System

Abstract

A system is provided.SOLUTION: A system comprising: means for providing a user interface for conducting a conversation with a user; means for interfacing with a database storing user interests and preferences; means for generating a personalized response based on user input using a generative model; and means for transmitting the personalized response to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional chatbot systems have the problem that conversations do not progress unless the user takes action, making it difficult to provide a natural conversational experience. Furthermore, personalized responses are insufficient, and many users find the conversations to be unhuman. As a result, user satisfaction and continuity of use decline. Furthermore, the unnatural nature of advertising product recommendations makes it difficult for users to accept the system. There is a need for a system that can solve these issues and provide a more natural and personalized conversational experience. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means: A user interface for conversing with a user is provided, and is connected to a database that stores the user's hobbies and preferences. Furthermore, a generative model is used to generate personalized responses based on the user's input. The generated personalized responses are then sent to the user, providing a natural conversational experience. The generative model performs context analysis using the user's conversation history and information stored in the database, and can naturally recommend products and services related to the user's hobbies and preferences. Furthermore, an interface is provided that allows the user to customize their own interests and settings, creating a familiar experience. This improves user satisfaction and usage continuity, and makes advertising products more natural and comfortable to accept.

[0006] "User interface" refers to the overall interface, including the operation screen and input means that allow the user to interact with the system.

[0007] "Database" refers to a data storage system for storing information such as a user's hobbies, preferences, and interaction history.

[0008] A "generative model" refers to an algorithm or machine learning model that generates optimal responses based on input data.

[0009] "Personalized responses" refer to answers that are individually customized based on a user's unique interests and preferences.

[0010] "Context analysis" refers to the process of analyzing topics and related information from user input and past dialogue history.

[0011] "Recommendation" refers to the act of recommending specific products or services based on a user's needs and interests.

[0012] An "interface" refers to the means or mechanism by which a user interacts with a system.

[0013] "Conversational means" refers to the methods and techniques by which a user and a system exchange information and engage in dialogue. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of that dialogue. The system is composed of a user interface, a database, a generative model, and a back-end server that exchanges data between them.

[0036] User Interface

[0037] The user interface is what allows the user to interact with the system. It uses a messaging platform such as the LINE app to provide input and output screens for the user. Data entered by the user is sent to the server via the device.

[0038] Database

[0039] The database stores information such as the user's hobbies, preferences, and interaction history, providing the foundation for the generative model to generate optimal responses based on past data. The database is updated in real time as the user adds new interests or preferences.

[0040] Generative Model

[0041] Generative models use user input data and information stored in a database to generate personalized responses. Generative models use machine learning techniques, particularly contextual analysis, to accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[0042] server

[0043] The server receives the data sent by the user and generates a response based on the user profile and interaction history. The server uses the generative model to send personalized messages to the user through the user interface, allowing the user to enjoy natural interactions.

[0044] Example

[0045] The operation of the present invention will be described below through specific examples.

[0046] Example 1:

[0047] A user sends a message through the LINE app saying, "I'd like to know about a new game."

[0048] 1. The terminal sends this message to the server.

[0049] 2. The server retrieves the user's profile information from the database, which may include "Interests: Gaming" and "Recent Activity: Searching for Gaming Gear."

[0050] 3. The server passes this information and the user's message to the generative model for contextual analysis. The generative model identifies information relevant to the "game" and generates an appropriate response.

[0051] 4. The server generates a response and sends it to the device: "If you're interested in gaming, why not check out this new game store?"

[0052] 5. The terminal displays this message to the user.

[0053] Example 2:

[0054] Users update their interests and preferences.

[0055] 1. The user opens the settings screen within the LINE app and changes their interests and character settings.

[0056] 2. The device sends this change information to the server.

[0057] 3. The server updates the user profile information in the database.

[0058] 4. Based on the new settings, the generative model generates a new personalized response from the next interaction.

[0059] This allows users to enjoy a natural conversational experience while always staying connected to the latest information. Product and service recommendations are also made at the appropriate time, achieving both user convenience and profitability for service providers.

[0060] The processing flow will be explained below.

[0061] Specific processing flow when a user requests new information

[0062] Step 1:

[0063] A user types a message through the LINE app saying, "I'd like to know about new games."

[0064] Step 2:

[0065] The device receives the user's message as text data and sends it to the server via the LINE app API.

[0066] Step 3:

[0067] The server analyzes the message received from the LINE API and identifies the sender's user ID.

[0068] Step 4:

[0069] The server accesses the database and retrieves profile information (interests, preferences, interaction history) associated with the user ID.

[0070] Step 5:

[0071] The server passes the acquired profile information and the user's message to the generative model, which analyzes the input data and identifies the context.

[0072] Step 6:

[0073] The generative model analyzes the context of "new game" and simultaneously confirms from profile information that the user's interest is "gaming."

[0074] Step 7:

[0075] The generative model generates the optimal response message based on the user's interests, such as, "If you're interested in gaming, why not check out this new game store?"

[0076] Step 8:

[0077] The server receives the response message from the generative model and sends it to the device via the LINE API.

[0078] Step 9:

[0079] The device displays the received message on the user's LINE app screen, providing the user with new information.

[0080] The specific process flow when a user changes their settings

[0081] Step 1:

[0082] The user opens the settings screen within the LINE app and changes their interests and character settings.

[0083] Step 2:

[0084] The terminal captures the user's selected settings and sends them to the server.

[0085] Step 3:

[0086] The server receives the configuration information and associates it with the user's ID.

[0087] Step 4:

[0088] The server accesses the database and updates the user's profile information based on the received setting information.

[0089] Step 5:

[0090] The server generates a confirmation message for the setting change and sends it to the device via the LINE API.

[0091] Step 6:

[0092] The device will display a confirmation message to the user, informing them that their settings have been updated.

[0093] This allows users to easily and efficiently obtain information and change settings through interaction with the system.

[0094] Example 1

[0095] 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."

[0096] Conventional dialogue systems, which rely on user interfaces, struggle to provide users with personalized and relevant responses instantly. They also lack efficient methods for recommending products and services that match users' hobbies and preferences. Furthermore, they have limited means for users to easily customize their interests and preferences.

[0097] 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.

[0098] In this invention, the server includes: means for providing an information display device for conversation with a user; means for connecting to a storage device that stores the user's hobbies and preferences; means for generating a personalized response based on the user's input using a generative AI model; means for the terminal to send a message to the server; means for the server to retrieve a user profile from a database; means for the server to send the generated response to the terminal; and means for the terminal to display the response to the user. This allows the user to enjoy natural conversations based on their hobbies and preferences and timely recommendations. In addition, the user can easily customize their interests and settings, allowing for a more personalized conversation experience.

[0099] An "information display device" is a device that provides an interface for a user to interact with a system.

[0100] A "storage device" is a device that includes a database that stores information such as a user's hobbies, preferences, and conversation history.

[0101] A "generative AI model" is a machine learning model that uses user input data and information stored in a storage device to generate personalized responses.

[0102] A "terminal" is a device such as a smartphone or tablet that allows a user to interact with the system.

[0103] A "server" is a back-end system that processes input data from a user and generates and sends a personalized response.

[0104] "Profile information" is personal information including a user's hobbies, preferences, interaction history, and the like.

[0105] "Context analysis" is the process of understanding the context from user input and past dialogue history and generating an appropriate response.

[0106] "Recommendation" refers to recommending products or services based on a user's interests and preferences.

[0107] "Customization" is the process by which users themselves change and update their interests and settings.

[0108] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of that dialogue. This invention is composed of a user interface, a database, a generative AI model, and a back-end server that exchanges data between them.

[0109] User Interface

[0110] The user interface is what allows the user to interact with the system. This interface utilizes a messaging platform such as the LINE app. The LINE app provides an input and output screen for the user, receives the user's input message, and displays the generated response. Through this interface, the user sends a message, which is then sent to the server via the device.

[0111] Database

[0112] The database stores information such as the user's hobbies, preferences, and interaction history. This provides the foundation for the generative AI model to generate optimal responses based on past data. The database can be a common RDBMS (relational database management system). Specific examples include MySQL and PostgreSQL. This database is updated in real time as the user adds new interests or preferences.

[0113] Generative AI Models

[0114] Generative AI models use user input data and information stored in a database to generate personalized responses. These models use advanced machine learning techniques such as GPT-3 and BERT. Contextual analysis, in particular, can accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[0115] server

[0116] The server receives data sent by the user, retrieves the user profile from the database, and provides information to the generative AI model. The server processes the received information and generated responses and sends personalized messages to the device. This process allows the user to enjoy natural interactions.

[0117] Specific examples

[0118] The operation of the present invention will be explained below by showing a specific example.

[0119] Example 1: Want to know about a new game?

[0120] When a user sends a message through the LINE app saying "I want to know about new games," the processing flow is as follows:

[0121] 1. The terminal sends this message to the server.

[0122] 2. The server retrieves the user's profile information from the database, which may include "Interests: Gaming" and "Recent Activity: Searching for Gaming Gear."

[0123] 3. The server passes this information and the user's message to a generative AI model for contextual analysis. The generative model identifies information relevant to the "game" and generates an appropriate response.

[0124] 4. The server generates a response and sends it to the device: "If you're interested in gaming, why not check out this new game store?"

[0125] 5. The terminal displays this message to the user.

[0126] Example 2: Updating interests and preferences

[0127] The process flow when a user changes interests or settings on the settings screen within the LINE app is as follows:

[0128] 1. The user opens the settings screen within the LINE app and changes their interests and character settings.

[0129] 2. The device sends this change information to the server.

[0130] 3. The server updates the user profile information in the database.

[0131] 4. Based on the new settings, the generative AI model generates a new personalized response from the next interaction.

[0132] Prompt Sentence Examples

[0133] I want to know about new games

[0134] "Tell me some recent hit movies."

[0135] "Tell me about a recommended cafe nearby."

[0136] In this way, users can enjoy a natural dialogue experience while constantly staying connected with new information. The system can also provide instant responses to various needs and recommend products and services at the appropriate time, achieving both user convenience and profitability for service providers.

[0137] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0138] Step 1:

[0139] A user uses the LINE app to input and send a message saying, "I want to know about new games." The input is the text message sent by the user, and the output is the message data sent by the device to the next processing step.

[0140] Specific behavior:

[0141] The user opens the LINE app.

[0142] Type "I want to know about new games" into the message input field.

[0143] Tap the send message button.

[0144] Step 2:

[0145] The terminal sends the received message to the server. In this process, the input is the message data sent by the user, and the output is the data packet sent to the server.

[0146] Specific behavior:

[0147] The LINE app on the device captures the message sending event.

[0148] A data packet is created containing the message content and the user ID.

[0149] Sends a data packet to a server-side API endpoint.

[0150] Step 3:

[0151] The server analyzes the received message data, extracts the user ID, and retrieves the user profile information from the database. The input of this process is the data packet sent from the terminal, and the output is the user profile information.

[0152] Specific behavior:

[0153] The server analyzes the received data packets.

[0154] A database query is generated to retrieve profile information based on the user ID.

[0155] Get "Interests" and "Recent Activity" information from search results.

[0156] Step 4:

[0157] The server passes the acquired user profile information and message to the generative AI model for context analysis and response generation. The input to this process is the user profile information and user message, and the output is the response message generated by the generative AI model.

[0158] Specific behavior:

[0159] The server sends the data to the API endpoint of the generative AI model.

[0160] The transmitted data includes the user's messages, profile information, and interaction history.

[0161] The generative AI model performs contextual analysis and generates an appropriate response.

[0162] Step 5:

[0163] The server sends the generated response message to the terminal. The input of this process is the response data from the generative AI model, and the output is a response data packet sent to the terminal.

[0164] Specific behavior:

[0165] The server receives the response data from the generative model.

[0166] Convert the received response data into a format suitable for the terminal.

[0167] Send the formatted data to the API endpoint on the device.

[0168] Step 6:

[0169] The terminal displays the response message received from the server to the user. The input of this process is the response data packet sent from the server, and the output is the response message displayed to the user.

[0170] Specific behavior:

[0171] The terminal receives the response data from the server.

[0172] It analyzes the received data and generates a message to display to the user.

[0173] The message display area will display the response message "If you're interested in gaming, why not check out this new game store?"

[0174] (Application example 1)

[0175] 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."

[0176] In today's brick-and-mortar stores, it is difficult for shoppers to easily obtain detailed information about products in the store and efficiently search for products and services that match their hobbies and preferences. Furthermore, there are limitations to face-to-face recommendations by store clerks, making it difficult to provide personalized suggestions. This reduces convenience for shoppers and leads to missed sales opportunities for stores. Therefore, there is a need for a method to provide personalized recommendations based on users' individual profiles in real time in brick-and-mortar stores through natural dialogue.

[0177] 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.

[0178] In this invention, the server includes means for providing a user interface for conversation with a user, means for connecting to a database that stores the user's hobbies and preferences, means for generating a personalized response based on the user's input using a generative model, and means for sending the personalized response to the user in a physical store and recommending products and services at an appropriate time. This enables the user to receive recommendations for products and services that match their hobbies and preferences through natural conversation, even in a physical store.

[0179] "User interface" is a general term for the screens and applications that allow a purchaser to interact with the system through an electronic device.

[0180] A "database" is a collection of information that systematically stores information such as a buyer's hobbies, preferences, and purchase history, and allows it to be quickly retrieved as needed.

[0181] A "generative model" is an algorithm or program that uses machine learning techniques to generate personalized responses based on input from shoppers and information stored in a database.

[0182] A "brick and mortar store" is a physical location, a sales establishment where customers can physically visit and view and touch products.

[0183] "Personalized responses" refer to answers and suggestions that are optimized to suit a buyer's individual tastes and preferences.

[0184] "Goods and services" is a general term for goods and services provided that a purchaser is interested in and can consider purchasing or using.

[0185] "Recommendation" refers to the act of the system suggesting appropriate products or services based on the buyer's profile and conversation content.

[0186] "Contextual analysis" is a processing method for understanding text, conversation flow, and background information and deriving appropriate responses based on that.

[0187] The present invention provides a system that engages in natural dialogue with a user, generates personalized responses based on the content of the dialogue, and efficiently recommends products and services in a physical store. Specific embodiments of the system are described below.

[0188] System configuration

[0189] User Interface

[0190] The user interface is provided through a smartphone app. Customers can launch the app and interact with the system via text or voice. For example, a customer might say, "I want to see new fashion items."

[0191] Database

[0192] The server is connected to a database that stores information such as the buyer's hobbies, preferences, purchase history, etc. This database makes it possible to quickly obtain information that interests the buyer.

[0193] Generative Model

[0194] Generative models use machine learning techniques, particularly generative AI models. Specifically, generative AI models such as OpenAI's GPT-3 are used. The generative model generates personalized responses using the buyer's input data and information stored in the database. For example, if a buyer inputs, "I want to see new fashion items," the generative model will generate new product information related to fashion and respond appropriately.

[0195] Sending personalized responses

[0196] The server then sends the generated personalized response to the customer in the physical store, allowing the customer to receive personalized information in real time, such as a message like, "We have new fashion items that match your taste. Check out this section."

[0197] Hardware and software used

[0198] Hardware: Smartphones, in-store Wi-Fi

[0199] Software: React Native is used on the client side, and Flask is used on the server side as a web application framework. Relational databases such as MySQL and PostgreSQL are used as databases, and OpenAI's GPT-3 is used as a generative model.

[0200] Specific examples

[0201] 1. The buyer enters the physical store and launches the app on their smartphone.

[0202] 2. The app will display an initial message saying "Hello! What are you looking for?"

[0203] 3. The buyer enters "I want to see new fashion items" in the message field.

[0204] 4. The app sends a request to the server.

[0205] 5. The server retrieves the buyer's profile information from the database and generates the appropriate response using the generative model.

[0206] 6. The app will say, "We have new fashion items that fit your taste. Check out this section."

[0207] Prompt Sentence Examples

[0208] User input: "I want to see new fashion items."

[0209] User profile: "interests: ['fashion', 'technology'], purchase_history: ['smartwatch']"

[0210] Generative model prompt: "The buyer is interested in fashion and is looking for new products. Please suggest new fashion items that would suit him / her."

[0211] The above is a specific embodiment for carrying out the present invention.

[0212] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0213] Step 1:

[0214] The user launches the smartphone app and enters a message saying, "I want to see new fashion items."

[0215] Input: User message: "I want to see new fashion items."

[0216] Output: Request data generated on the terminal

[0217] How it works: A user enters text into the app's message input field, and that text is generated on the device as request data.

[0218] Step 2:

[0219] The terminal sends the user's message to the server.

[0220] Input: Request data

[0221] Output: The request sent to the server

[0222] Operation: The terminal sends the generated request data to the server.

[0223] Step 3:

[0224] The server receives the request data and retrieves the user's profile information from a database.

[0225] Input: The request received by the server, the user ID from the database

[0226] Output: User profile information

[0227] How it works: The server analyzes the request data, obtains the user ID, and uses that user ID to retrieve the user's profile information from the database.

[0228] Step 4:

[0229] The server passes the user's profile information and the user's message to a generative model to generate a personalized response.

[0230] Input: User profile information, User message

[0231] Output: Personalized response

[0232] How it works: The server inputs the user's profile information and the user's message as a prompt into the generative AI model, which then generates a personalized response. At this time, the generative AI model performs contextual analysis to create an optimized response.

[0233] Step 5:

[0234] The server sends the generated personalized response to the terminal.

[0235] Input: Personalized Response

[0236] Output: Response data sent to the device

[0237] Operation: The server packages the generated response, formats it as a request to be sent to the device, and sends it to the device.

[0238] Step 6:

[0239] The terminal displays the personalized response received from the server to the user.

[0240] Input: Response data received from the server

[0241] Output: A personalized response that is displayed on the screen

[0242] Operation: The device analyzes the response data received from the server and displays it on the screen as a response. For example, it displays a message such as "We have new fashion items that suit your taste. Check out this section."

[0243] The above is a series of processing steps that allow users to receive recommendations through natural dialogue in a physical store.

[0244] 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.

[0245] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of the dialogue and emotional data. The system is composed of a user interface, a database, a generative model, an emotional engine, and a back-end server that exchanges data between these elements.

[0246] User Interface

[0247] The user interface is what allows the user to interact with the system. It uses a messaging platform such as the LINE app to provide input and output screens for the user. Data entered by the user is sent to the server via the device.

[0248] Database

[0249] The database stores users' hobbies, preferences, interaction history, and emotional data, providing the foundation for the generative model and emotion engine to generate optimal responses based on past data. The database is updated in real time as users add new interests or preferences.

[0250] Generative Model

[0251] Generative models use user input data and information stored in a database to generate personalized responses. Generative models use machine learning techniques, particularly contextual analysis, to accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[0252] Emotion Engine

[0253] The emotion engine analyzes emotion data obtained from the user interface, such as tone of voice, facial expressions, and context. The analysis results are provided to the generative model to realize personalized responses based on the user's emotions. The emotion engine also stores the user's emotion data in a database, allowing the generative model to generate responses based on past emotion history.

[0254] server

[0255] The server receives the data sent by the user and generates a response based on the user profile, interaction history, and emotion data. The server uses the generative model and emotion engine to send personalized messages to the user through the user interface, allowing the user to enjoy natural interactions.

[0256] Example

[0257] The operation of the present invention will be described below through specific examples.

[0258] Example 1:

[0259] A user sends a message through the LINE app saying, "I'd like to know about a new game."

[0260] 1. The terminal sends this message to the server.

[0261] 2. The server retrieves the user's profile information from the database, including "Interests: Gaming" and emotional data.

[0262] 3. The server passes this information and the user's message to the generative model for contextual analysis. The generative model identifies information relevant to the "game" and generates an appropriate response.

[0263] 4. The emotion engine retrieves emotion data from the user interface and analyzes the user's current emotional state. This analysis result is also provided to the generative model.

[0264] 5. The generative model generates an optimal response message based on the user's interests and emotions, such as, "If you're interested in gaming, why not check out this new game store?"

[0265] 6. The server sends the generated response message to the terminal.

[0266] 7. The device will display this message on the user's LINE app screen, providing the user with the new information.

[0267] Example 2:

[0268] When users' emotions change during everyday interactions.

[0269] 1. Users send emojis or words that express their emotions through the LINE app.

[0270] 2. The device sends the user's input data and emotion data to the server.

[0271] 3. The server retrieves the user's emotional data from the database and analyzes the changes.

[0272] 4. The emotion engine analyzes the additional emotion data obtained from the user interface.

[0273] 5. The generative model generates new responses based on the analyzed emotional data and profile information. For example, if the user is feeling down, it generates a response like, "Why don't you cheer up and relax with the latest game?"

[0274] 6. The server sends the generated response message to the terminal.

[0275] 7. The device will display this message on the user's LINE app screen and provide appropriate support to the user.

[0276] This allows users to have an optimal conversational experience that is tailored to their emotions through their interactions with the system.

[0277] The processing flow will be explained below.

[0278] Specific processing flow when requesting new information based on information including user emotions

[0279] Step 1:

[0280] A user types a message through the LINE app saying, "I'd like to know about new games."

[0281] Step 2:

[0282] The device collects emotional data such as tone of voice and emojis along with the user's text message and sends it to the server using the LINE API.

[0283] Step 3:

[0284] The server analyzes the message and emotion data received from the LINE API and identifies the sender's user ID.

[0285] Step 4:

[0286] The server accesses the database and retrieves profile information (interests, preferences, interaction history, and emotional data) associated with the user ID.

[0287] Step 5:

[0288] The server passes the acquired profile information and the user's message to the generative model for context analysis. The generative model analyzes the input data and identifies the context.

[0289] Step 6:

[0290] The generative model analyzes the context of "new game" and further confirms from profile information that the user's interest is "gaming."

[0291] Step 7:

[0292] The emotion engine analyzes emotional data obtained from the user interface (tone of voice, facial expressions, emojis, etc.) to identify the user's current emotional state.

[0293] Step 8:

[0294] The generative model combines the results of contextual analysis with emotional data from the emotion engine to generate an optimal response, such as "If you're interested in gaming, why not check out this new game store?"

[0295] Step 9:

[0296] The server receives the response message from the generative model and sends it to the device via the LINE API.

[0297] Step 10:

[0298] The device displays the received message on the user's LINE app screen, providing the user with new information.

[0299] Specific process flow when a user changes their own settings

[0300] Step 1:

[0301] The user opens the settings screen within the LINE app and changes their interests, character settings, and emotion settings.

[0302] Step 2:

[0303] The terminal captures the setting information and emotion data selected by the user and transmits them to the server.

[0304] Step 3:

[0305] The server receives the setting information and associates it with the corresponding user ID.

[0306] Step 4:

[0307] The server accesses the database and updates the user's profile with the received settings, including the emotion settings.

[0308] Step 5:

[0309] The server generates a confirmation message for the setting change and sends it to the device via the LINE API.

[0310] Step 6:

[0311] The device will display a confirmation message to the user, informing them that their settings have been updated.

[0312] This allows users to change their own settings through real-time interaction with the system, providing an optimal interaction experience tailored to their emotions.

[0313] Example 2

[0314] 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."

[0315] Conventional dialogue systems have difficulty generating responses that reflect the user's emotional state as well as providing personalized responses based on the user's hobbies and preferences, which can result in a mechanical and unnatural dialogue experience for the user.

[0316] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for providing a user interface for conversation with a user, a means for connecting to a database that stores the user's hobbies and preferences, a means for generating a personalized response based on the user's input using a generative model, a means for connecting to an emotion engine that analyzes emotion data and reflects the emotion data in the response, and a means for sending the personalized response to the user. This makes it possible to provide a natural dialogue experience that is not only based on the user's hobbies and preferences but also on their emotional state.

[0317] A "user interface" is a mechanism that provides a screen and input means for a user to interact with a system.

[0318] A "database" is a system that stores and manages information such as a user's hobbies and preferences, dialogue history, and emotional data.

[0319] A "generative model" is an algorithm that uses machine learning techniques to generate personalized responses based on user input data and information stored in a database.

[0320] The "emotion engine" is a system that analyzes emotional data obtained from the user's voice, facial expressions, context, etc., and provides the analysis results to a generative model.

[0321] The "server" is a central processing unit that receives data sent by a user, generates a response through a generative model and an emotion engine, and sends the response to the user.

[0322] A "personalized response" is a response message that is tailored to an individual based on the user's individual tastes, preferences, and emotional state.

[0323] "Context analysis" is a technology that understands and analyzes the context and meaning of the current dialogue based on the user's input data and past dialogue history.

[0324] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of the dialogue and emotional data. The system is composed of a user interface, a database, a generative model, an emotional engine, and a back-end server that exchanges data between these elements.

[0325] User Interface

[0326] The user interface is what allows the user to interact with the system. For example, a messaging platform is used to provide input and output screens for the user. Specifically, the LINE app is used. Data entered by the user is sent to the server via the device.

[0327] Database

[0328] The database stores users' hobbies, preferences, interaction history, and emotional data, providing the foundation for the generative model and emotion engine to generate optimal responses based on past data. The database is updated in real time as users add new interests or preferences.

[0329] Generative Model

[0330] Generative models use user input data and information stored in a database to generate personalized responses. Generative models use machine learning techniques, particularly contextual analysis, to accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[0331] Emotion Engine

[0332] The emotion engine analyzes emotion data obtained from the user interface, such as tone of voice, facial expressions, and context. The analysis results are provided to the generative model to realize personalized responses based on the user's emotions. The emotion engine also stores the user's emotion data in a database, allowing the generative model to generate responses based on past emotion history.

[0333] server

[0334] The server receives the data sent by the user and generates a response based on the user profile, interaction history, and emotion data. The server uses the generative model and emotion engine to send personalized messages to the user through the user interface, allowing the user to enjoy natural interactions.

[0335] Example

[0336] The operation of the present invention will be described below through specific examples.

[0337] Example 1:

[0338] A user sends a message through the LINE app saying, "I'd like to know about a new game."

[0339] 1. A user sends a message through the LINE app saying, "I want to know about a new game."

[0340] 2. The device sends this message to the server.

[0341] 3. The server retrieves the user's profile information ("Interests: Gaming") and emotion data from the database.

[0342] 4. The server passes this information and the user's message to the generative model for contextual analysis.

[0343] 5. The generative model identifies information related to "games" and generates content such as, "If you're interested in gaming, why not check out this new game store?"

[0344] 6. The emotion engine retrieves emotion data from the user interface and analyzes the user's current emotional state.

[0345] 7. The generative model generates optimal responses based on the user's interests and emotions.

[0346] 8. The server sends the generated response message to the terminal.

[0347] 9. The device will display this message on the LINE app screen and provide the user with new information.

[0348] Example 2:

[0349] When users' emotions change during everyday interactions.

[0350] 1. Users send emojis or words that express their emotions through the LINE app.

[0351] 2. The device sends the user's input data and emotion data to the server.

[0352] 3. The server retrieves the user's emotional data from the database and analyzes the changes.

[0353] 4. The emotion engine analyzes the additional emotion data obtained from the user interface.

[0354] 5. The generative model generates new responses based on the analyzed emotional data and profile information. For example, if the user is feeling down, it generates a response like, "Why don't you cheer up and relax with the latest game?"

[0355] 6. The server sends the generated response message to the terminal.

[0356] 7. The device will display this message on the LINE app screen and provide appropriate support to the user.

[0357] In this way, users can have an optimal emotional interaction experience through their interactions with the system.

[0358] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0359] Step 1:

[0360] A user uses the LINE app to send a message saying, "I want to know about new games." This message represents a user request, and the system receives this message and begins processing. The input is the user's message, and the output is that the message is sent to the device.

[0361] Step 2:

[0362] The terminal receives the user's message and sends it to the server. The terminal receives the message data, assigns the user ID to it, and sends it to the server. The input is the user's message and user ID, and the output is that the message and user ID are sent to the server.

[0363] Step 3:

[0364] The server accesses the database based on the user ID and obtains the user's profile information and past interaction history. The server obtains this data and stores it for processing. The input is the user ID, and the output is the user's profile information and past interaction history. Specifically, it obtains "interests: gaming" and emotional data.

[0365] Step 4:

[0366] The server passes the acquired profile information and user message to a generative model. The generative model uses machine learning techniques to perform contextual analysis and generate an appropriate response based on the user's interests. The input is the profile information and user message, and the output is a personalized response message. For example, a response might be generated that says, "If you're interested in gaming, why not check out this new game store?"

[0367] Step 5:

[0368] The server passes emotion data obtained from the user interface to the emotion engine, which analyzes emotions from voice tone, emojis, etc. and provides the results to the generative model. The input is emotion data, and the output is the analyzed emotional state.

[0369] Step 6:

[0370] The generative model uses the analysis results from the emotion engine to determine the optimal response message. The generative model takes into account the user's interests and current emotional state to generate the most appropriate response. The input is the analysis results and profile information, and the output is the final response message. For example, if the user is excited, the generative model generates a message saying, "If you're interested in gaming, why not check out this new game store? It's fun!"

[0371] Step 7:

[0372] The server sends the generated optimal response message to the terminal. Here, the server encodes the response message and sends it to the terminal. The input is the final response message, and the output is the message sent to the terminal.

[0373] Step 8:

[0374] The device displays the response message received from the server on the user's LINE app screen. The device decodes the message and displays it on the user interface to provide the user with new information. The input is the response message from the server, and the output is the message displayed in the LINE app.

[0375] This completes the entire processing flow, allowing the user to receive personalized responses from the system and enjoy a natural interaction experience.

[0376] (Application example 2)

[0377] 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."

[0378] In modern stores, customer service is extremely important, but it is difficult for store staff to make appropriate suggestions and responses based on each customer's interests and emotions. It is also difficult to immediately determine what a customer is looking for or what their emotional state is. This can result in lower customer satisfaction and negatively impact store sales. Therefore, there is a need for a system that can suggest personalized services and products based on a customer's emotional state and preferences.

[0379] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for providing a user interface for conversation with a user, means for connecting to a database that stores the user's hobbies and preferences, means for generating a personalized response based on the user's input using a generative model, means for providing an emotion engine that analyzes the user's emotion data, means for displaying information on a head-mounted display for customer service support, and means for transmitting the personalized response to the user. This enables store staff to suggest optimal products and services in real time based on the customer's emotional state and preferences.

[0380] "User interface" refers to the screen and operating means that allow a user to interact with a system.

[0381] The "database" is a system that stores and manages users' hobbies, preferences, conversation history, emotional data, etc.

[0382] A "generative model" refers to an algorithm or machine learning technique that generates personalized responses based on user input data and information stored in a database.

[0383] The "emotion engine" is a system that analyzes emotional data such as tone of voice, facial expressions, and context obtained from the user interface and provides the analysis results to a generative model.

[0384] A "head-mounted display" is a display device worn on the user's head, and is used to display information for customer service support.

[0385] A "personalized response" refers to a response that is individually generated based on the user's tastes, preferences, and emotional state.

[0386] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of the dialogue and emotional data. The system is composed of a user interface, a database, a generative model, an emotional engine, and a server that exchanges data between these elements.

[0387] User Interface

[0388] The terminal provides a user interface for user interaction with the system. This interface uses a messaging platform (e.g., a messaging application) and provides the user with input and output screens. Data entered by the user is sent to the server through the terminal.

[0389] Database

[0390] The server connects to a database that stores users' hobbies, preferences, interaction history, and emotional data. This provides the foundation for the generative model and emotion engine to generate optimal responses based on past data. The database is updated in real time as users add new interests or preferences.

[0391] Generative Model

[0392] The server uses a generative model to generate personalized responses based on the user's input data and information stored in the database. The generative model uses machine learning techniques, particularly contextual analysis, to accurately identify the user's current interests and concerns. This enables natural and timely recommendations.

[0393] Emotion Engine

[0394] The server uses an emotion engine to analyze emotion data obtained from the user interface, such as tone of voice, facial expression, and context. The analysis results are provided to a generative model to realize personalized responses based on the user's emotions. The emotion engine also stores the user's emotion data in a database, allowing the generative model to generate responses based on past emotion history.

[0395] head-mounted display

[0396] A head-mounted display (HMD) is used by store staff to interact with customers, displaying information sent from the server in real time, allowing staff to make optimal suggestions based on the customer's emotional state and interests.

[0397] Specific examples

[0398] Example 1:

[0399] Consider a case where a user says, "I'm looking for new sneakers." The user's facial expression captured by the camera indicates that they are excited. This information is sent to the server, where it is analyzed by the generative model. Based on the user's interests and emotional state, the server displays a message on the HMD saying, "This new model is perfect for you. Would you like to try them on?" This allows store staff to provide the customer with the best possible product suggestions.

[0400] Example prompt sentence:

[0401] "When a customer says, 'I'm looking for new sneakers,' the emotion they're feeling is excitement. Based on this, generate the perfect sneaker suggestions for them."

[0402] This invention allows store staff to suggest optimal products and services in real time based on a customer's emotional state and preferences.

[0403] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0404] Program processing steps

[0405] Step 1:

[0406] The user puts on the HMD and starts the system.

[0407] How it works: When a user turns on the dedicated device (HMD), the user interface starts up and the camera and microphone capture the customer's video and audio in real time.

[0408] Input: Camera video data, microphone audio data.

[0409] Output: Real-time video and audio data is processed.

[0410] ---

[0411] Step 2:

[0412] The device (HMD) transmits camera images and audio data to the server.

[0413] How it works: The HMD transmits captured video and audio data to a server via wireless communication.

[0414] Input: Real-time video and audio data.

[0415] Output: Video and audio data sent to the server.

[0416] ---

[0417] Step 3:

[0418] The server analyzes the video data using an emotion engine to identify the customer's emotional state.

[0419] How it works: The server uses an emotion engine to analyze the customer's facial expressions from the video data and identify their emotional state. For example, it determines their emotion based on features such as a smile or wrinkles between the eyebrows.

[0420] Input: Video data.

[0421] Output: Emotional state data (e.g., happy, excited, calm, etc.).

[0422] ---

[0423] Step 4:

[0424] The server analyzes the voice data and converts what the customer says into text.

[0425] How it works: The server uses voice recognition technology to convert the audio data into text, extracting important keywords and phrases.

[0426] Input: Audio data.

[0427] Output: Text data.

[0428] ---

[0429] Step 5:

[0430] The server uses a generative model to generate a personalized response based on the text data and the emotional state data.

[0431] How it works: The server inputs text data and emotional state data into a generative model, which generates responses based on the user's interests and history from an existing database.

[0432] Input: Text data, emotional state data.

[0433] Output: A personalized response message.

[0434] ---

[0435] Step 6:

[0436] The server sends the generated response message to the HMD.

[0437] Operation: The server generates and sends a personalized response message in a format that can be displayed on the HMD's display.

[0438] Input: A personalized response message.

[0439] Output: Message sent to the HMD.

[0440] ---

[0441] Step 7:

[0442] The terminal (HMD) displays the response message received from the server to the store staff.

[0443] How it works: The HMD displays the received message on its display, allowing store staff to make suggestions to the customer.

[0444] Input: A personalized response message.

[0445] Output: Message displayed on the HMD display.

[0446] ---

[0447] Examples:

[0448] For example, if a user says, "I'm looking for new sneakers," and the camera shows that the user is excited, the server will display a response message on the HMD saying, "This new model is perfect for you. Would you like to try them on?"

[0449] Example prompt sentence:

[0450] "When a customer says, 'I'm looking for new sneakers,' the emotion they're feeling is excitement. Based on this, generate the perfect sneaker suggestions for them."

[0451] 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.

[0452] 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.

[0453] 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.

[0454] [Second embodiment]

[0455] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0456] 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.

[0457] 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).

[0458] 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.

[0459] 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.

[0460] 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).

[0461] 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.

[0462] 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.

[0463] 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.

[0464] 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.

[0465] 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.

[0466] 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."

[0467] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of that dialogue. The system is composed of a user interface, a database, a generative model, and a back-end server that exchanges data between them.

[0468] User Interface

[0469] The user interface is what allows the user to interact with the system. It uses a messaging platform such as the LINE app to provide input and output screens for the user. Data entered by the user is sent to the server via the device.

[0470] Database

[0471] The database stores information such as the user's hobbies, preferences, and interaction history, providing the foundation for the generative model to generate optimal responses based on past data. The database is updated in real time as the user adds new interests or preferences.

[0472] Generative Model

[0473] Generative models use user input data and information stored in a database to generate personalized responses. Generative models use machine learning techniques, particularly contextual analysis, to accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[0474] server

[0475] The server receives the data sent by the user and generates a response based on the user profile and interaction history. The server uses the generative model to send personalized messages to the user through the user interface, allowing the user to enjoy natural interactions.

[0476] Example

[0477] The operation of the present invention will be described below through specific examples.

[0478] Example 1:

[0479] A user sends a message through the LINE app saying, "I'd like to know about a new game."

[0480] 1. The terminal sends this message to the server.

[0481] 2. The server retrieves the user's profile information from the database, which may include "Interests: Gaming" and "Recent Activity: Searching for Gaming Gear."

[0482] 3. The server passes this information and the user's message to the generative model for contextual analysis. The generative model identifies information relevant to the "game" and generates an appropriate response.

[0483] 4. The server generates a response and sends it to the device: "If you're interested in gaming, why not check out this new game store?"

[0484] 5. The terminal displays this message to the user.

[0485] Example 2:

[0486] Users update their interests and preferences.

[0487] 1. The user opens the settings screen within the LINE app and changes their interests and character settings.

[0488] 2. The device sends this change information to the server.

[0489] 3. The server updates the user profile information in the database.

[0490] 4. Based on the new settings, the generative model generates a new personalized response from the next interaction.

[0491] This allows users to enjoy a natural conversational experience while always staying connected to the latest information. Product and service recommendations are also made at the appropriate time, achieving both user convenience and profitability for service providers.

[0492] The processing flow will be explained below.

[0493] Specific processing flow when a user requests new information

[0494] Step 1:

[0495] A user types a message through the LINE app saying, "I'd like to know about new games."

[0496] Step 2:

[0497] The device receives the user's message as text data and sends it to the server via the LINE app API.

[0498] Step 3:

[0499] The server analyzes the message received from the LINE API and identifies the sender's user ID.

[0500] Step 4:

[0501] The server accesses the database and retrieves profile information (interests, preferences, interaction history) associated with the user ID.

[0502] Step 5:

[0503] The server passes the acquired profile information and the user's message to the generative model, which analyzes the input data and identifies the context.

[0504] Step 6:

[0505] The generative model analyzes the context of "new game" and simultaneously confirms from profile information that the user's interest is "gaming."

[0506] Step 7:

[0507] The generative model generates the optimal response message based on the user's interests, such as, "If you're interested in gaming, why not check out this new game store?"

[0508] Step 8:

[0509] The server receives the response message from the generative model and sends it to the device via the LINE API.

[0510] Step 9:

[0511] The device displays the received message on the user's LINE app screen, providing the user with new information.

[0512] The specific process flow when a user changes their settings

[0513] Step 1:

[0514] The user opens the settings screen within the LINE app and changes their interests and character settings.

[0515] Step 2:

[0516] The terminal captures the user's selected settings and sends them to the server.

[0517] Step 3:

[0518] The server receives the configuration information and associates it with the user's ID.

[0519] Step 4:

[0520] The server accesses the database and updates the user's profile information based on the received setting information.

[0521] Step 5:

[0522] The server generates a confirmation message for the setting change and sends it to the device via the LINE API.

[0523] Step 6:

[0524] The device will display a confirmation message to the user, informing them that their settings have been updated.

[0525] This allows users to easily and efficiently obtain information and change settings through interaction with the system.

[0526] Example 1

[0527] 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."

[0528] Conventional dialogue systems, which rely on user interfaces, struggle to provide users with personalized and relevant responses instantly. They also lack efficient methods for recommending products and services that match users' hobbies and preferences. Furthermore, they have limited means for users to easily customize their interests and preferences.

[0529] 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.

[0530] In this invention, the server includes: means for providing an information display device for conversation with a user; means for connecting to a storage device that stores the user's hobbies and preferences; means for generating a personalized response based on the user's input using a generative AI model; means for the terminal to send a message to the server; means for the server to retrieve a user profile from a database; means for the server to send the generated response to the terminal; and means for the terminal to display the response to the user. This allows the user to enjoy natural conversations based on their hobbies and preferences and timely recommendations. In addition, the user can easily customize their interests and settings, allowing for a more personalized conversation experience.

[0531] An "information display device" is a device that provides an interface for a user to interact with a system.

[0532] A "storage device" is a device that includes a database that stores information such as a user's hobbies, preferences, and conversation history.

[0533] A "generative AI model" is a machine learning model that uses user input data and information stored in a storage device to generate personalized responses.

[0534] A "terminal" is a device such as a smartphone or tablet that allows a user to interact with the system.

[0535] A "server" is a back-end system that processes input data from a user and generates and sends a personalized response.

[0536] "Profile information" is personal information including a user's hobbies, preferences, interaction history, and the like.

[0537] "Context analysis" is the process of understanding the context from user input and past dialogue history and generating an appropriate response.

[0538] "Recommendation" refers to recommending products or services based on a user's interests and preferences.

[0539] "Customization" is the process by which users themselves change and update their interests and settings.

[0540] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of that dialogue. This invention is composed of a user interface, a database, a generative AI model, and a back-end server that exchanges data between them.

[0541] User Interface

[0542] The user interface is what allows the user to interact with the system. This interface utilizes a messaging platform such as the LINE app. The LINE app provides an input and output screen for the user, receives the user's input message, and displays the generated response. Through this interface, the user sends a message, which is then sent to the server via the device.

[0543] Database

[0544] The database stores information such as the user's hobbies, preferences, and interaction history. This provides the foundation for the generative AI model to generate optimal responses based on past data. The database can be a common RDBMS (relational database management system). Specific examples include MySQL and PostgreSQL. This database is updated in real time as the user adds new interests or preferences.

[0545] Generative AI Models

[0546] Generative AI models use user input data and information stored in a database to generate personalized responses. These models use advanced machine learning techniques such as GPT-3 and BERT. Contextual analysis, in particular, can accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[0547] server

[0548] The server receives data sent by the user, retrieves the user profile from the database, and provides information to the generative AI model. The server processes the received information and generated responses and sends personalized messages to the device. This process allows the user to enjoy natural interactions.

[0549] Specific examples

[0550] The operation of the present invention will be explained below by showing a specific example.

[0551] Example 1: Want to know about a new game?

[0552] When a user sends a message through the LINE app saying "I want to know about new games," the processing flow is as follows:

[0553] 1. The terminal sends this message to the server.

[0554] 2. The server retrieves the user's profile information from the database, which may include "Interests: Gaming" and "Recent Activity: Searching for Gaming Gear."

[0555] 3. The server passes this information and the user's message to a generative AI model for contextual analysis. The generative model identifies information relevant to the "game" and generates an appropriate response.

[0556] 4. The server generates a response and sends it to the device: "If you're interested in gaming, why not check out this new game store?"

[0557] 5. The terminal displays this message to the user.

[0558] Example 2: Updating interests and preferences

[0559] The process flow when a user changes interests or settings on the settings screen within the LINE app is as follows:

[0560] 1. The user opens the settings screen within the LINE app and changes their interests and character settings.

[0561] 2. The device sends this change information to the server.

[0562] 3. The server updates the user profile information in the database.

[0563] 4. Based on the new settings, the generative AI model generates a new personalized response from the next interaction.

[0564] Prompt Sentence Examples

[0565] I want to know about new games

[0566] "Tell me some recent hit movies."

[0567] "Tell me about a recommended cafe nearby."

[0568] In this way, users can enjoy a natural dialogue experience while constantly staying connected with new information. The system can also provide instant responses to various needs and recommend products and services at the appropriate time, achieving both user convenience and profitability for service providers.

[0569] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0570] Step 1:

[0571] A user uses the LINE app to input and send a message saying, "I want to know about new games." The input is the text message sent by the user, and the output is the message data sent by the device to the next processing step.

[0572] Specific behavior:

[0573] The user opens the LINE app.

[0574] Type "I want to know about new games" into the message input field.

[0575] Tap the send message button.

[0576] Step 2:

[0577] The terminal sends the received message to the server. In this process, the input is the message data sent by the user, and the output is the data packet sent to the server.

[0578] Specific behavior:

[0579] The LINE app on the device captures the message sending event.

[0580] A data packet is created containing the message content and the user ID.

[0581] Sends a data packet to a server-side API endpoint.

[0582] Step 3:

[0583] The server analyzes the received message data, extracts the user ID, and retrieves the user profile information from the database. The input of this process is the data packet sent from the terminal, and the output is the user profile information.

[0584] Specific behavior:

[0585] The server analyzes the received data packets.

[0586] A database query is generated to retrieve profile information based on the user ID.

[0587] Get "Interests" and "Recent Activity" information from search results.

[0588] Step 4:

[0589] The server passes the acquired user profile information and message to the generative AI model for context analysis and response generation. The input to this process is the user profile information and user message, and the output is the response message generated by the generative AI model.

[0590] Specific behavior:

[0591] The server sends the data to the API endpoint of the generative AI model.

[0592] The transmitted data includes the user's messages, profile information, and interaction history.

[0593] The generative AI model performs contextual analysis and generates an appropriate response.

[0594] Step 5:

[0595] The server sends the generated response message to the terminal. The input of this process is the response data from the generative AI model, and the output is a response data packet sent to the terminal.

[0596] Specific behavior:

[0597] The server receives the response data from the generative model.

[0598] Convert the received response data into a format suitable for the terminal.

[0599] Send the formatted data to the API endpoint on the device.

[0600] Step 6:

[0601] The terminal displays the response message received from the server to the user. The input of this process is the response data packet sent from the server, and the output is the response message displayed to the user.

[0602] Specific behavior:

[0603] The terminal receives the response data from the server.

[0604] It analyzes the received data and generates a message to display to the user.

[0605] The message display area will display the response message "If you're interested in gaming, why not check out this new game store?"

[0606] (Application example 1)

[0607] 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."

[0608] In today's brick-and-mortar stores, it is difficult for shoppers to easily obtain detailed information about products in the store and efficiently search for products and services that match their hobbies and preferences. Furthermore, there are limitations to face-to-face recommendations by store clerks, making it difficult to provide personalized suggestions. This reduces convenience for shoppers and leads to missed sales opportunities for stores. Therefore, there is a need for a method to provide personalized recommendations based on users' individual profiles in real time in brick-and-mortar stores through natural dialogue.

[0609] 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.

[0610] In this invention, the server includes means for providing a user interface for conversation with a user, means for connecting to a database that stores the user's hobbies and preferences, means for generating a personalized response based on the user's input using a generative model, and means for sending the personalized response to the user in a physical store and recommending products and services at an appropriate time. This enables the user to receive recommendations for products and services that match their hobbies and preferences through natural conversation, even in a physical store.

[0611] "User interface" is a general term for the screens and applications that allow a purchaser to interact with the system through an electronic device.

[0612] A "database" is a collection of information that systematically stores information such as a purchaser's hobbies, preferences, and purchase history, and allows it to be quickly retrieved as needed.

[0613] A "generative model" is an algorithm or program that uses machine learning techniques to generate personalized responses based on input from shoppers and information stored in a database.

[0614] A "brick and mortar store" is a physical location, a sales establishment where customers can physically visit and view and touch products.

[0615] "Personalized responses" refer to answers and suggestions that are optimized to suit a buyer's individual tastes and preferences.

[0616] "Goods and services" is a general term for goods and services provided that a purchaser is interested in and can consider purchasing or using.

[0617] "Recommendation" refers to the act of the system suggesting appropriate products or services based on the buyer's profile and conversation content.

[0618] "Contextual analysis" is a processing method for understanding text, conversation flow, and background information and deriving appropriate responses based on that.

[0619] The present invention provides a system that engages in natural dialogue with a user, generates personalized responses based on the content of the dialogue, and efficiently recommends products and services in a physical store. Specific embodiments of the system are described below.

[0620] System configuration

[0621] User Interface

[0622] The user interface is provided through a smartphone app. Customers can launch the app and interact with the system via text or voice. For example, a customer might say, "I want to see new fashion items."

[0623] Database

[0624] The server is connected to a database that stores information such as the buyer's hobbies, preferences, purchase history, etc. This database makes it possible to quickly obtain information that interests the buyer.

[0625] Generative Model

[0626] Generative models use machine learning techniques, particularly generative AI models. Specifically, generative AI models such as OpenAI's GPT-3 are used. The generative model generates personalized responses using the buyer's input data and information stored in the database. For example, if a buyer inputs, "I want to see new fashion items," the generative model will generate new product information related to fashion and respond appropriately.

[0627] Sending personalized responses

[0628] The server then sends the generated personalized response to the customer in the physical store, allowing the customer to receive personalized information in real time, such as a message like, "We have new fashion items that match your taste. Check out this section."

[0629] Hardware and software used

[0630] Hardware: Smartphones, in-store Wi-Fi

[0631] Software: React Native is used on the client side, and Flask is used on the server side as a web application framework. Relational databases such as MySQL and PostgreSQL are used as databases, and OpenAI's GPT-3 is used as a generative model.

[0632] Specific examples

[0633] 1. The buyer enters the physical store and launches the app on their smartphone.

[0634] 2. The app will display an initial message saying "Hello! What are you looking for?"

[0635] 3. The buyer enters "I want to see new fashion items" in the message field.

[0636] 4. The app sends a request to the server.

[0637] 5. The server retrieves the buyer's profile information from the database and generates the appropriate response using the generative model.

[0638] 6. The app will say, "We have new fashion items that fit your taste. Check out this section."

[0639] Prompt Sentence Examples

[0640] User input: "I want to see new fashion items."

[0641] User profile: "interests: ['fashion', 'technology'], purchase_history: ['smartwatch']"

[0642] Generative model prompt: "The buyer is interested in fashion and is looking for new products. Please suggest new fashion items that would suit him / her."

[0643] The above is a specific embodiment for carrying out the present invention.

[0644] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0645] Step 1:

[0646] The user launches the smartphone app and enters a message saying, "I want to see new fashion items."

[0647] Input: User message: "I want to see new fashion items."

[0648] Output: Request data generated on the terminal

[0649] How it works: A user enters text into the app's message input field, and that text is generated on the device as request data.

[0650] Step 2:

[0651] The terminal sends the user's message to the server.

[0652] Input: Request data

[0653] Output: The request sent to the server

[0654] Operation: The terminal sends the generated request data to the server.

[0655] Step 3:

[0656] The server receives the request data and retrieves the user's profile information from a database.

[0657] Input: The request received by the server, the user ID from the database

[0658] Output: User profile information

[0659] How it works: The server analyzes the request data, obtains the user ID, and uses that user ID to retrieve the user's profile information from the database.

[0660] Step 4:

[0661] The server passes the user's profile information and the user's message to a generative model to generate a personalized response.

[0662] Input: User profile information, User message

[0663] Output: Personalized response

[0664] How it works: The server inputs the user's profile information and the user's message as a prompt into the generative AI model, which then generates a personalized response. At this time, the generative AI model performs contextual analysis to create an optimized response.

[0665] Step 5:

[0666] The server sends the generated personalized response to the terminal.

[0667] Input: Personalized Response

[0668] Output: Response data sent to the device

[0669] Operation: The server packages the generated response, formats it as a request to be sent to the device, and sends it to the device.

[0670] Step 6:

[0671] The terminal displays the personalized response received from the server to the user.

[0672] Input: Response data received from the server

[0673] Output: A personalized response that is displayed on the screen

[0674] Operation: The device analyzes the response data received from the server and displays it on the screen as a response. For example, it displays a message such as "We have new fashion items that suit your taste. Check out this section."

[0675] The above is a series of processing steps that allow users to receive recommendations through natural dialogue in a physical store.

[0676] 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.

[0677] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of the dialogue and emotional data. The system is composed of a user interface, a database, a generative model, an emotional engine, and a back-end server that exchanges data between these elements.

[0678] User Interface

[0679] The user interface is what allows the user to interact with the system. It uses a messaging platform such as the LINE app to provide input and output screens for the user. Data entered by the user is sent to the server via the device.

[0680] Database

[0681] The database stores users' hobbies, preferences, interaction history, and emotional data, providing the foundation for the generative model and emotion engine to generate optimal responses based on past data. The database is updated in real time as users add new interests or preferences.

[0682] Generative Model

[0683] Generative models use user input data and information stored in a database to generate personalized responses. Generative models use machine learning techniques, particularly contextual analysis, to accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[0684] Emotion Engine

[0685] The emotion engine analyzes emotion data obtained from the user interface, such as tone of voice, facial expressions, and context. The analysis results are provided to the generative model to realize personalized responses based on the user's emotions. The emotion engine also stores the user's emotion data in a database, allowing the generative model to generate responses based on past emotion history.

[0686] server

[0687] The server receives the data sent by the user and generates a response based on the user profile, interaction history, and emotion data. The server uses the generative model and emotion engine to send personalized messages to the user through the user interface, allowing the user to enjoy natural interactions.

[0688] Example

[0689] The operation of the present invention will be described below through specific examples.

[0690] Example 1:

[0691] A user sends a message through the LINE app saying, "I'd like to know about a new game."

[0692] 1. The terminal sends this message to the server.

[0693] 2. The server retrieves the user's profile information from the database, including "Interests: Gaming" and emotional data.

[0694] 3. The server passes this information and the user's message to the generative model for contextual analysis. The generative model identifies information relevant to the "game" and generates an appropriate response.

[0695] 4. The emotion engine retrieves emotion data from the user interface and analyzes the user's current emotional state. This analysis result is also provided to the generative model.

[0696] 5. The generative model generates an optimal response message based on the user's interests and emotions, such as, "If you're interested in gaming, why not check out this new game store?"

[0697] 6. The server sends the generated response message to the terminal.

[0698] 7. The device will display this message on the user's LINE app screen, providing the user with the new information.

[0699] Example 2:

[0700] When users' emotions change during everyday interactions.

[0701] 1. Users send emojis or words that express their emotions through the LINE app.

[0702] 2. The device sends the user's input data and emotion data to the server.

[0703] 3. The server retrieves the user's emotional data from the database and analyzes the changes.

[0704] 4. The emotion engine analyzes the additional emotion data obtained from the user interface.

[0705] 5. The generative model generates new responses based on the analyzed emotional data and profile information. For example, if the user is feeling down, it generates a response like, "Why don't you cheer up and relax with the latest game?"

[0706] 6. The server sends the generated response message to the terminal.

[0707] 7. The device will display this message on the user's LINE app screen and provide appropriate support to the user.

[0708] This allows users to have an optimal conversational experience that is tailored to their emotions through their interactions with the system.

[0709] The processing flow will be explained below.

[0710] Specific processing flow when requesting new information based on information including user emotions

[0711] Step 1:

[0712] A user types a message through the LINE app saying, "I'd like to know about new games."

[0713] Step 2:

[0714] The device collects emotional data such as tone of voice and emojis along with the user's text message and sends it to the server using the LINE API.

[0715] Step 3:

[0716] The server analyzes the message and emotion data received from the LINE API and identifies the sender's user ID.

[0717] Step 4:

[0718] The server accesses the database and retrieves profile information (interests, preferences, interaction history, and emotional data) associated with the user ID.

[0719] Step 5:

[0720] The server passes the acquired profile information and the user's message to the generative model for context analysis. The generative model analyzes the input data and identifies the context.

[0721] Step 6:

[0722] The generative model analyzes the context of "new game" and further confirms from profile information that the user's interest is "gaming."

[0723] Step 7:

[0724] The emotion engine analyzes emotional data obtained from the user interface (tone of voice, facial expressions, emojis, etc.) to identify the user's current emotional state.

[0725] Step 8:

[0726] The generative model combines the results of contextual analysis with emotional data from the emotion engine to generate an optimal response, such as "If you're interested in gaming, why not check out this new game store?"

[0727] Step 9:

[0728] The server receives the response message from the generative model and sends it to the device via the LINE API.

[0729] Step 10:

[0730] The device displays the received message on the user's LINE app screen, providing the user with new information.

[0731] Specific process flow when a user changes their own settings

[0732] Step 1:

[0733] The user opens the settings screen within the LINE app and changes their interests, character settings, and emotion settings.

[0734] Step 2:

[0735] The terminal captures the setting information and emotion data selected by the user and transmits them to the server.

[0736] Step 3:

[0737] The server receives the setting information and associates it with the corresponding user ID.

[0738] Step 4:

[0739] The server accesses the database and updates the user's profile with the received settings, including the emotion settings.

[0740] Step 5:

[0741] The server generates a confirmation message for the setting change and sends it to the device via the LINE API.

[0742] Step 6:

[0743] The device will display a confirmation message to the user, informing them that their settings have been updated.

[0744] This allows users to change their own settings through real-time interaction with the system, providing an optimal interaction experience tailored to their emotions.

[0745] Example 2

[0746] 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."

[0747] Conventional dialogue systems have difficulty generating responses that reflect the user's emotional state as well as providing personalized responses based on the user's hobbies and preferences, which can result in a mechanical and unnatural dialogue experience for the user.

[0748] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for providing a user interface for conversation with a user, a means for connecting to a database that stores the user's hobbies and preferences, a means for generating a personalized response based on the user's input using a generative model, a means for connecting to an emotion engine that analyzes emotion data and reflects the emotion data in the response, and a means for sending the personalized response to the user. This makes it possible to provide a natural dialogue experience that is not only based on the user's hobbies and preferences but also on their emotional state.

[0749] A "user interface" is a mechanism that provides a screen and input means for a user to interact with a system.

[0750] A "database" is a system that stores and manages information such as a user's hobbies and preferences, dialogue history, and emotional data.

[0751] A "generative model" is an algorithm that uses machine learning techniques to generate personalized responses based on user input data and information stored in a database.

[0752] The "emotion engine" is a system that analyzes emotional data obtained from the user's voice, facial expressions, context, etc., and provides the analysis results to a generative model.

[0753] The "server" is a central processing unit that receives data sent by a user, generates a response through a generative model and an emotion engine, and sends the response to the user.

[0754] A "personalized response" is a response message that is tailored to an individual based on the user's individual tastes, preferences, and emotional state.

[0755] "Context analysis" is a technology that understands and analyzes the context and meaning of the current dialogue based on the user's input data and past dialogue history.

[0756] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of the dialogue and emotional data. The system is composed of a user interface, a database, a generative model, an emotional engine, and a back-end server that exchanges data between these elements.

[0757] User Interface

[0758] The user interface is what allows the user to interact with the system. For example, a messaging platform is used to provide input and output screens for the user. Specifically, the LINE app is used. Data entered by the user is sent to the server via the device.

[0759] Database

[0760] The database stores users' hobbies, preferences, interaction history, and emotional data, providing the foundation for the generative model and emotion engine to generate optimal responses based on past data. The database is updated in real time as users add new interests or preferences.

[0761] Generative Model

[0762] Generative models use user input data and information stored in a database to generate personalized responses. Generative models use machine learning techniques, particularly contextual analysis, to accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[0763] Emotion Engine

[0764] The emotion engine analyzes emotion data obtained from the user interface, such as tone of voice, facial expressions, and context. The analysis results are provided to the generative model to realize personalized responses based on the user's emotions. The emotion engine also stores the user's emotion data in a database, allowing the generative model to generate responses based on past emotion history.

[0765] server

[0766] The server receives the data sent by the user and generates a response based on the user profile, interaction history, and emotion data. The server uses the generative model and emotion engine to send personalized messages to the user through the user interface, allowing the user to enjoy natural interactions.

[0767] Example

[0768] The operation of the present invention will be described below through specific examples.

[0769] Example 1:

[0770] A user sends a message through the LINE app saying, "I'd like to know about a new game."

[0771] 1. A user sends a message through the LINE app saying, "I want to know about a new game."

[0772] 2. The device sends this message to the server.

[0773] 3. The server retrieves the user's profile information ("Interests: Gaming") and emotion data from the database.

[0774] 4. The server passes this information and the user's message to the generative model for contextual analysis.

[0775] 5. The generative model identifies information related to "games" and generates content such as, "If you're interested in gaming, why not check out this new game store?"

[0776] 6. The emotion engine retrieves emotion data from the user interface and analyzes the user's current emotional state.

[0777] 7. The generative model generates optimal responses based on the user's interests and emotions.

[0778] 8. The server sends the generated response message to the terminal.

[0779] 9. The device will display this message on the LINE app screen and provide the user with new information.

[0780] Example 2:

[0781] When users' emotions change during everyday interactions.

[0782] 1. Users send emojis or words that express their emotions through the LINE app.

[0783] 2. The device sends the user's input data and emotion data to the server.

[0784] 3. The server retrieves the user's emotional data from the database and analyzes the changes.

[0785] 4. The emotion engine analyzes the additional emotion data obtained from the user interface.

[0786] 5. The generative model generates new responses based on the analyzed emotional data and profile information. For example, if the user is feeling down, it generates a response like, "Why don't you cheer up and relax with the latest game?"

[0787] 6. The server sends the generated response message to the terminal.

[0788] 7. The device will display this message on the LINE app screen and provide appropriate support to the user.

[0789] In this way, users can have an optimal emotional interaction experience through their interactions with the system.

[0790] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0791] Step 1:

[0792] A user uses the LINE app to send a message saying, "I want to know about new games." This message represents a user request, and the system receives this message and begins processing. The input is the user's message, and the output is that the message is sent to the device.

[0793] Step 2:

[0794] The terminal receives the user's message and sends it to the server. The terminal receives the message data, assigns the user ID to it, and sends it to the server. The input is the user's message and user ID, and the output is that the message and user ID are sent to the server.

[0795] Step 3:

[0796] The server accesses the database based on the user ID and obtains the user's profile information and past interaction history. The server obtains this data and stores it for processing. The input is the user ID, and the output is the user's profile information and past interaction history. Specifically, it obtains "interests: gaming" and emotional data.

[0797] Step 4:

[0798] The server passes the acquired profile information and user message to a generative model. The generative model uses machine learning techniques to perform contextual analysis and generate an appropriate response based on the user's interests. The input is the profile information and user message, and the output is a personalized response message. For example, a response might be generated that says, "If you're interested in gaming, why not check out this new game store?"

[0799] Step 5:

[0800] The server passes emotion data obtained from the user interface to the emotion engine, which analyzes emotions from voice tone, emojis, etc. and provides the results to the generative model. The input is emotion data, and the output is the analyzed emotional state.

[0801] Step 6:

[0802] The generative model uses the analysis results from the emotion engine to determine the optimal response message. The generative model takes into account the user's interests and current emotional state to generate the most appropriate response. The input is the analysis results and profile information, and the output is the final response message. For example, if the user is excited, the generative model generates a message saying, "If you're interested in gaming, why not check out this new game store? It's fun!"

[0803] Step 7:

[0804] The server sends the generated optimal response message to the terminal. Here, the server encodes the response message and sends it to the terminal. The input is the final response message, and the output is the message sent to the terminal.

[0805] Step 8:

[0806] The device displays the response message received from the server on the user's LINE app screen. The device decodes the message and displays it on the user interface to provide the user with new information. The input is the response message from the server, and the output is the message displayed in the LINE app.

[0807] This completes the entire processing flow, allowing the user to receive personalized responses from the system and enjoy a natural interaction experience.

[0808] (Application example 2)

[0809] 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."

[0810] In modern stores, customer service is extremely important, but it is difficult for store staff to make appropriate suggestions and responses based on each customer's interests and emotions. It is also difficult to immediately determine what a customer is looking for or what their emotional state is. This can result in lower customer satisfaction and negatively impact store sales. Therefore, there is a need for a system that can suggest personalized services and products based on a customer's emotional state and preferences.

[0811] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for providing a user interface for conversation with a user, means for connecting to a database that stores the user's hobbies and preferences, means for generating a personalized response based on the user's input using a generative model, means for providing an emotion engine that analyzes the user's emotion data, means for displaying information on a head-mounted display for customer service support, and means for transmitting the personalized response to the user. This enables store staff to suggest optimal products and services in real time based on the customer's emotional state and preferences.

[0812] "User interface" refers to the screen and operating means that allow a user to interact with a system.

[0813] The "database" is a system that stores and manages users' hobbies, preferences, conversation history, emotional data, etc.

[0814] A "generative model" refers to an algorithm or machine learning technique that generates personalized responses based on user input data and information stored in a database.

[0815] The "emotion engine" is a system that analyzes emotional data such as tone of voice, facial expressions, and context obtained from the user interface and provides the analysis results to a generative model.

[0816] A "head-mounted display" is a display device worn on the user's head, and is used to display information for customer service support.

[0817] A "personalized response" refers to a response that is individually generated based on the user's tastes, preferences, and emotional state.

[0818] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of the dialogue and emotional data. The system is composed of a user interface, a database, a generative model, an emotional engine, and a server that exchanges data between these elements.

[0819] User Interface

[0820] The terminal provides a user interface for user interaction with the system. This interface uses a messaging platform (e.g., a messaging application) and provides the user with input and output screens. Data entered by the user is sent to the server through the terminal.

[0821] Database

[0822] The server connects to a database that stores users' hobbies, preferences, interaction history, and emotional data. This provides the foundation for the generative model and emotion engine to generate optimal responses based on past data. The database is updated in real time as users add new interests or preferences.

[0823] Generative Model

[0824] The server uses a generative model to generate personalized responses based on the user's input data and information stored in the database. The generative model uses machine learning techniques, particularly contextual analysis, to accurately identify the user's current interests and concerns. This enables natural and timely recommendations.

[0825] Emotion Engine

[0826] The server uses an emotion engine to analyze emotion data obtained from the user interface, such as tone of voice, facial expression, and context. The analysis results are provided to a generative model to realize personalized responses based on the user's emotions. The emotion engine also stores the user's emotion data in a database, allowing the generative model to generate responses based on past emotion history.

[0827] head-mounted display

[0828] A head-mounted display (HMD) is used by store staff to interact with customers, displaying information sent from the server in real time, allowing staff to make optimal suggestions based on the customer's emotional state and interests.

[0829] Specific examples

[0830] Example 1:

[0831] Consider a case where a user says, "I'm looking for new sneakers." The user's facial expression captured by the camera indicates that they are excited. This information is sent to the server, where it is analyzed by the generative model. Based on the user's interests and emotional state, the server displays a message on the HMD saying, "This new model is perfect for you. Would you like to try them on?" This allows store staff to provide the customer with the best possible product suggestions.

[0832] Example prompt sentence:

[0833] "When a customer says, 'I'm looking for new sneakers,' the emotion they're feeling is excitement. Based on this, generate the perfect sneaker suggestions for them."

[0834] This invention allows store staff to suggest optimal products and services in real time based on a customer's emotional state and preferences.

[0835] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0836] Program processing steps

[0837] Step 1:

[0838] The user puts on the HMD and starts the system.

[0839] How it works: When a user turns on the dedicated device (HMD), the user interface starts up and the camera and microphone capture the customer's video and audio in real time.

[0840] Input: Camera video data, microphone audio data.

[0841] Output: Real-time video and audio data is processed.

[0842] ---

[0843] Step 2:

[0844] The device (HMD) transmits camera images and audio data to the server.

[0845] How it works: The HMD transmits captured video and audio data to a server via wireless communication.

[0846] Input: Real-time video and audio data.

[0847] Output: Video and audio data sent to the server.

[0848] ---

[0849] Step 3:

[0850] The server analyzes the video data using an emotion engine to identify the customer's emotional state.

[0851] How it works: The server uses an emotion engine to analyze the customer's facial expressions from the video data and identify their emotional state. For example, it determines their emotion based on features such as a smile or wrinkles between the eyebrows.

[0852] Input: Video data.

[0853] Output: Emotional state data (e.g., happy, excited, calm, etc.).

[0854] ---

[0855] Step 4:

[0856] The server analyzes the voice data and converts what the customer says into text.

[0857] How it works: The server uses voice recognition technology to convert the audio data into text, extracting important keywords and phrases.

[0858] Input: Audio data.

[0859] Output: Text data.

[0860] ---

[0861] Step 5:

[0862] The server uses a generative model to generate a personalized response based on the text data and the emotional state data.

[0863] How it works: The server inputs text data and emotional state data into a generative model, which generates responses based on the user's interests and history from an existing database.

[0864] Input: Text data, emotional state data.

[0865] Output: A personalized response message.

[0866] ---

[0867] Step 6:

[0868] The server sends the generated response message to the HMD.

[0869] Operation: The server generates and sends a personalized response message in a format that can be displayed on the HMD's display.

[0870] Input: A personalized response message.

[0871] Output: Message sent to the HMD.

[0872] ---

[0873] Step 7:

[0874] The terminal (HMD) displays the response message received from the server to the store staff.

[0875] How it works: The HMD displays the received message on its display, allowing store staff to make suggestions to the customer.

[0876] Input: A personalized response message.

[0877] Output: Message displayed on the HMD display.

[0878] ---

[0879] Examples:

[0880] For example, if a user says, "I'm looking for new sneakers," and the camera shows that the user is excited, the server will display a response message on the HMD saying, "This new model is perfect for you. Would you like to try them on?"

[0881] Example prompt sentence:

[0882] "When a customer says, 'I'm looking for new sneakers,' the emotion they're feeling is excitement. Based on this, generate the perfect sneaker suggestions for them."

[0883] 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.

[0884] 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.

[0885] 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.

[0886] [Third embodiment]

[0887] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0888] 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.

[0889] 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).

[0890] 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.

[0891] 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.

[0892] 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).

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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."

[0899] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of that dialogue. The system is composed of a user interface, a database, a generative model, and a back-end server that exchanges data between them.

[0900] User Interface

[0901] The user interface is what allows the user to interact with the system. It uses a messaging platform such as the LINE app to provide input and output screens for the user. Data entered by the user is sent to the server via the device.

[0902] Database

[0903] The database stores information such as the user's hobbies, preferences, and interaction history, providing the foundation for the generative model to generate optimal responses based on past data. The database is updated in real time as the user adds new interests or preferences.

[0904] Generative Model

[0905] Generative models use user input data and information stored in a database to generate personalized responses. Generative models use machine learning techniques, particularly contextual analysis, to accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[0906] server

[0907] The server receives the data sent by the user and generates a response based on the user profile and interaction history. The server uses the generative model to send personalized messages to the user through the user interface, allowing the user to enjoy natural interactions.

[0908] Example

[0909] The operation of the present invention will be described below through specific examples.

[0910] Example 1:

[0911] A user sends a message through the LINE app saying, "I'd like to know about a new game."

[0912] 1. The terminal sends this message to the server.

[0913] 2. The server retrieves the user's profile information from the database, which may include "Interests: Gaming" and "Recent Activity: Searching for Gaming Gear."

[0914] 3. The server passes this information and the user's message to the generative model for contextual analysis. The generative model identifies information relevant to the "game" and generates an appropriate response.

[0915] 4. The server generates a response and sends it to the device: "If you're interested in gaming, why not check out this new game store?"

[0916] 5. The terminal displays this message to the user.

[0917] Example 2:

[0918] Users update their interests and preferences.

[0919] 1. The user opens the settings screen within the LINE app and changes their interests and character settings.

[0920] 2. The device sends this change information to the server.

[0921] 3. The server updates the user profile information in the database.

[0922] 4. Based on the new settings, the generative model generates a new personalized response from the next interaction.

[0923] This allows users to enjoy a natural conversational experience while always staying connected to the latest information. Product and service recommendations are also made at the appropriate time, achieving both user convenience and profitability for service providers.

[0924] The processing flow will be explained below.

[0925] Specific processing flow when a user requests new information

[0926] Step 1:

[0927] A user types a message through the LINE app saying, "I'd like to know about new games."

[0928] Step 2:

[0929] The device receives the user's message as text data and sends it to the server via the LINE app API.

[0930] Step 3:

[0931] The server analyzes the message received from the LINE API and identifies the sender's user ID.

[0932] Step 4:

[0933] The server accesses the database and retrieves profile information (interests, preferences, interaction history) associated with the user ID.

[0934] Step 5:

[0935] The server passes the acquired profile information and the user's message to the generative model, which analyzes the input data and identifies the context.

[0936] Step 6:

[0937] The generative model analyzes the context of "new game" and simultaneously confirms from profile information that the user's interest is "gaming."

[0938] Step 7:

[0939] The generative model generates the optimal response message based on the user's interests, such as, "If you're interested in gaming, why not check out this new game store?"

[0940] Step 8:

[0941] The server receives the response message from the generative model and sends it to the device via the LINE API.

[0942] Step 9:

[0943] The device displays the received message on the user's LINE app screen, providing the user with new information.

[0944] The specific process flow when a user changes their settings

[0945] Step 1:

[0946] The user opens the settings screen within the LINE app and changes their interests and character settings.

[0947] Step 2:

[0948] The terminal captures the user's selected settings and sends them to the server.

[0949] Step 3:

[0950] The server receives the configuration information and associates it with the user's ID.

[0951] Step 4:

[0952] The server accesses the database and updates the user's profile information based on the received setting information.

[0953] Step 5:

[0954] The server generates a confirmation message for the setting change and sends it to the device via the LINE API.

[0955] Step 6:

[0956] The device will display a confirmation message to the user, informing them that their settings have been updated.

[0957] This allows users to easily and efficiently obtain information and change settings through interaction with the system.

[0958] Example 1

[0959] 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."

[0960] Conventional dialogue systems, which rely on user interfaces, struggle to provide users with personalized and relevant responses instantly. They also lack efficient methods for recommending products and services that match users' hobbies and preferences. Furthermore, they have limited means for users to easily customize their interests and preferences.

[0961] 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.

[0962] In this invention, the server includes: means for providing an information display device for conversation with a user; means for connecting to a storage device that stores the user's hobbies and preferences; means for generating a personalized response based on the user's input using a generative AI model; means for the terminal to send a message to the server; means for the server to retrieve a user profile from a database; means for the server to send the generated response to the terminal; and means for the terminal to display the response to the user. This allows the user to enjoy natural conversations based on their hobbies and preferences and timely recommendations. In addition, the user can easily customize their interests and settings, allowing for a more personalized conversation experience.

[0963] An "information display device" is a device that provides an interface for a user to interact with a system.

[0964] A "storage device" is a device that includes a database that stores information such as a user's hobbies, preferences, and conversation history.

[0965] A "generative AI model" is a machine learning model that uses user input data and information stored in a storage device to generate personalized responses.

[0966] A "terminal" is a device such as a smartphone or tablet that allows a user to interact with the system.

[0967] A "server" is a back-end system that processes input data from a user and generates and sends a personalized response.

[0968] "Profile information" is personal information including a user's hobbies, preferences, interaction history, and the like.

[0969] "Context analysis" is the process of understanding the context from user input and past dialogue history and generating an appropriate response.

[0970] "Recommendation" refers to recommending products or services based on a user's interests and preferences.

[0971] "Customization" is the process by which users themselves change and update their interests and settings.

[0972] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of that dialogue. This invention is composed of a user interface, a database, a generative AI model, and a back-end server that exchanges data between them.

[0973] User Interface

[0974] The user interface is what allows the user to interact with the system. This interface utilizes a messaging platform such as the LINE app. The LINE app provides an input and output screen for the user, receives the user's input message, and displays the generated response. Through this interface, the user sends a message, which is then sent to the server via the device.

[0975] Database

[0976] The database stores information such as the user's hobbies, preferences, and interaction history. This provides the foundation for the generative AI model to generate optimal responses based on past data. The database can be a common RDBMS (relational database management system). Specific examples include MySQL and PostgreSQL. This database is updated in real time as the user adds new interests or preferences.

[0977] Generative AI Models

[0978] Generative AI models use user input data and information stored in a database to generate personalized responses. These models use advanced machine learning techniques such as GPT-3 and BERT. Contextual analysis, in particular, can accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[0979] server

[0980] The server receives data sent by the user, retrieves the user profile from the database, and provides information to the generative AI model. The server processes the received information and generated responses and sends personalized messages to the device. This process allows the user to enjoy natural interactions.

[0981] Specific examples

[0982] The operation of the present invention will be explained below by showing a specific example.

[0983] Example 1: Want to know about a new game?

[0984] When a user sends a message through the LINE app saying "I want to know about new games," the processing flow is as follows:

[0985] 1. The terminal sends this message to the server.

[0986] 2. The server retrieves the user's profile information from the database, which may include "Interests: Gaming" and "Recent Activity: Searching for Gaming Gear."

[0987] 3. The server passes this information and the user's message to a generative AI model for contextual analysis. The generative model identifies information relevant to the "game" and generates an appropriate response.

[0988] 4. The server generates a response and sends it to the device: "If you're interested in gaming, why not check out this new game store?"

[0989] 5. The terminal displays this message to the user.

[0990] Example 2: Updating interests and preferences

[0991] The process flow when a user changes interests or settings on the settings screen within the LINE app is as follows:

[0992] 1. The user opens the settings screen within the LINE app and changes their interests and character settings.

[0993] 2. The device sends this change information to the server.

[0994] 3. The server updates the user profile information in the database.

[0995] 4. Based on the new settings, the generative AI model generates a new personalized response from the next interaction.

[0996] Prompt Sentence Examples

[0997] I want to know about new games

[0998] "Tell me some recent hit movies."

[0999] "Tell me about a recommended cafe nearby."

[1000] In this way, users can enjoy a natural dialogue experience while constantly maintaining new information and relationships. The system can also provide instant responses to various needs and recommend products and services at the appropriate time, achieving both user convenience and profitability for service providers.

[1001] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1002] Step 1:

[1003] A user uses the LINE app to input and send a message saying, "I want to know about new games." The input is the text message sent by the user, and the output is the message data sent by the device to the next processing step.

[1004] Specific behavior:

[1005] The user opens the LINE app.

[1006] Type "I want to know about new games" into the message input field.

[1007] Tap the send message button.

[1008] Step 2:

[1009] The terminal sends the received message to the server. In this process, the input is the message data sent by the user, and the output is the data packet sent to the server.

[1010] Specific behavior:

[1011] The LINE app on the device captures the message sending event.

[1012] A data packet is created containing the message content and the user ID.

[1013] Sends a data packet to a server-side API endpoint.

[1014] Step 3:

[1015] The server analyzes the received message data, extracts the user ID, and retrieves the user profile information from the database. The input of this process is the data packet sent from the terminal, and the output is the user profile information.

[1016] Specific behavior:

[1017] The server analyzes the received data packets.

[1018] A database query is generated to retrieve profile information based on the user ID.

[1019] Get "Interests" and "Recent Activity" information from search results.

[1020] Step 4:

[1021] The server passes the acquired user profile information and message to the generative AI model for context analysis and response generation. The input to this process is the user profile information and user message, and the output is the response message generated by the generative AI model.

[1022] Specific behavior:

[1023] The server sends the data to the API endpoint of the generative AI model.

[1024] The transmitted data includes the user's messages, profile information, and interaction history.

[1025] The generative AI model performs contextual analysis and generates an appropriate response.

[1026] Step 5:

[1027] The server sends the generated response message to the terminal. The input of this process is the response data from the generative AI model, and the output is a response data packet sent to the terminal.

[1028] Specific behavior:

[1029] The server receives the response data from the generative model.

[1030] Convert the received response data into a format suitable for the terminal.

[1031] Send the formatted data to the API endpoint on the device.

[1032] Step 6:

[1033] The terminal displays the response message received from the server to the user. The input of this process is the response data packet sent from the server, and the output is the response message displayed to the user.

[1034] Specific behavior:

[1035] The terminal receives the response data from the server.

[1036] It analyzes the received data and generates a message to display to the user.

[1037] The message display area will display the response message "If you're interested in gaming, why not check out this new game store?"

[1038] (Application example 1)

[1039] 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."

[1040] In today's brick-and-mortar stores, it is difficult for shoppers to easily obtain detailed information about products in the store and efficiently search for products and services that match their hobbies and preferences. Furthermore, there are limitations to face-to-face recommendations by store clerks, making it difficult to provide personalized suggestions. This reduces convenience for shoppers and leads to missed sales opportunities for stores. Therefore, there is a need for a method to provide personalized recommendations based on users' individual profiles in real time in brick-and-mortar stores through natural dialogue.

[1041] 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.

[1042] In this invention, the server includes means for providing a user interface for conversation with a user, means for connecting to a database that stores the user's hobbies and preferences, means for generating a personalized response based on the user's input using a generative model, and means for sending the personalized response to the user in a physical store and recommending products and services at an appropriate time. This enables the user to receive recommendations for products and services that match their hobbies and preferences through natural conversation, even in a physical store.

[1043] "User interface" is a general term for the screens and applications that allow a purchaser to interact with the system through an electronic device.

[1044] A "database" is a collection of information that systematically stores information such as a buyer's hobbies, preferences, and purchase history, and allows it to be quickly retrieved as needed.

[1045] A "generative model" is an algorithm or program that uses machine learning techniques to generate personalized responses based on input from shoppers and information stored in a database.

[1046] A "brick and mortar store" is a physical location, a sales establishment where customers can physically visit and view and touch products.

[1047] "Personalized responses" refer to answers and suggestions that are optimized to suit a buyer's individual tastes and preferences.

[1048] "Goods and services" is a general term for goods and services provided that a purchaser is interested in and can consider purchasing or using.

[1049] "Recommendation" refers to the act of the system suggesting appropriate products or services based on the buyer's profile and conversation content.

[1050] "Contextual analysis" is a processing method for understanding text, conversation flow, and background information and deriving appropriate responses based on that.

[1051] The present invention provides a system that engages in natural dialogue with a user, generates personalized responses based on the content of the dialogue, and efficiently recommends products and services in a physical store. Specific embodiments of the system are described below.

[1052] System configuration

[1053] User Interface

[1054] The user interface is provided through a smartphone app. Customers can launch the app and interact with the system via text or voice. For example, a customer might say, "I want to see new fashion items."

[1055] Database

[1056] The server is connected to a database that stores information such as the buyer's hobbies, preferences, purchase history, etc. This database makes it possible to quickly obtain information that interests the buyer.

[1057] Generative Model

[1058] Generative models use machine learning techniques, particularly generative AI models. Specifically, generative AI models such as OpenAI's GPT-3 are used. The generative model generates personalized responses using the buyer's input data and information stored in the database. For example, if a buyer inputs, "I want to see new fashion items," the generative model will generate new product information related to fashion and respond appropriately.

[1059] Sending personalized responses

[1060] The server then sends the generated personalized response to the customer in the physical store, allowing the customer to receive personalized information in real time, such as a message like, "We have new fashion items that match your taste. Check out this section."

[1061] Hardware and software used

[1062] Hardware: Smartphones, in-store Wi-Fi

[1063] Software: React Native is used on the client side, and Flask is used on the server side as a web application framework. Relational databases such as MySQL and PostgreSQL are used as databases, and OpenAI's GPT-3 is used as a generative model.

[1064] Specific examples

[1065] 1. The buyer enters the physical store and launches the app on their smartphone.

[1066] 2. The app will display an initial message saying "Hello! What are you looking for?"

[1067] 3. The buyer enters "I want to see new fashion items" in the message field.

[1068] 4. The app sends a request to the server.

[1069] 5. The server retrieves the buyer's profile information from the database and generates the appropriate response using the generative model.

[1070] 6. The app will say, "We have new fashion items that fit your taste. Check out this section."

[1071] Prompt Sentence Examples

[1072] User input: "I want to see new fashion items."

[1073] User profile: "interests: ['fashion', 'technology'], purchase_history: ['smartwatch']"

[1074] Generative model prompt: "The buyer is interested in fashion and is looking for new products. Please suggest new fashion items that would suit him / her."

[1075] The above is a specific embodiment for carrying out the present invention.

[1076] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1077] Step 1:

[1078] The user launches the smartphone app and enters a message saying, "I want to see new fashion items."

[1079] Input: User message: "I want to see new fashion items."

[1080] Output: Request data generated on the terminal

[1081] How it works: A user enters text into the app's message input field, and that text is generated on the device as request data.

[1082] Step 2:

[1083] The terminal sends the user's message to the server.

[1084] Input: Request data

[1085] Output: The request sent to the server

[1086] Operation: The terminal sends the generated request data to the server.

[1087] Step 3:

[1088] The server receives the request data and retrieves the user's profile information from a database.

[1089] Input: The request received by the server, the user ID from the database

[1090] Output: User profile information

[1091] How it works: The server analyzes the request data, obtains the user ID, and uses that user ID to retrieve the user's profile information from the database.

[1092] Step 4:

[1093] The server passes the user's profile information and the user's message to a generative model to generate a personalized response.

[1094] Input: User profile information, User message

[1095] Output: Personalized response

[1096] How it works: The server inputs the user's profile information and the user's message as a prompt into the generative AI model, which then generates a personalized response. At this time, the generative AI model performs contextual analysis to create an optimized response.

[1097] Step 5:

[1098] The server sends the generated personalized response to the terminal.

[1099] Input: Personalized Response

[1100] Output: Response data sent to the device

[1101] Operation: The server packages the generated response, formats it as a request to be sent to the device, and sends it to the device.

[1102] Step 6:

[1103] The terminal displays the personalized response received from the server to the user.

[1104] Input: Response data received from the server

[1105] Output: A personalized response that is displayed on the screen

[1106] Operation: The device analyzes the response data received from the server and displays it on the screen as a response. For example, it displays a message such as "We have new fashion items that suit your taste. Check out this section."

[1107] The above is a series of processing steps that allow users to receive recommendations through natural dialogue in a physical store.

[1108] 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.

[1109] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of the dialogue and emotional data. The system is composed of a user interface, a database, a generative model, an emotional engine, and a back-end server that exchanges data between these elements.

[1110] User Interface

[1111] The user interface is what allows the user to interact with the system. It uses a messaging platform such as the LINE app to provide input and output screens for the user. Data entered by the user is sent to the server via the device.

[1112] Database

[1113] The database stores users' hobbies, preferences, interaction history, and emotional data, providing the foundation for the generative model and emotion engine to generate optimal responses based on past data. The database is updated in real time as users add new interests or preferences.

[1114] Generative Model

[1115] Generative models use user input data and information stored in a database to generate personalized responses. Generative models use machine learning techniques, particularly contextual analysis, to accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[1116] Emotion Engine

[1117] The emotion engine analyzes emotion data obtained from the user interface, such as tone of voice, facial expressions, and context. The analysis results are provided to the generative model to realize personalized responses based on the user's emotions. The emotion engine also stores the user's emotion data in a database, allowing the generative model to generate responses based on past emotion history.

[1118] server

[1119] The server receives the data sent by the user and generates a response based on the user profile, interaction history, and emotion data. The server uses the generative model and emotion engine to send personalized messages to the user through the user interface, allowing the user to enjoy natural interactions.

[1120] Example

[1121] The operation of the present invention will be described below through specific examples.

[1122] Example 1:

[1123] A user sends a message through the LINE app saying, "I'd like to know about a new game."

[1124] 1. The terminal sends this message to the server.

[1125] 2. The server retrieves the user's profile information from the database, including "Interests: Gaming" and emotional data.

[1126] 3. The server passes this information and the user's message to the generative model for contextual analysis. The generative model identifies information relevant to the "game" and generates an appropriate response.

[1127] 4. The emotion engine retrieves emotion data from the user interface and analyzes the user's current emotional state. This analysis result is also provided to the generative model.

[1128] 5. The generative model generates an optimal response message based on the user's interests and emotions, such as, "If you're interested in gaming, why not check out this new game store?"

[1129] 6. The server sends the generated response message to the terminal.

[1130] 7. The device will display this message on the user's LINE app screen, providing the user with the new information.

[1131] Example 2:

[1132] When users' emotions change during everyday interactions.

[1133] 1. Users send emojis or words that express their emotions through the LINE app.

[1134] 2. The device sends the user's input data and emotion data to the server.

[1135] 3. The server retrieves the user's emotional data from the database and analyzes the changes.

[1136] 4. The emotion engine analyzes the additional emotion data obtained from the user interface.

[1137] 5. The generative model generates new responses based on the analyzed emotional data and profile information. For example, if the user is feeling down, it generates a response like, "Why don't you cheer up and relax with the latest game?"

[1138] 6. The server sends the generated response message to the terminal.

[1139] 7. The device will display this message on the user's LINE app screen and provide appropriate support to the user.

[1140] This allows users to have an optimal conversational experience that is tailored to their emotions through their interactions with the system.

[1141] The processing flow will be explained below.

[1142] Specific processing flow when requesting new information based on information including user emotions

[1143] Step 1:

[1144] A user types a message through the LINE app saying, "I'd like to know about new games."

[1145] Step 2:

[1146] The device collects emotional data such as tone of voice and emojis along with the user's text message and sends it to the server using the LINE API.

[1147] Step 3:

[1148] The server analyzes the message and emotion data received from the LINE API and identifies the sender's user ID.

[1149] Step 4:

[1150] The server accesses the database and retrieves profile information (interests, preferences, interaction history, and emotional data) associated with the user ID.

[1151] Step 5:

[1152] The server passes the acquired profile information and the user's message to the generative model for context analysis. The generative model analyzes the input data and identifies the context.

[1153] Step 6:

[1154] The generative model analyzes the context of "new game" and further confirms from profile information that the user's interest is "gaming."

[1155] Step 7:

[1156] The emotion engine analyzes emotional data obtained from the user interface (tone of voice, facial expressions, emojis, etc.) to identify the user's current emotional state.

[1157] Step 8:

[1158] The generative model combines the results of contextual analysis with emotional data from the emotion engine to generate an optimal response, such as "If you're interested in gaming, why not check out this new game store?"

[1159] Step 9:

[1160] The server receives the response message from the generative model and sends it to the device via the LINE API.

[1161] Step 10:

[1162] The device displays the received message on the user's LINE app screen, providing the user with new information.

[1163] Specific process flow when a user changes their own settings

[1164] Step 1:

[1165] The user opens the settings screen within the LINE app and changes their interests, character settings, and emotion settings.

[1166] Step 2:

[1167] The terminal captures the setting information and emotion data selected by the user and transmits them to the server.

[1168] Step 3:

[1169] The server receives the setting information and associates it with the corresponding user ID.

[1170] Step 4:

[1171] The server accesses the database and updates the user's profile with the received settings, including the emotion settings.

[1172] Step 5:

[1173] The server generates a confirmation message for the setting change and sends it to the device via the LINE API.

[1174] Step 6:

[1175] The device will display a confirmation message to the user, informing them that their settings have been updated.

[1176] This allows users to change their own settings through real-time interaction with the system, providing an optimal interaction experience tailored to their emotions.

[1177] Example 2

[1178] 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."

[1179] Conventional dialogue systems have difficulty generating responses that reflect the user's emotional state as well as providing personalized responses based on the user's hobbies and preferences, which can result in a mechanical and unnatural dialogue experience for the user.

[1180] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for providing a user interface for conversation with a user, a means for connecting to a database that stores the user's hobbies and preferences, a means for generating a personalized response based on the user's input using a generative model, a means for connecting to an emotion engine that analyzes emotion data and reflects the emotion data in the response, and a means for sending the personalized response to the user. This makes it possible to provide a natural dialogue experience that is not only based on the user's hobbies and preferences but also on their emotional state.

[1181] A "user interface" is a mechanism that provides a screen and input means for a user to interact with a system.

[1182] A "database" is a system that stores and manages information such as a user's hobbies and preferences, dialogue history, and emotional data.

[1183] A "generative model" is an algorithm that uses machine learning techniques to generate personalized responses based on user input data and information stored in a database.

[1184] The "emotion engine" is a system that analyzes emotional data obtained from the user's voice, facial expressions, context, etc., and provides the analysis results to a generative model.

[1185] The "server" is a central processing unit that receives data sent by a user, generates a response through a generative model and an emotion engine, and sends the response to the user.

[1186] A "personalized response" is a response message that is tailored to an individual based on the user's individual tastes, preferences, and emotional state.

[1187] "Context analysis" is a technology that understands and analyzes the context and meaning of the current dialogue based on the user's input data and past dialogue history.

[1188] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of the dialogue and emotional data. The system is composed of a user interface, a database, a generative model, an emotional engine, and a back-end server that exchanges data between these elements.

[1189] User Interface

[1190] The user interface is what allows the user to interact with the system. For example, a messaging platform is used to provide input and output screens for the user. Specifically, the LINE app is used. Data entered by the user is sent to the server via the device.

[1191] Database

[1192] The database stores users' hobbies, preferences, interaction history, and emotional data, providing the foundation for the generative model and emotion engine to generate optimal responses based on past data. The database is updated in real time as users add new interests or preferences.

[1193] Generative Model

[1194] Generative models use user input data and information stored in a database to generate personalized responses. Generative models use machine learning techniques, particularly contextual analysis, to accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[1195] Emotion Engine

[1196] The emotion engine analyzes emotion data obtained from the user interface, such as tone of voice, facial expressions, and context. The analysis results are provided to the generative model to realize personalized responses based on the user's emotions. The emotion engine also stores the user's emotion data in a database, allowing the generative model to generate responses based on past emotion history.

[1197] server

[1198] The server receives the data sent by the user and generates a response based on the user profile, interaction history, and emotion data. The server uses the generative model and emotion engine to send personalized messages to the user through the user interface, allowing the user to enjoy natural interactions.

[1199] Example

[1200] The operation of the present invention will be described below through specific examples.

[1201] Example 1:

[1202] A user sends a message through the LINE app saying, "I'd like to know about a new game."

[1203] 1. A user sends a message through the LINE app saying, "I want to know about a new game."

[1204] 2. The device sends this message to the server.

[1205] 3. The server retrieves the user's profile information ("Interests: Gaming") and emotion data from the database.

[1206] 4. The server passes this information and the user's message to the generative model for contextual analysis.

[1207] 5. The generative model identifies information related to "games" and generates content such as, "If you're interested in gaming, why not check out this new game store?"

[1208] 6. The emotion engine retrieves emotion data from the user interface and analyzes the user's current emotional state.

[1209] 7. The generative model generates optimal responses based on the user's interests and emotions.

[1210] 8. The server sends the generated response message to the terminal.

[1211] 9. The device will display this message on the LINE app screen and provide the user with new information.

[1212] Example 2:

[1213] When users' emotions change during everyday interactions.

[1214] 1. Users send emojis or words that express their emotions through the LINE app.

[1215] 2. The device sends the user's input data and emotion data to the server.

[1216] 3. The server retrieves the user's emotional data from the database and analyzes the changes.

[1217] 4. The emotion engine analyzes the additional emotion data obtained from the user interface.

[1218] 5. The generative model generates new responses based on the analyzed emotional data and profile information. For example, if the user is feeling down, it generates a response like, "Why don't you cheer up and relax with the latest game?"

[1219] 6. The server sends the generated response message to the terminal.

[1220] 7. The device will display this message on the LINE app screen and provide appropriate support to the user.

[1221] In this way, users can have an optimal emotional interaction experience through their interactions with the system.

[1222] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1223] Step 1:

[1224] A user uses the LINE app to send a message saying, "I want to know about new games." This message represents a user request, and the system receives this message and begins processing. The input is the user's message, and the output is that the message is sent to the device.

[1225] Step 2:

[1226] The terminal receives the user's message and sends it to the server. The terminal receives the message data, assigns the user ID to it, and sends it to the server. The input is the user's message and user ID, and the output is that the message and user ID are sent to the server.

[1227] Step 3:

[1228] The server accesses the database based on the user ID and obtains the user's profile information and past interaction history. The server obtains this data and stores it for processing. The input is the user ID, and the output is the user's profile information and past interaction history. Specifically, it obtains "interests: gaming" and emotional data.

[1229] Step 4:

[1230] The server passes the acquired profile information and user message to a generative model. The generative model uses machine learning techniques to perform contextual analysis and generate an appropriate response based on the user's interests. The input is the profile information and user message, and the output is a personalized response message. For example, a response might be generated that says, "If you're interested in gaming, why not check out this new game store?"

[1231] Step 5:

[1232] The server passes emotion data obtained from the user interface to the emotion engine, which analyzes emotions from voice tone, emojis, etc. and provides the results to the generative model. The input is emotion data, and the output is the analyzed emotional state.

[1233] Step 6:

[1234] The generative model uses the analysis results from the emotion engine to determine the optimal response message. The generative model takes into account the user's interests and current emotional state to generate the most appropriate response. The input is the analysis results and profile information, and the output is the final response message. For example, if the user is excited, the generative model generates a message saying, "If you're interested in gaming, why not check out this new game store? It's fun!"

[1235] Step 7:

[1236] The server sends the generated optimal response message to the terminal. Here, the server encodes the response message and sends it to the terminal. The input is the final response message, and the output is the message sent to the terminal.

[1237] Step 8:

[1238] The device displays the response message received from the server on the user's LINE app screen. The device decodes the message and displays it on the user interface to provide the user with new information. The input is the response message from the server, and the output is the message displayed in the LINE app.

[1239] This completes the entire processing flow, allowing the user to receive personalized responses from the system and enjoy a natural interaction experience.

[1240] (Application example 2)

[1241] 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."

[1242] In modern stores, customer service is extremely important, but it is difficult for store staff to make appropriate suggestions and responses based on each customer's interests and emotions. It is also difficult to immediately determine what a customer is looking for or what their emotional state is. This can result in lower customer satisfaction and negatively impact store sales. Therefore, there is a need for a system that can suggest personalized services and products based on a customer's emotional state and preferences.

[1243] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for providing a user interface for conversation with a user, means for connecting to a database that stores the user's hobbies and preferences, means for generating a personalized response based on the user's input using a generative model, means for providing an emotion engine that analyzes the user's emotion data, means for displaying information on a head-mounted display for customer service support, and means for transmitting the personalized response to the user. This enables store staff to suggest optimal products and services in real time based on the customer's emotional state and preferences.

[1244] "User interface" refers to the screen and operating means that allow a user to interact with a system.

[1245] The "database" is a system that stores and manages users' hobbies, preferences, conversation history, emotional data, etc.

[1246] A "generative model" refers to an algorithm or machine learning technique that generates personalized responses based on user input data and information stored in a database.

[1247] The "emotion engine" is a system that analyzes emotional data such as tone of voice, facial expressions, and context obtained from the user interface and provides the analysis results to a generative model.

[1248] A "head-mounted display" is a display device worn on the user's head, and is used to display information for customer service support.

[1249] A "personalized response" refers to a response that is individually generated based on the user's tastes, preferences, and emotional state.

[1250] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of the dialogue and emotional data. The system is composed of a user interface, a database, a generative model, an emotional engine, and a server that exchanges data between these elements.

[1251] User Interface

[1252] The terminal provides a user interface for user interaction with the system. This interface uses a messaging platform (e.g., a messaging application) and provides the user with input and output screens. Data entered by the user is sent to the server through the terminal.

[1253] Database

[1254] The server connects to a database that stores users' hobbies, preferences, interaction history, and emotional data. This provides the foundation for the generative model and emotion engine to generate optimal responses based on past data. The database is updated in real time as users add new interests or preferences.

[1255] Generative Model

[1256] The server uses a generative model to generate personalized responses based on the user's input data and information stored in the database. The generative model uses machine learning techniques, particularly contextual analysis, to accurately identify the user's current interests and concerns. This enables natural and timely recommendations.

[1257] Emotion Engine

[1258] The server uses an emotion engine to analyze emotion data obtained from the user interface, such as tone of voice, facial expression, and context. The analysis results are provided to a generative model to realize personalized responses based on the user's emotions. The emotion engine also stores the user's emotion data in a database, allowing the generative model to generate responses based on past emotion history.

[1259] head-mounted display

[1260] A head-mounted display (HMD) is used by store staff to interact with customers, displaying information sent from the server in real time, allowing staff to make optimal suggestions based on the customer's emotional state and interests.

[1261] Specific examples

[1262] Example 1:

[1263] Consider a case where a user says, "I'm looking for new sneakers." The user's facial expression captured by the camera indicates that they are excited. This information is sent to the server, where it is analyzed by the generative model. Based on the user's interests and emotional state, the server displays a message on the HMD saying, "This new model is perfect for you. Would you like to try them on?" This allows store staff to provide the customer with the best possible product suggestions.

[1264] Example prompt sentence:

[1265] "When a customer says, 'I'm looking for new sneakers,' the emotion they're feeling is excitement. Based on this, generate the perfect sneaker suggestions for them."

[1266] This invention allows store staff to suggest optimal products and services in real time based on a customer's emotional state and preferences.

[1267] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1268] Program processing steps

[1269] Step 1:

[1270] The user puts on the HMD and starts the system.

[1271] How it works: When a user turns on the dedicated device (HMD), the user interface starts up and the camera and microphone capture the customer's video and audio in real time.

[1272] Input: Camera video data, microphone audio data.

[1273] Output: Real-time video and audio data is processed.

[1274] ---

[1275] Step 2:

[1276] The device (HMD) transmits camera images and audio data to the server.

[1277] How it works: The HMD transmits captured video and audio data to a server via wireless communication.

[1278] Input: Real-time video and audio data.

[1279] Output: Video and audio data sent to the server.

[1280] ---

[1281] Step 3:

[1282] The server analyzes the video data using an emotion engine to identify the customer's emotional state.

[1283] How it works: The server uses an emotion engine to analyze the customer's facial expressions from the video data and identify their emotional state. For example, it determines their emotion based on features such as a smile or wrinkles between the eyebrows.

[1284] Input: Video data.

[1285] Output: Emotional state data (e.g., happy, excited, calm, etc.).

[1286] ---

[1287] Step 4:

[1288] The server analyzes the voice data and converts what the customer says into text.

[1289] How it works: The server uses voice recognition technology to convert the audio data into text, extracting important keywords and phrases.

[1290] Input: Audio data.

[1291] Output: Text data.

[1292] ---

[1293] Step 5:

[1294] The server uses a generative model to generate a personalized response based on the text data and the emotional state data.

[1295] How it works: The server inputs text data and emotional state data into a generative model, which generates responses based on the user's interests and history from an existing database.

[1296] Input: Text data, emotional state data.

[1297] Output: A personalized response message.

[1298] ---

[1299] Step 6:

[1300] The server sends the generated response message to the HMD.

[1301] Operation: The server generates and sends a personalized response message in a format that can be displayed on the HMD's display.

[1302] Input: A personalized response message.

[1303] Output: Message sent to the HMD.

[1304] ---

[1305] Step 7:

[1306] The terminal (HMD) displays the response message received from the server to the store staff.

[1307] How it works: The HMD displays the received message on its display, allowing store staff to make suggestions to the customer.

[1308] Input: A personalized response message.

[1309] Output: Message displayed on the HMD display.

[1310] ---

[1311] Examples:

[1312] For example, if a user says, "I'm looking for new sneakers," and the camera shows that the user is excited, the server will display a response message on the HMD saying, "This new model is perfect for you. Would you like to try them on?"

[1313] Example prompt sentence:

[1314] "When a customer says, 'I'm looking for new sneakers,' the emotion they're feeling is excitement. Based on this, generate the perfect sneaker suggestions for them."

[1315] 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.

[1316] 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.

[1317] 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.

[1318] [Fourth embodiment]

[1319] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1320] 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.

[1321] 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).

[1322] 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.

[1323] 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.

[1324] 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).

[1325] 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.

[1326] 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.

[1327] 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.

[1328] 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.

[1329] 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.

[1330] 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.

[1331] 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."

[1332] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of that dialogue. The system is composed of a user interface, a database, a generative model, and a back-end server that exchanges data between them.

[1333] User Interface

[1334] The user interface is what allows the user to interact with the system. It uses a messaging platform such as the LINE app to provide input and output screens for the user. Data entered by the user is sent to the server via the device.

[1335] Database

[1336] The database stores information such as the user's hobbies, preferences, and interaction history, providing the foundation for the generative model to generate optimal responses based on past data. The database is updated in real time as the user adds new interests or preferences.

[1337] Generative Model

[1338] Generative models use user input data and information stored in a database to generate personalized responses. Generative models use machine learning techniques, particularly contextual analysis, to accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[1339] server

[1340] The server receives the data sent by the user and generates a response based on the user profile and interaction history. The server uses the generative model to send personalized messages to the user through the user interface, allowing the user to enjoy natural interactions.

[1341] Example

[1342] The operation of the present invention will be described below through specific examples.

[1343] Example 1:

[1344] A user sends a message through the LINE app saying, "I'd like to know about a new game."

[1345] 1. The terminal sends this message to the server.

[1346] 2. The server retrieves the user's profile information from the database, which may include "Interests: Gaming" and "Recent Activity: Searching for Gaming Gear."

[1347] 3. The server passes this information and the user's message to the generative model for contextual analysis. The generative model identifies information relevant to the "game" and generates an appropriate response.

[1348] 4. The server generates a response and sends it to the device: "If you're interested in gaming, why not check out this new game store?"

[1349] 5. The terminal displays this message to the user.

[1350] Example 2:

[1351] Users update their interests and preferences.

[1352] 1. The user opens the settings screen within the LINE app and changes their interests and character settings.

[1353] 2. The device sends this change information to the server.

[1354] 3. The server updates the user profile information in the database.

[1355] 4. Based on the new settings, the generative model generates a new personalized response from the next interaction.

[1356] This allows users to enjoy a natural conversational experience while always staying connected to the latest information. Product and service recommendations are also made at the appropriate time, achieving both user convenience and profitability for service providers.

[1357] The processing flow will be explained below.

[1358] Specific processing flow when a user requests new information

[1359] Step 1:

[1360] A user types a message through the LINE app saying, "I'd like to know about new games."

[1361] Step 2:

[1362] The device receives the user's message as text data and sends it to the server via the LINE app API.

[1363] Step 3:

[1364] The server analyzes the message received from the LINE API and identifies the sender's user ID.

[1365] Step 4:

[1366] The server accesses the database and retrieves profile information (interests, preferences, interaction history) associated with the user ID.

[1367] Step 5:

[1368] The server passes the acquired profile information and the user's message to the generative model, which analyzes the input data and identifies the context.

[1369] Step 6:

[1370] The generative model analyzes the context of "new game" and simultaneously confirms from profile information that the user's interest is "gaming."

[1371] Step 7:

[1372] The generative model generates the optimal response message based on the user's interests, such as, "If you're interested in gaming, why not check out this new game store?"

[1373] Step 8:

[1374] The server receives the response message from the generative model and sends it to the device via the LINE API.

[1375] Step 9:

[1376] The device displays the received message on the user's LINE app screen, providing the user with new information.

[1377] The specific process flow when a user changes their settings

[1378] Step 1:

[1379] The user opens the settings screen within the LINE app and changes their interests and character settings.

[1380] Step 2:

[1381] The terminal captures the user's selected settings and sends them to the server.

[1382] Step 3:

[1383] The server receives the configuration information and associates it with the user's ID.

[1384] Step 4:

[1385] The server accesses the database and updates the user's profile information based on the received setting information.

[1386] Step 5:

[1387] The server generates a confirmation message for the setting change and sends it to the device via the LINE API.

[1388] Step 6:

[1389] The device will display a confirmation message to the user, informing them that their settings have been updated.

[1390] This allows users to easily and efficiently obtain information and change settings through interaction with the system.

[1391] Example 1

[1392] 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."

[1393] Conventional dialogue systems, which rely on user interfaces, struggle to provide users with personalized and relevant responses instantly. They also lack efficient methods for recommending products and services that match users' hobbies and preferences. Furthermore, they have limited means for users to easily customize their interests and preferences.

[1394] 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.

[1395] In this invention, the server includes: means for providing an information display device for conversation with a user; means for connecting to a storage device that stores the user's hobbies and preferences; means for generating a personalized response based on the user's input using a generative AI model; means for the terminal to send a message to the server; means for the server to retrieve a user profile from a database; means for the server to send the generated response to the terminal; and means for the terminal to display the response to the user. This allows the user to enjoy natural conversations based on their hobbies and preferences and timely recommendations. In addition, the user can easily customize their interests and settings, allowing for a more personalized conversation experience.

[1396] An "information display device" is a device that provides an interface for a user to interact with a system.

[1397] A "storage device" is a device that includes a database that stores information such as a user's hobbies, preferences, and conversation history.

[1398] A "generative AI model" is a machine learning model that uses user input data and information stored in a storage device to generate personalized responses.

[1399] A "terminal" is a device such as a smartphone or tablet that allows a user to interact with the system.

[1400] A "server" is a back-end system that processes input data from a user and generates and sends a personalized response.

[1401] "Profile information" is personal information including a user's hobbies, preferences, interaction history, and the like.

[1402] "Context analysis" is the process of understanding the context from user input and past dialogue history and generating an appropriate response.

[1403] "Recommendation" refers to recommending products or services based on a user's interests and preferences.

[1404] "Customization" is the process by which users themselves change and update their interests and settings.

[1405] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of that dialogue. This invention is composed of a user interface, a database, a generative AI model, and a back-end server that exchanges data between them.

[1406] User Interface

[1407] The user interface is what allows the user to interact with the system. This interface utilizes a messaging platform such as the LINE app. The LINE app provides an input and output screen for the user, receives the user's input message, and displays the generated response. Through this interface, the user sends a message, which is then sent to the server via the device.

[1408] Database

[1409] The database stores information such as the user's hobbies, preferences, and interaction history. This provides the foundation for the generative AI model to generate optimal responses based on past data. The database can be a common RDBMS (relational database management system). Specific examples include MySQL and PostgreSQL. This database is updated in real time as the user adds new interests or preferences.

[1410] Generative AI Models

[1411] Generative AI models use user input data and information stored in a database to generate personalized responses. These models use advanced machine learning techniques such as GPT-3 and BERT. Contextual analysis, in particular, can accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[1412] server

[1413] The server receives data sent by the user, retrieves the user profile from the database, and provides information to the generative AI model. The server processes the received information and generated responses and sends personalized messages to the device. This process allows the user to enjoy natural interactions.

[1414] Specific examples

[1415] The operation of the present invention will be explained below by showing a specific example.

[1416] Example 1: Want to know about a new game?

[1417] When a user sends a message through the LINE app saying "I want to know about new games," the processing flow is as follows:

[1418] 1. The terminal sends this message to the server.

[1419] 2. The server retrieves the user's profile information from the database, which may include "Interests: Gaming" and "Recent Activity: Searching for Gaming Gear."

[1420] 3. The server passes this information and the user's message to a generative AI model for contextual analysis. The generative model identifies information relevant to the "game" and generates an appropriate response.

[1421] 4. The server generates a response and sends it to the device: "If you're interested in gaming, why not check out this new game store?"

[1422] 5. The terminal displays this message to the user.

[1423] Example 2: Updating interests and preferences

[1424] The process flow when a user changes interests or settings on the settings screen within the LINE app is as follows:

[1425] 1. The user opens the settings screen within the LINE app and changes their interests and character settings.

[1426] 2. The device sends this change information to the server.

[1427] 3. The server updates the user profile information in the database.

[1428] 4. Based on the new settings, the generative AI model generates a new personalized response from the next interaction.

[1429] Prompt Sentence Examples

[1430] I want to know about new games

[1431] "Tell me some recent hit movies."

[1432] "Tell me about a recommended cafe nearby."

[1433] In this way, users can enjoy a natural dialogue experience while constantly staying connected with new information. The system can also provide instant responses to various needs and recommend products and services at the appropriate time, achieving both user convenience and profitability for service providers.

[1434] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1435] Step 1:

[1436] A user uses the LINE app to input and send a message saying, "I want to know about new games." The input is the text message sent by the user, and the output is the message data sent by the device to the next processing step.

[1437] Specific behavior:

[1438] The user opens the LINE app.

[1439] Type "I want to know about new games" into the message input field.

[1440] Tap the send message button.

[1441] Step 2:

[1442] The terminal sends the received message to the server. In this process, the input is the message data sent by the user, and the output is the data packet sent to the server.

[1443] Specific behavior:

[1444] The LINE app on the device captures the message sending event.

[1445] A data packet is created containing the message content and the user ID.

[1446] Sends a data packet to a server-side API endpoint.

[1447] Step 3:

[1448] The server analyzes the received message data, extracts the user ID, and retrieves the user profile information from the database. The input of this process is the data packet sent from the terminal, and the output is the user profile information.

[1449] Specific behavior:

[1450] The server analyzes the received data packets.

[1451] A database query is generated to retrieve profile information based on the user ID.

[1452] Get "Interests" and "Recent Activity" information from search results.

[1453] Step 4:

[1454] The server passes the acquired user profile information and message to the generative AI model for context analysis and response generation. The input to this process is the user profile information and user message, and the output is the response message generated by the generative AI model.

[1455] Specific behavior:

[1456] The server sends the data to the API endpoint of the generative AI model.

[1457] The transmitted data includes the user's messages, profile information, and interaction history.

[1458] The generative AI model performs contextual analysis and generates an appropriate response.

[1459] Step 5:

[1460] The server sends the generated response message to the terminal. The input of this process is the response data from the generative AI model, and the output is a response data packet sent to the terminal.

[1461] Specific behavior:

[1462] The server receives the response data from the generative model.

[1463] Convert the received response data into a format suitable for the terminal.

[1464] Send the formatted data to the API endpoint on the device.

[1465] Step 6:

[1466] The terminal displays the response message received from the server to the user. The input of this process is the response data packet sent from the server, and the output is the response message displayed to the user.

[1467] Specific behavior:

[1468] The terminal receives the response data from the server.

[1469] It analyzes the received data and generates a message to display to the user.

[1470] The message display area will display the response message "If you're interested in gaming, why not check out this new game store?"

[1471] (Application example 1)

[1472] 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."

[1473] In today's brick-and-mortar stores, it is difficult for shoppers to easily obtain detailed information about products in the store and efficiently search for products and services that match their hobbies and preferences. Furthermore, there are limitations to face-to-face recommendations by store clerks, making it difficult to provide personalized suggestions. This reduces convenience for shoppers and leads to missed sales opportunities for stores. Therefore, there is a need for a method to provide personalized recommendations based on users' individual profiles in real time in brick-and-mortar stores through natural dialogue.

[1474] 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.

[1475] In this invention, the server includes means for providing a user interface for conversation with a user, means for connecting to a database that stores the user's hobbies and preferences, means for generating a personalized response based on the user's input using a generative model, and means for sending the personalized response to the user in a physical store and recommending products and services at an appropriate time. This enables the user to receive recommendations for products and services that match their hobbies and preferences through natural conversation, even in a physical store.

[1476] "User interface" is a general term for the screens and applications that allow a purchaser to interact with the system through an electronic device.

[1477] A "database" is a collection of information that systematically stores information such as a buyer's hobbies, preferences, and purchase history, and allows it to be quickly retrieved as needed.

[1478] A "generative model" is an algorithm or program that uses machine learning techniques to generate personalized responses based on input from shoppers and information stored in a database.

[1479] A "brick and mortar store" is a physical location, a sales establishment where customers can physically visit and view and touch products.

[1480] "Personalized responses" refer to answers and suggestions that are optimized to suit a buyer's individual tastes and preferences.

[1481] "Goods and services" is a general term for goods and services provided that a purchaser is interested in and can consider purchasing or using.

[1482] "Recommendation" refers to the act of the system suggesting appropriate products or services based on the buyer's profile and conversation content.

[1483] "Contextual analysis" is a processing method for understanding text, conversation flow, and background information and deriving appropriate responses based on that.

[1484] The present invention provides a system that engages in natural dialogue with a user, generates personalized responses based on the content of the dialogue, and efficiently recommends products and services in a physical store. Specific embodiments of the system are described below.

[1485] System configuration

[1486] User Interface

[1487] The user interface is provided through a smartphone app. Customers can launch the app and interact with the system via text or voice. For example, a customer might say, "I want to see new fashion items."

[1488] Database

[1489] The server is connected to a database that stores information such as the buyer's hobbies, preferences, purchase history, etc. This database makes it possible to quickly obtain information that interests the buyer.

[1490] Generative Model

[1491] Generative models use machine learning techniques, particularly generative AI models. Specifically, generative AI models such as OpenAI's GPT-3 are used. The generative model generates personalized responses using the buyer's input data and information stored in the database. For example, if a buyer inputs, "I want to see new fashion items," the generative model will generate new product information related to fashion and respond appropriately.

[1492] Sending personalized responses

[1493] The server then sends the generated personalized response to the customer in the physical store, allowing the customer to receive personalized information in real time, such as a message like, "We have new fashion items that match your taste. Check out this section."

[1494] Hardware and software used

[1495] Hardware: Smartphones, in-store Wi-Fi

[1496] Software: React Native is used on the client side, and Flask is used on the server side as a web application framework. Relational databases such as MySQL and PostgreSQL are used as databases, and OpenAI's GPT-3 is used as a generative model.

[1497] Specific examples

[1498] 1. The buyer enters the physical store and launches the app on their smartphone.

[1499] 2. The app will display an initial message saying "Hello! What are you looking for?"

[1500] 3. The buyer enters "I want to see new fashion items" in the message field.

[1501] 4. The app sends a request to the server.

[1502] 5. The server retrieves the buyer's profile information from the database and generates the appropriate response using the generative model.

[1503] 6. The app will say, "We have new fashion items that fit your taste. Check out this section."

[1504] Prompt Sentence Examples

[1505] User input: "I want to see new fashion items."

[1506] User profile: "interests: ['fashion', 'technology'], purchase_history: ['smartwatch']"

[1507] Generative model prompt: "The buyer is interested in fashion and is looking for new products. Please suggest new fashion items that would suit him / her."

[1508] The above is a specific embodiment for carrying out the present invention.

[1509] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1510] Step 1:

[1511] The user launches the smartphone app and enters a message saying, "I want to see new fashion items."

[1512] Input: User message: "I want to see new fashion items."

[1513] Output: Request data generated on the terminal

[1514] How it works: A user enters text into the app's message input field, and that text is generated on the device as request data.

[1515] Step 2:

[1516] The terminal sends the user's message to the server.

[1517] Input: Request data

[1518] Output: The request sent to the server

[1519] Operation: The terminal sends the generated request data to the server.

[1520] Step 3:

[1521] The server receives the request data and retrieves the user's profile information from a database.

[1522] Input: The request received by the server, the user ID from the database

[1523] Output: User profile information

[1524] How it works: The server analyzes the request data, obtains the user ID, and uses that user ID to retrieve the user's profile information from the database.

[1525] Step 4:

[1526] The server passes the user's profile information and the user's message to a generative model to generate a personalized response.

[1527] Input: User profile information, User message

[1528] Output: Personalized response

[1529] How it works: The server inputs the user's profile information and the user's message as a prompt into the generative AI model, which then generates a personalized response. At this time, the generative AI model performs contextual analysis to create an optimized response.

[1530] Step 5:

[1531] The server sends the generated personalized response to the terminal.

[1532] Input: Personalized Response

[1533] Output: Response data sent to the device

[1534] Operation: The server packages the generated response, formats it as a request to be sent to the device, and sends it to the device.

[1535] Step 6:

[1536] The terminal displays the personalized response received from the server to the user.

[1537] Input: Response data received from the server

[1538] Output: A personalized response that is displayed on the screen

[1539] Operation: The device analyzes the response data received from the server and displays it on the screen as a response. For example, it displays a message such as "We have new fashion items that suit your taste. Check out this section."

[1540] The above is a series of processing steps that allow users to receive recommendations through natural dialogue in a physical store.

[1541] 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.

[1542] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of the dialogue and emotional data. The system is composed of a user interface, a database, a generative model, an emotional engine, and a back-end server that exchanges data between these elements.

[1543] User Interface

[1544] The user interface is what allows the user to interact with the system. It uses a messaging platform such as the LINE app to provide input and output screens for the user. Data entered by the user is sent to the server via the device.

[1545] Database

[1546] The database stores users' hobbies, preferences, interaction history, and emotional data, providing the foundation for the generative model and emotion engine to generate optimal responses based on past data. The database is updated in real time as users add new interests or preferences.

[1547] Generative Model

[1548] Generative models use user input data and information stored in a database to generate personalized responses. Generative models use machine learning techniques, particularly contextual analysis, to accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[1549] Emotion Engine

[1550] The emotion engine analyzes emotion data obtained from the user interface, such as tone of voice, facial expressions, and context. The analysis results are provided to the generative model to realize personalized responses based on the user's emotions. The emotion engine also stores the user's emotion data in a database, allowing the generative model to generate responses based on past emotion history.

[1551] server

[1552] The server receives the data sent by the user and generates a response based on the user profile, interaction history, and emotion data. The server uses the generative model and emotion engine to send personalized messages to the user through the user interface, allowing the user to enjoy natural interactions.

[1553] Example

[1554] The operation of the present invention will be described below through specific examples.

[1555] Example 1:

[1556] A user sends a message through the LINE app saying, "I'd like to know about a new game."

[1557] 1. The terminal sends this message to the server.

[1558] 2. The server retrieves the user's profile information from the database, including "Interests: Gaming" and emotional data.

[1559] 3. The server passes this information and the user's message to the generative model for contextual analysis. The generative model identifies information relevant to the "game" and generates an appropriate response.

[1560] 4. The emotion engine retrieves emotion data from the user interface and analyzes the user's current emotional state. This analysis result is also provided to the generative model.

[1561] 5. The generative model generates an optimal response message based on the user's interests and emotions, such as, "If you're interested in gaming, why not check out this new game store?"

[1562] 6. The server sends the generated response message to the terminal.

[1563] 7. The device will display this message on the user's LINE app screen, providing the user with the new information.

[1564] Example 2:

[1565] When users' emotions change during everyday interactions.

[1566] 1. Users send emojis or words that express their emotions through the LINE app.

[1567] 2. The device sends the user's input data and emotion data to the server.

[1568] 3. The server retrieves the user's emotional data from the database and analyzes the changes.

[1569] 4. The emotion engine analyzes the additional emotion data obtained from the user interface.

[1570] 5. The generative model generates new responses based on the analyzed emotional data and profile information. For example, if the user is feeling down, it generates a response like, "Why don't you cheer up and relax with the latest game?"

[1571] 6. The server sends the generated response message to the terminal.

[1572] 7. The device will display this message on the user's LINE app screen and provide appropriate support to the user.

[1573] This allows users to have an optimal conversational experience that is tailored to their emotions through their interactions with the system.

[1574] The processing flow will be explained below.

[1575] Specific processing flow when requesting new information based on information including user emotions

[1576] Step 1:

[1577] A user types a message through the LINE app saying, "I'd like to know about new games."

[1578] Step 2:

[1579] The device collects emotional data such as tone of voice and emojis along with the user's text message and sends it to the server using the LINE API.

[1580] Step 3:

[1581] The server analyzes the message and emotion data received from the LINE API and identifies the sender's user ID.

[1582] Step 4:

[1583] The server accesses the database and retrieves profile information (interests, preferences, interaction history, and emotional data) associated with the user ID.

[1584] Step 5:

[1585] The server passes the acquired profile information and the user's message to the generative model for context analysis. The generative model analyzes the input data and identifies the context.

[1586] Step 6:

[1587] The generative model analyzes the context of "new game" and further confirms from profile information that the user's interest is "gaming."

[1588] Step 7:

[1589] The emotion engine analyzes emotional data obtained from the user interface (tone of voice, facial expressions, emojis, etc.) to identify the user's current emotional state.

[1590] Step 8:

[1591] The generative model combines the results of contextual analysis with emotional data from the emotion engine to generate an optimal response, such as "If you're interested in gaming, why not check out this new game store?"

[1592] Step 9:

[1593] The server receives the response message from the generative model and sends it to the device via the LINE API.

[1594] Step 10:

[1595] The device displays the received message on the user's LINE app screen, providing the user with new information.

[1596] Specific process flow when a user changes their own settings

[1597] Step 1:

[1598] The user opens the settings screen within the LINE app and changes their interests, character settings, and emotion settings.

[1599] Step 2:

[1600] The terminal captures the setting information and emotion data selected by the user and transmits them to the server.

[1601] Step 3:

[1602] The server receives the setting information and associates it with the corresponding user ID.

[1603] Step 4:

[1604] The server accesses the database and updates the user's profile with the received settings, including the emotion settings.

[1605] Step 5:

[1606] The server generates a confirmation message for the setting change and sends it to the device via the LINE API.

[1607] Step 6:

[1608] The device will display a confirmation message to the user, informing them that their settings have been updated.

[1609] This allows users to change their own settings through real-time interaction with the system, providing an optimal interaction experience tailored to their emotions.

[1610] Example 2

[1611] 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."

[1612] Conventional dialogue systems have difficulty generating responses that reflect the user's emotional state as well as providing personalized responses based on the user's hobbies and preferences, which can result in a mechanical and unnatural dialogue experience for the user.

[1613] The specification process by the specification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for providing a user interface for conversation with a user, a means for connecting to a database that stores the user's hobbies and preferences, a means for generating a personalized response based on the user's input using a generative model, a means for connecting to an emotion engine that analyzes emotion data and reflects the emotion data in the response, and a means for sending the personalized response to the user. This makes it possible to provide a natural dialogue experience that is not only based on the user's hobbies and preferences but also on their emotional state.

[1614] A "user interface" is a mechanism that provides a screen and input means for a user to interact with a system.

[1615] A "database" is a system that stores and manages information such as a user's hobbies and preferences, dialogue history, and emotional data.

[1616] A "generative model" is an algorithm that uses machine learning techniques to generate personalized responses based on user input data and information stored in a database.

[1617] The "emotion engine" is a system that analyzes emotional data obtained from the user's voice, facial expressions, context, etc., and provides the analysis results to a generative model.

[1618] The "server" is a central processing unit that receives data sent by a user, generates a response through a generative model and an emotion engine, and sends the response to the user.

[1619] A "personalized response" is a response message that is tailored to an individual based on the user's individual tastes, preferences, and emotional state.

[1620] "Context analysis" is a technology that understands and analyzes the context and meaning of the current dialogue based on the user's input data and past dialogue history.

[1621] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of the dialogue and emotional data. The system is composed of a user interface, a database, a generative model, an emotional engine, and a back-end server that exchanges data between these elements.

[1622] User Interface

[1623] The user interface is what allows the user to interact with the system. For example, a messaging platform is used to provide input and output screens for the user. Specifically, the LINE app is used. Data entered by the user is sent to the server via the device.

[1624] Database

[1625] The database stores users' hobbies, preferences, interaction history, and emotional data, providing the foundation for the generative model and emotion engine to generate optimal responses based on past data. The database is updated in real time as users add new interests or preferences.

[1626] Generative Model

[1627] Generative models use user input data and information stored in a database to generate personalized responses. Generative models use machine learning techniques, particularly contextual analysis, to accurately identify a user's current interests and concerns, enabling natural and timely recommendations.

[1628] Emotion Engine

[1629] The emotion engine analyzes emotion data obtained from the user interface, such as tone of voice, facial expressions, and context. The analysis results are provided to the generative model to realize personalized responses based on the user's emotions. The emotion engine also stores the user's emotion data in a database, allowing the generative model to generate responses based on past emotion history.

[1630] server

[1631] The server receives the data sent by the user and generates a response based on the user profile, interaction history, and emotion data. The server uses the generative model and emotion engine to send personalized messages to the user through the user interface, allowing the user to enjoy natural interactions.

[1632] Example

[1633] The operation of the present invention will be described below through specific examples.

[1634] Example 1:

[1635] A user sends a message through the LINE app saying, "I'd like to know about a new game."

[1636] 1. A user sends a message through the LINE app saying, "I want to know about a new game."

[1637] 2. The device sends this message to the server.

[1638] 3. The server retrieves the user's profile information ("Interests: Gaming") and emotion data from the database.

[1639] 4. The server passes this information and the user's message to the generative model for contextual analysis.

[1640] 5. The generative model identifies information related to "games" and generates content such as, "If you're interested in gaming, why not check out this new game store?"

[1641] 6. The emotion engine retrieves emotion data from the user interface and analyzes the user's current emotional state.

[1642] 7. The generative model generates optimal responses based on the user's interests and emotions.

[1643] 8. The server sends the generated response message to the terminal.

[1644] 9. The device will display this message on the LINE app screen and provide the user with new information.

[1645] Example 2:

[1646] When users' emotions change during everyday interactions.

[1647] 1. Users send emojis or words that express their emotions through the LINE app.

[1648] 2. The device sends the user's input data and emotion data to the server.

[1649] 3. The server retrieves the user's emotional data from the database and analyzes the changes.

[1650] 4. The emotion engine analyzes the additional emotion data obtained from the user interface.

[1651] 5. The generative model generates new responses based on the analyzed emotional data and profile information. For example, if the user is feeling down, it generates a response like, "Why don't you cheer up and relax with the latest game?"

[1652] 6. The server sends the generated response message to the terminal.

[1653] 7. The device will display this message on the LINE app screen and provide appropriate support to the user.

[1654] In this way, users can have an optimal emotional interaction experience through their interactions with the system.

[1655] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1656] Step 1:

[1657] A user uses the LINE app to send a message saying, "I want to know about new games." This message represents a user request, and the system receives this message and begins processing. The input is the user's message, and the output is that the message is sent to the device.

[1658] Step 2:

[1659] The terminal receives the user's message and sends it to the server. The terminal receives the message data, assigns the user ID to it, and sends it to the server. The input is the user's message and user ID, and the output is that the message and user ID are sent to the server.

[1660] Step 3:

[1661] The server accesses the database based on the user ID and obtains the user's profile information and past interaction history. The server obtains this data and stores it for processing. The input is the user ID, and the output is the user's profile information and past interaction history. Specifically, it obtains "interests: gaming" and emotional data.

[1662] Step 4:

[1663] The server passes the acquired profile information and user message to a generative model. The generative model uses machine learning techniques to perform contextual analysis and generate an appropriate response based on the user's interests. The input is the profile information and user message, and the output is a personalized response message. For example, a response might be generated that says, "If you're interested in gaming, why not check out this new game store?"

[1664] Step 5:

[1665] The server passes emotion data obtained from the user interface to the emotion engine, which analyzes emotions from voice tone, emojis, etc. and provides the results to the generative model. The input is emotion data, and the output is the analyzed emotional state.

[1666] Step 6:

[1667] The generative model uses the analysis results from the emotion engine to determine the optimal response message. The generative model takes into account the user's interests and current emotional state to generate the most appropriate response. The input is the analysis results and profile information, and the output is the final response message. For example, if the user is excited, the generative model generates a message saying, "If you're interested in gaming, why not check out this new game store? It's fun!"

[1668] Step 7:

[1669] The server sends the generated optimal response message to the terminal. Here, the server encodes the response message and sends it to the terminal. The input is the final response message, and the output is the message sent to the terminal.

[1670] Step 8:

[1671] The device displays the response message received from the server on the user's LINE app screen. The device decodes the message and displays it on the user interface to provide the user with new information. The input is the response message from the server, and the output is the message displayed in the LINE app.

[1672] This completes the entire processing flow, allowing the user to receive personalized responses from the system and enjoy a natural interaction experience.

[1673] (Application example 2)

[1674] 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."

[1675] In modern stores, customer service is extremely important, but it is difficult for store staff to make appropriate suggestions and responses based on each customer's interests and emotions. It is also difficult to immediately determine what a customer is looking for or what their emotional state is. This can result in lower customer satisfaction and negatively impact store sales. Therefore, there is a need for a system that can suggest personalized services and products based on a customer's emotional state and preferences.

[1676] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for providing a user interface for conversation with a user, means for connecting to a database that stores the user's hobbies and preferences, means for generating a personalized response based on the user's input using a generative model, means for providing an emotion engine that analyzes the user's emotion data, means for displaying information on a head-mounted display for customer service support, and means for transmitting the personalized response to the user. This enables store staff to suggest optimal products and services in real time based on the customer's emotional state and preferences.

[1677] "User interface" refers to the screen and operating means that allow a user to interact with a system.

[1678] The "database" is a system that stores and manages users' hobbies, preferences, conversation history, emotional data, etc.

[1679] A "generative model" refers to an algorithm or machine learning technique that generates personalized responses based on user input data and information stored in a database.

[1680] The "emotion engine" is a system that analyzes emotional data such as tone of voice, facial expressions, and context obtained from the user interface and provides the analysis results to a generative model.

[1681] A "head-mounted display" is a display device worn on the user's head, and is used to display information for customer service support.

[1682] A "personalized response" refers to a response that is individually generated based on the user's tastes, preferences, and emotional state.

[1683] This invention is a system that engages in natural dialogue with a user and generates personalized responses based on the content of the dialogue and emotional data. The system is composed of a user interface, a database, a generative model, an emotional engine, and a server that exchanges data between these elements.

[1684] User Interface

[1685] The terminal provides a user interface for user interaction with the system. This interface uses a messaging platform (e.g., a messaging application) and provides the user with input and output screens. Data entered by the user is sent to the server through the terminal.

[1686] Database

[1687] The server connects to a database that stores users' hobbies, preferences, interaction history, and emotional data. This provides the foundation for the generative model and emotion engine to generate optimal responses based on past data. The database is updated in real time as users add new interests or preferences.

[1688] Generative Model

[1689] The server uses a generative model to generate personalized responses based on the user's input data and information stored in the database. The generative model uses machine learning techniques, particularly contextual analysis, to accurately identify the user's current interests and concerns. This enables natural and timely recommendations.

[1690] Emotion Engine

[1691] The server uses an emotion engine to analyze emotion data obtained from the user interface, such as tone of voice, facial expression, and context. The analysis results are provided to a generative model to realize personalized responses based on the user's emotions. The emotion engine also stores the user's emotion data in a database, allowing the generative model to generate responses based on past emotion history.

[1692] head-mounted display

[1693] A head-mounted display (HMD) is used by store staff to interact with customers, displaying information sent from the server in real time, allowing staff to make optimal suggestions based on the customer's emotional state and interests.

[1694] Specific examples

[1695] Example 1:

[1696] Consider a case where a user says, "I'm looking for new sneakers." The user's facial expression captured by the camera indicates that they are excited. This information is sent to the server, where it is analyzed by the generative model. Based on the user's interests and emotional state, the server displays a message on the HMD saying, "This new model is perfect for you. Would you like to try them on?" This allows store staff to provide the customer with the best possible product suggestions.

[1697] Example prompt sentence:

[1698] "When a customer says, 'I'm looking for new sneakers,' the emotion they're feeling is excitement. Based on this, generate the perfect sneaker suggestions for them."

[1699] This invention allows store staff to suggest optimal products and services in real time based on a customer's emotional state and preferences.

[1700] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1701] Program processing steps

[1702] Step 1:

[1703] The user puts on the HMD and starts the system.

[1704] How it works: When a user turns on the dedicated device (HMD), the user interface starts up and the camera and microphone capture the customer's video and audio in real time.

[1705] Input: Camera video data, microphone audio data.

[1706] Output: Real-time video and audio data is processed.

[1707] ---

[1708] Step 2:

[1709] The device (HMD) transmits camera images and audio data to the server.

[1710] How it works: The HMD transmits captured video and audio data to a server via wireless communication.

[1711] Input: Real-time video and audio data.

[1712] Output: Video and audio data sent to the server.

[1713] ---

[1714] Step 3:

[1715] The server analyzes the video data using an emotion engine to identify the customer's emotional state.

[1716] How it works: The server uses an emotion engine to analyze the customer's facial expressions from the video data and identify their emotional state. For example, it determines their emotion based on features such as a smile or wrinkles between the eyebrows.

[1717] Input: Video data.

[1718] Output: Emotional state data (e.g., happy, excited, calm, etc.).

[1719] ---

[1720] Step 4:

[1721] The server analyzes the voice data and converts what the customer says into text.

[1722] How it works: The server uses voice recognition technology to convert the audio data into text, extracting important keywords and phrases.

[1723] Input: Audio data.

[1724] Output: Text data.

[1725] ---

[1726] Step 5:

[1727] The server uses a generative model to generate a personalized response based on the text data and the emotional state data.

[1728] How it works: The server inputs text data and emotional state data into a generative model, which generates responses based on the user's interests and history from an existing database.

[1729] Input: Text data, emotional state data.

[1730] Output: A personalized response message.

[1731] ---

[1732] Step 6:

[1733] The server sends the generated response message to the HMD.

[1734] Operation: The server generates and sends a personalized response message in a format that can be displayed on the HMD's display.

[1735] Input: A personalized response message.

[1736] Output: Message sent to the HMD.

[1737] ---

[1738] Step 7:

[1739] The terminal (HMD) displays the response message received from the server to the store staff.

[1740] How it works: The HMD displays the received message on its display, allowing store staff to make suggestions to the customer.

[1741] Input: A personalized response message.

[1742] Output: Message displayed on the HMD display.

[1743] ---

[1744] Examples:

[1745] For example, if a user says, "I'm looking for new sneakers," and the camera shows that the user is excited, the server will display a response message on the HMD saying, "This new model is perfect for you. Would you like to try them on?"

[1746] Example prompt sentence:

[1747] "When a customer says, 'I'm looking for new sneakers,' the emotion they're feeling is excitement. Based on this, generate the perfect sneaker suggestions for them."

[1748] 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.

[1749] 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.

[1750] 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.

[1751] 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.

[1752] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1753] 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.

[1754] 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).

[1755] 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.

[1756] 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."

[1757] 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.

[1758] 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).

[1759] 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.

[1760] 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.

[1761] 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.

[1762] 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.

[1763] 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.

[1764] 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.

[1765] 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.

[1766] 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.

[1767] 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.

[1768] 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.

[1769] The following is further disclosed regarding the above embodiment.

[1770] (Claim 1)

[1771] means for providing a user interface for interacting with a user;

[1772] means for connecting to a database storing user hobbies and preferences;

[1773] means for generating a personalized response based on user input using the generative model;

[1774] means for sending the personalized response to a user;

[1775] A system including:

[1776] (Claim 2)

[1777] The system according to claim 1, wherein the generative model comprises means for performing context analysis using the user's dialogue history and information stored in a database, and recommending products and services related to the user's hobbies and preferences.

[1778] (Claim 3)

[1779] 10. The system of claim 1, further comprising an interface that provides a means for a user to customize their interests and settings.

[1780] "Example 1"

[1781] (Claim 1)

[1782] means for providing an information display device for conversation with a user;

[1783] means for connecting to a storage device for storing user hobbies and preferences;

[1784] a means for generating a personalized response based on user input using a generative AI model;

[1785] means for sending the personalized response to a user;

[1786] means for the terminal to send a message to the server;

[1787] a means for the server to retrieve a user profile from a database;

[1788] means for the server to send the generated response to the terminal;

[1789] means for the terminal to display the response to the user;

[1790] A system including:

[1791] (Claim 2)

[1792] The system of claim 1, wherein the generative AI model performs context analysis using the user's dialogue history and information stored in a storage device, and recommends products and services related to the user's hobbies and preferences.

[1793] (Claim 3)

[1794] 10. The system of claim 1, further comprising an information display device that provides a means for a user to customize their interests and settings.

[1795] "Application Example 1"

[1796] (Claim 1)

[1797] means for providing a user interface for interacting with a user;

[1798] means for connecting to a database storing user hobbies and preferences;

[1799] means for generating a personalized response based on user input using the generative model;

[1800] A way to send personalized responses to users in physical stores and recommend products and services at the right time;

[1801] A system including:

[1802] (Claim 2)

[1803] The system according to claim 1, wherein the generative model comprises means for performing context analysis using the user's dialogue history and information stored in the database, and recommending products and services related to the user's hobbies and preferences.

[1804] (Claim 3)

[1805] 10. The system of claim 1, further comprising an interface that provides a means for a user to customize their interests and settings.

[1806] "Example 2: Combining Emotion Engines"

[1807] (Claim 1)

[1808] means for providing a user interface for interacting with a user;

[1809] means for connecting to a database storing user hobbies and preferences;

[1810] means for generating a personalized response based on user input using the generative model;

[1811] means for connecting to an emotion engine for analyzing emotion data and reflecting it in responses;

[1812] means for transmitting the personalized response to a user.

[1813] (Claim 2)

[1814] The system according to claim 1, wherein the generative model comprises means for performing context analysis using the user's dialogue history and information stored in a database, and recommending products and services related to the user's hobbies and preferences.

[1815] (Claim 3)

[1816] 10. The system of claim 1, further comprising an interface that provides a means for a user to customize their interests and settings.

[1817] "Application example 2 when combining emotion engines"

[1818] (Claim 1)

[1819] means for providing a user interface for interacting with a user;

[1820] means for connecting to a database storing user hobbies and preferences;

[1821] means for generating a personalized response based on user input using the generative model;

[1822] means for providing an emotion engine for analyzing emotion data of a user;

[1823] a means for displaying information on a head-mounted display for customer service support;

[1824] means for sending the personalized response to a user;

[1825] A system including:

[1826] (Claim 2)

[1827] The system according to claim 1, wherein the generative model comprises means for performing context analysis using the user's dialogue history and information stored in a database, and recommending products and services related to the user's hobbies and preferences.

[1828] (Claim 3)

[1829] 10. The system of claim 1, further comprising an interface that provides a means for a user to customize their interests and settings. [Explanation of symbols]

[1830] 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. means for providing a user interface for interacting with a user; means for connecting to a database storing user hobbies and preferences; means for generating a personalized response based on user input using the generative model; means for sending the personalized response to a user; A system including:

2. The system according to claim 1 , wherein the generative model performs context analysis using the user's interaction history and information stored in a database, and recommends products and services related to the user's hobbies and preferences.

3. 10. The system of claim 1, further comprising an interface that provides a means for a user to customize their interests and settings.

Images