What it does: Tap an option such as "Customer Support" from the application's menu.

[0313] Step 4:

[0314] The server establishes the call session

[0315] Input: The call initiation request sent from the device and the user's profile data.

[0316] Data computation: The server loads the appropriate generative artificial intelligence model and retrieves past conversation content from the database.

[0317] Output: The call session is ready to begin and the device is notified.

[0318] What it does: The server loads profile data and conversation history and sets up the AI ​​model for operation.

[0319] Step 5:

[0320] Generative AI starts the conversation

[0321] Input: The initial input from the user (e.g., "What are the features of this phone?").

[0322] Data Computation: Generative AI processes input text and generates appropriate prompts.

[0323] Output: A response based on the generated prompt is returned to the user.

[0324] What it does: Uses ChatGPT API to generate and reply to responses based on user input in real time.

[0325] Step 6:

[0326] The server records the conversation

[0327] Input: Real-time generated AI responses and user input.

[0328] Data calculation: The contents of the conversation are saved in a database and managed as history for use in future conversations.

[0329] Output: The save completion confirmation status is updated internally.

[0330] Specific operation: The server inserts and updates the received conversation data into the database in real time.

[0331] Step 7:

[0332] User ends the call and provides feedback

[0333] Input: Feedback entered by the user at the end of the call (e.g., "Thank you for your prompt response").

[0334] Data processing: The terminal sends the termination request and feedback information to the server.

[0335] Output: The feedback information is stored in the server and a completion message is returned to the user terminal.

[0336] Specific actions: The user taps the "End call" button, enters their opinion in the feedback form, and taps the "Submit" button.

[0337] Step 8:

[0338] The server improves the AI ​​model based on the feedback.

[0339] Input: Feedback information from the user.

[0340] Data calculation: The server analyzes the feedback and reflects it to improve the response accuracy of the generative AI.

[0341] Output: The AI ​​model has been improved and will be reflected in future calls.

[0342] What it does: Analyzes the feedback data and retrains the model by adding it to the generative artificial intelligence training dataset.

[0343] 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.

[0344] The present invention is a system that combines generative artificial intelligence with an emotion engine that recognizes the user's emotions. This allows for more personalized and emotionally appropriate dialogue for the user. Specifically, the system inputs and saves basic user information, uses generative artificial intelligence to communicate with the user, and has the ability to remember the content of past conversations and reflect it in the next conversation.

[0345] System Overview

[0346] The system mainly consists of a user device, a server, a generative AI (ChatGPT), and an emotion engine. Users install and launch the app on their smartphone or tablet.

[0347] User registration and profile settings

[0348] User:

[0349] Users install and launch the app and enter basic information such as their name, age, and hobbies, which allows the application to set up a personalized profile for the user.

[0350] Device:

[0351] The terminal transmits the information entered by the user to the server and stores it as profile data.

[0352] server:

[0353] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[0354] AI selection and call initiation

[0355] User:

[0356] From the app's home screen, users select the AI ​​they want to talk to from the chat AI, consultation AI, or learning support AI, and tap the "Start Call" button.

[0357] Device:

[0358] The terminal transmits the selected AI information and a call start request to the server to request a call session.

[0359] server:

[0360] The server loads the appropriate generative artificial intelligence model based on the selected AI and establishes the call session, as well as the user's profile data and past conversation records.

[0361] Utilizing the Emotion Engine

[0362] Emotion Engine:

[0363] The emotion engine analyzes emotions from the user's voice and text input, and transmits them to the server in real time, which reflects them in the generative artificial intelligence's responses.

[0364] Generative AI (ChatGPT):

[0365] Based on user input, the generative AI takes in emotional data analyzed by the emotion engine and generates an appropriate response, allowing users to easily find someone to talk to.

[0366] Conversation progression and data recording

[0367] server:

[0368] The server records all conversations in real time and stores them in a database. The recorded conversation data is used in subsequent calls. Emotion engine data is also stored and used to analyze the user's emotional patterns.

[0369] Specific examples

[0370] Let's say a user is suffering from insomnia in the middle of the night. The user opens the app, selects the consultation AI, and starts a call.

[0371] User:

[0372] "Work has been so stressful lately that I can't sleep."

[0373] Emotion Engine:

[0374] Detects stress and fatigue from the user's tone of voice and choice of words.

[0375] Generative AI:

[0376] "That's tough. What exactly is stressing you out?"

[0377] server:

[0378] The server records this conversation and emotional data and stores it for reference during the next call.

[0379] Ending a call and feedback

[0380] User:

[0381] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed.

[0382] Device:

[0383] The terminal sends a termination request and feedback information to the server.

[0384] server:

[0385] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model and emotion engine.

[0386] As a result, the system based on the present invention can understand the user's emotions and provide an appropriate response, thereby providing psychological support to the user.

[0387] The processing flow will be explained below.

[0388] Step 1:

[0389] User:

[0390] The user installs the app on their smartphone or tablet and launches it.

[0391] Step 2:

[0392] User:

[0393] Users enter basic information such as their name, age, email address, and hobbies on the account creation screen and tap the "Sign up" button.

[0394] Step 3:

[0395] Device:

[0396] The terminal transmits the input basic information to the server.

[0397] Step 4:

[0398] server:

[0399] The server verifies the received information and, if there are no problems, stores the user's basic information in a database. The server then sends the user a confirmation email to complete the account creation.

[0400] Step 5:

[0401] User:

[0402] The user clicks on the link in the confirmation email they receive to complete their account registration.

[0403] Step 6:

[0404] User:

[0405] Users enter additional information such as hobbies, interests, and goals in the app's profile settings screen.

[0406] Step 7:

[0407] Device:

[0408] The terminal transmits the input profile information to the server.

[0409] Step 8:

[0410] server:

[0411] The server stores the received profile information in a database and generates a detailed profile for the user.

[0412] Step 9:

[0413] User:

[0414] On the home screen, users can select the AI ​​they want to talk to from among the chat AI, consultation AI, and learning support AI.

[0415] Step 10:

[0416] Device:

[0417] The device sends the selected AI information to the server and requests a call session.

[0418] Step 11:

[0419] server:

[0420] The server receives the request and loads the generative artificial intelligence model according to the selected AI, as well as the user's profile data and past conversation records.

[0421] Step 12:

[0422] User:

[0423] The user taps the "Start Call" button.

[0424] Step 13:

[0425] Device:

[0426] The terminal sends a call initiation request to the server.

[0427] Step 14:

[0428] server:

[0429] The server establishes a call session, initializes the generative AI (ChatGPT), prepares to receive user input in real time, and starts the emotion engine to prepare to analyze user input.

[0430] Step 15:

[0431] User:

[0432] The user initiates a call with the generative AI and types or speaks what they want to say.

[0433] Step 16:

[0434] Emotion Engine:

[0435] The emotion engine analyzes emotions from the user's voice and text input and sends the data to the server in real time.

[0436] Step 17:

[0437] Generative AI (ChatGPT):

[0438] Based on input from the user, generative AI takes in emotional data analyzed by the emotion engine and generates an appropriate response.

[0439] Step 18:

[0440] server:

[0441] The server records all conversation content and emotional data in real time and stores it in a database, allowing past conversation data and emotional patterns to be accumulated and used in the next conversation.

[0442] Step 19:

[0443] User:

[0444] When the user finishes the call, he taps the "end call" button.

[0445] Step 20:

[0446] Device:

[0447] The terminal sends a call termination request to the server.

[0448] Step 21:

[0449] server:

[0450] The server ends the call session and stores the information in a database at the time of termination. The recorded data is analyzed and used to provide the user with a more appropriate response in the next conversation.

[0451] Step 22:

[0452] User:

[0453] The user enters their thoughts and feedback on the call on the post-call screen.

[0454] Step 23:

[0455] Device:

[0456] The terminal transmits the feedback information to the server.

[0457] Step 24:

[0458] server:

[0459] The server receives the feedback and stores it in a database. The feedback information is analyzed and used to improve the generative AI and emotion engine models.

[0460] As a result, the system based on the present invention is a system that can recognize the user's emotions in real time and provide an appropriate response, thereby providing psychological support to the user.

[0461] Example 2

[0462] 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."

[0463] Conventional dialogue systems using generative AI generally respond without considering the user's emotions, which prevents them from providing sufficient personalization or emotional support. Furthermore, they fail to fully utilize past conversations, making it difficult to build a lasting relationship with the user. Furthermore, they lack a mechanism for incorporating user feedback into system improvements.

[0464] 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.

[0465] In this invention, the server includes a means for inputting and saving basic user information, a means for using generative artificial intelligence to communicate with the user, a means for storing the content of the user's past conversations and reflecting that content in the next conversation, and a means for analyzing the user's emotions and reflecting that content in the conversation. This enables personalized dialogue that understands emotions, providing psychological support to the user and building a lasting relationship. Furthermore, user feedback can be used to improve the artificial intelligence model, thereby improving system performance.

[0466] "Basic user information" is data indicating personal attributes such as the user's name, age, hobbies, etc.

[0467] "Generative AI" refers to an AI system that uses natural language processing to interact with users, such as ChatGPT.

[0468] "Means for communicating with the user" refers to a mechanism for two-way communication with the user via voice or text via generative artificial intelligence.

[0469] "Means of remembering the content of a user's past conversations and reflecting it in the next conversation" is a function that stores records of past conversations with the user in a database and uses that information to make the content of the next conversation more personalized.

[0470] "Means for analyzing emotions and reflecting them in the content of the call" refers to a mechanism that reads emotions from the user's voice and text and incorporates the results into the generative AI's response, thereby enabling a dialogue that is sensitive to the user's emotions.

[0471] "Personalized dialogue" refers to generating optimal responses for a user by taking into account the user's individual information, past conversations, emotional state, etc.

[0472] "Feedback" refers to the thoughts and opinions provided by users after a call ends, and is data used to improve the performance of the system and generative artificial intelligence.

[0473] The present invention relates to a system that understands user emotions and provides more personalized interactions. This system consists of a user terminal, a server, a generative artificial intelligence (e.g., ChatGPT), and an emotion engine.

[0474] Overall system overview

[0475] Users install and launch a dedicated application using a network-connected device such as a smartphone or tablet. The application inputs and saves the user's basic information and communicates with the user via a generative AI. It also uses an emotion engine to analyze the user's emotions and reflects them in the generative AI's responses.

[0476] User registration and profile settings

[0477] Through the application, users enter basic information such as name, age, hobbies, etc. This information is sent via the device to the server, which verifies the information received and stores it in a database to create a detailed user profile.

[0478] AI selection and call initiation

[0479] From the app's home screen, users select the AI ​​they want to talk to from among several AI models (such as chat AI, consultation AI, and learning support AI), and tap the "Start Call" button. The device sends this information and a call start request to the server, which then loads the appropriate generative AI model and establishes a call session. Additionally, the user's profile data and past conversation records are also loaded.

[0480] Use of emotion engine

[0481] The emotion engine analyzes the user's voice and text input in real time to generate emotional data. This allows the server to detect the user's emotions, such as stress or joy, and provides this information to the generative AI. The generative AI then takes in this emotional data and generates an appropriate response.

[0482] Specific examples

[0483] For example, consider a case where a user is suffering from insomnia. The user opens the application, selects a consultation AI, and starts a call.

[0484] 1. A user says, "Work has been so stressful lately that I can't sleep."

[0485] 2. The emotion engine detects the user's stress and fatigue from this statement.

[0486] 3. The generative AI responds, "That's tough. What exactly is stressing you out?"

[0487] 4. The server records this conversation and emotion data and stores it for reference during the next call.

[0488] Ending a call and feedback

[0489] When the call ends, the user taps the "End Call" button and optionally enters their thoughts and feedback. The device sends the end request and feedback information to the server, which then ends the call session and stores the end information in a database. The server also receives user feedback and uses it to improve the generative AI model and emotion engine.

[0490] Example prompts to input to the generative AI model

[0491] prompt:

[0492] "Please use the template below to respond to a user who is suffering from insomnia. Detect stress or fatigue from the user's tone of voice and choice of words, and engage in appropriate dialogue."

[0493] 1. User: "I've been so stressed out at work lately that I can't sleep."

[0494] 2. Emotion engine: Detects stress and fatigue.

[0495] 3. Generative AI: "That sounds tough. What exactly is stressing you out?"

[0496] In this way, the system according to the present invention can understand the user's emotions and provide more appropriate interactions.

[0497] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0498] Step 1:

[0499] The user enters basic information.

[0500] Input: The user enters basic information such as name, age, and hobbies into the input form displayed on the terminal.

[0501] Specific behavior: The user enters information and taps the submit button.

[0502] Output: The entered information is saved on the device.

[0503] Step 2:

[0504] The terminal sends the information to the server.

[0505] Input: Basic information entered by the user in step 1.

[0506] Specific operation: The terminal generates a data packet for transmitting the input basic information to the server.

[0507] Output: The user's basic information is sent to the server.

[0508] Step 3:

[0509] The server verifies the information and stores it in a database.

[0510] Input: Basic information of the user sent from the device.

[0511] Specific operations: The server validates the format of the data received and saves it to the database. A user ID is generated and associated with basic information.

[0512] Output: The user profile is saved in the database.

[0513] Step 4:

[0514] The user selects the AI.

[0515] Input: On the app's home screen, the user selects the AI ​​they want to talk to from among the chat AI, consultation AI, and learning support AI.

[0516] Specific operation: The user selects the desired AI and taps the "Start call" button.

[0517] Output: The information of the selected AI is saved on the device.

[0518] Step 5:

[0519] The device sends a request to the server.

[0520] Input: Selected AI information and call start request.

[0521] Specific operation: The terminal generates a data packet for transmitting the selected AI information and a call start request.

[0522] Output: A call start request and selected AI information is sent to the server.

[0523] Step 6:

[0524] The server establishes the session.

[0525] Input: The call initiation request sent from the device and selected AI information.

[0526] What it does: The server loads the appropriate generative artificial intelligence model and establishes the call session, along with the user's profile data and past conversation records.

[0527] Output: A call session is started.

[0528] Step 7:

[0529] The emotion engine analyzes emotions.

[0530] Input: User voice and text input.

[0531] Specific operation: The emotion engine analyzes voice and text data to detect the user's emotions (stress, joy, fatigue, etc.).

[0532] Output: The analyzed emotion data is sent to the server.

[0533] Step 8:

[0534] The server receives the emotion data and provides it to the generative artificial intelligence.

[0535] Input: Emotion data sent from the emotion engine.

[0536] Specific operation: The server receives emotion data and generates a data packet to provide to the generative artificial intelligence.

[0537] Output: Emotion data is provided to a generative AI.

[0538] Step 9:

[0539] Generative artificial intelligence generates responses.

[0540] Input: Initial input and emotion data from the user.

[0541] Specific behavior: Based on the input, the generative AI takes in the emotional data analyzed by the emotion engine and generates a response. For example, "What specifically is causing you stress?"

[0542] Output: The generated response is returned to the user.

[0543] Step 10:

[0544] The server records the conversation and stores it in a database.

[0545] Input: Conversational content and emotional data between the generative AI and the user.

[0546] Specific operation: The server records all conversation content in a database and saves it for future reference.

[0547] Output: Conversation records and emotion data are stored in a database.

[0548] Step 11:

[0549] The user ends the call and provides feedback.

[0550] Input: End-of-call instructions and feedback information.

[0551] What happens: The user taps the "End Call" button and optionally enters thoughts or feedback.

[0552] Output: The termination request and feedback information are saved to the terminal.

[0553] Step 12:

[0554] The terminal sends a termination request to the server.

[0555] Input: Call termination request and feedback information.

[0556] Specific operation: The terminal generates a data packet for transmitting a termination request and feedback information.

[0557] Output: A termination request and feedback information is sent to the server.

[0558] Step 13:

[0559] The server ends the session and saves the feedback.

[0560] Input: The termination request and feedback information sent from the terminal.

[0561] Specific operation: The server ends the call session and stores the end information in a database. It also uses the received feedback information to improve the generative AI model and emotion engine.

[0562] Output: The end of the call session and feedback information are stored in a database and used to improve the system.

[0563] (Application example 2)

[0564] 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."

[0565] Conventional AI dialogue systems generate uniform responses without considering the user's emotional state, resulting in low dialogue quality and insufficient user satisfaction. Furthermore, in customer support at physical stores, they are unable to provide personalized services that reflect the customer's real-time emotional state.

[0566] 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.

[0567] In this invention, the server includes means for inputting and saving basic information about the user, means for using a generative artificial intelligence to have a dialogue with the user, means for storing the content of the user's past conversations and reflecting that content in the next conversation, means for analyzing the user's emotional state using an emotion analysis engine, and means for adjusting the response of the generative artificial intelligence based on the analyzed emotional state. This enables personalized responses that take into account the individual emotional state of the user, thereby providing higher levels of satisfaction in customer support at physical stores.

[0568] "Basic user information" refers to individual information such as the user's name, age, and hobbies.

[0569] "Generative AI" is AI that generates natural dialogue based on user input, such as systems like ChatGPT.

[0570] "Means for dialogue" refers to an interface or system that allows real-time conversations and message exchanges between the user and generative AI.

[0571] "Means for storing the contents of a user's past conversations and reflecting them in the next conversation" refers to a means for saving the contents of previous conversations with a user and using them to improve the next conversation.

[0572] An "emotion analysis engine" is an engine that analyzes the user's emotional state from their voice or text input and outputs the results.

[0573] The "means for adjusting the response" is a means for changing the dialogue content generated by the generative artificial intelligence based on the output results of the emotion analysis engine, and providing an appropriate response.

[0574] A "brick and mortar store" is a commercial establishment or service location located in a physical location.

[0575] "Customer support" refers to support activities to respond to customer questions and inquiries and resolve problems.

[0576] The present invention is a system for providing customer support in brick-and-mortar stores. In the specific embodiment shown below, real-time dialogue is provided using a combination of generative artificial intelligence and an emotion analysis engine, using a terminal such as a smartphone, tablet, or information robot installed in the store.

[0577] User registration and profile settings

[0578] Users install the application on their smartphones or tablets and enter basic information such as their name, age, purchase history, hobbies, etc. This information is sent from the device to a server and stored in a database, creating a detailed profile for each user.

[0579] Starting a conversation

[0580] The user selects a customer support AI from the application's home screen and taps the "Start Dialogue" button. The device sends the selected AI information and a dialogue start request to the server, requesting a dialogue session. The server loads an appropriate generative AI model and establishes a dialogue session. It also loads the user's profile and past conversation records to use in the next dialogue.

[0581] Utilizing a sentiment analysis engine

[0582] The emotion analysis engine analyzes emotions from the user's voice and text input and sends the results to the server in real time. The generative AI then takes this emotional data and generates an appropriate response. For example, if a user expresses confusion or dissatisfaction, a response incorporating that emotion will be provided, allowing the user to receive more satisfying support.

[0583] Conversation progression and data recording

[0584] The server records all conversations in real time and stores them in a database. The recorded conversation data and emotion data are used in subsequent conversations. In particular, past problem history and complaint information are reflected in the next assistance, allowing for higher quality service.

[0585] Closing the conversation and feedback

[0586] After the dialogue is finished, the user taps the "End dialogue" button, and an end request is sent to the server. If necessary, the user can enter their thoughts or feedback, which is also sent to the server. The server stores the end information in a database and uses the feedback information to improve the generative AI model and sentiment analysis engine.

[0587] Hardware and Software Configuration

[0588] The system of the present invention uses the following hardware and software.

[0589] Hardware: Smartphones, tablets, information robots

[0590] Software: Generative AI model (ChatGPT), emotion analysis engine (EmotionEngine), database (SQLite), server program

[0591] Suggested concrete examples

[0592] For example, if a user says in a store, "Tell me more about this product," the following prompt sentence can be generated and responded to:

[0593] Input prompt for the generative AI model:

[0594] My name is Taro Sato. I'm interested in music and painting. My current emotion is joy. Please tell me more about this product.

[0595] Based on this prompt, the generative AI will return an appropriate response such as, "This product is a cutting-edge music player that combines high sound quality with ease of use. It is especially recommended for music lovers!" This allows users to obtain appropriate information quickly, improving satisfaction.

[0596] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0597] Step 1:

[0598] The user installs the application on the terminal and starts the application.

[0599] Specific operation: After downloading the application, the user enters basic information such as name, age, and hobbies.

[0600] Input and Output: The user's basic information is entered and sent by the device to the server, which stores this information in a database and creates a profile for each user.

[0601] Step 2:

[0602] The user selects the customer support AI from the application's home screen and taps the "Start conversation" button.

[0603] Specific operation: The user selects the AI ​​they want to interact with on the home screen and sends a request to start interacting.

[0604] Input and Output: The device receives the user's selection information and a request to initiate a dialogue, which it then sends to the server. The server loads the generative AI model and establishes a dialogue session. It also loads the user's profile data and past conversation records.

[0605] Step 3:

[0606] The emotion analysis engine analyzes emotions from the user's voice and text input and sends the results to the server.

[0607] Specific operation: The user's voice and text are input into an emotion analysis engine, which analyzes their emotional state (happiness, confusion, frustration, etc.).

[0608] Input and output: User voice and text are input, and the emotion analysis engine analyzes and outputs emotional data. This is received by the server.

[0609] Step 4:

[0610] Generative AI generates appropriate responses for users based on data from the sentiment analysis engine.

[0611] How it works: Emotional data is fed into a generative AI model to generate personalized responses for the user.

[0612] Input and output: Emotional data from the sentiment analysis engine is input, and the generative AI outputs an appropriate response. For example, in response to a user's input such as "Tell me more about this product," the system generates a response such as "This product is a cutting-edge music player that combines high sound quality with ease of use."

[0613] Step 5:

[0614] The server records all conversations in real time and stores them in a database.

[0615] Specific operation: The dialogue content and emotion data are sent to the server in real time and recorded in a database.

[0616] Input and output: The user's dialogue and emotional data are input and stored in a database as a record, which can then be used in future dialogues.

[0617] Step 6:

[0618] After the conversation is over, the user taps the "End conversation" button to send a request to the server to end the conversation. If necessary, the user can enter their thoughts or feedback.

[0619] Specific operation: After the user finishes the interaction, he / she sends an end request and feedback information.

[0620] Input and Output: User exit requests and feedback are input and stored on the server. Feedback information is used to improve the generative artificial intelligence and sentiment analysis engine.

[0621] 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.

[0622] 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.

[0623] 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.

[0624] [Second embodiment]

[0625] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0626] 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.

[0627] 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).

[0628] 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.

[0629] 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.

[0630] 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).

[0631] 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.

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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."

[0637] The present invention is a system that allows users to easily find someone to talk to through a call with a generative AI of their choice. Specifically, the system inputs and saves basic information about the user, uses the generative AI to talk to the user, and also has the ability to remember the content of past conversations and reflect it in the next conversation.

[0638] System Overview

[0639] The system mainly consists of a user device, a server, and a generative artificial intelligence (ChatGPT). Users install and launch the app using their smartphone or tablet.

[0640] User registration and profile settings

[0641] User:

[0642] Users install and launch the app and enter basic information such as their name, age, and hobbies, which allows the application to set up a personalized profile for the user.

[0643] Device:

[0644] The terminal transmits the information entered by the user to the server and stores it as profile data.

[0645] server:

[0646] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[0647] AI selection and call initiation

[0648] User:

[0649] From the app's home screen, users can choose from chat AI, consultation AI, or learning support AI, and then tap the "Start Call" button to begin the call.

[0650] Device:

[0651] The terminal sends the selected AI information and a call start request to the server and prepares to establish a call session.

[0652] server:

[0653] The server loads the appropriate generative artificial intelligence model based on the selected AI information, establishes a call session, and loads the user's profile data and past conversation records.

[0654] Conversation progression and data recording

[0655] Generative AI (ChatGPT):

[0656] Generative AI generates appropriate responses in real time based on user input, allowing users to easily find someone to talk to.

[0657] server:

[0658] The server records all conversations in real time and stores them in a database, which can be used in subsequent calls.

[0659] Specific examples

[0660] Let's say a user is suffering from insomnia in the middle of the night. The user opens the app, selects the consultation AI, and starts a call.

[0661] User:

[0662] "Work has been so stressful lately that I can't sleep."

[0663] Generative AI:

[0664] "That's tough. What exactly is stressing you out?"

[0665] server:

[0666] The server records this conversation and stores it for reference during the next call.

[0667] Ending a call and feedback

[0668] User:

[0669] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed.

[0670] Device:

[0671] The terminal sends a termination request and feedback information to the server.

[0672] server:

[0673] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model.

[0674] As a result, the system based on the present invention functions as a friend that can provide appropriate responses to the user 24 hours a day, 365 days a year, thereby reducing the user's mental burden and improving their quality of life.

[0675] The processing flow will be explained below.

[0676] Step 1:

[0677] User:

[0678] The user installs the app on their smartphone or tablet and launches it.

[0679] Step 2:

[0680] User:

[0681] Users enter basic information such as their name, age, and email address on the account creation screen and tap the "Sign up" button.

[0682] Step 3:

[0683] Device:

[0684] The terminal transmits the input basic information to the server.

[0685] Step 4:

[0686] server:

[0687] The server verifies the received information and, if there are no problems, stores the user's basic information in a database.

[0688] The server will send a confirmation email to the user to complete the account creation.

[0689] Step 5:

[0690] User:

[0691] The user clicks on the link in the confirmation email they receive to complete their account registration.

[0692] Step 6:

[0693] User:

[0694] Users enter additional information such as hobbies, interests, and goals in the app's profile settings screen.

[0695] Step 7:

[0696] Device:

[0697] The terminal transmits the input profile information to the server.

[0698] Step 8:

[0699] server:

[0700] The server stores the received profile information in a database and generates a detailed profile for the user.

[0701] Step 9:

[0702] User:

[0703] On the home screen, users can select the AI ​​they want to talk to from among the chat AI, consultation AI, and learning support AI.

[0704] Step 10:

[0705] Device:

[0706] The device sends the selected AI information to the server and requests a call session.

[0707] Step 11:

[0708] server:

[0709] The server receives the request and loads the generative artificial intelligence model according to the selected AI, as well as the user's profile data and past conversation records.

[0710] Step 12:

[0711] User:

[0712] The user taps the "Start Call" button.

[0713] Step 13:

[0714] Device:

[0715] The terminal sends a call initiation request to the server.

[0716] Step 14:

[0717] server:

[0718] The server establishes the call session, initializes the generative AI (ChatGPT), and prepares to receive user input in real time.

[0719] Step 15:

[0720] Generative AI (ChatGPT):

[0721] Generative AI generates appropriate responses based on input from the user and replies to the user.

[0722] Step 16:

[0723] server:

[0724] The server records all conversations in real time and stores them in a database, allowing past conversation data to be accumulated and used for the next conversation.

[0725] Step 17:

[0726] User:

[0727] When the user finishes the call, he taps the "end call" button.

[0728] Step 18:

[0729] Device:

[0730] The terminal sends a call termination request to the server.

[0731] Step 19:

[0732] server:

[0733] The server terminates the call session and stores the termination information in a database.

[0734] Step 20:

[0735] User:

[0736] The user enters their thoughts and feedback on the call on the post-call screen.

[0737] Step 21:

[0738] Device:

[0739] The terminal transmits the feedback information to the server.

[0740] Step 22:

[0741] server:

[0742] The server receives the feedback and stores it in a database. The feedback information is analyzed and used to improve the generative AI model.

[0743] The above are the specific processing steps of the present invention.

[0744] Example 1

[0745] 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."

[0746] Conventional communication systems have the problem that it is difficult to provide a conversation partner in real time and lack the functionality to effectively reflect the user's past conversation content, which hinders the improvement of the user experience. Furthermore, there is no mechanism for reflecting user feedback in the AI ​​model, making it difficult to maintain and improve call quality.

[0747] 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.

[0748] In this invention, the server includes means for inputting and saving basic user information, means for using generative artificial intelligence to conduct phone calls with the user, and means for storing the content of the user's past conversations and incorporating it into the next conversation. This allows the user to find someone to talk to in real time, and the content of the past conversations can be used for the next call, improving the user experience. The server also includes means for establishing a call with a generative artificial intelligence model selected by the user, means for recording the content of the call in real time and saving it in a format that can be referenced later, and means for receiving feedback from the user after the call ends and using it to improve the artificial intelligence model. This allows the feedback to be incorporated into the artificial intelligence model, enabling the maintenance and improvement of call quality.

[0749] "Basic information" is data entered by the user for personal identification and individualization, such as name, age, hobbies, etc.

[0750] "Generative AI" is an AI system that generates responses in natural language in response to input from a user.

[0751] "Call" refers to interactive communication with a user via generative artificial intelligence.

[0752] "Profile data" is a data set that includes basic information about a user and the contents of past conversations.

[0753] A "call session" is a continuous process of interaction with a user conducted using generative artificial intelligence.

[0754] "Real-time" refers to interactions being processed and reacted to the instant they are sent or received.

[0755] "Feedback" refers to information such as evaluations, impressions, and requests for improvement provided by users after a call has ended.

[0756] A "database" is an information repository where user profile data and conversations are stored.

[0757] "Model improvement" is the process of improving the response accuracy and quality of generative artificial intelligence based on feedback from users.

[0758] The "selected generative artificial intelligence model" is the generative artificial intelligence algorithm that is most suitable for the application specified by the user.

[0759] The present invention is a system that allows users to easily find someone to talk to using a generative AI selected by the user. This system consists of a user terminal, a server, and a generative AI (e.g., ChatGPT). The following describes the specific steps and operation methods for implementing the present invention.

[0760] User registration and profile settings

[0761] User:

[0762] Users install and launch the dedicated app on their smartphone or tablet and enter basic information such as their name, age, hobbies, etc. For example, a user may say their name is "Taro," their age is "30," and their hobby is "reading."

[0763] Device:

[0764] The terminal transmits the information entered by the user to the server, including the user's name, age, and hobbies.

[0765] server:

[0766] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[0767] AI selection and call initiation

[0768] User:

[0769] From the app's home screen, users can select one of the following AIs: chat AI, consultation AI, or learning support AI, and then tap the "Start Call" button. For example, select "Consultation AI."

[0770] Device:

[0771] The terminal sends the selected AI information and a call start request to the server. The user ID and AI type are sent.

[0772] server:

[0773] The server loads the appropriate generative AI model (e.g., ChatGPT) based on the selected AI information and establishes the call session, along with the user's profile data and past conversation records.

[0774] Conversation progression and data recording

[0775] User:

[0776] The user can freely converse with the generative AI. For example, the user can input, "I've been stressed out at work lately and I can't sleep."

[0777] Generative AI (ChatGPT):

[0778] The generative AI responds, "That's tough. What exactly is stressing you out?" and generates an appropriate response in real time.

[0779] server:

[0780] The server records all conversations in real time and stores them in a database, allowing this information to be used in future calls.

[0781] Ending a call and feedback

[0782] User:

[0783] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed. For example, they can enter feedback such as "That was very helpful."

[0784] Device:

[0785] The terminal sends a termination request and feedback information to the server.

[0786] server:

[0787] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model.

[0788] Examples of concrete examples and prompts

[0789] Specific examples

[0790] Consider a situation where a user is suffering from insomnia in the middle of the night. The user opens the app, selects the consultation AI, and starts a call.

[0791] User:

[0792] "Work has been so stressful lately that I can't sleep."

[0793] Generative AI (ChatGPT):

[0794] "That's tough. What exactly is stressing you out?"

[0795] server:

[0796] The server records this conversation and stores it for reference during the next call.

[0797] Prompt Sentence Examples

[0798] "Recently, I've been having trouble sleeping because of stress at work. What can I do to make myself feel a little better?"

[0799] Through this prompt, the user can receive appropriate advice from the generative artificial intelligence.

[0800] According to the above procedures and operation methods, the system based on the present invention can function as a friend who is available to the user 24 hours a day, 365 days a year, reducing the user's mental burden and improving the quality of life.

[0801] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0802] Step 1:

[0803] User registration and profile settings

[0804] User:

[0805] Users install and launch the app and enter basic information (name, age, hobbies, etc.).

[0806] Input: User's name, age, hobbies

[0807] Output: Data sent from the basic information input screen

[0808] Device:

[0809] The device sends the information entered by the user to the server, including the user's name, age, and hobbies.

[0810] Input: Data entered by the user

[0811] Output: Data sent to the server

[0812] server:

[0813] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[0814] Input: Basic user information sent from the device

[0815] Output: User profile data stored in a database

[0816] Step 2:

[0817] AI selection and call initiation

[0818] User:

[0819] From the app's home screen, users select one of the chat AI, consultation AI, or learning support AI and tap the "Start Call" button.

[0820] Input: User's AI selection and call start request

[0821] Output: AI selection instructions and call start request

[0822] Device:

[0823] The terminal sends the selected AI information and a call start request to the server. Specifically, the AI ​​type and user ID are sent.

[0824] Input: User's AI selection information and call start request

[0825] Output: The request data sent to the server

[0826] server:

[0827] The server loads the appropriate generative artificial intelligence model based on the selected AI and establishes the call session, as well as the user's profile data and past conversation records.

[0828] Input: AI selection information and call start request sent from the device

[0829] Output: A loaded generative AI model, an established call session

[0830] Step 3:

[0831] Conversation progression and data recording

[0832] User:

[0833] The user can freely converse with the generative AI, for example, by inputting, "I've been so stressed out at work lately that I can't sleep."

[0834] Input: User spoken input

[0835] Output: prompts for generative AI

[0836] Generative AI (ChatGPT):

[0837] Based on user input, generative AI generates appropriate responses in real time, such as, "That's tough. What exactly is stressing you out?"

[0838] Input: Prompt from user

[0839] Output: The generated response

[0840] server:

[0841] The server records all conversations in real time and stores them in a database, allowing this information to be used in future calls.

[0842] Input: Conversation data between the generative AI and the user

[0843] Output: Conversation transcript stored in database

[0844] Step 4:

[0845] Ending a call and feedback

[0846] User:

[0847] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed. For example, they can enter feedback such as "That was very helpful."

[0848] Input: Tap the end call button, feedback

[0849] Output: Call termination request, feedback data

[0850] Device:

[0851] The terminal sends a termination request and feedback information to the server.

[0852] Input: User end call request, feedback

[0853] Output: Finished request and feedback data sent to the server

[0854] server:

[0855] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model.

[0856] Input: End call request sent from the device, feedback

[0857] Output: Call termination information stored in a database, feedback data for model improvement

[0858] (Application example 1)

[0859] 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."

[0860] In today's world, when users purchase products online, they need a lot of information, and if they do not receive appropriate support, their motivation to purchase decreases. Furthermore, if customers cannot resolve specific questions about a product, they risk missing out on a purchasing opportunity. Furthermore, online stores face the challenge of finding personalized product recommendations and support for each individual customer.

[0861] 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.

[0862] In this invention, the server includes means for inputting and saving basic information about the user, means for using generative artificial intelligence to communicate with the user, means for storing the content of past conversations with the user and reflecting this in the next conversation, means for using generative artificial intelligence selected by the user to provide product-related questions and advice in real time within a virtual store, means for recommending optimal products to the user based on their purchase history and the content of past conversations, and means for collecting feedback and improving support quality. This allows users to receive prompt and accurate support in real time when making online purchases, increasing their desire to purchase and enabling optimal product recommendations.

[0863] "Basic user information" refers to information necessary to form an individual profile, such as the user's name, age, and purchase history.

[0864] "Generative AI" is an AI system that generates appropriate responses in real time based on user input.

[0865] "Means for making calls" refers to a means of communication that allows the generative artificial intelligence and the user to interact in real time.

[0866] "Means for remembering the content of past conversations and reflecting it in the next conversation" refers to a means for providing continuous support by saving the content of the previous conversation and referring to it in the next conversation.

[0867] A "virtual store" is an online shopping environment used via the Internet where users can browse and purchase products.

[0868] The "means for providing product-related questions and advice in real time" is an interactive support system that can answer questions about products and how to use them on the spot when users ask questions within the virtual store.

[0869] "Purchase history" is a record of products that a user has purchased in the past.

[0870] "Means for recommending optimal products to users based on past conversation content" refers to a system that suggests products that meet individual user needs based on the user's past conversations and behavioral history.

[0871] "Means for collecting feedback and improving support quality" refers to a means for incorporating user evaluations and opinions into the system and using them to improve the performance and response accuracy of the generative artificial intelligence.

[0872] This invention is a system that provides optimal support to users in a virtual store by inputting and saving basic information about the user, using generative artificial intelligence to communicate with the user, and storing the content of past conversations and reflecting it in the next conversation. Specific embodiments for implementing this invention are described below.

[0873] System configuration

[0874] The system consists of the following main components:

[0875] 1. User Device

[0876] Using mobile devices such as smartphones and tablets, users can access virtual stores and talk to AI.

[0877] 2. Server

[0878] A high-performance database server is used to store and manage basic user information, purchase history, past conversations, etc. A cloud-based database such as AWS RDS is suitable for the server.

[0879] 3. Generative Artificial Intelligence

[0880] Using OpenAI's ChatGPT API, the system generates responses to users' real-time questions. This AI generates appropriate responses based on user input, maintaining the continuity of the conversation.

[0881] Processing Flow

[0882] 1. User Registration and Profile Settings

[0883] The application is installed on the user's device and launched. The user enters basic information such as name, age, hobbies, and purchasing history. This data is sent to the server and stored in a database.

[0884] 2. AI selection and call initiation

[0885] The user selects "Customer Support" from the application's home screen and taps the "Start Call" button. The server loads the user's profile data and loads the appropriate generative artificial intelligence model.

[0886] 3. Conversation management and data recording

[0887] The generative artificial intelligence (ChatGPT) responds to user questions and requests in real time. For example, if a user asks, "What are the features of this smartphone?", the AI ​​will respond, "This smartphone is equipped with a high-resolution camera, a state-of-the-art processor, and boasts a long battery life. It is also waterproof."

[0888] 4. Call End and Feedback

[0889] When the user finishes the call, they tap the "End Call" button and the call ends. After the call ends, the user enters feedback, which is sent to the server. The server collects the feedback and uses it to improve the AI ​​model.

[0890] Explanation of program processing

[0891] The server first stores the user's basic information in a database. Then, when the user sends a request to talk to a specific AI, the server loads the user's past conversations and launches the appropriate generative AI model. During the call, the server records the AI's responses and the user's input in real time, making them available for reference in the next conversation.

[0892] For hardware, smartphones and tablets are used as user devices, and cloud-based solutions such as AWS RDS are used as database servers. For software, OpenAI's ChatGPT API is used for generative artificial intelligence, and React Native is used for application development.

[0893] Prompt Sentence Examples

[0894] Examples of specific prompts include:

[0895] "User: Tell me about the new features on your smartphone these days. Generative AI:"

[0896] "User: What's the best way to use this camera? Generative AI:"

[0897] This allows users to receive prompt and accurate support in real time when making online purchases, which increases purchasing motivation and enables optimal product recommendations.

[0898] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0899] Step 1:

[0900] The user enters basic information

[0901] Input: Users enter basic information such as name, age, hobbies, and purchase history into an application on their smartphone or tablet.

[0902] Data processing: The terminal formats the entered user information and converts it into a format that can be sent to the server.

[0903] Output: The formatted user information is sent to the server.

[0904] Specific actions: Enter user information into the application form and tap the "Submit" button.

[0905] Step 2:

[0906] The server stores basic information

[0907] Input: Basic information of the user sent from the device.

[0908] Data Calculation: The server verifies the received user information and stores it in the database.

[0909] Output: A confirmation message that the save was successful is returned to the terminal.

[0910] Specific operation: The server checks the integrity of the received data and saves the information to the MySQL database using an INSERT statement.

[0911] Step 3:

[0912] The user selects the generative AI

[0913] Input: The user selects "Customer Support" or another AI model from the application home screen.

[0914] Data processing: The device generates a request to send information about the selected AI model to the server.

[0915] Output: The generated request is sent to the server.

[0916] What it does: Tap an option such as "Customer Support" from the application's menu.

[0917] Step 4:

[0918] The server establishes the call session

[0919] Input: The call initiation request sent from the device and the user's profile data.

[0920] Data computation: The server loads the appropriate generative artificial intelligence model and retrieves past conversation content from the database.

[0921] Output: The call session is ready to begin and the device is notified.

[0922] What it does: The server loads profile data and conversation history and sets up the AI ​​model for operation.

[0923] Step 5:

[0924] Generative AI starts the conversation

[0925] Input: The initial input from the user (e.g., "What are the features of this phone?").

[0926] Data Computation: Generative AI processes input text and generates appropriate prompts.

[0927] Output: A response based on the generated prompt is returned to the user.

[0928] What it does: Uses ChatGPT API to generate and reply to responses based on user input in real time.

[0929] Step 6:

[0930] The server records the conversation

[0931] Input: Real-time generated AI responses and user input.

[0932] Data calculation: The contents of the conversation are saved in a database and managed as history for use in future conversations.

[0933] Output: The save completion confirmation status is updated internally.

[0934] Specific operation: The server inserts and updates the received conversation data into the database in real time.

[0935] Step 7:

[0936] User ends the call and provides feedback

[0937] Input: Feedback entered by the user at the end of the call (e.g., "Thank you for your prompt response").

[0938] Data processing: The terminal sends the termination request and feedback information to the server.

[0939] Output: The feedback information is stored in the server and a completion message is returned to the user terminal.

[0940] Specific actions: The user taps the "End call" button, enters their opinion in the feedback form, and taps the "Submit" button.

[0941] Step 8:

[0942] The server improves the AI ​​model based on the feedback.

[0943] Input: Feedback information from the user.

[0944] Data calculation: The server analyzes the feedback and reflects it to improve the response accuracy of the generative AI.

[0945] Output: The AI ​​model has been improved and will be reflected in future calls.

[0946] What it does: Analyzes the feedback data and retrains the model by adding it to the generative artificial intelligence training dataset.

[0947] 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.

[0948] The present invention is a system that combines generative artificial intelligence with an emotion engine that recognizes the user's emotions. This allows for more personalized and emotionally appropriate dialogue for the user. Specifically, the system inputs and saves basic user information, uses generative artificial intelligence to communicate with the user, and has the ability to remember the content of past conversations and reflect it in the next conversation.

[0949] System Overview

[0950] The system mainly consists of a user device, a server, a generative AI (ChatGPT), and an emotion engine. Users install and launch the app on their smartphone or tablet.

[0951] User registration and profile settings

[0952] User:

[0953] Users install and launch the app and enter basic information such as their name, age, and hobbies, which allows the application to set up a personalized profile for the user.

[0954] Device:

[0955] The terminal transmits the information entered by the user to the server and stores it as profile data.

[0956] server:

[0957] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[0958] AI selection and call initiation

[0959] User:

[0960] From the app's home screen, users select the AI ​​they want to talk to from the chat AI, consultation AI, or learning support AI, and tap the "Start Call" button.

[0961] Device:

[0962] The terminal transmits the selected AI information and a call start request to the server to request a call session.

[0963] server:

[0964] The server loads the appropriate generative artificial intelligence model based on the selected AI and establishes the call session, as well as the user's profile data and past conversation records.

[0965] Utilizing the Emotion Engine

[0966] Emotion Engine:

[0967] The emotion engine analyzes emotions from the user's voice and text input, and transmits them to the server in real time, which reflects them in the generative artificial intelligence's responses.

[0968] Generative AI (ChatGPT):

[0969] Based on user input, the generative AI takes in emotional data analyzed by the emotion engine and generates an appropriate response, allowing users to easily find someone to talk to.

[0970] Conversation progression and data recording

[0971] server:

[0972] The server records all conversations in real time and stores them in a database. The recorded conversation data is used in subsequent calls. Emotion engine data is also stored and used to analyze the user's emotional patterns.

[0973] Specific examples

[0974] Let's say a user is suffering from insomnia in the middle of the night. The user opens the app, selects the consultation AI, and starts a call.

[0975] User:

[0976] "Work has been so stressful lately that I can't sleep."

[0977] Emotion Engine:

[0978] Detects stress and fatigue from the user's tone of voice and choice of words.

[0979] Generative AI:

[0980] "That's tough. What exactly is stressing you out?"

[0981] server:

[0982] The server records this conversation and emotional data and stores it for reference during the next call.

[0983] Ending a call and feedback

[0984] User:

[0985] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed.

[0986] Device:

[0987] The terminal sends a termination request and feedback information to the server.

[0988] server:

[0989] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model and emotion engine.

[0990] As a result, the system based on the present invention can understand the user's emotions and provide an appropriate response, thereby providing psychological support to the user.

[0991] The processing flow will be explained below.

[0992] Step 1:

[0993] User:

[0994] The user installs the app on their smartphone or tablet and launches it.

[0995] Step 2:

[0996] User:

[0997] Users enter basic information such as their name, age, email address, and hobbies on the account creation screen and tap the "Sign up" button.

[0998] Step 3:

[0999] Device:

[1000] The terminal transmits the input basic information to the server.

[1001] Step 4:

[1002] server:

[1003] The server verifies the received information and, if there are no problems, stores the user's basic information in a database. The server then sends the user a confirmation email to complete the account creation.

[1004] Step 5:

[1005] User:

[1006] The user clicks on the link in the confirmation email they receive to complete their account registration.

[1007] Step 6:

[1008] User:

[1009] Users enter additional information such as hobbies, interests, and goals in the app's profile settings screen.

[1010] Step 7:

[1011] Device:

[1012] The terminal transmits the input profile information to the server.

[1013] Step 8:

[1014] server:

[1015] The server stores the received profile information in a database and generates a detailed profile for the user.

[1016] Step 9:

[1017] User:

[1018] On the home screen, users can select the AI ​​they want to talk to from among the chat AI, consultation AI, and learning support AI.

[1019] Step 10:

[1020] Device:

[1021] The device sends the selected AI information to the server and requests a call session.

[1022] Step 11:

[1023] server:

[1024] The server receives the request and loads the generative artificial intelligence model according to the selected AI, as well as the user's profile data and past conversation records.

[1025] Step 12:

[1026] User:

[1027] The user taps the "Start Call" button.

[1028] Step 13:

[1029] Device:

[1030] The terminal sends a call initiation request to the server.

[1031] Step 14:

[1032] server:

[1033] The server establishes a call session, initializes the generative AI (ChatGPT), prepares to receive user input in real time, and starts the emotion engine to prepare to analyze user input.

[1034] Step 15:

[1035] User:

[1036] The user initiates a call with the generative AI and types or speaks what they want to say.

[1037] Step 16:

[1038] Emotion Engine:

[1039] The emotion engine analyzes emotions from the user's voice and text input and sends the data to the server in real time.

[1040] Step 17:

[1041] Generative AI (ChatGPT):

[1042] Based on input from the user, generative AI takes in emotional data analyzed by the emotion engine and generates an appropriate response.

[1043] Step 18:

[1044] server:

[1045] The server records all conversation content and emotional data in real time and stores it in a database, allowing past conversation data and emotional patterns to be accumulated and used in the next conversation.

[1046] Step 19:

[1047] User:

[1048] When the user finishes the call, he taps the "end call" button.

[1049] Step 20:

[1050] Device:

[1051] The terminal sends a call termination request to the server.

[1052] Step 21:

[1053] server:

[1054] The server ends the call session and stores the information in a database at the time of termination. The recorded data is analyzed and used to provide the user with a more appropriate response in the next conversation.

[1055] Step 22:

[1056] User:

[1057] The user enters their thoughts and feedback on the call on the post-call screen.

[1058] Step 23:

[1059] Device:

[1060] The terminal transmits the feedback information to the server.

[1061] Step 24:

[1062] server:

[1063] The server receives the feedback and stores it in a database. The feedback information is analyzed and used to improve the generative AI and emotion engine models.

[1064] As a result, the system based on the present invention is a system that can recognize the user's emotions in real time and provide an appropriate response, thereby providing psychological support to the user.

[1065] Example 2

[1066] 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."

[1067] Conventional dialogue systems using generative AI generally respond without considering the user's emotions, which prevents them from providing sufficient personalization or emotional support. Furthermore, they fail to fully utilize past conversations, making it difficult to build a lasting relationship with the user. Furthermore, they lack a mechanism for incorporating user feedback into system improvements.

[1068] 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.

[1069] In this invention, the server includes a means for inputting and saving basic user information, a means for using generative artificial intelligence to communicate with the user, a means for storing the content of the user's past conversations and reflecting that content in the next conversation, and a means for analyzing the user's emotions and reflecting that content in the conversation. This enables personalized dialogue that understands emotions, providing psychological support to the user and building a lasting relationship. Furthermore, user feedback can be used to improve the artificial intelligence model, thereby improving system performance.

[1070] "Basic user information" is data indicating personal attributes such as the user's name, age, hobbies, etc.

[1071] "Generative AI" refers to an AI system that uses natural language processing to interact with users, such as ChatGPT.

[1072] "Means for communicating with the user" refers to a mechanism for two-way communication with the user via voice or text via generative artificial intelligence.

[1073] "Means of remembering the content of a user's past conversations and reflecting it in the next conversation" is a function that stores records of past conversations with the user in a database and uses that information to make the content of the next conversation more personalized.

[1074] "Means for analyzing emotions and reflecting them in the content of the call" refers to a mechanism that reads emotions from the user's voice and text and incorporates the results into the generative AI's response, thereby enabling a dialogue that is sensitive to the user's emotions.

[1075] "Personalized dialogue" refers to generating optimal responses for a user by taking into account the user's individual information, past conversations, emotional state, etc.

[1076] "Feedback" refers to the thoughts and opinions provided by users after a call ends, and is data used to improve the performance of the system and generative artificial intelligence.

[1077] The present invention relates to a system that understands user emotions and provides more personalized interactions. This system consists of a user terminal, a server, a generative artificial intelligence (e.g., ChatGPT), and an emotion engine.

[1078] Overall system overview

[1079] Users install and launch a dedicated application using a network-connected device such as a smartphone or tablet. The application inputs and saves the user's basic information and communicates with the user via a generative AI. It also uses an emotion engine to analyze the user's emotions and reflects them in the generative AI's responses.

[1080] User registration and profile settings

[1081] Through the application, users enter basic information such as name, age, hobbies, etc. This information is sent via the device to the server, which verifies the information received and stores it in a database to create a detailed user profile.

[1082] AI selection and call initiation

[1083] From the app's home screen, users select the AI ​​they want to talk to from among several AI models (such as chat AI, consultation AI, and learning support AI), and tap the "Start Call" button. The device sends this information and a call start request to the server, which then loads the appropriate generative AI model and establishes a call session. Additionally, the user's profile data and past conversation records are also loaded.

[1084] Use of emotion engine

[1085] The emotion engine analyzes the user's voice and text input in real time to generate emotional data. This allows the server to detect the user's emotions, such as stress or joy, and provides this information to the generative AI. The generative AI then takes in this emotional data and generates an appropriate response.

[1086] Specific examples

[1087] For example, consider a case where a user is suffering from insomnia. The user opens the application, selects a consultation AI, and starts a call.

[1088] 1. A user says, "Work has been so stressful lately that I can't sleep."

[1089] 2. The emotion engine detects the user's stress and fatigue from this statement.

[1090] 3. The generative AI responds, "That's tough. What exactly is stressing you out?"

[1091] 4. The server records this conversation and emotion data and stores it for reference during the next call.

[1092] Ending a call and feedback

[1093] When the call ends, the user taps the "End Call" button and optionally enters their thoughts and feedback. The device sends the end request and feedback information to the server, which then ends the call session and stores the end information in a database. The server also receives user feedback and uses it to improve the generative AI model and emotion engine.

[1094] Example prompts to input to the generative AI model

[1095] prompt:

[1096] "Please use the template below to respond to a user who is suffering from insomnia. Detect stress or fatigue from the user's tone of voice and choice of words, and engage in appropriate dialogue."

[1097] 1. User: "I've been so stressed out at work lately that I can't sleep."

[1098] 2. Emotion engine: Detects stress and fatigue.

[1099] 3. Generative AI: "That sounds tough. What exactly is stressing you out?"

[1100] In this way, the system according to the present invention can understand the user's emotions and provide more appropriate interactions.

[1101] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1102] Step 1:

[1103] The user enters basic information.

[1104] Input: The user enters basic information such as name, age, and hobbies into the input form displayed on the terminal.

[1105] Specific behavior: The user enters information and taps the submit button.

[1106] Output: The entered information is saved on the device.

[1107] Step 2:

[1108] The terminal sends the information to the server.

[1109] Input: Basic information entered by the user in step 1.

[1110] Specific operation: The terminal generates a data packet for transmitting the input basic information to the server.

[1111] Output: The user's basic information is sent to the server.

[1112] Step 3:

[1113] The server verifies the information and stores it in a database.

[1114] Input: Basic information of the user sent from the device.

[1115] Specific operations: The server validates the format of the data received and saves it to the database. A user ID is generated and associated with basic information.

[1116] Output: The user profile is saved in the database.

[1117] Step 4:

[1118] The user selects the AI.

[1119] Input: On the app's home screen, the user selects the AI ​​they want to talk to from among the chat AI, consultation AI, and learning support AI.

[1120] Specific operation: The user selects the desired AI and taps the "Start call" button.

[1121] Output: The information of the selected AI is saved on the device.

[1122] Step 5:

[1123] The device sends a request to the server.

[1124] Input: Selected AI information and call start request.

[1125] Specific operation: The terminal generates a data packet for transmitting the selected AI information and a call start request.

[1126] Output: A call start request and selected AI information is sent to the server.

[1127] Step 6:

[1128] The server establishes the session.

[1129] Input: The call initiation request sent from the device and selected AI information.

[1130] What it does: The server loads the appropriate generative artificial intelligence model and establishes the call session, along with the user's profile data and past conversation records.

[1131] Output: A call session is started.

[1132] Step 7:

[1133] The emotion engine analyzes emotions.

[1134] Input: User voice and text input.

[1135] Specific operation: The emotion engine analyzes voice and text data to detect the user's emotions (stress, joy, fatigue, etc.).

[1136] Output: The analyzed emotion data is sent to the server.

[1137] Step 8:

[1138] The server receives the emotion data and provides it to the generative artificial intelligence.

[1139] Input: Emotion data sent from the emotion engine.

[1140] Specific operation: The server receives emotion data and generates a data packet to provide to the generative artificial intelligence.

[1141] Output: Emotion data is provided to a generative AI.

[1142] Step 9:

[1143] Generative artificial intelligence generates responses.

[1144] Input: Initial input and emotion data from the user.

[1145] Specific behavior: Based on the input, the generative AI takes in the emotional data analyzed by the emotion engine and generates a response. For example, "What specifically is causing you stress?"

[1146] Output: The generated response is returned to the user.

[1147] Step 10:

[1148] The server records the conversation and stores it in a database.

[1149] Input: Conversational content and emotional data between the generative AI and the user.

[1150] Specific operation: The server records all conversation content in a database and saves it for future reference.

[1151] Output: Conversation records and emotion data are stored in a database.

[1152] Step 11:

[1153] The user ends the call and provides feedback.

[1154] Input: End-of-call instructions and feedback information.

[1155] What happens: The user taps the "End Call" button and optionally enters thoughts or feedback.

[1156] Output: The termination request and feedback information are saved to the terminal.

[1157] Step 12:

[1158] The terminal sends a termination request to the server.

[1159] Input: Call termination request and feedback information.

[1160] Specific operation: The terminal generates a data packet for transmitting a termination request and feedback information.

[1161] Output: A termination request and feedback information is sent to the server.

[1162] Step 13:

[1163] The server ends the session and saves the feedback.

[1164] Input: The termination request and feedback information sent from the terminal.

[1165] Specific operation: The server ends the call session and stores the end information in a database. It also uses the received feedback information to improve the generative AI model and emotion engine.

[1166] Output: The end of the call session and feedback information are stored in a database and used to improve the system.

[1167] (Application example 2)

[1168] 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."

[1169] Conventional AI dialogue systems generate uniform responses without considering the user's emotional state, resulting in low dialogue quality and insufficient user satisfaction. Furthermore, in customer support at physical stores, they are unable to provide personalized services that reflect the customer's real-time emotional state.

[1170] 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.

[1171] In this invention, the server includes means for inputting and saving basic information about the user, means for using a generative artificial intelligence to have a dialogue with the user, means for storing the content of the user's past conversations and reflecting that content in the next conversation, means for analyzing the user's emotional state using an emotion analysis engine, and means for adjusting the response of the generative artificial intelligence based on the analyzed emotional state. This enables personalized responses that take into account the individual emotional state of the user, thereby providing higher levels of satisfaction in customer support at physical stores.

[1172] "Basic user information" refers to individual information such as the user's name, age, and hobbies.

[1173] "Generative AI" is AI that generates natural dialogue based on user input, such as systems like ChatGPT.

[1174] "Means for dialogue" refers to an interface or system that allows real-time conversations and message exchanges between the user and generative AI.

[1175] "Means for storing the contents of a user's past conversations and reflecting them in the next conversation" refers to a means for saving the contents of previous conversations with a user and using them to improve the next conversation.

[1176] An "emotion analysis engine" is an engine that analyzes the user's emotional state from their voice or text input and outputs the results.

[1177] The "means for adjusting the response" is a means for changing the dialogue content generated by the generative artificial intelligence based on the output results of the emotion analysis engine, and providing an appropriate response.

[1178] A "brick and mortar store" is a commercial establishment or service location located in a physical location.

[1179] "Customer support" refers to support activities to respond to customer questions and inquiries and resolve problems.

[1180] The present invention is a system for providing customer support in brick-and-mortar stores. In the specific embodiment shown below, real-time dialogue is provided using a combination of generative artificial intelligence and an emotion analysis engine, using a terminal such as a smartphone, tablet, or information robot installed in the store.

[1181] User registration and profile settings

[1182] Users install the application on their smartphones or tablets and enter basic information such as their name, age, purchase history, hobbies, etc. This information is sent from the device to a server and stored in a database, creating a detailed profile for each user.

[1183] Starting a conversation

[1184] The user selects a customer support AI from the application's home screen and taps the "Start Dialogue" button. The device sends the selected AI information and a dialogue start request to the server, requesting a dialogue session. The server loads an appropriate generative AI model and establishes a dialogue session. It also loads the user's profile and past conversation records to use in the next dialogue.

[1185] Utilizing a sentiment analysis engine

[1186] The emotion analysis engine analyzes emotions from the user's voice and text input and sends the results to the server in real time. The generative AI then takes this emotional data and generates an appropriate response. For example, if a user expresses confusion or dissatisfaction, a response incorporating that emotion will be provided, allowing the user to receive more satisfying support.

[1187] Conversation progression and data recording

[1188] The server records all conversations in real time and stores them in a database. The recorded conversation data and emotion data are used in subsequent conversations. In particular, past problem history and complaint information are reflected in the next assistance, allowing for higher quality service.

[1189] Closing the conversation and feedback

[1190] After the dialogue is finished, the user taps the "End dialogue" button, and an end request is sent to the server. If necessary, the user can enter their thoughts or feedback, which is also sent to the server. The server stores the end information in a database and uses the feedback information to improve the generative AI model and sentiment analysis engine.

[1191] Hardware and Software Configuration

[1192] The system of the present invention uses the following hardware and software.

[1193] Hardware: Smartphones, tablets, information robots

[1194] Software: Generative AI model (ChatGPT), emotion analysis engine (EmotionEngine), database (SQLite), server program

[1195] Suggested concrete examples

[1196] For example, if a user says in a store, "Tell me more about this product," the following prompt sentence can be generated and responded to:

[1197] Input prompt for the generative AI model:

[1198] My name is Taro Sato. I'm interested in music and painting. My current emotion is joy. Please tell me more about this product.

[1199] Based on this prompt, the generative AI will return an appropriate response such as, "This product is a cutting-edge music player that combines high sound quality with ease of use. It is especially recommended for music lovers!" This allows users to obtain appropriate information quickly, improving satisfaction.

[1200] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1201] Step 1:

[1202] The user installs the application on the terminal and starts the application.

[1203] Specific operation: After downloading the application, the user enters basic information such as name, age, and hobbies.

[1204] Input and Output: The user's basic information is entered and sent by the device to the server, which stores this information in a database and creates a profile for each user.

[1205] Step 2:

[1206] The user selects the customer support AI from the application's home screen and taps the "Start conversation" button.

[1207] Specific operation: The user selects the AI ​​they want to interact with on the home screen and sends a request to start interacting.

[1208] Input and Output: The device receives the user's selection information and a request to initiate a dialogue, which it then sends to the server. The server loads the generative AI model and establishes a dialogue session. It also loads the user's profile data and past conversation records.

[1209] Step 3:

[1210] The emotion analysis engine analyzes emotions from the user's voice and text input and sends the results to the server.

[1211] Specific operation: The user's voice and text are input into an emotion analysis engine, which analyzes their emotional state (happiness, confusion, frustration, etc.).

[1212] Input and output: User voice and text are input, and the emotion analysis engine analyzes and outputs emotional data. This is received by the server.

[1213] Step 4:

[1214] Generative AI generates appropriate responses for users based on data from the sentiment analysis engine.

[1215] How it works: Emotional data is fed into a generative AI model to generate personalized responses for the user.

[1216] Input and output: Emotional data from the sentiment analysis engine is input, and the generative AI outputs an appropriate response. For example, in response to a user's input such as "Tell me more about this product," the system generates a response such as "This product is a cutting-edge music player that combines high sound quality with ease of use."

[1217] Step 5:

[1218] The server records all conversations in real time and stores them in a database.

[1219] Specific operation: The dialogue content and emotion data are sent to the server in real time and recorded in a database.

[1220] Input and output: The user's dialogue and emotional data are input and stored in a database as a record, which can then be used in future dialogues.

[1221] Step 6:

[1222] After the conversation is over, the user taps the "End conversation" button to send a request to the server to end the conversation. If necessary, the user can enter their thoughts or feedback.

[1223] Specific operation: After the user finishes the interaction, he / she sends an end request and feedback information.

[1224] Input and Output: User exit requests and feedback are input and stored on the server. Feedback information is used to improve the generative artificial intelligence and sentiment analysis engine.

[1225] 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.

[1226] 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.

[1227] 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.

[1228] [Third embodiment]

[1229] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1230] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1231] 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).

[1232] 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.

[1233] 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.

[1234] 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).

[1235] 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.

[1236] 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.

[1237] 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.

[1238] 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.

[1239] 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.

[1240] 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."

[1241] The present invention is a system that allows users to easily find someone to talk to through a call with a generative AI of their choice. Specifically, the system inputs and saves basic information about the user, uses the generative AI to talk to the user, and also has the ability to remember the content of past conversations and reflect it in the next conversation.

[1242] System Overview

[1243] The system mainly consists of a user device, a server, and a generative artificial intelligence (ChatGPT). Users install and launch the app using their smartphone or tablet.

[1244] User registration and profile settings

[1245] User:

[1246] Users install and launch the app and enter basic information such as their name, age, and hobbies, which allows the application to set up a personalized profile for the user.

[1247] Device:

[1248] The terminal transmits the information entered by the user to the server and stores it as profile data.

[1249] server:

[1250] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[1251] AI selection and call initiation

[1252] User:

[1253] From the app's home screen, users can choose from chat AI, consultation AI, or learning support AI, and then tap the "Start Call" button to begin the call.

[1254] Device:

[1255] The terminal sends the selected AI information and a call start request to the server and prepares to establish a call session.

[1256] server:

[1257] The server loads the appropriate generative artificial intelligence model based on the selected AI information, establishes a call session, and loads the user's profile data and past conversation records.

[1258] Conversation progression and data recording

[1259] Generative AI (ChatGPT):

[1260] Generative AI generates appropriate responses in real time based on user input, allowing users to easily find someone to talk to.

[1261] server:

[1262] The server records all conversations in real time and stores them in a database, which can be used in subsequent calls.

[1263] Specific examples

[1264] Let's say a user is suffering from insomnia in the middle of the night. The user opens the app, selects the consultation AI, and starts a call.

[1265] User:

[1266] "Work has been so stressful lately that I can't sleep."

[1267] Generative AI:

[1268] "That's tough. What exactly is stressing you out?"

[1269] server:

[1270] The server records this conversation and stores it for reference during the next call.

[1271] Ending a call and feedback

[1272] User:

[1273] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed.

[1274] Device:

[1275] The terminal sends a termination request and feedback information to the server.

[1276] server:

[1277] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model.

[1278] As a result, the system based on the present invention functions as a friend that can provide appropriate responses to the user 24 hours a day, 365 days a year, thereby reducing the user's mental burden and improving their quality of life.

[1279] The processing flow will be explained below.

[1280] Step 1:

[1281] User:

[1282] The user installs the app on their smartphone or tablet and launches it.

[1283] Step 2:

[1284] User:

[1285] Users enter basic information such as their name, age, and email address on the account creation screen and tap the "Sign up" button.

[1286] Step 3:

[1287] Device:

[1288] The terminal transmits the input basic information to the server.

[1289] Step 4:

[1290] server:

[1291] The server verifies the received information and, if there are no problems, stores the user's basic information in a database.

[1292] The server will send a confirmation email to the user to complete the account creation.

[1293] Step 5:

[1294] User:

[1295] The user clicks on the link in the confirmation email they receive to complete their account registration.

[1296] Step 6:

[1297] User:

[1298] Users enter additional information such as hobbies, interests, and goals in the app's profile settings screen.

[1299] Step 7:

[1300] Device:

[1301] The terminal transmits the input profile information to the server.

[1302] Step 8:

[1303] server:

[1304] The server stores the received profile information in a database and generates a detailed profile for the user.

[1305] Step 9:

[1306] User:

[1307] On the home screen, users can select the AI ​​they want to talk to from among the chat AI, consultation AI, and learning support AI.

[1308] Step 10:

[1309] Device:

[1310] The device sends the selected AI information to the server and requests a call session.

[1311] Step 11:

[1312] server:

[1313] The server receives the request and loads the generative artificial intelligence model according to the selected AI, as well as the user's profile data and past conversation records.

[1314] Step 12:

[1315] User:

[1316] The user taps the "Start Call" button.

[1317] Step 13:

[1318] Device:

[1319] The terminal sends a call initiation request to the server.

[1320] Step 14:

[1321] server:

[1322] The server establishes the call session, initializes the generative AI (ChatGPT), and prepares to receive user input in real time.

[1323] Step 15:

[1324] Generative AI (ChatGPT):

[1325] Generative AI generates appropriate responses based on input from the user and replies to the user.

[1326] Step 16:

[1327] server:

[1328] The server records all conversations in real time and stores them in a database, allowing past conversation data to be accumulated and used for the next conversation.

[1329] Step 17:

[1330] User:

[1331] When the user finishes the call, he taps the "end call" button.

[1332] Step 18:

[1333] Device:

[1334] The terminal sends a call termination request to the server.

[1335] Step 19:

[1336] server:

[1337] The server terminates the call session and stores the termination information in a database.

[1338] Step 20:

[1339] User:

[1340] The user enters their thoughts and feedback on the call on the post-call screen.

[1341] Step 21:

[1342] Device:

[1343] The terminal transmits the feedback information to the server.

[1344] Step 22:

[1345] server:

[1346] The server receives the feedback and stores it in a database. The feedback information is analyzed and used to improve the generative AI model.

[1347] The above are the specific processing steps of the present invention.

[1348] Example 1

[1349] 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."

[1350] Conventional communication systems have the problem that it is difficult to provide a conversation partner in real time and lack the functionality to effectively reflect the user's past conversation content, which hinders the improvement of the user experience. Furthermore, there is no mechanism for reflecting user feedback in the AI ​​model, making it difficult to maintain and improve call quality.

[1351] 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.

[1352] In this invention, the server includes means for inputting and saving basic user information, means for using generative artificial intelligence to conduct phone calls with the user, and means for storing the content of the user's past conversations and incorporating it into the next conversation. This allows the user to find someone to talk to in real time, and the content of the past conversations can be used for the next call, improving the user experience. The server also includes means for establishing a call with a generative artificial intelligence model selected by the user, means for recording the content of the call in real time and saving it in a format that can be referenced later, and means for receiving feedback from the user after the call ends and using it to improve the artificial intelligence model. This allows the feedback to be incorporated into the artificial intelligence model, enabling the maintenance and improvement of call quality.

[1353] "Basic information" is data entered by the user for personal identification and individualization, such as name, age, hobbies, etc.

[1354] "Generative AI" is an AI system that generates responses in natural language in response to input from a user.

[1355] "Call" refers to interactive communication with a user via generative artificial intelligence.

[1356] "Profile data" is a data set that includes basic information about a user and the contents of past conversations.

[1357] A "call session" is a continuous process of interaction with a user conducted using generative artificial intelligence.

[1358] "Real-time" refers to interactions being processed and reacted to the instant they are sent or received.

[1359] "Feedback" refers to information such as evaluations, impressions, and requests for improvement provided by users after a call has ended.

[1360] A "database" is an information repository where user profile data and conversations are stored.

[1361] "Model improvement" is the process of improving the response accuracy and quality of generative artificial intelligence based on feedback from users.

[1362] The "selected generative artificial intelligence model" is the generative artificial intelligence algorithm that is most suitable for the application specified by the user.

[1363] The present invention is a system that allows users to easily find someone to talk to using a generative AI selected by the user. This system consists of a user terminal, a server, and a generative AI (e.g., ChatGPT). The following describes the specific steps and operation methods for implementing the present invention.

[1364] User registration and profile settings

[1365] User:

[1366] Users install and launch the dedicated app on their smartphone or tablet and enter basic information such as their name, age, hobbies, etc. For example, a user may say their name is "Taro," their age is "30," and their hobby is "reading."

[1367] Device:

[1368] The terminal transmits the information entered by the user to the server, including the user's name, age, and hobbies.

[1369] server:

[1370] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[1371] AI selection and call initiation

[1372] User:

[1373] From the app's home screen, users can select one of the following AIs: chat AI, consultation AI, or learning support AI, and then tap the "Start Call" button. For example, select "Consultation AI."

[1374] Device:

[1375] The terminal sends the selected AI information and a call start request to the server. The user ID and AI type are sent.

[1376] server:

[1377] The server loads the appropriate generative AI model (e.g., ChatGPT) based on the selected AI information and establishes the call session, along with the user's profile data and past conversation records.

[1378] Conversation progression and data recording

[1379] User:

[1380] The user can freely converse with the generative AI. For example, the user can input, "I've been stressed out at work lately and I can't sleep."

[1381] Generative AI (ChatGPT):

[1382] The generative AI responds, "That's tough. What exactly is stressing you out?" and generates an appropriate response in real time.

[1383] server:

[1384] The server records all conversations in real time and stores them in a database, allowing this information to be used in future calls.

[1385] Ending a call and feedback

[1386] User:

[1387] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed. For example, they can enter feedback such as "That was very helpful."

[1388] Device:

[1389] The terminal sends a termination request and feedback information to the server.

[1390] server:

[1391] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model.

[1392] Examples of concrete examples and prompts

[1393] Specific examples

[1394] Consider a situation where a user is suffering from insomnia in the middle of the night. The user opens the app, selects the consultation AI, and starts a call.

[1395] User:

[1396] "Work has been so stressful lately that I can't sleep."

[1397] Generative AI (ChatGPT):

[1398] "That's tough. What exactly is stressing you out?"

[1399] server:

[1400] The server records this conversation and stores it for reference during the next call.

[1401] Prompt Sentence Examples

[1402] "Recently, I've been having trouble sleeping because of stress at work. What can I do to make myself feel a little better?"

[1403] Through this prompt, the user can receive appropriate advice from the generative artificial intelligence.

[1404] According to the above procedures and operation methods, the system based on the present invention can function as a friend who is available to the user 24 hours a day, 365 days a year, reducing the user's mental burden and improving the quality of life.

[1405] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1406] Step 1:

[1407] User registration and profile settings

[1408] User:

[1409] Users install and launch the app and enter basic information (name, age, hobbies, etc.).

[1410] Input: User's name, age, hobbies

[1411] Output: Data sent from the basic information input screen

[1412] Device:

[1413] The device sends the information entered by the user to the server, including the user's name, age, and hobbies.

[1414] Input: Data entered by the user

[1415] Output: Data sent to the server

[1416] server:

[1417] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[1418] Input: Basic user information sent from the device

[1419] Output: User profile data stored in a database

[1420] Step 2:

[1421] AI selection and call initiation

[1422] User:

[1423] From the app's home screen, users select one of the chat AI, consultation AI, or learning support AI and tap the "Start Call" button.

[1424] Input: User's AI selection and call start request

[1425] Output: AI selection instructions and call start request

[1426] Device:

[1427] The terminal sends the selected AI information and a call start request to the server. Specifically, the AI ​​type and user ID are sent.

[1428] Input: User's AI selection information and call start request

[1429] Output: The request data sent to the server

[1430] server:

[1431] The server loads the appropriate generative artificial intelligence model based on the selected AI and establishes the call session, as well as the user's profile data and past conversation records.

[1432] Input: AI selection information and call start request sent from the device

[1433] Output: A loaded generative AI model, an established call session

[1434] Step 3:

[1435] Conversation progression and data recording

[1436] User:

[1437] The user can freely converse with the generative AI, for example, by inputting, "I've been so stressed out at work lately that I can't sleep."

[1438] Input: User spoken input

[1439] Output: prompts for generative AI

[1440] Generative AI (ChatGPT):

[1441] Based on user input, generative AI generates appropriate responses in real time, such as, "That's tough. What exactly is stressing you out?"

[1442] Input: Prompt from user

[1443] Output: The generated response

[1444] server:

[1445] The server records all conversations in real time and stores them in a database, allowing this information to be used in future calls.

[1446] Input: Conversation data between the generative AI and the user

[1447] Output: Conversation transcript stored in database

[1448] Step 4:

[1449] Ending a call and feedback

[1450] User:

[1451] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed. For example, they can enter feedback such as "That was very helpful."

[1452] Input: Tap the end call button, feedback

[1453] Output: Call termination request, feedback data

[1454] Device:

[1455] The terminal sends a termination request and feedback information to the server.

[1456] Input: User end call request, feedback

[1457] Output: Finished request and feedback data sent to the server

[1458] server:

[1459] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model.

[1460] Input: End call request sent from the device, feedback

[1461] Output: Call termination information stored in a database, feedback data for model improvement

[1462] (Application example 1)

[1463] 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."

[1464] In today's world, when users purchase products online, they need a lot of information, and if they do not receive appropriate support, their motivation to purchase decreases. Furthermore, if customers cannot resolve specific questions about a product, they risk missing out on a purchasing opportunity. Furthermore, online stores face the challenge of finding personalized product recommendations and support for each individual customer.

[1465] 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.

[1466] In this invention, the server includes means for inputting and saving basic information about the user, means for using generative artificial intelligence to communicate with the user, means for storing the content of past conversations with the user and reflecting this in the next conversation, means for using generative artificial intelligence selected by the user to provide product-related questions and advice in real time within a virtual store, means for recommending optimal products to the user based on their purchase history and the content of past conversations, and means for collecting feedback and improving support quality. This allows users to receive prompt and accurate support in real time when making online purchases, increasing their desire to purchase and enabling optimal product recommendations.

[1467] "Basic user information" refers to information necessary to form an individual profile, such as the user's name, age, and purchase history.

[1468] "Generative AI" is an AI system that generates appropriate responses in real time based on user input.

[1469] "Means for making calls" refers to a means of communication that allows the generative artificial intelligence and the user to interact in real time.

[1470] "Means for remembering the content of past conversations and reflecting it in the next conversation" refers to a means for providing continuous support by saving the content of the previous conversation and referring to it in the next conversation.

[1471] A "virtual store" is an online shopping environment used via the Internet where users can browse and purchase products.

[1472] The "means for providing product-related questions and advice in real time" is an interactive support system that can answer questions about products and how to use them on the spot when users ask questions within the virtual store.

[1473] "Purchase history" is a record of products that a user has purchased in the past.

[1474] "Means for recommending optimal products to users based on past conversation content" refers to a system that suggests products that meet individual user needs based on the user's past conversations and behavioral history.

[1475] "Means for collecting feedback and improving support quality" refers to a means for incorporating user evaluations and opinions into the system and using them to improve the performance and response accuracy of the generative artificial intelligence.

[1476] This invention is a system that provides optimal support to users in a virtual store by inputting and saving basic information about the user, using generative artificial intelligence to communicate with the user, and storing the content of past conversations and reflecting it in the next conversation. Specific embodiments for implementing this invention are described below.

[1477] System configuration

[1478] The system consists of the following main components:

[1479] 1. User Device

[1480] Using mobile devices such as smartphones and tablets, users can access virtual stores and talk to AI.

[1481] 2. Server

[1482] A high-performance database server is used to store and manage basic user information, purchase history, past conversations, etc. A cloud-based database such as AWS RDS is suitable for the server.

[1483] 3. Generative Artificial Intelligence

[1484] Using OpenAI's ChatGPT API, the system generates responses to users' real-time questions. This AI generates appropriate responses based on user input, maintaining the continuity of the conversation.

[1485] Processing Flow

[1486] 1. User Registration and Profile Settings

[1487] The application is installed on the user's device and launched. The user enters basic information such as name, age, hobbies, and purchasing history. This data is sent to the server and stored in a database.

[1488] 2. AI selection and call initiation

[1489] The user selects "Customer Support" from the application's home screen and taps the "Start Call" button. The server loads the user's profile data and loads the appropriate generative artificial intelligence model.

[1490] 3. Conversation management and data recording

[1491] The generative artificial intelligence (ChatGPT) responds to user questions and requests in real time. For example, if a user asks, "What are the features of this smartphone?", the AI ​​will respond, "This smartphone is equipped with a high-resolution camera, a state-of-the-art processor, and boasts a long battery life. It is also waterproof."

[1492] 4. Call End and Feedback

[1493] When the user finishes the call, they tap the "End Call" button and the call ends. After the call ends, the user enters feedback, which is sent to the server. The server collects the feedback and uses it to improve the AI ​​model.

[1494] Explanation of program processing

[1495] The server first stores the user's basic information in a database. Then, when the user sends a request to talk to a specific AI, the server loads the user's past conversations and launches the appropriate generative AI model. During the call, the server records the AI's responses and the user's input in real time, making them available for reference in the next conversation.

[1496] For hardware, smartphones and tablets are used as user devices, and cloud-based solutions such as AWS RDS are used as database servers. For software, OpenAI's ChatGPT API is used for generative artificial intelligence, and React Native is used for application development.

[1497] Prompt Sentence Examples

[1498] Examples of specific prompts include:

[1499] "User: Tell me about the new features on your smartphone these days. Generative AI:"

[1500] "User: What's the best way to use this camera? Generative AI:"

[1501] This allows users to receive prompt and accurate support in real time when making online purchases, which increases purchasing motivation and enables optimal product recommendations.

[1502] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1503] Step 1:

[1504] The user enters basic information

[1505] Input: Users enter basic information such as name, age, hobbies, and purchase history into an application on their smartphone or tablet.

[1506] Data processing: The terminal formats the entered user information and converts it into a format that can be sent to the server.

[1507] Output: The formatted user information is sent to the server.

[1508] Specific actions: Enter user information into the application form and tap the "Submit" button.

[1509] Step 2:

[1510] The server stores basic information

[1511] Input: Basic information of the user sent from the device.

[1512] Data Calculation: The server verifies the received user information and stores it in the database.

[1513] Output: A confirmation message that the save was successful is returned to the terminal.

[1514] Specific operation: The server checks the integrity of the received data and saves the information to the MySQL database using an INSERT statement.

[1515] Step 3:

[1516] The user selects the generative AI

[1517] Input: The user selects "Customer Support" or another AI model from the application home screen.

[1518] Data processing: The device generates a request to send information about the selected AI model to the server.

[1519] Output: The generated request is sent to the server.

[1520] What it does: Tap an option such as "Customer Support" from the application's menu.

[1521] Step 4:

[1522] The server establishes the call session

[1523] Input: The call initiation request sent from the device and the user's profile data.

[1524] Data computation: The server loads the appropriate generative artificial intelligence model and retrieves past conversation content from the database.

[1525] Output: The call session is ready to begin and the device is notified.

[1526] What it does: The server loads profile data and conversation history and sets up the AI ​​model for operation.

[1527] Step 5:

[1528] Generative AI starts the conversation

[1529] Input: The initial input from the user (e.g., "What are the features of this phone?").

[1530] Data Computation: Generative AI processes input text and generates appropriate prompts.

[1531] Output: A response based on the generated prompt is returned to the user.

[1532] What it does: Uses ChatGPT API to generate and reply to responses based on user input in real time.

[1533] Step 6:

[1534] The server records the conversation

[1535] Input: Real-time generated AI responses and user input.

[1536] Data calculation: The contents of the conversation are saved in a database and managed as history for use in future conversations.

[1537] Output: The save completion confirmation status is updated internally.

[1538] Specific operation: The server inserts and updates the received conversation data into the database in real time.

[1539] Step 7:

[1540] User ends the call and provides feedback

[1541] Input: Feedback entered by the user at the end of the call (e.g., "Thank you for your prompt response").

[1542] Data processing: The terminal sends the termination request and feedback information to the server.

[1543] Output: The feedback information is stored in the server and a completion message is returned to the user terminal.

[1544] Specific actions: The user taps the "End call" button, enters their opinion in the feedback form, and taps the "Submit" button.

[1545] Step 8:

[1546] The server improves the AI ​​model based on the feedback.

[1547] Input: Feedback information from the user.

[1548] Data calculation: The server analyzes the feedback and reflects it to improve the response accuracy of the generative AI.

[1549] Output: The AI ​​model has been improved and will be reflected in future calls.

[1550] What it does: Analyzes the feedback data and retrains the model by adding it to the generative artificial intelligence training dataset.

[1551] 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.

[1552] The present invention is a system that combines generative artificial intelligence with an emotion engine that recognizes the user's emotions. This allows for more personalized and emotionally appropriate dialogue for the user. Specifically, the system inputs and saves basic user information, uses generative artificial intelligence to communicate with the user, and has the ability to remember the content of past conversations and reflect it in the next conversation.

[1553] System Overview

[1554] The system mainly consists of a user device, a server, a generative AI (ChatGPT), and an emotion engine. Users install and launch the app on their smartphone or tablet.

[1555] User registration and profile settings

[1556] User:

[1557] Users install and launch the app and enter basic information such as their name, age, and hobbies, which allows the application to set up a personalized profile for the user.

[1558] Device:

[1559] The terminal transmits the information entered by the user to the server and stores it as profile data.

[1560] server:

[1561] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[1562] AI selection and call initiation

[1563] User:

[1564] From the app's home screen, users select the AI ​​they want to talk to from the chat AI, consultation AI, or learning support AI, and tap the "Start Call" button.

[1565] Device:

[1566] The terminal transmits the selected AI information and a call start request to the server to request a call session.

[1567] server:

[1568] The server loads the appropriate generative artificial intelligence model based on the selected AI and establishes the call session, as well as the user's profile data and past conversation records.

[1569] Utilizing the Emotion Engine

[1570] Emotion Engine:

[1571] The emotion engine analyzes emotions from the user's voice and text input, and transmits them to the server in real time, which reflects them in the generative artificial intelligence's responses.

[1572] Generative AI (ChatGPT):

[1573] Based on user input, the generative AI takes in emotional data analyzed by the emotion engine and generates an appropriate response, allowing users to easily find someone to talk to.

[1574] Conversation progression and data recording

[1575] server:

[1576] The server records all conversations in real time and stores them in a database. The recorded conversation data is used in subsequent calls. Emotion engine data is also stored and used to analyze the user's emotional patterns.

[1577] Specific examples

[1578] Let's say a user is suffering from insomnia in the middle of the night. The user opens the app, selects the consultation AI, and starts a call.

[1579] User:

[1580] "Work has been so stressful lately that I can't sleep."

[1581] Emotion Engine:

[1582] Detects stress and fatigue from the user's tone of voice and choice of words.

[1583] Generative AI:

[1584] "That's tough. What exactly is stressing you out?"

[1585] server:

[1586] The server records this conversation and emotional data and stores it for reference during the next call.

[1587] Ending a call and feedback

[1588] User:

[1589] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed.

[1590] Device:

[1591] The terminal sends a termination request and feedback information to the server.

[1592] server:

[1593] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model and emotion engine.

[1594] As a result, the system based on the present invention can understand the user's emotions and provide an appropriate response, thereby providing psychological support to the user.

[1595] The processing flow will be explained below.

[1596] Step 1:

[1597] User:

[1598] The user installs the app on their smartphone or tablet and launches it.

[1599] Step 2:

[1600] User:

[1601] Users enter basic information such as their name, age, email address, and hobbies on the account creation screen and tap the "Sign up" button.

[1602] Step 3:

[1603] Device:

[1604] The terminal transmits the input basic information to the server.

[1605] Step 4:

[1606] server:

[1607] The server verifies the received information and, if there are no problems, stores the user's basic information in a database. The server then sends the user a confirmation email to complete the account creation.

[1608] Step 5:

[1609] User:

[1610] The user clicks on the link in the confirmation email they receive to complete their account registration.

[1611] Step 6:

[1612] User:

[1613] Users enter additional information such as hobbies, interests, and goals in the app's profile settings screen.

[1614] Step 7:

[1615] Device:

[1616] The terminal transmits the input profile information to the server.

[1617] Step 8:

[1618] server:

[1619] The server stores the received profile information in a database and generates a detailed profile for the user.

[1620] Step 9:

[1621] User:

[1622] On the home screen, users can select the AI ​​they want to talk to from among the chat AI, consultation AI, and learning support AI.

[1623] Step 10:

[1624] Device:

[1625] The device sends the selected AI information to the server and requests a call session.

[1626] Step 11:

[1627] server:

[1628] The server receives the request and loads the generative artificial intelligence model according to the selected AI, as well as the user's profile data and past conversation records.

[1629] Step 12:

[1630] User:

[1631] The user taps the "Start Call" button.

[1632] Step 13:

[1633] Device:

[1634] The terminal sends a call initiation request to the server.

[1635] Step 14:

[1636] server:

[1637] The server establishes a call session, initializes the generative AI (ChatGPT), prepares to receive user input in real time, and starts the emotion engine to prepare to analyze user input.

[1638] Step 15:

[1639] User:

[1640] The user initiates a call with the generative AI and types or speaks what they want to say.

[1641] Step 16:

[1642] Emotion Engine:

[1643] The emotion engine analyzes emotions from the user's voice and text input and sends the data to the server in real time.

[1644] Step 17:

[1645] Generative AI (ChatGPT):

[1646] Based on input from the user, generative AI takes in emotional data analyzed by the emotion engine and generates an appropriate response.

[1647] Step 18:

[1648] server:

[1649] The server records all conversation content and emotional data in real time and stores it in a database, allowing past conversation data and emotional patterns to be accumulated and used in the next conversation.

[1650] Step 19:

[1651] User:

[1652] When the user finishes the call, he taps the "end call" button.

[1653] Step 20:

[1654] Device:

[1655] The terminal sends a call termination request to the server.

[1656] Step 21:

[1657] server:

[1658] The server ends the call session and stores the information in a database at the time of termination. The recorded data is analyzed and used to provide the user with a more appropriate response in the next conversation.

[1659] Step 22:

[1660] User:

[1661] The user enters their thoughts and feedback on the call on the post-call screen.

[1662] Step 23:

[1663] Device:

[1664] The terminal transmits the feedback information to the server.

[1665] Step 24:

[1666] server:

[1667] The server receives the feedback and stores it in a database. The feedback information is analyzed and used to improve the generative AI and emotion engine models.

[1668] As a result, the system based on the present invention is a system that can recognize the user's emotions in real time and provide an appropriate response, thereby providing psychological support to the user.

[1669] Example 2

[1670] 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."

[1671] Conventional dialogue systems using generative AI generally respond without considering the user's emotions, which prevents them from providing sufficient personalization or emotional support. Furthermore, they fail to fully utilize past conversations, making it difficult to build a lasting relationship with the user. Furthermore, they lack a mechanism for incorporating user feedback into system improvements.

[1672] 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.

[1673] In this invention, the server includes a means for inputting and saving basic user information, a means for using generative artificial intelligence to communicate with the user, a means for storing the content of the user's past conversations and reflecting that content in the next conversation, and a means for analyzing the user's emotions and reflecting that content in the conversation. This enables personalized dialogue that understands emotions, providing psychological support to the user and building a lasting relationship. Furthermore, user feedback can be used to improve the artificial intelligence model, thereby improving system performance.

[1674] "Basic user information" is data indicating personal attributes such as the user's name, age, hobbies, etc.

[1675] "Generative AI" refers to an AI system that uses natural language processing to interact with users, such as ChatGPT.

[1676] "Means for communicating with the user" refers to a mechanism for two-way communication with the user via voice or text via generative artificial intelligence.

[1677] "Means of remembering the content of a user's past conversations and reflecting it in the next conversation" is a function that stores records of past conversations with the user in a database and uses that information to make the content of the next conversation more personalized.

[1678] "Means for analyzing emotions and reflecting them in the content of the call" refers to a mechanism that reads emotions from the user's voice and text and incorporates the results into the generative AI's response, thereby enabling a dialogue that is sensitive to the user's emotions.

[1679] "Personalized dialogue" refers to generating optimal responses for a user by taking into account the user's individual information, past conversations, emotional state, etc.

[1680] "Feedback" refers to the thoughts and opinions provided by users after a call ends, and is data used to improve the performance of the system and generative artificial intelligence.

[1681] The present invention relates to a system that understands user emotions and provides more personalized interactions. This system consists of a user terminal, a server, a generative artificial intelligence (e.g., ChatGPT), and an emotion engine.

[1682] Overall system overview

[1683] Users install and launch a dedicated application using a network-connected device such as a smartphone or tablet. The application inputs and saves the user's basic information and communicates with the user via a generative AI. It also uses an emotion engine to analyze the user's emotions and reflects them in the generative AI's responses.

[1684] User registration and profile settings

[1685] Through the application, users enter basic information such as name, age, hobbies, etc. This information is sent via the device to the server, which verifies the information received and stores it in a database to create a detailed user profile.

[1686] AI selection and call initiation

[1687] From the app's home screen, users select the AI ​​they want to talk to from among several AI models (such as chat AI, consultation AI, and learning support AI), and tap the "Start Call" button. The device sends this information and a call start request to the server, which then loads the appropriate generative AI model and establishes a call session. Additionally, the user's profile data and past conversation records are also loaded.

[1688] Use of emotion engine

[1689] The emotion engine analyzes the user's voice and text input in real time to generate emotional data. This allows the server to detect the user's emotions, such as stress or joy, and provides this information to the generative AI. The generative AI then takes in this emotional data and generates an appropriate response.

[1690] Specific examples

[1691] For example, consider a case where a user is suffering from insomnia. The user opens the application, selects a consultation AI, and starts a call.

[1692] 1. A user says, "Work has been so stressful lately that I can't sleep."

[1693] 2. The emotion engine detects the user's stress and fatigue from this statement.

[1694] 3. The generative AI responds, "That's tough. What exactly is stressing you out?"

[1695] 4. The server records this conversation and emotion data and stores it for reference during the next call.

[1696] Ending a call and feedback

[1697] When the call ends, the user taps the "End Call" button and optionally enters their thoughts and feedback. The device sends the end request and feedback information to the server, which then ends the call session and stores the end information in a database. The server also receives user feedback and uses it to improve the generative AI model and emotion engine.

[1698] Example prompts to input to the generative AI model

[1699] prompt:

[1700] "Please use the template below to respond to a user who is suffering from insomnia. Detect stress or fatigue from the user's tone of voice and choice of words, and engage in appropriate dialogue."

[1701] 1. User: "I've been so stressed out at work lately that I can't sleep."

[1702] 2. Emotion engine: Detects stress and fatigue.

[1703] 3. Generative AI: "That sounds tough. What exactly is stressing you out?"

[1704] In this way, the system according to the present invention can understand the user's emotions and provide more appropriate interactions.

[1705] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1706] Step 1:

[1707] The user enters basic information.

[1708] Input: The user enters basic information such as name, age, and hobbies into the input form displayed on the terminal.

[1709] Specific behavior: The user enters information and taps the submit button.

[1710] Output: The entered information is saved on the device.

[1711] Step 2:

[1712] The terminal sends the information to the server.

[1713] Input: Basic information entered by the user in step 1.

[1714] Specific operation: The terminal generates a data packet for transmitting the input basic information to the server.

[1715] Output: The user's basic information is sent to the server.

[1716] Step 3:

[1717] The server verifies the information and stores it in a database.

[1718] Input: Basic information of the user sent from the device.

[1719] Specific operations: The server validates the format of the data received and saves it to the database. A user ID is generated and associated with basic information.

[1720] Output: The user profile is saved in the database.

[1721] Step 4:

[1722] The user selects the AI.

[1723] Input: On the app's home screen, the user selects the AI ​​they want to talk to from among the chat AI, consultation AI, and learning support AI.

[1724] Specific operation: The user selects the desired AI and taps the "Start call" button.

[1725] Output: The information of the selected AI is saved on the device.

[1726] Step 5:

[1727] The device sends a request to the server.

[1728] Input: Selected AI information and call start request.

[1729] Specific operation: The terminal generates a data packet for transmitting the selected AI information and a call start request.

[1730] Output: A call start request and selected AI information is sent to the server.

[1731] Step 6:

[1732] The server establishes the session.

[1733] Input: The call initiation request sent from the device and selected AI information.

[1734] What it does: The server loads the appropriate generative artificial intelligence model and establishes the call session, along with the user's profile data and past conversation records.

[1735] Output: A call session is started.

[1736] Step 7:

[1737] The emotion engine analyzes emotions.

[1738] Input: User voice and text input.

[1739] Specific operation: The emotion engine analyzes voice and text data to detect the user's emotions (stress, joy, fatigue, etc.).

[1740] Output: The analyzed emotion data is sent to the server.

[1741] Step 8:

[1742] The server receives the emotion data and provides it to the generative artificial intelligence.

[1743] Input: Emotion data sent from the emotion engine.

[1744] Specific operation: The server receives emotion data and generates a data packet to provide to the generative artificial intelligence.

[1745] Output: Emotion data is provided to a generative AI.

[1746] Step 9:

[1747] Generative artificial intelligence generates responses.

[1748] Input: Initial input and emotion data from the user.

[1749] Specific behavior: Based on the input, the generative AI takes in the emotional data analyzed by the emotion engine and generates a response. For example, "What specifically is causing you stress?"

[1750] Output: The generated response is returned to the user.

[1751] Step 10:

[1752] The server records the conversation and stores it in a database.

[1753] Input: Conversational content and emotional data between the generative AI and the user.

[1754] Specific operation: The server records all conversation content in a database and saves it for future reference.

[1755] Output: Conversation records and emotion data are stored in a database.

[1756] Step 11:

[1757] The user ends the call and provides feedback.

[1758] Input: End-of-call instructions and feedback information.

[1759] What happens: The user taps the "End Call" button and optionally enters thoughts or feedback.

[1760] Output: The termination request and feedback information are saved to the terminal.

[1761] Step 12:

[1762] The terminal sends a termination request to the server.

[1763] Input: Call termination request and feedback information.

[1764] Specific operation: The terminal generates a data packet for transmitting a termination request and feedback information.

[1765] Output: A termination request and feedback information is sent to the server.

[1766] Step 13:

[1767] The server ends the session and saves the feedback.

[1768] Input: The termination request and feedback information sent from the terminal.

[1769] Specific operation: The server ends the call session and stores the end information in a database. It also uses the received feedback information to improve the generative AI model and emotion engine.

[1770] Output: The end of the call session and feedback information are stored in a database and used to improve the system.

[1771] (Application example 2)

[1772] 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."

[1773] Conventional AI dialogue systems generate uniform responses without considering the user's emotional state, resulting in low dialogue quality and insufficient user satisfaction. Furthermore, in customer support at physical stores, they are unable to provide personalized services that reflect the customer's real-time emotional state.

[1774] 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.

[1775] In this invention, the server includes means for inputting and saving basic information about the user, means for using a generative artificial intelligence to have a dialogue with the user, means for storing the content of the user's past conversations and reflecting that content in the next conversation, means for analyzing the user's emotional state using an emotion analysis engine, and means for adjusting the response of the generative artificial intelligence based on the analyzed emotional state. This enables personalized responses that take into account the individual emotional state of the user, thereby providing higher levels of satisfaction in customer support at physical stores.

[1776] "Basic user information" refers to individual information such as the user's name, age, and hobbies.

[1777] "Generative AI" is AI that generates natural dialogue based on user input, such as systems like ChatGPT.

[1778] "Means for dialogue" refers to an interface or system that allows real-time conversations and message exchanges between the user and generative AI.

[1779] "Means for storing the contents of a user's past conversations and reflecting them in the next conversation" refers to a means for saving the contents of previous conversations with a user and using them to improve the next conversation.

[1780] An "emotion analysis engine" is an engine that analyzes the user's emotional state from their voice or text input and outputs the results.

[1781] The "means for adjusting the response" is a means for changing the dialogue content generated by the generative artificial intelligence based on the output results of the emotion analysis engine, and providing an appropriate response.

[1782] A "brick and mortar store" is a commercial establishment or service location located in a physical location.

[1783] "Customer support" refers to support activities to respond to customer questions and inquiries and resolve problems.

[1784] The present invention is a system for providing customer support in brick-and-mortar stores. In the specific embodiment shown below, real-time dialogue is provided using a combination of generative artificial intelligence and an emotion analysis engine, using a terminal such as a smartphone, tablet, or information robot installed in the store.

[1785] User registration and profile settings

[1786] Users install the application on their smartphones or tablets and enter basic information such as their name, age, purchase history, hobbies, etc. This information is sent from the device to a server and stored in a database, creating a detailed profile for each user.

[1787] Starting a conversation

[1788] The user selects a customer support AI from the application's home screen and taps the "Start Dialogue" button. The device sends the selected AI information and a dialogue start request to the server, requesting a dialogue session. The server loads an appropriate generative AI model and establishes a dialogue session. It also loads the user's profile and past conversation records to use in the next dialogue.

[1789] Utilizing a sentiment analysis engine

[1790] The emotion analysis engine analyzes emotions from the user's voice and text input and sends the results to the server in real time. The generative AI then takes this emotional data and generates an appropriate response. For example, if a user expresses confusion or dissatisfaction, a response incorporating that emotion will be provided, allowing the user to receive more satisfying support.

[1791] Conversation progression and data recording

[1792] The server records all conversations in real time and stores them in a database. The recorded conversation data and emotion data are used in subsequent conversations. In particular, past problem history and complaint information are reflected in the next assistance, allowing for higher quality service.

[1793] Closing the conversation and feedback

[1794] After the dialogue is finished, the user taps the "End dialogue" button, and an end request is sent to the server. If necessary, the user can enter their thoughts or feedback, which is also sent to the server. The server stores the end information in a database and uses the feedback information to improve the generative AI model and sentiment analysis engine.

[1795] Hardware and Software Configuration

[1796] The system of the present invention uses the following hardware and software.

[1797] Hardware: Smartphones, tablets, information robots

[1798] Software: Generative AI model (ChatGPT), emotion analysis engine (EmotionEngine), database (SQLite), server program

[1799] Suggested concrete examples

[1800] For example, if a user says in a store, "Tell me more about this product," the following prompt sentence can be generated and responded to:

[1801] Input prompt for the generative AI model:

[1802] My name is Taro Sato. I'm interested in music and painting. My current emotion is joy. Please tell me more about this product.

[1803] Based on this prompt, the generative AI will return an appropriate response such as, "This product is a cutting-edge music player that combines high sound quality with ease of use. It is especially recommended for music lovers!" This allows users to obtain appropriate information quickly, improving satisfaction.

[1804] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1805] Step 1:

[1806] The user installs the application on the terminal and starts the application.

[1807] Specific operation: After downloading the application, the user enters basic information such as name, age, and hobbies.

[1808] Input and Output: The user's basic information is entered and sent by the device to the server, which stores this information in a database and creates a profile for each user.

[1809] Step 2:

[1810] The user selects the customer support AI from the application's home screen and taps the "Start conversation" button.

[1811] Specific operation: The user selects the AI ​​they want to interact with on the home screen and sends a request to start interacting.

[1812] Input and Output: The device receives the user's selection information and a request to initiate a dialogue, which it then sends to the server. The server loads the generative AI model and establishes a dialogue session. It also loads the user's profile data and past conversation records.

[1813] Step 3:

[1814] The emotion analysis engine analyzes emotions from the user's voice and text input and sends the results to the server.

[1815] Specific operation: The user's voice and text are input into an emotion analysis engine, which analyzes their emotional state (happiness, confusion, frustration, etc.).

[1816] Input and output: User voice and text are input, and the emotion analysis engine analyzes and outputs emotional data. This is received by the server.

[1817] Step 4:

[1818] Generative AI generates appropriate responses for users based on data from the sentiment analysis engine.

[1819] How it works: Emotional data is fed into a generative AI model to generate personalized responses for the user.

[1820] Input and output: Emotional data from the sentiment analysis engine is input, and the generative AI outputs an appropriate response. For example, in response to a user's input such as "Tell me more about this product," the system generates a response such as "This product is a cutting-edge music player that combines high sound quality with ease of use."

[1821] Step 5:

[1822] The server records all conversations in real time and stores them in a database.

[1823] Specific operation: The dialogue content and emotion data are sent to the server in real time and recorded in a database.

[1824] Input and output: The user's dialogue and emotional data are input and stored in a database as a record, which can then be used in future dialogues.

[1825] Step 6:

[1826] After the conversation is over, the user taps the "End conversation" button to send a request to the server to end the conversation. If necessary, the user can enter their thoughts or feedback.

[1827] Specific operation: After the user finishes the interaction, he / she sends an end request and feedback information.

[1828] Input and Output: User exit requests and feedback are input and stored on the server. Feedback information is used to improve the generative artificial intelligence and sentiment analysis engine.

[1829] 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.

[1830] 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.

[1831] 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.

[1832] [Fourth embodiment]

[1833] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1834] 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.

[1835] 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).

[1836] 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.

[1837] 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.

[1838] 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).

[1839] 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.

[1840] 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.

[1841] 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.

[1842] 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.

[1843] 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.

[1844] 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.

[1845] 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."

[1846] The present invention is a system that allows users to easily find someone to talk to through a call with a generative AI of their choice. Specifically, the system inputs and saves basic information about the user, uses the generative AI to talk to the user, and also has the ability to remember the content of past conversations and reflect it in the next conversation.

[1847] System Overview

[1848] The system mainly consists of a user device, a server, and a generative artificial intelligence (ChatGPT). Users install and launch the app using their smartphone or tablet.

[1849] User registration and profile settings

[1850] User:

[1851] Users install and launch the app and enter basic information such as their name, age, and hobbies, which allows the application to set up a personalized profile for the user.

[1852] Device:

[1853] The terminal transmits the information entered by the user to the server and stores it as profile data.

[1854] server:

[1855] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[1856] AI selection and call initiation

[1857] User:

[1858] From the app's home screen, users can choose from chat AI, consultation AI, or learning support AI, and then tap the "Start Call" button to begin the call.

[1859] Device:

[1860] The terminal sends the selected AI information and a call start request to the server and prepares to establish a call session.

[1861] server:

[1862] The server loads the appropriate generative artificial intelligence model based on the selected AI information, establishes a call session, and loads the user's profile data and past conversation records.

[1863] Conversation progression and data recording

[1864] Generative AI (ChatGPT):

[1865] Generative AI generates appropriate responses in real time based on user input, allowing users to easily find someone to talk to.

[1866] server:

[1867] The server records all conversations in real time and stores them in a database, which can be used in subsequent calls.

[1868] Specific examples

[1869] Let's say a user is suffering from insomnia in the middle of the night. The user opens the app, selects the consultation AI, and starts a call.

[1870] User:

[1871] "Work has been so stressful lately that I can't sleep."

[1872] Generative AI:

[1873] "That's tough. What exactly is stressing you out?"

[1874] server:

[1875] The server records this conversation and stores it for reference during the next call.

[1876] Ending a call and feedback

[1877] User:

[1878] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed.

[1879] Device:

[1880] The terminal sends a termination request and feedback information to the server.

[1881] server:

[1882] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model.

[1883] As a result, the system based on the present invention functions as a friend that can provide appropriate responses to the user 24 hours a day, 365 days a year, thereby reducing the user's mental burden and improving their quality of life.

[1884] The processing flow will be explained below.

[1885] Step 1:

[1886] User:

[1887] The user installs the app on their smartphone or tablet and launches it.

[1888] Step 2:

[1889] User:

[1890] Users enter basic information such as their name, age, and email address on the account creation screen and tap the "Sign up" button.

[1891] Step 3:

[1892] Device:

[1893] The terminal transmits the input basic information to the server.

[1894] Step 4:

[1895] server:

[1896] The server verifies the received information and, if there are no problems, stores the user's basic information in a database.

[1897] The server will send a confirmation email to the user to complete the account creation.

[1898] Step 5:

[1899] User:

[1900] The user clicks on the link in the confirmation email they receive to complete their account registration.

[1901] Step 6:

[1902] User:

[1903] Users enter additional information such as hobbies, interests, and goals in the app's profile settings screen.

[1904] Step 7:

[1905] Device:

[1906] The terminal transmits the input profile information to the server.

[1907] Step 8:

[1908] server:

[1909] The server stores the received profile information in a database and generates a detailed profile for the user.

[1910] Step 9:

[1911] User:

[1912] On the home screen, users can select the AI ​​they want to talk to from among the chat AI, consultation AI, and learning support AI.

[1913] Step 10:

[1914] Device:

[1915] The device sends the selected AI information to the server and requests a call session.

[1916] Step 11:

[1917] server:

[1918] The server receives the request and loads the generative artificial intelligence model according to the selected AI, as well as the user's profile data and past conversation records.

[1919] Step 12:

[1920] User:

[1921] The user taps the "Start Call" button.

[1922] Step 13:

[1923] Device:

[1924] The terminal sends a call initiation request to the server.

[1925] Step 14:

[1926] server:

[1927] The server establishes the call session, initializes the generative AI (ChatGPT), and prepares to receive user input in real time.

[1928] Step 15:

[1929] Generative AI (ChatGPT):

[1930] Generative AI generates appropriate responses based on input from the user and replies to the user.

[1931] Step 16:

[1932] server:

[1933] The server records all conversations in real time and stores them in a database, allowing past conversation data to be accumulated and used for the next conversation.

[1934] Step 17:

[1935] User:

[1936] When the user finishes the call, he taps the "end call" button.

[1937] Step 18:

[1938] Device:

[1939] The terminal sends a call termination request to the server.

[1940] Step 19:

[1941] server:

[1942] The server terminates the call session and stores the termination information in a database.

[1943] Step 20:

[1944] User:

[1945] The user enters their thoughts and feedback on the call on the post-call screen.

[1946] Step 21:

[1947] Device:

[1948] The terminal transmits the feedback information to the server.

[1949] Step 22:

[1950] server:

[1951] The server receives the feedback and stores it in a database. The feedback information is analyzed and used to improve the generative AI model.

[1952] The above are the specific processing steps of the present invention.

[1953] Example 1

[1954] 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."

[1955] Conventional communication systems have the problem that it is difficult to provide a conversation partner in real time and lack the functionality to effectively reflect the user's past conversation content, which hinders the improvement of the user experience. Furthermore, there is no mechanism for reflecting user feedback in the AI ​​model, making it difficult to maintain and improve call quality.

[1956] 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.

[1957] In this invention, the server includes means for inputting and saving basic user information, means for using generative artificial intelligence to conduct phone calls with the user, and means for storing the content of the user's past conversations and incorporating it into the next conversation. This allows the user to find someone to talk to in real time, and the content of the past conversations can be used for the next call, improving the user experience. The server also includes means for establishing a call with a generative artificial intelligence model selected by the user, means for recording the content of the call in real time and saving it in a format that can be referenced later, and means for receiving feedback from the user after the call ends and using it to improve the artificial intelligence model. This allows the feedback to be incorporated into the artificial intelligence model, enabling the maintenance and improvement of call quality.

[1958] "Basic information" is data entered by the user for personal identification and individualization, such as name, age, hobbies, etc.

[1959] "Generative AI" is an AI system that generates responses in natural language in response to input from a user.

[1960] "Call" refers to interactive communication with a user via generative artificial intelligence.

[1961] "Profile data" is a data set that includes basic information about a user and the contents of past conversations.

[1962] A "call session" is a continuous process of interaction with a user conducted using generative artificial intelligence.

[1963] "Real-time" refers to interactions being processed and reacted to the instant they are sent or received.

[1964] "Feedback" refers to information such as evaluations, impressions, and requests for improvement provided by users after a call has ended.

[1965] A "database" is an information repository where user profile data and conversations are stored.

[1966] "Model improvement" is the process of improving the response accuracy and quality of generative artificial intelligence based on feedback from users.

[1967] The "selected generative artificial intelligence model" is the generative artificial intelligence algorithm that is most suitable for the application specified by the user.

[1968] The present invention is a system that allows users to easily find someone to talk to using a generative AI selected by the user. This system consists of a user terminal, a server, and a generative AI (e.g., ChatGPT). The following describes the specific steps and operation methods for implementing the present invention.

[1969] User registration and profile settings

[1970] User:

[1971] Users install and launch the dedicated app on their smartphone or tablet and enter basic information such as their name, age, hobbies, etc. For example, a user may say their name is "Taro," their age is "30," and their hobby is "reading."

[1972] Device:

[1973] The terminal transmits the information entered by the user to the server, including the user's name, age, and hobbies.

[1974] server:

[1975] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[1976] AI selection and call initiation

[1977] User:

[1978] From the app's home screen, users can select one of the following AIs: chat AI, consultation AI, or learning support AI, and then tap the "Start Call" button. For example, select "Consultation AI."

[1979] Device:

[1980] The terminal sends the selected AI information and a call start request to the server. The user ID and AI type are sent.

[1981] server:

[1982] The server loads the appropriate generative AI model (e.g., ChatGPT) based on the selected AI information and establishes the call session, along with the user's profile data and past conversation records.

[1983] Conversation progression and data recording

[1984] User:

[1985] The user can freely converse with the generative AI. For example, the user can input, "I've been stressed out at work lately and I can't sleep."

[1986] Generative AI (ChatGPT):

[1987] The generative AI responds, "That's tough. What exactly is stressing you out?" and generates an appropriate response in real time.

[1988] server:

[1989] The server records all conversations in real time and stores them in a database, allowing this information to be used in future calls.

[1990] Ending a call and feedback

[1991] User:

[1992] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed. For example, they can enter feedback such as "That was very helpful."

[1993] Device:

[1994] The terminal sends a termination request and feedback information to the server.

[1995] server:

[1996] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model.

[1997] Examples of concrete examples and prompts

[1998] Specific examples

[1999] Consider a situation where a user is suffering from insomnia in the middle of the night. The user opens the app, selects the consultation AI, and starts a call.

[2000] User:

[2001] "Work has been so stressful lately that I can't sleep."

[2002] Generative AI (ChatGPT):

[2003] "That's tough. What exactly is stressing you out?"

[2004] server:

[2005] The server records this conversation and stores it for reference during the next call.

[2006] Prompt Sentence Examples

[2007] "Recently, I've been having trouble sleeping because of stress at work. What can I do to make myself feel a little better?"

[2008] Through this prompt, the user can receive appropriate advice from the generative artificial intelligence.

[2009] According to the above procedures and operation methods, the system based on the present invention can function as a friend who is available to the user 24 hours a day, 365 days a year, reducing the user's mental burden and improving the quality of life.

[2010] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2011] Step 1:

[2012] User registration and profile settings

[2013] User:

[2014] Users install and launch the app and enter basic information (name, age, hobbies, etc.).

[2015] Input: User's name, age, hobbies

[2016] Output: Data sent from the basic information input screen

[2017] Device:

[2018] The device sends the information entered by the user to the server, including the user's name, age, and hobbies.

[2019] Input: Data entered by the user

[2020] Output: Data sent to the server

[2021] server:

[2022] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[2023] Input: Basic user information sent from the device

[2024] Output: User profile data stored in a database

[2025] Step 2:

[2026] AI selection and call initiation

[2027] User:

[2028] From the app's home screen, users select one of the chat AI, consultation AI, or learning support AI and tap the "Start Call" button.

[2029] Input: User's AI selection and call start request

[2030] Output: AI selection instructions and call start request

[2031] Device:

[2032] The terminal sends the selected AI information and a call start request to the server. Specifically, the AI ​​type and user ID are sent.

[2033] Input: User's AI selection information and call start request

[2034] Output: The request data sent to the server

[2035] server:

[2036] The server loads the appropriate generative artificial intelligence model based on the selected AI and establishes the call session, as well as the user's profile data and past conversation records.

[2037] Input: AI selection information and call start request sent from the device

[2038] Output: A loaded generative AI model, an established call session

[2039] Step 3:

[2040] Conversation progression and data recording

[2041] User:

[2042] The user can freely converse with the generative AI, for example, by inputting, "I've been so stressed out at work lately that I can't sleep."

[2043] Input: User spoken input

[2044] Output: prompts for generative AI

[2045] Generative AI (ChatGPT):

[2046] Based on user input, generative AI generates appropriate responses in real time, such as, "That's tough. What exactly is stressing you out?"

[2047] Input: Prompt from user

[2048] Output: The generated response

[2049] server:

[2050] The server records all conversations in real time and stores them in a database, allowing this information to be used in future calls.

[2051] Input: Conversation data between the generative AI and the user

[2052] Output: Conversation transcript stored in database

[2053] Step 4:

[2054] Ending a call and feedback

[2055] User:

[2056] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed. For example, they can enter feedback such as "That was very helpful."

[2057] Input: Tap the end call button, feedback

[2058] Output: Call termination request, feedback data

[2059] Device:

[2060] The terminal sends a termination request and feedback information to the server.

[2061] Input: User end call request, feedback

[2062] Output: Finished request and feedback data sent to the server

[2063] server:

[2064] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model.

[2065] Input: End call request sent from the device, feedback

[2066] Output: Call termination information stored in a database, feedback data for model improvement

[2067] (Application example 1)

[2068] 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."

[2069] In today's world, when users purchase products online, they need a lot of information, and if they do not receive appropriate support, their motivation to purchase decreases. Furthermore, if customers cannot resolve specific questions about a product, they risk missing out on a purchasing opportunity. Furthermore, online stores face the challenge of finding personalized product recommendations and support for each individual customer.

[2070] 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.

[2071] In this invention, the server includes means for inputting and saving basic information about the user, means for using generative artificial intelligence to communicate with the user, means for storing the content of past conversations with the user and reflecting this in the next conversation, means for using generative artificial intelligence selected by the user to provide product-related questions and advice in real time within a virtual store, means for recommending optimal products to the user based on their purchase history and the content of past conversations, and means for collecting feedback and improving support quality. This allows users to receive prompt and accurate support in real time when making online purchases, increasing their desire to purchase and enabling optimal product recommendations.

[2072] "Basic user information" refers to information necessary to form an individual profile, such as the user's name, age, and purchase history.

[2073] "Generative AI" is an AI system that generates appropriate responses in real time based on user input.

[2074] "Means for making calls" refers to a means of communication that allows the generative artificial intelligence and the user to interact in real time.

[2075] "Means for remembering the content of past conversations and reflecting it in the next conversation" refers to a means for providing continuous support by saving the content of the previous conversation and referring to it in the next conversation.

[2076] A "virtual store" is an online shopping environment used via the Internet where users can browse and purchase products.

[2077] The "means for providing product-related questions and advice in real time" is an interactive support system that can answer questions about products and how to use them on the spot when users ask questions within the virtual store.

[2078] "Purchase history" is a record of products that a user has purchased in the past.

[2079] "Means for recommending optimal products to users based on past conversation content" refers to a system that suggests products that meet individual user needs based on the user's past conversations and behavioral history.

[2080] "Means for collecting feedback and improving support quality" refers to a means for incorporating user evaluations and opinions into the system and using them to improve the performance and response accuracy of the generative artificial intelligence.

[2081] This invention is a system that provides optimal support to users in a virtual store by inputting and saving basic information about the user, using generative artificial intelligence to communicate with the user, and storing the content of past conversations and reflecting it in the next conversation. Specific embodiments for implementing this invention are described below.

[2082] System configuration

[2083] The system consists of the following main components:

[2084] 1. User Device

[2085] Using mobile devices such as smartphones and tablets, users can access virtual stores and talk to AI.

[2086] 2. Server

[2087] A high-performance database server is used to store and manage basic user information, purchase history, past conversations, etc. A cloud-based database such as AWS RDS is suitable for the server.

[2088] 3. Generative Artificial Intelligence

[2089] Using OpenAI's ChatGPT API, the system generates responses to users' real-time questions. This AI generates appropriate responses based on user input, maintaining the continuity of the conversation.

[2090] Processing Flow

[2091] 1. User Registration and Profile Settings

[2092] The application is installed on the user's device and launched. The user enters basic information such as name, age, hobbies, and purchasing history. This data is sent to the server and stored in a database.

[2093] 2. AI selection and call initiation

[2094] The user selects "Customer Support" from the application's home screen and taps the "Start Call" button. The server loads the user's profile data and loads the appropriate generative artificial intelligence model.

[2095] 3. Conversation management and data recording

[2096] The generative artificial intelligence (ChatGPT) responds to user questions and requests in real time. For example, if a user asks, "What are the features of this smartphone?", the AI ​​will respond, "This smartphone is equipped with a high-resolution camera, a state-of-the-art processor, and boasts a long battery life. It is also waterproof."

[2097] 4. Call End and Feedback

[2098] When the user finishes the call, they tap the "End Call" button and the call ends. After the call ends, the user enters feedback, which is sent to the server. The server collects the feedback and uses it to improve the AI ​​model.

[2099] Explanation of program processing

[2100] The server first stores the user's basic information in a database. Then, when the user sends a request to talk to a specific AI, the server loads the user's past conversations and launches the appropriate generative AI model. During the call, the server records the AI's responses and the user's input in real time, making them available for reference in the next conversation.

[2101] For hardware, smartphones and tablets are used as user devices, and cloud-based solutions such as AWS RDS are used as database servers. For software, OpenAI's ChatGPT API is used for generative artificial intelligence, and React Native is used for application development.

[2102] Prompt Sentence Examples

[2103] Examples of specific prompts include:

[2104] "User: Tell me about the new features on your smartphone these days. Generative AI:"

[2105] "User: What's the best way to use this camera? Generative AI:"

[2106] This allows users to receive prompt and accurate support in real time when making online purchases, which increases purchasing motivation and enables optimal product recommendations.

[2107] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2108] Step 1:

[2109] The user enters basic information

[2110] Input: Users enter basic information such as name, age, hobbies, and purchase history into an application on their smartphone or tablet.

[2111] Data processing: The terminal formats the entered user information and converts it into a format that can be sent to the server.

[2112] Output: The formatted user information is sent to the server.

[2113] Specific actions: Enter user information into the application form and tap the "Submit" button.

[2114] Step 2:

[2115] The server stores basic information

[2116] Input: Basic information of the user sent from the device.

[2117] Data Calculation: The server verifies the received user information and stores it in the database.

[2118] Output: A confirmation message that the save was successful is returned to the terminal.

[2119] Specific operation: The server checks the integrity of the received data and saves the information to the MySQL database using an INSERT statement.

[2120] Step 3:

[2121] The user selects the generative AI

[2122] Input: The user selects "Customer Support" or another AI model from the application home screen.

[2123] Data processing: The device generates a request to send information about the selected AI model to the server.

[2124] Output: The generated request is sent to the server.

[2125] What it does: Tap an option such as "Customer Support" from the application's menu.

[2126] Step 4:

[2127] The server establishes the call session

[2128] Input: The call initiation request sent from the device and the user's profile data.

[2129] Data computation: The server loads the appropriate generative artificial intelligence model and retrieves past conversation content from the database.

[2130] Output: The call session is ready to begin and the device is notified.

[2131] What it does: The server loads profile data and conversation history and sets up the AI ​​model for operation.

[2132] Step 5:

[2133] Generative AI starts the conversation

[2134] Input: The initial input from the user (e.g., "What are the features of this phone?").

[2135] Data Computation: Generative AI processes input text and generates appropriate prompts.

[2136] Output: A response based on the generated prompt is returned to the user.

[2137] What it does: Uses ChatGPT API to generate and reply to responses based on user input in real time.

[2138] Step 6:

[2139] The server records the conversation

[2140] Input: Real-time generated AI responses and user input.

[2141] Data calculation: The contents of the conversation are saved in a database and managed as history for use in future conversations.

[2142] Output: The save completion confirmation status is updated internally.

[2143] Specific operation: The server inserts and updates the received conversation data into the database in real time.

[2144] Step 7:

[2145] User ends the call and provides feedback

[2146] Input: Feedback entered by the user at the end of the call (e.g., "Thank you for your prompt response").

[2147] Data processing: The terminal sends the termination request and feedback information to the server.

[2148] Output: The feedback information is stored in the server and a completion message is returned to the user terminal.

[2149] Specific actions: The user taps the "End call" button, enters their opinion in the feedback form, and taps the "Submit" button.

[2150] Step 8:

[2151] The server improves the AI ​​model based on the feedback.

[2152] Input: Feedback information from the user.

[2153] Data calculation: The server analyzes the feedback and reflects it to improve the response accuracy of the generative AI.

[2154] Output: The AI ​​model has been improved and will be reflected in future calls.

[2155] What it does: Analyzes the feedback data and retrains the model by adding it to the generative artificial intelligence training dataset.

[2156] 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.

[2157] The present invention is a system that combines generative artificial intelligence with an emotion engine that recognizes the user's emotions. This allows for more personalized and emotionally appropriate dialogue for the user. Specifically, the system inputs and saves basic user information, uses generative artificial intelligence to communicate with the user, and has the ability to remember the content of past conversations and reflect it in the next conversation.

[2158] System Overview

[2159] The system mainly consists of a user device, a server, a generative AI (ChatGPT), and an emotion engine. Users install and launch the app on their smartphone or tablet.

[2160] User registration and profile settings

[2161] User:

[2162] Users install and launch the app and enter basic information such as their name, age, and hobbies, which allows the application to set up a personalized profile for the user.

[2163] Device:

[2164] The terminal transmits the information entered by the user to the server and stores it as profile data.

[2165] server:

[2166] The server verifies the information it receives and stores it in a database, creating a detailed profile for each user.

[2167] AI selection and call initiation

[2168] User:

[2169] From the app's home screen, users select the AI ​​they want to talk to from the chat AI, consultation AI, or learning support AI, and tap the "Start Call" button.

[2170] Device:

[2171] The terminal transmits the selected AI information and a call start request to the server to request a call session.

[2172] server:

[2173] The server loads the appropriate generative artificial intelligence model based on the selected AI and establishes the call session, as well as the user's profile data and past conversation records.

[2174] Utilizing the Emotion Engine

[2175] Emotion Engine:

[2176] The emotion engine analyzes emotions from the user's voice and text input, and transmits them to the server in real time, which reflects them in the generative artificial intelligence's responses.

[2177] Generative AI (ChatGPT):

[2178] Based on user input, the generative AI takes in emotional data analyzed by the emotion engine and generates an appropriate response, allowing users to easily find someone to talk to.

[2179] Conversation progression and data recording

[2180] server:

[2181] The server records all conversations in real time and stores them in a database. The recorded conversation data is used in subsequent calls. Emotion engine data is also stored and used to analyze the user's emotional patterns.

[2182] Specific examples

[2183] Let's say a user is suffering from insomnia in the middle of the night. The user opens the app, selects the consultation AI, and starts a call.

[2184] User:

[2185] "Work has been so stressful lately that I can't sleep."

[2186] Emotion Engine:

[2187] Detects stress and fatigue from the user's tone of voice and choice of words.

[2188] Generative AI:

[2189] "That's tough. What exactly is stressing you out?"

[2190] server:

[2191] The server records this conversation and emotional data and stores it for reference during the next call.

[2192] Ending a call and feedback

[2193] User:

[2194] When the call ends, the user taps the "End Call" button. After the call ends, the user can enter their thoughts or feedback as needed.

[2195] Device:

[2196] The terminal sends a termination request and feedback information to the server.

[2197] server:

[2198] The server ends the call session, stores the termination information in a database, and receives feedback information to help improve the artificial intelligence model and emotion engine.

[2199] As a result, the system based on the present invention can understand the user's emotions and provide an appropriate response, thereby providing psychological support to the user.

[2200] The processing flow will be explained below.

[2201] Step 1:

[2202] User:

[2203] The user installs the app on their smartphone or tablet and launches it.

[2204] Step 2:

[2205] User:

[2206] Users enter basic information such as their name, age, email address, and hobbies on the account creation screen and tap the "Sign up" button.

[2207] Step 3:

[2208] Device:

[2209] The terminal transmits the input basic information to the server.

[2210] Step 4:

[2211] server:

[2212] The server verifies the received information and, if there are no problems, stores the user's basic information in a database. The server then sends the user a confirmation email to complete the account creation.

[2213] Step 5:

[2214] User:

[2215] The user clicks on the link in the confirmation email they receive to complete their account registration.

[2216] Step 6:

[2217] User:

[2218] Users enter additional information such as hobbies, interests, and goals in the app's profile settings screen.

[2219] Step 7:

[2220] Device:

[2221] The terminal transmits the input profile information to the server.

[2222] Step 8:

[2223] server:

[2224] The server stores the received profile information in a database and generates a detailed profile for the user.

[2225] Step 9:

[2226] User:

[2227] On the home screen, users can select the AI ​​they want to talk to from among the chat AI, consultation AI, and learning support AI.

[2228] Step 10:

[2229] Device:

[2230] The device sends the selected AI information to the server and requests a call session.

[2231] Step 11:

[2232] server:

[2233] The server receives the request and loads the generative artificial intelligence model according to the selected AI, as well as the user's profile data and past conversation records.

[2234] Step 12:

[2235] User:

[2236] The user taps the "Start Call" button.

[2237] Step 13:

[2238] Device:

[2239] The terminal sends a call initiation request to the server.

[2240] Step 14:

[2241] server:

[2242] The server establishes a call session, initializes the generative AI (ChatGPT), prepares to receive user input in real time, and starts the emotion engine to prepare to analyze user input.

[2243] Step 15:

[2244] User:

[2245] The user initiates a call with the generative AI and types or speaks what they want to say.

[2246] Step 16:

[2247] Emotion Engine:

[2248] The emotion engine analyzes emotions from the user's voice and text input and sends the data to the server in real time.

[2249] Step 17:

[2250] Generative AI (ChatGPT):

[2251] Based on input from the user, generative AI takes in emotional data analyzed by the emotion engine and generates an appropriate response.

[2252] Step 18:

[2253] server:

[2254] The server records all conversation content and emotional data in real time and stores it in a database, allowing past conversation data and emotional patterns to be accumulated and used in the next conversation.

[2255] Step 19:

[2256] User:

[2257] When the user finishes the call, he taps the "end call" button.

[2258] Step 20:

[2259] Device:

[2260] The terminal sends a call termination request to the server.

[2261] Step 21:

[2262] server:

[2263] The server ends the call session and stores the information in a database at the time of termination. The recorded data is analyzed and used to provide the user with a more appropriate response in the next conversation.

[2264] Step 22:

[2265] User:

[2266] The user enters their thoughts and feedback on the call on the post-call screen.

[2267] Step 23:

[2268] Device:

[2269] The terminal transmits the feedback information to the server.

[2270] Step 24:

[2271] server:

[2272] The server receives the feedback and stores it in a database. The feedback information is analyzed and used to improve the generative AI and emotion engine models.

[2273] As a result, the system based on the present invention is a system that can recognize the user's emotions in real time and provide an appropriate response, thereby providing psychological support to the user.

[2274] Example 2

[2275] 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."

[2276] Conventional dialogue systems using generative AI generally respond without considering the user's emotions, which prevents them from providing sufficient personalization or emotional support. Furthermore, they fail to fully utilize past conversations, making it difficult to build a lasting relationship with the user. Furthermore, they lack a mechanism for incorporating user feedback into system improvements.

[2277] 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.

[2278] In this invention, the server includes a means for inputting and saving basic user information, a means for using generative artificial intelligence to communicate with the user, a means for storing the content of the user's past conversations and reflecting that content in the next conversation, and a means for analyzing the user's emotions and reflecting that content in the conversation. This enables personalized dialogue that understands emotions, providing psychological support to the user and building a lasting relationship. Furthermore, user feedback can be used to improve the artificial intelligence model, thereby improving system performance.

[2279] "Basic user information" is data indicating personal attributes such as the user's name, age, hobbies, etc.

[2280] "Generative AI" refers to an AI system that uses natural language processing to interact with users, such as ChatGPT.

[2281] "Means for communicating with the user" refers to a mechanism for two-way communication with the user via voice or text via generative artificial intelligence.

[2282] "Means of remembering the content of a user's past conversations and reflecting it in the next conversation" is a function that stores records of past conversations with the user in a database and uses that information to make the content of the next conversation more personalized.

[2283] "Means for analyzing emotions and reflecting them in the content of the call" refers to a mechanism that reads emotions from the user's voice and text and incorporates the results into the generative AI's response, thereby enabling a dialogue that is sensitive to the user's emotions.

[2284] "Personalized dialogue" refers to generating optimal responses for a user by taking into account the user's individual information, past conversations, emotional state, etc.

[2285] "Feedback" refers to the thoughts and opinions provided by users after a call ends, and is data used to improve the performance of the system and generative artificial intelligence.

[2286] The present invention relates to a system that understands user emotions and provides more personalized interactions. This system consists of a user terminal, a server, a generative artificial intelligence (e.g., ChatGPT), and an emotion engine.

[2287] Overall system overview

[2288] Users install and launch a dedicated application using a network-connected device such as a smartphone or tablet. The application inputs and saves the user's basic information and communicates with the user via a generative AI. It also uses an emotion engine to analyze the user's emotions and reflects them in the generative AI's responses.

[2289] User registration and profile settings

[2290] Through the application, users enter basic information such as name, age, hobbies, etc. This information is sent via the device to the server, which verifies the information received and stores it in a database to create a detailed user profile.

[2291] AI selection and call initiation

[2292] From the app's home screen, users select the AI ​​they want to talk to from among several AI models (such as chat AI, consultation AI, and learning support AI), and tap the "Start Call" button. The device sends this information and a call start request to the server, which then loads the appropriate generative AI model and establishes a call session. Additionally, the user's profile data and past conversation records are also loaded.

[2293] Use of emotion engine

[2294] The emotion engine analyzes the user's voice and text input in real time to generate emotional data. This allows the server to detect the user's emotions, such as stress or joy, and provides this information to the generative AI. The generative AI then takes in this emotional data and generates an appropriate response.

[2295] Specific examples

[2296] For example, consider a case where a user is suffering from insomnia. The user opens the application, selects a consultation AI, and starts a call.

[2297] 1. A user says, "Work has been so stressful lately that I can't sleep."

[2298] 2. The emotion engine detects the user's stress and fatigue from this statement.

[2299] 3. The generative AI responds, "That's tough. What exactly is stressing you out?"

[2300] 4. The server records this conversation and emotion data and stores it for reference during the next call.

[2301] Ending a call and feedback

[2302] When the call ends, the user taps the "End Call" button and optionally enters their thoughts and feedback. The device sends the end request and feedback information to the server, which then ends the call session and stores the end information in a database. The server also receives user feedback and uses it to improve the generative AI model and emotion engine.

[2303] Example prompts to input to the generative AI model

[2304] prompt:

[2305] "Please use the template below to respond to a user who is suffering from insomnia. Detect stress or fatigue from the user's tone of voice and choice of words, and engage in appropriate dialogue."

[2306] 1. User: "I've been so stressed out at work lately that I can't sleep."

[2307] 2. Emotion engine: Detects stress and fatigue.

[2308] 3. Generative AI: "That sounds tough. What exactly is stressing you out?"

[2309] In this way, the system according to the present invention can understand the user's emotions and provide more appropriate interactions.

[2310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2311] Step 1:

[2312] The user enters basic information.

[2313] Input: The user enters basic information such as name, age, and hobbies into the input form displayed on the terminal.

[2314] Specific behavior: The user enters information and taps the submit button.

[2315] Output: The entered information is saved on the device.

[2316] Step 2:

[2317] The terminal sends the information to the server.

[2318] Input: Basic information entered by the user in step 1.

[2319] Specific operation: The terminal generates a data packet for transmitting the input basic information to the server.

[2320] Output: The user's basic information is sent to the server.

[2321] Step 3:

[2322] The server verifies the information and stores it in a database.

[2323] Input: Basic information of the user sent from the device.

[2324] Specific operations: The server validates the format of the data received and saves it to the database. A user ID is generated and associated with basic information.

[2325] Output: The user profile is saved in the database.

[2326] Step 4:

[2327] The user selects the AI.

[2328] Input: On the app's home screen, the user selects the AI ​​they want to talk to from among the chat AI, consultation AI, and learning support AI.

[2329] Specific operation: The user selects the desired AI and taps the "Start call" button.

[2330] Output: The information of the selected AI is saved on the device.

[2331] Step 5:

[2332] The device sends a request to the server.

[2333] Input: Selected AI information and call start request.

[2334] Specific operation: The terminal generates a data packet for transmitting the selected AI information and a call start request.

[2335] Output: A call start request and selected AI information is sent to the server.

[2336] Step 6:

[2337] The server establishes the session.

[2338] Input: The call initiation request sent from the device and selected AI information.

[2339] What it does: The server loads the appropriate generative artificial intelligence model and establishes the call session, along with the user's profile data and past conversation records.

[2340] Output: A call session is started.

[2341] Step 7:

[2342] The emotion engine analyzes emotions.

[2343] Input: User voice and text input.

[2344] Specific operation: The emotion engine analyzes voice and text data to detect the user's emotions (stress, joy, fatigue, etc.).

[2345] Output: The analyzed emotion data is sent to the server.

[2346] Step 8:

[2347] The server receives the emotion data and provides it to the generative artificial intelligence.

[2348] Input: Emotion data sent from the emotion engine.

[2349] Specific operation: The server receives emotion data and generates a data packet to provide to the generative artificial intelligence.

[2350] Output: Emotion data is provided to a generative AI.

[2351] Step 9:

[2352] Generative artificial intelligence generates responses.

[2353] Input: Initial input and emotion data from the user.

[2354] Specific behavior: Based on the input, the generative AI takes in the emotional data analyzed by the emotion engine and generates a response. For example, "What specifically is causing you stress?"

[2355] Output: The generated response is returned to the user.

[2356] Step 10:

[2357] The server records the conversation and stores it in a database.

[2358] Input: Conversational content and emotional data between the generative AI and the user.

[2359] Specific operation: The server records all conversation content in a database and saves it for future reference.

[2360] Output: Conversation records and emotion data are stored in a database.

[2361] Step 11:

[2362] The user ends the call and provides feedback.

[2363] Input: End-of-call instructions and feedback information.

[2364] What happens: The user taps the "End Call" button and optionally enters thoughts or feedback.

[2365] Output: The termination request and feedback information are saved to the terminal.

[2366] Step 12:

[2367] The terminal sends a termination request to the server.

[2368] Input: Call termination request and feedback information.

[2369] Specific operation: The terminal generates a data packet for transmitting a termination request and feedback information.

[2370] Output: A termination request and feedback information is sent to the server.

[2371] Step 13:

[2372] The server ends the session and saves the feedback.

[2373] Input: The termination request and feedback information sent from the terminal.

[2374] Specific operation: The server ends the call session and stores the end information in a database. It also uses the received feedback information to improve the generative AI model and emotion engine.

[2375] Output: The end of the call session and feedback information are stored in a database and used to improve the system.

[2376] (Application example 2)

[2377] 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."

[2378] Conventional AI dialogue systems generate uniform responses without considering the user's emotional state, resulting in low dialogue quality and insufficient user satisfaction. Furthermore, in customer support at physical stores, they are unable to provide personalized services that reflect the customer's real-time emotional state.

[2379] 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.

[2380] In this invention, the server includes means for inputting and saving basic information about the user, means for using a generative artificial intelligence to have a dialogue with the user, means for storing the content of the user's past conversations and reflecting that content in the next conversation, means for analyzing the user's emotional state using an emotion analysis engine, and means for adjusting the response of the generative artificial intelligence based on the analyzed emotional state. This enables personalized responses that take into account the individual emotional state of the user, thereby providing higher levels of satisfaction in customer support at physical stores.

[2381] "Basic user information" refers to individual information such as the user's name, age, and hobbies.

[2382] "Generative AI" is AI that generates natural dialogue based on user input, such as systems like ChatGPT.

[2383] "Means for dialogue" refers to an interface or system that allows real-time conversations and message exchanges between the user and generative AI.

[2384] "Means for storing the contents of a user's past conversations and reflecting them in the next conversation" refers to a means for saving the contents of previous conversations with a user and using them to improve the next conversation.

[2385] An "emotion analysis engine" is an engine that analyzes the user's emotional state from their voice or text input and outputs the results.

[2386] The "means for adjusting the response" is a means for changing the dialogue content generated by the generative artificial intelligence based on the output results of the emotion analysis engine, and providing an appropriate response.

[2387] A "brick and mortar store" is a commercial establishment or service location located in a physical location.

[2388] "Customer support" refers to support activities to respond to customer questions and inquiries and resolve problems.

[2389] The present invention is a system for providing customer support in brick-and-mortar stores. In the specific embodiment shown below, real-time dialogue is provided using a combination of generative artificial intelligence and an emotion analysis engine, using a terminal such as a smartphone, tablet, or information robot installed in the store.

[2390] User registration and profile settings

[2391] Users install the application on their smartphones or tablets and enter basic information such as their name, age, purchase history, hobbies, etc. This information is sent from the device to a server and stored in a database, creating a detailed profile for each user.

[2392] Starting a conversation

[2393] The user selects a customer support AI from the application's home screen and taps the "Start Dialogue" button. The device sends the selected AI information and a dialogue start request to the server, requesting a dialogue session. The server loads an appropriate generative AI model and establishes a dialogue session. It also loads the user's profile and past conversation records to use in the next dialogue.

[2394] Utilizing a sentiment analysis engine

[2395] The emotion analysis engine analyzes emotions from the user's voice and text input and sends the results to the server in real time. The generative AI then takes this emotional data and generates an appropriate response. For example, if a user expresses confusion or dissatisfaction, a response incorporating that emotion will be provided, allowing the user to receive more satisfying support.

[2396] Conversation progression and data recording

[2397] The server records all conversations in real time and stores them in a database. The recorded conversation data and emotion data are used in subsequent conversations. In particular, past problem history and complaint information are reflected in the next assistance, allowing for higher quality service.

[2398] Closing the conversation and feedback

[2399] After the dialogue is finished, the user taps the "End dialogue" button, and an end request is sent to the server. If necessary, the user can enter their thoughts or feedback, which is also sent to the server. The server stores the end information in a database and uses the feedback information to improve the generative AI model and sentiment analysis engine.

[2400] Hardware and Software Configuration

[2401] The system of the present invention uses the following hardware and software.

[2402] Hardware: Smartphones, tablets, information robots

[2403] Software: Generative AI model (ChatGPT), emotion analysis engine (EmotionEngine), database (SQLite), server program

[2404] Suggested concrete examples

[2405] For example, if a user says in a store, "Tell me more about this product," the following prompt sentence can be generated and responded to:

[2406] Input prompt for the generative AI model:

[2407] My name is Taro Sato. I'm interested in music and painting. My current emotion is joy. Please tell me more about this product.

[2408] Based on this prompt, the generative AI will return an appropriate response such as, "This product is a cutting-edge music player that combines high sound quality with ease of use. It is especially recommended for music lovers!" This allows users to obtain appropriate information quickly, improving satisfaction.

[2409] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2410] Step 1:

[2411] The user installs the application on the terminal and starts the application.

[2412] Specific operation: After downloading the application, the user enters basic information such as name, age, and hobbies.

[2413] Input and Output: The user's basic information is entered and sent by the device to the server, which stores this information in a database and creates a profile for each user.

[2414] Step 2:

[2415] The user selects the customer support AI from the application's home screen and taps the "Start conversation" button.

[2416] Specific operation: The user selects the AI ​​they want to interact with on the home screen and sends a request to start interacting.

[2417] Input and Output: The device receives the user's selection information and a request to initiate a dialogue, which it then sends to the server. The server loads the generative AI model and establishes a dialogue session. It also loads the user's profile data and past conversation records.

[2418] Step 3:

[2419] The emotion analysis engine analyzes emotions from the user's voice and text input and sends the results to the server.

[2420] Specific operation: The user's voice and text are input into an emotion analysis engine, which analyzes their emotional state (happiness, confusion, frustration, etc.).

[2421] Input and output: User voice and text are input, and the emotion analysis engine analyzes and outputs emotional data. This is received by the server.

[2422] Step 4:

[2423] Generative AI generates appropriate responses for users based on data from the sentiment analysis engine.

[2424] How it works: Emotional data is fed into a generative AI model to generate personalized responses for the user.

[2425] Input and output: Emotional data from the sentiment analysis engine is input, and the generative AI outputs an appropriate response. For example, in response to a user's input such as "Tell me more about this product," the system generates a response such as "This product is a cutting-edge music player that combines high sound quality with ease of use."

[2426] Step 5:

[2427] The server records all conversations in real time and stores them in a database.

[2428] Specific operation: The dialogue content and emotion data are sent to the server in real time and recorded in a database.

[2429] Input and output: The user's dialogue and emotional data are input and stored in a database as a record, which can then be used in future dialogues.

[2430] Step 6:

[2431] After the conversation is over, the user taps the "End conversation" button to send a request to the server to end the conversation. If necessary, the user can enter their thoughts or feedback.

[2432] Specific operation: After the user finishes the interaction, he / she sends an end request and feedback information.

[2433] Input and Output: User exit requests and feedback are input and stored on the server. Feedback information is used to improve the generative artificial intelligence and sentiment analysis engine.

[2434] 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.

[2435] 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.

[2436] 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.

[2437] 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.

[2438] FIG. 9 illustrates 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 behaviors 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.

[2439] 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.

[2440] 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).

[2441] 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.

[2442] 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."

[2443] 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.

[2444] 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).

[2445] 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.

[2446] 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.

[2447] 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.

[2448] 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.

[2449] 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.

[2450] 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.

[2451] 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.

[2452] 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.

[2453] 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.

[2454] 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.

[2455] The following is further disclosed regarding the above embodiment.

[2456] (Claim 1)

[2457] A means for entering and storing basic user information;

[2458] A means for using generative artificial intelligence to communicate with a user;

[2459] A means for storing the contents of a user's past conversations and reflecting them in the next conversation;

[2460] A system including:

[2461] (Claim 2)

[2462] 10. The system of claim 1, further comprising means for selecting a particular model from among a plurality of artificial intelligence models based on a user selection.

[2463] (Claim 3)

[2464] 10. The system of claim 1, further comprising means for receiving feedback from a user and utilizing it to improve the artificial intelligence model.

[2465] "Example 1"

[2466] (Claim 1)

[2467] A means for entering and storing basic user information;

[2468] A means for using generative artificial intelligence to communicate with a user;

[2469] A means for storing the contents of a user's past conversations and reflecting them in the next conversation;

[2470] means for establishing a call with a user-selected generative artificial intelligence model;

[2471] A means to record calls in real time and save them in a format that can be viewed later;

[2472] A means of receiving user feedback after the call is completed and using it to improve the artificial intelligence model; and

[2473] A system including:

[2474] (Claim 2)

[2475] 10. The system of claim 1, further comprising means for selecting a particular model from among a plurality of generative artificial intelligence models based on a user selection.

[2476] (Claim 3)

[2477] 2. The system according to claim 1, further comprising means for transmitting input information from the user terminal to a server, and for the server to verify and store the information.

[2478] "Application Example 1"

[2479] (Claim 1)

[2480] A means for entering and storing basic user information;

[2481] A means for using generative artificial intelligence to communicate with a user;

[2482] A means for storing the contents of a user's past conversations and reflecting them in the next conversation;

[2483] A means for providing real-time product-related questions and advice within the virtual store using a user-selected generative artificial intelligence;

[2484] A means to recommend the best products to users based on their purchase history and past conversations,

[2485] A means to gather feedback and improve the quality of support;

[2486] A system including:

[2487] (Claim 2)

[2488] 10. The system of claim 1, further comprising means for selecting a particular model from among a plurality of artificial intelligence models based on a user selection.

[2489] (Claim 3)

[2490] 10. The system of claim 1, further comprising means for receiving feedback from a user and utilizing it to improve the artificial intelligence model.

[2491] "Example 2: Combining Emotion Engines"

[2492] (Claim 1)

[2493] A means for entering and storing basic user information;

[2494] A means for using generative artificial intelligence to communicate with a user;

[2495] A means for storing the contents of a user's past conversations and reflecting them in the next conversation;

[2496] A means for analyzing the user's emotions and reflecting them in the content of the call;

[2497] A system including:

[2498] (Claim 2)

[2499] 10. The system of claim 1, further comprising means for selecting a particular model from among a plurality of artificial intelligence models based on a user selection.

[2500] (Claim 3)

[2501] 10. The system of claim 1, further comprising means for receiving feedback from a user and utilizing it to improve the artificial intelligence model.

[2502] "Application example 2 when combining emotion engines"

[2503] (Claim 1)

[2504] A means for entering and storing basic user information;

[2505] A means for interacting with a user using generative artificial intelligence;

[2506] A means for storing the contents of a user's past conversations and reflecting them in the next conversation;

[2507] means for analyzing the emotional state of a user using an emotion analysis engine;

[2508] means for adjusting the response of the generative artificial intelligence based on the analyzed emotional state;

[2509] A system including:

[2510] (Claim 2)

[2511] 10. The system of claim 1, further comprising means for selecting a particular model from among a plurality of artificial intelligence models based on a user selection.

[2512] (Claim 3)

[2513] 10. The system of claim 1, further comprising means for receiving feedback from a user and utilizing it to improve the artificial intelligence model. [Explanation of symbols]

[2514] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for entering and storing basic user information; A means for using generative artificial intelligence to communicate with a user; A means for storing the contents of a user's past conversations and reflecting them in the next conversation; A system including:

2. The system of claim 1 , further comprising means for selecting a particular model from among a plurality of artificial intelligence models based on a user selection.

3. The system of claim 1 further comprising means for receiving feedback from a user and utilizing it to improve the artificial intelligence model.

Images