System

Abstract

A system is provided.SOLUTION: The system includes a means for enabling a user to input ideal appearance and personality setting information, a generation means for generating a virtual partner on the basis of the input appearance and personality setting information, and a communication means for storing a conversation history with the user and providing natural exchange.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] ---

[0005] In real life, it is difficult to find one's ideal partner. Furthermore, in conventional dating simulation games, it is difficult to accurately generate a partner with the user's ideal appearance and personality, and the conversations are often unnatural. As a result, many users are unable to achieve their ideal romantic experience, which reduces the appeal of the game. The purpose of this invention is to solve the above problems and provide a more natural and realistic dating simulation experience. [Means for solving the problem]

[0006] In order to solve the above problems, the present invention provides the following means.

[0007] The system includes a means for enabling a user to input ideal appearance and personality setting information, a generation means for generating a virtual partner based on the input appearance and personality setting information, a communication means for storing a conversation history with the user and providing natural interaction, and a means for displaying an image of the generated virtual partner.

[0008] The system further includes a means for transmitting information set by the user to the server and a means for receiving image data and conversation responses of the generated virtual partner from the server. Additionally, the system also includes a means for utilizing the conversation history to provide continuous, natural conversation responses based on the conversation with the generated virtual partner. This allows the user to enjoy interactions with their own ideal romantic partner.

[0009] ---

[0010] "User" refers to a person who uses this system to set up a virtual partner and engage in a dialogue.

[0011] "Ideal appearance" refers to the external characteristics of the virtual partner set by the user, and includes attributes such as hairstyle, eye color, height, and physique.

[0012] "Personality setting information" refers to the internal characteristics of the virtual partner set by the user, including kindness, humor, knowledge, hobbies, and the like.

[0013] "Virtual partner" refers to a digital character that is generated based on the appearance and personality settings set by the user.

[0014] "Generation means" refers to the technology and algorithms for generating a virtual partner based on the appearance and personality setting information entered by the user.

[0015] "Image data" refers to digital data containing a visual representation of the generated virtual partner.

[0016] "Means of communication" refers to the technologies and algorithms that enable natural conversation between the user and the virtual partner, including methods for storing and reusing conversation history.

[0017] "Conversation history" refers to a record of past conversations between a user and a virtual partner.

[0018] "Server" refers to a central processing unit that receives information set by the user and generates images of virtual partners and conversational responses.

[0019] A "terminal" is a device that allows a user to use an application, and includes a smartphone, a personal computer, etc.

[0020] "Display means" refers to a technique or device for displaying an image of the generated virtual partner to the user. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] ---

[0043] This invention is a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game, and interact with them through natural conversation. This system includes a generation means, a display means, and a communication means, and is realized through a user interface.

[0044] Entering configuration information

[0045] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies), which generates setting information according to the user's preferences.

[0046] Creating a Virtual Partner

[0047] The device sends the setting information entered by the user to the server. The server uses image generation AI based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[0048] Conversation initiation and memory

[0049] The user talks to the virtual partner created on the device, for example, asking, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server.

[0050] The server analyzes the received user speech data and uses a generation AI to generate an appropriate response text. For example, a response such as "Hello! I went running today. How was it?" is generated. This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[0051] Ongoing exchanges

[0052] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. The server generates continuous, natural conversation responses based on the conversation history. For example, in response to the user's question, "How was your run yesterday?", the server responds, "I ran 5km yesterday. It felt great!" In this way, the conversations between the user and the virtual partner are accumulated, enabling more intimate communication.

[0053] Specific examples

[0054] 1. Example of user settings

[0055] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[0056] 2. Example of Virtual Partner Generation

[0057] Terminal: Sends configuration information to the server.

[0058] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[0059] Terminal: displays the generated image to the user.

[0060] 3. Example conversation

[0061] User: Asks the generated partner, "How was your run yesterday?"

[0062] Terminal: Sends the user's question to the server.

[0063] Server: Based on the conversation history, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[0064] Terminal: displays the response to the user.

[0065] In this way, the system can provide users with a more natural and realistic dating simulation experience.

[0066] ---

[0067] The processing flow will be explained below.

[0068] ---

[0069] Step 1:

[0070] Launching the application

[0071] User: Launches a dedicated application on the device.

[0072] Terminal: Displays the main screen of the application.

[0073] Step 2:

[0074] Ideal partner setting

[0075] Terminal: Displays an interface for the user to input their ideal appearance (hairstyle, eye color, height, etc.) and personality (kindness, humor, knowledge, etc.).

[0076] User: Follow the interface and enter the configuration information of your ideal partner.

[0077] Terminal: Manages the entered setting information.

[0078] Step 3:

[0079] Sending configuration information

[0080] Terminal: The setting information entered by the user is sent to the server in JSON format.

[0081] Step 4:

[0082] Receiving a Partner Generation Request

[0083] Server: Receives the setting information (JSON data) sent from the device.

[0084] Step 5:

[0085] Calling image generation AI

[0086] Server: Based on the received setting information, the image generation AI is called and an image of a partner with the ideal appearance is generated.

[0087] Step 6:

[0088] Sending the generated results

[0089] Server: Sends the generated partner image data back to the device.

[0090] Step 7:

[0091] Displaying partner images

[0092] Terminal: Displays the received image data to the user.

[0093] Step 8:

[0094] Start a conversation

[0095] User: Talk to the generated partner through the device.

[0096] Terminal: Records user comments as text data.

[0097] Step 9:

[0098] Sending conversation data

[0099] Terminal: Sends recorded user speech data to the server.

[0100] Step 10:

[0101] Generating conversational responses

[0102] Server: Analyzes the received user speech data and generates appropriate response text using a generative AI model.

[0103] Step 11:

[0104] Sending a Generate Response

[0105] Server: Sends the generated response text to the terminal.

[0106] Step 12:

[0107] Viewing the response

[0108] Terminal: Displays the response text received from the server to the user.

[0109] Step 13:

[0110] Save conversation history

[0111] Server: Stores the conversation history between the user and the partner in a database.

[0112] Step 14:

[0113] Re-login

[0114] User: Relaunches the application on a daily basis and continues the conversation with the partner.

[0115] Device: Requests user information and past conversation history from the server.

[0116] Step 15:

[0117] Retrieving conversation history

[0118] Server: Retrieves the user's conversation history from the database and sends it to the terminal.

[0119] Step 16:

[0120] Use of history

[0121] Device: Displays the received conversation history on the screen, allowing the user to review past interactions.

[0122] Step 17:

[0123] Continuing Conversation

[0124] User: Continue a new conversation with your partner while referring to your conversation history.

[0125] Server: Receives new user utterances and uses stored history to generate more natural responses.

[0126] Step 18:

[0127] Generating a continuation response

[0128] Server: Again generates a conversation response and sends it to the terminal.

[0129] Terminal: displays the generated response to the user.

[0130] ---

[0131] The above is a detailed explanation of the system program processing divided into specific steps.

[0132] Example 1

[0133] 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."

[0134] Conventional dating simulation games have had difficulty in flexibly generating characters according to user preferences. They also have had issues with not being able to realize natural conversations, limiting the user experience. Furthermore, they lacked a mechanism for deepening relationships with users through ongoing conversations.

[0135] 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.

[0136] In this invention, the server includes means for allowing a user to input ideal appearance and personality setting information, means for transmitting the input appearance and personality setting information to the server, means for generating a virtual partner based on the input appearance and personality setting information, means for receiving image data of the generated virtual partner from the server, means for displaying image data of the generated virtual partner, means for recording user utterances on the terminal and transmitting them to the server, communication means for storing a conversation history with the user and providing natural conversation using a generative AI model, means for receiving conversation responses generated from the server, means for displaying the received conversation responses, and means for providing continuous conversation based on the past conversation history, thereby enabling character generation according to user preferences and natural conversation exchange.

[0137] "User" refers to a person who utilizes the system to generate and interact with an ideal virtual partner.

[0138] "Terminal" refers to a device operated by a user that runs dedicated applications to generate and interact with virtual partners.

[0139] "Server" refers to a central control device that receives setting information sent by a user, generates a virtual partner, and responds to conversations.

[0140] "Ideal appearance and personality setting information" refers to information that the user specifically inputs about the appearance and personality traits that the user desires in a virtual partner.

[0141] "Virtual partner" refers to a fictional character that is generated based on the user's setting information.

[0142] "Generative AI model" refers to artificial intelligence (AI) technology that generates images and conversational responses of virtual partners based on user settings.

[0143] A "prompt sentence" is text information input to a generative AI model to provide instructions on the virtual partner's characteristics and conversation content.

[0144] "Image Data" refers to data in digital form that represents a visual representation of a virtual partner generated by a generative AI model.

[0145] "Utterance data" refers to the recorded text of what the user says to the virtual partner.

[0146] "Conversation history" refers to a record of past interactions between a user and a virtual partner.

[0147] "Communication means" refers to the functions and processes necessary for natural interaction between the user and the virtual partner.

[0148] "Continuous conversation" refers to an ongoing dialogue between a virtual partner and a user based on past dialogue history.

[0149] This invention is a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game, and interact with them through natural conversation. This system includes a generation means, a display means, and a communication means, and is realized through a user interface.

[0150] Entering configuration information

[0151] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies). For example, the user may set a partner who is "black hair, blue eyes, 180cm tall, athletic," and "kind and humorous." This generates setting information that matches the user's preferences.

[0152] Creating a Virtual Partner

[0153] The device sends the setting information entered by the user to the server. The server uses an image generation AI (e.g., DALL-E, Stable Diffusion) based on the received setting information to generate image data for the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[0154] Conversation initiation and memory

[0155] The user speaks to the virtual partner generated on the device. For example, they might ask, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generation AI (e.g., GPT-3 (registered trademark)). For example, a response such as "Hello! I went for a run today. How was it for you?" is generated. This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[0156] Ongoing exchanges

[0157] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. The server generates continuous, natural conversation responses based on the conversation history. For example, if the user asks, "How was your run yesterday?", the server may respond, based on the past conversation history, with, "I ran 5km yesterday. It felt great!" In this way, the conversation between the user and the virtual partner is accumulated, enabling more intimate communication.

[0158] Specific examples

[0159] 1. Example of user settings

[0160] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[0161] 2. Example of Virtual Partner Generation

[0162] Terminal: Sends configuration information to the server.

[0163] Server: Image generation AI (e.g., Stable Diffusion) generates an image of the virtual partner based on the configuration information and sends it to the device.

[0164] Terminal: displays the generated image to the user.

[0165] 3. Example conversation

[0166] User: Asks the generated partner, "How was your run yesterday?"

[0167] Terminal: Sends the user's question to the server.

[0168] Server: Based on the conversation history, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[0169] Terminal: displays the response to the user.

[0170] In this way, the system can provide users with a more natural and realistic dating simulation experience.

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

[0172] Step 1:

[0173] The user launches the dedicated application on the device. At this time, an interface appears on the device's display, allowing the user to input the appearance and personality settings of their ideal virtual partner. Through this interface, the user inputs settings that suit their preferences. Specific inputs include "black hair, blue eyes, an athletic man who is 180 cm tall," as well as "kind and humorous." This input information is temporarily recorded on the device.

[0174] Step 2:

[0175] The device sends the setting information entered by the user to the server. The transmitted data includes the appearance and personality setting information entered by the user. When the server receives this setting information, it automatically prepares to input the setting information as a prompt to the image generation AI (e.g., DALL-E, Stable Diffusion). This prompt includes the specific characteristics desired by the user.

[0176] Step 3:

[0177] The server uses image generation AI based on the received setting information to generate image data of a virtual partner. A prompt such as "black hair, blue eyes, 180cm tall, athletic, kind and humorous" is input into the generation AI model. The image generation AI outputs an image of a partner with the specified characteristics according to this prompt. This image data is generated on the server side.

[0178] Step 4:

[0179] The generated image data of the virtual partner is sent from the server to the terminal. The terminal displays the received image data on the user interface. This display allows the user to check the visual appearance of the virtual partner based on the information set by the user.

[0180] Step 5:

[0181] The user starts a conversation with the virtual partner generated on the terminal. For example, the user enters "Hello, how was your day?" This utterance is recorded as text data on the terminal. The recorded text data is then sent by the terminal to the server.

[0182] Step 6:

[0183] The server analyzes the received user utterance data and calls a generative AI model (e.g., GPT-3). The utterance data is input to the generative AI model as a prompt sentence. For example, the user asks the virtual partner, "Hello, how was your day?" The generative AI model generates an appropriate response text (e.g., "Hello! I went for a run today. How was it for you?"). This response text is generated by the server.

[0184] Step 7:

[0185] The server sends the generated response to the terminal, which displays the received response text on the user interface, allowing the user to check the response from the virtual partner.

[0186] Step 8:

[0187] The server stores a conversation history with the user, including what the user said and the responses generated, allowing future conversations to reference past interactions.

[0188] Step 9:

[0189] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the conversation history, the server generates continuous, natural conversation responses. For example, in response to the question, "How was your run yesterday?", the server responds, "I ran 5km yesterday. It felt great!" This response text is generated and sent to the device.

[0190] Step 10:

[0191] The device then displays the received response on the user interface, allowing the user to enjoy a continuous dialogue based on the past conversation history.

[0192] As described above, this system can provide users with a more natural and realistic dating simulation experience.

[0193] (Application example 1)

[0194] 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."

[0195] Current food delivery services face the challenge of providing personalized suggestions that fully take into account the user's individual preferences and background information, resulting in a limited user experience. In particular, providing more intimate and effective services to users through personalized suggestions in food delivery is a challenge.

[0196] 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.

[0197] In this invention, the server includes means for allowing a user to input information on ideal appearance and personality settings, means for generating a virtual partner based on the input information on appearance and personality settings, means for storing a conversation history with the user and providing natural interaction, and means for making delivery suggestions based on the user's order information and conversation history, thereby enabling personalized delivery suggestions to be made to the user.

[0198] A "user" is someone who uses the system to interact with their ideal virtual partner and order and customize food.

[0199] "Appearance setting information" is information about the virtual partner's appearance, such as hairstyle, eye color, height, and build, set by the user.

[0200] "Personality setting information" is information about the inner qualities of the virtual partner set by the user, such as kindness, humor, knowledge, hobbies, etc.

[0201] A "virtual partner" is a digital character that is generated based on the user's settings information and with which the user can interact.

[0202] The "generation means" is a technology that has a function for generating a virtual partner based on information input by the user.

[0203] "Communication means" refers to technology that provides a function for realizing natural conversation between a virtual partner and a user and storing the conversation history.

[0204] "Order information" refers to information about the content that a user inputs when ordering or customizing food.

[0205] "Delivery Suggestion" is a function that suggests optimal foods and services to users based on their order information and conversation history.

[0206] A "generative AI model" is an artificial intelligence algorithm that generates images and responses of virtual partners based on the user's settings and conversations.

[0207] A "prompt" is an instruction or question that is input to a generative AI model to obtain a specific output.

[0208] This invention is a system that allows users to create a virtual partner with ideal appearance and personality, interact with them through natural conversation, and provide personalized suggestions for food delivery services. The system includes the following main means:

[0209] 1. Enter your user settings

[0210] The user starts a dedicated application installed on their smartphone and uses the interface to set the appearance (e.g., hairstyle, eye color, height, physique, etc.) and personality (e.g., kindness, humor, knowledge, hobbies, etc.) of their ideal virtual partner. This generates setting information.

[0211] 2. Generation of Virtual Partners

[0212] The smartphone sends the setting information entered by the user to the server. The server uses the generative AI model based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the smartphone and displayed to the user.

[0213] 3. Initiating and remembering conversations

[0214] The user speaks to the virtual partner generated on the device. For example, they might ask, "Good evening, what should I eat today?" The user's utterances are recorded as text data on the smartphone and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI model. For example, a response might be generated such as, "Why don't you order pizza today? We have recommended toppings." This generated response is sent to the smartphone and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[0215] 4. Continuous communication and suggestions

[0216] When the user launches the application again and continues the conversation with the virtual partner, the smartphone retrieves the user's past conversation history from the server. Based on the conversation history, the server provides delivery suggestions along with continuous, natural conversational responses. For example, in response to a user's question, "How was the pizza yesterday?", the server responds with, "Was the pizza delicious yesterday? Why not try the side dish next time?" In this way, more intimate and personalized suggestions are possible based on the user's preferences and past ordering history.

[0217] Hardware and software used

[0218] Hardware: Smartphone

[0219] Software: Python, OpenAI's GPT-3, Image Generation API

[0220] Specific examples

[0221] 1. Example of user settings

[0222] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[0223] 2. Example of Virtual Partner Generation

[0224] Smartphone: Sends configuration information to the server.

[0225] Server: Using a generative AI model, it generates an image of the virtual partner based on the settings information and sends it to the smartphone.

[0226] Smartphone: The generated image is displayed to the user.

[0227] 3. Example conversation

[0228] User: "I'm craving pizza today. What do you recommend?"

[0229] Smartphone: Sends the user's question to the server.

[0230] Server: Based on the conversation history, it generates a response such as, "You've been ordering Margherita pizza lately. Why not try a slightly spicy Diavolo today?" and sends it to your smartphone.

[0231] Smartphone: Display the response to the user.

[0232] Prompt Sentence Examples

[0233] "Generate natural conversational responses for your virtual partner based on the following text: User: I'm craving pizza today. What do you recommend? Virtual partner: You've been ordering Margherita pizzas lately. How about trying a slightly spicy Diavolo today?"

[0234] In this way, the system can provide users with personalized delivery suggestions as well as a more natural and realistic communication experience.

[0235] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0236] Step 1: The user launches a dedicated application on their smartphone. This application allows the user to input the appearance and personality settings of their ideal virtual partner through a user interface. Input data includes hairstyle, eye color, height, physique, kindness, humor, knowledge, hobbies, etc. The input information is then recorded on the device.

[0237] Step 2: The device sends the setting information entered by the user to the server. The data is sent to the server using a communication means. The server analyzes the received data and converts it into an appropriate format. This formatted data is provided as input to the image generation AI model.

[0238] Step 3: The server uses the image generation AI model based on the received data to generate image data of the virtual partner. The image generation AI model generates an image of the virtual partner based on the user's settings, and the generated image data is temporarily stored on the server. The generated data is then sent back to the device.

[0239] Step 4: The terminal displays the image data of the generated virtual partner received from the server on the user interface. The user can check the image of the generated virtual partner. Here, the virtual partner and the user can interact with each other.

[0240] Step 5: The user speaks to the virtual partner generated on the device. For example, the user types, "Hello, what should I eat today?" The user's speech is recorded as text data on the device and then sent to the server. The device sends the user's speech data to the server in text format.

[0241] Step 6: The server analyzes the received user utterance data and inputs it into the generative AI model to generate an appropriate response. Prompt sentences include "User: Hello, what should I eat today?" The generative AI model generates a response text based on the prompt sentence. For example, a response such as "How about ordering pizza today?" is generated. This generated response data is sent to the device.

[0242] Step 7: The terminal displays the response data received from the server on the user interface. The user can check the virtual partner's response and continue the conversation. At the same time, the server stores this exchange as a conversation history.

[0243] Step 8: When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the user's past conversation history, the server provides continuous, natural conversational responses, such as food delivery suggestions. For example, in response to the user's question, "How was the pizza yesterday?", a response such as "Was the pizza delicious yesterday? Why not try the side dish today?" is generated. This response is also sent to the device and displayed.

[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] ---

[0246] This invention combines a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game and interact with them through natural conversation, with an emotion engine that recognizes the user's emotions. This system includes generation means, display means, communication means, and the emotion engine, and is realized through a user interface.

[0247] Entering configuration information

[0248] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies), which generates setting information according to the user's preferences.

[0249] Creating a Virtual Partner

[0250] The device sends the setting information entered by the user to the server. The server uses image generation AI based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[0251] Conversation initiation and memory

[0252] The user talks to the virtual partner created on the device, for example, asking, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server.

[0253] The server analyzes the received user speech data and uses a generation AI to generate an appropriate response text. For example, a response such as "Hello! I went for a walk today. How was it?" is generated. This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[0254] User Emotion Recognition

[0255] The emotion engine recognizes emotions from the user's speech and facial expression data. For example, if the user is smiling while speaking, the emotion "joy" is recognized. This allows the virtual partner's response to be adjusted to match the user's emotion. For example, if the user is angry, the virtual partner can ask, "Is something wrong?"

[0256] Ongoing exchanges

[0257] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the conversation history, the server uses an emotion engine to generate continuous, natural conversation responses. For example, if the user previously said "I'm tired," the server remembers this and generates a response such as "Did you sleep well last night?" In this way, the conversations between the user and the virtual partner are accumulated, enabling more intimate communication.

[0258] Specific examples

[0259] 1. Example of user settings

[0260] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[0261] 2. Example of Virtual Partner Generation

[0262] Terminal: Sends configuration information to the server.

[0263] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[0264] Terminal: displays the generated image to the user.

[0265] 3. Example conversation

[0266] User: Asks the generated partner, "How was your run yesterday?"

[0267] Terminal: Sends the user's question to the server.

[0268] Server: Based on the conversation history and emotion engine, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[0269] Terminal: displays the response to the user.

[0270] 4. Emotion recognition example

[0271] User: Smile while talking to your virtual partner.

[0272] Device: Sends the user's smile to the emotion engine via the camera function.

[0273] Server: The emotion engine recognizes "joy" and generates a response based on that.

[0274] In this way, the system provides the user with a more natural and realistic dating simulation experience, while also realizing responses that correspond to the user's emotions.

[0275] The processing flow will be explained below.

[0276] ---

[0277] Step 1:

[0278] Launching the application

[0279] User: Launches a dedicated application on the device.

[0280] Terminal: Displays the main screen of the application.

[0281] Step 2:

[0282] Ideal partner setting

[0283] Terminal: Displays an interface for the user to input their ideal appearance (hairstyle, eye color, height, etc.) and personality (kindness, humor, knowledge, etc.).

[0284] User: Follow the interface and enter the configuration information of your ideal partner.

[0285] Terminal: Manages the entered setting information.

[0286] Step 3:

[0287] Sending configuration information

[0288] Terminal: The setting information entered by the user is sent to the server in JSON format.

[0289] Step 4:

[0290] Receiving a Partner Generation Request

[0291] Server: Receives the setting information (JSON data) sent from the device.

[0292] Step 5:

[0293] Calling image generation AI

[0294] Server: Calls the image generation AI based on the received setting information and generates an image of a partner with the ideal appearance.

[0295] Step 6:

[0296] Sending the generated results

[0297] Server: Sends the generated partner image data back to the device.

[0298] Step 7:

[0299] Displaying partner images

[0300] Terminal: Displays the received image data to the user.

[0301] Step 8:

[0302] Start a conversation

[0303] User: Talk to the generated partner through the device.

[0304] Terminal: Records user comments as text data.

[0305] Step 9:

[0306] Sending conversation data

[0307] Terminal: Sends recorded user speech data to the server.

[0308] Step 10:

[0309] Generating conversational responses

[0310] Server: Analyzes the received user speech data and generates appropriate response text using a generative AI model.

[0311] Step 11:

[0312] User Emotion Recognition

[0313] Terminal: Collects the user's facial expression data using an accessible camera function and sends it to the emotion engine.

[0314] Server: The emotion engine recognizes emotions (e.g., joy, anger, sadness) based on the user's speech and facial expression data.

[0315] Step 12:

[0316] Response adjustment

[0317] Server: Adjusts the generated response text based on the user's perceived emotions. For example, if the user is determined to be tired, it generates a gentle response such as "Thank you for your hard work. Maybe you should take a rest today."

[0318] Step 13:

[0319] Sending a Generate Response

[0320] Server: Sends the tailored response text to the device.

[0321] Step 14:

[0322] Viewing the response

[0323] Terminal: Displays the response text received from the server to the user.

[0324] Step 15:

[0325] Save conversation history

[0326] Server: Stores the conversation history and recognized emotion data of the user and partner in a database.

[0327] Step 16:

[0328] Re-login

[0329] User: Relaunches the application on a daily basis and continues the conversation with the partner.

[0330] Terminal: Requests user information, past conversation history, and emotion data from the server.

[0331] Step 17:

[0332] Retrieving conversation history

[0333] Server: Retrieves the user's conversation history and emotion data from the database and sends them to the device.

[0334] Step 18:

[0335] Use of history

[0336] Terminal: Displays the received conversation history and emotion history on the screen, allowing the user to check past interactions and emotional states.

[0337] Step 19:

[0338] Continuing Conversation

[0339] User: Continue a new conversation with your partner while referring to the conversation history and emotion history.

[0340] Server: Receives new user utterances and uses stored history to generate more natural responses.

[0341] Step 20:

[0342] Generating a continuation response

[0343] Server: Again generates a conversation response and sends it to the terminal.

[0344] Terminal: displays the generated response to the user.

[0345] ---

[0346] The above is a detailed explanation of the program processing of a system that combines an emotion engine, broken down into specific steps.

[0347] Example 2

[0348] 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."

[0349] In conventional dating simulation systems, it was difficult for users to create their ideal virtual partner and engage in continuous interaction. Furthermore, the system lacked a realistic experience because it did not provide responses based on the user's emotions. Furthermore, it lacked a means to conduct natural, continuous dialogue based on past conversation history.

[0350] The specification processing 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 means for allowing the user to input ideal appearance and personality setting information, generation means for generating a virtual partner based on the input appearance and personality setting information, communication means for storing utterances made by the user to the generated virtual partner and providing natural interactions, emotion recognition means for collecting facial expressions and voice data of the user and recognizing emotions, and means for adjusting the responses of the virtual partner based on the emotion recognition results. This enables the user to have continuous, natural conversations with their ideal virtual partner according to their emotions.

[0351] "User" refers to an individual who uses the dating simulation system.

[0352] "Ideal appearance" refers to information about the appearance of a virtual partner set by the user.

[0353] "Personality setting information" refers to information about the personality and characteristics of the virtual partner set by the user.

[0354] "Virtual partner" refers to a digital character that is generated based on information set by the user.

[0355] "Generation means" refers to a function that generates a virtual partner based on setting information input by the user.

[0356] "Communication means" refers to a function that stores conversation history with the user and provides natural interaction.

[0357] "Emotion recognition means" refers to a function for collecting facial expressions and voice data of the user and recognizing emotions.

[0358] "Adjustment means" refers to the ability to adjust the virtual partner's responses based on perceived emotions.

[0359] "Server" refers to a central control unit that manages user preferences and conversation history, and provides virtual partner generation and response.

[0360] "Terminal" refers to a device through which a user accesses and operates the system.

[0361] "Conversation history" refers to data that records past interactions between a user and a virtual partner.

[0362] "Continuous interaction" refers to continuous and natural dialogue based on past conversation history.

[0363] "Response according to emotions" refers to a response from a virtual partner that is generated taking into account the user's emotions.

[0364] "Natural interaction" refers to dialogue that flows like a human conversation.

[0365] This invention combines a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game and interact with them through natural conversation, with an emotion engine that recognizes the user's emotions. This system includes generation means, display means, communication means, and the emotion engine, and is realized through a user interface.

[0366] Entering configuration information

[0367] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies), which generates setting information according to the user's preferences.

[0368] Creating a Virtual Partner

[0369] The device sends the setting information entered by the user to the server. The server uses an image generation AI model (e.g., DALL-E or GAN) based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[0370] Conversation initiation and memory

[0371] The user speaks to the virtual partner generated on the device. For example, the user might ask, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generation AI (e.g., GPT-4 (registered trademark)). For example, a response such as "Hello! I went for a walk today. How was it for you?" is generated. This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[0372] User Emotion Recognition

[0373] The emotion engine recognizes emotions from the user's speech and facial expression data. For example, if the user is smiling while speaking, the emotion "joy" is recognized. This allows the virtual partner's response to be adjusted to match the user's emotion. For example, if the user is angry, the virtual partner can ask, "Is something wrong?"

[0374] Ongoing exchanges

[0375] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the conversation history, the server uses an emotion engine to generate continuous, natural conversation responses. For example, if the user previously said "I'm tired," the server remembers this and generates a response such as "Did you sleep well last night?" In this way, the conversations between the user and the virtual partner are accumulated, enabling more intimate communication.

[0376] Specific examples

[0377] 1. Example of user settings

[0378] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[0379] 2. Example of Virtual Partner Generation

[0380] Terminal: Sends configuration information to the server.

[0381] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[0382] Terminal: displays the generated image to the user.

[0383] 3. Example conversation

[0384] User: Asks the generated partner, "How was your run yesterday?"

[0385] Terminal: Sends the user's question to the server.

[0386] Server: Based on the conversation history and emotion engine, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[0387] Terminal: displays the response to the user.

[0388] 4. Emotion recognition example

[0389] User: Smile while talking to your virtual partner.

[0390] Device: Sends the user's smile to the emotion engine via the camera function.

[0391] Server: The emotion engine recognizes "joy" and generates a response based on that.

[0392] In this way, the system provides the user with a more natural and realistic love simulation experience, while also realizing responses that correspond to the user's emotions.

[0393] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0394] Step 1:

[0395] The user launches the dedicated application on their device and inputs their ideal appearance and personality through the interface. For example, they can select a character with black hair, blue eyes, a height of 180cm, an athletic body, and a kind and humorous personality. This input data is then saved on the device.

[0396] Input: User's ideal appearance and personality setting information (e.g., black hair, blue eyes, height 180 cm, athletic, kind, humorous)

[0397] Output: JSON data of configuration information

[0398] Specific behavior:

[0399] The user enters configuration information on the initial screen of the app.

[0400] The terminal converts the input data into JSON format and prepares it for the API request.

[0401] Step 2:

[0402] The device sends the setting information entered by the user to the server. The server uses an image generation AI model (e.g., GAN) based on the received setting information to generate image data of a virtual partner. The generated virtual partner data is then sent back to the device and displayed to the user.

[0403] Input: JSON data of setting information

[0404] Output: Image data of virtual partner

[0405] Specific behavior:

[0406] The device sends the configuration information to the server's API endpoint via a POST request.

[0407] The server inputs the prompt statement "A sportsman with black hair, blue eyes, and a height of 180 cm" into the generative AI model and generates image data.

[0408] The terminal displays the received image data on the user's screen.

[0409] Step 3:

[0410] The user speaks to the generated virtual partner via text or voice. For example, they might say, "Hello, how was your day?" The user's speech is recorded as text data on the device and sent to the server. The server analyzes the received user speech data, generates an appropriate response text using a generative AI model (e.g., GPT-4), and sends it back to the device. The device then displays the response to the user.

[0411] Input: User-spoken text (e.g., "Hello, how was your day?")

[0412] Output: Virtual partner's response text (e.g., "Hi! I went for a walk today. How was it for you?")

[0413] Specific behavior:

[0414] The user types "Hi, how was your day?" into the text box.

[0415] The device sends the entered text data to the server's API endpoint.

[0416] The server inputs a prompt sentence into the generative AI model and sends the generated response text back to the terminal.

[0417] The terminal displays the generated response to the user.

[0418] Step 4:

[0419] The device captures the user's facial expressions and voice data using a camera and microphone and sends it to the server, which then uses an emotion recognition engine to recognize the user's emotions from the captured data and adjusts the virtual partner's responses based on the results.

[0420] Input: User facial expression images or voice data

[0421] Output: Emotion recognition results and tailored response text

[0422] Specific behavior:

[0423] The user smiles during the conversation.

[0424] The device captures the user's facial expressions with a camera and sends them to the server.

[0425] The server analyzes the captured data using an emotion recognition engine, recognizes the emotion "joy," and generates a response based on the result: "You look happy. Did something good happen?"

[0426] The terminal displays the generated response to the user.

[0427] Step 5:

[0428] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the past conversation history from the server. Based on the conversation history, the server uses the generative AI model and emotion engine to generate continuous, natural-sounding conversation responses and send them to the device. The device then displays the responses to the user.

[0429] Input: User ID, past conversation history

[0430] Output: Natural conversational response text

[0431] Specific behavior:

[0432] The user restarts the app and types, "I'm curious to know what happened next from yesterday."

[0433] The device sends the user ID to the server and requests past conversation history.

[0434] The server references the conversation history and generates a response such as, "You said you were tired. Did you get enough rest?"

[0435] The terminal displays the generated response to the user.

[0436] The above are the processing steps of the program for this system.

[0437] (Application example 2)

[0438] 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."

[0439] The present invention relates to a system that allows users to have natural conversations with a virtual partner that reflects the user's ideal appearance and personality, and provides responses that correspond to the user's emotions. Conventional systems lack the ability to recognize the user's emotions, making it difficult to respond to emotions in real time. There has also been a demand for a system that enables a more realistic experience by expanding the interaction scene with the virtual partner to a virtual store. The objective of this system is to provide an environment in which users can enjoy deeper interactions in virtual space.

[0440] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0441] In this invention, the server includes means for allowing a user to input ideal appearance and personality setting information, means for generating a virtual partner based on the input appearance and personality setting information, means for recognizing emotions from the user's facial expression data, and means for realizing a dialogue between the generated virtual partner and the user in a virtual store. This not only allows the user to enjoy natural dialogue with their ideal virtual partner, but also enables a realistic experience in the virtual store, and makes it possible to provide responses that correspond to the user's emotions.

[0442] "Means enabling users to input ideal appearance and personality setting information" refers to a function that provides an interface for users to specifically customize the appearance and personality of their virtual partner based on their own preferences.

[0443] The "generation means for generating a virtual partner based on input appearance and personality setting information" refers to an algorithm and system for automatically generating the appearance and personality of a virtual partner based on setting information provided by the user.

[0444] "A communication method that remembers conversation history with the user and provides natural interactions" is a system that records the content of past conversations the user has had with a virtual partner and enables more natural and continuous conversations based on that history.

[0445] The "emotion recognition means for recognizing emotions from user's facial expression data" is a function that analyzes the user's facial expressions in real time and identifies the user's current emotional state (such as joy or sadness) from those expressions.

[0446] "Means for enabling interaction between the generated virtual partner and the user within a virtual store" refers to a function that enables direct interaction between the virtual partner and the user within a virtual space, and an example of such a space is a virtual store.

[0447] "Means for generating virtual partner responses using a generative AI model" refers to methods and systems for using a generative AI model (e.g., GPT-3) to generate virtual partner responses to user input.

[0448] "Means for inputting prompt sentences into a generative AI model to obtain an appropriate response" refers to the process of creating a text sentence (prompt sentence) to query the generative AI model so that the virtual partner can respond appropriately to what the user says, and obtaining a response based on that.

[0449] MODE FOR CARRYING OUT THE INVENTION

[0450] This invention combines a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game and interact with them through natural conversation, with an emotion engine that recognizes the user's emotions. This system includes generation means, display means, communication means, emotion recognition means, and means for realizing dialogue within a virtual store, and is realized through a user interface.

[0451] composition

[0452] The system consists of the following elements:

[0453] 1. User interface: An interface where the user inputs information about their ideal appearance and personality.

[0454] 2. Generator: A generative AI model for generating virtual partners based on input information.

[0455] 3. Display means: a display device for displaying an image of the virtual partner to the user.

[0456] 4. Communication tools: A generative AI model that remembers conversation history with the user and provides natural interactions.

[0457] 5. Emotion recognition means: A camera and analysis engine for recognizing emotions from the user's facial expression data.

[0458] 6. Means for realizing interaction within a virtual store: An environment that enables interaction within a virtual space.

[0459] Example Details

[0460] Entering configuration information

[0461] Users launch a dedicated application on their smartphone and use the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies).

[0462] Creating a Virtual Partner

[0463] The device sends the setting information entered by the user to the server. The server uses a generative AI model based on the received setting information to generate image data of a virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[0464] Conversation initiation and memory

[0465] The user speaks to the virtual partner generated on the device. For example, they might ask, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI model. For example, a response might be "Hello! I went for a walk today. How was it for you?" This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[0466] User Emotion Recognition

[0467] The emotion recognition means uses the smartphone's camera to acquire data on the user's facial expressions, and the analysis engine uses that data to recognize the user's emotions. For example, if the user is smiling while speaking, the emotion "joy" is recognized. This allows the virtual partner's response to be adjusted to match the user's emotions. For example, if the user is angry, the virtual partner can ask, "Is something wrong?"

[0468] Interactions in a virtual store

[0469] Users can enjoy interacting with virtual partners in a virtual store. In the virtual store, the virtual partners can introduce products to users and they can enjoy the virtual store together. This allows users to feel a more realistic experience in the virtual space.

[0470] Specific examples of use

[0471] 1. Example of user settings:

[0472] Through the application, users select a partner who is "black-haired, blue-eyed, 180cm tall, athletic," and "kind and humorous."

[0473] 2. Example of Virtual Partner Generation:

[0474] Terminal: Sends configuration information to the server.

[0475] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[0476] Terminal: displays the generated image to the user.

[0477] 3. Example conversation:

[0478] User: "Hi, how was your day?"

[0479] Server: Based on the conversation history and the generative AI model, it generates a response such as "Hello! I went for a walk today. How was it?" and sends it to the device.

[0480] 4. Emotion Recognition Example:

[0481] User: Smile while talking to your virtual partner.

[0482] Server: The emotion recognition engine recognizes "happiness" and generates a response based on that.

[0483] Example prompt for a generative AI model:

[0484] "Generate an image of a person with black hair, blue eyes, and a height of 180 cm, who has a kind and humorous personality."

[0485] In this way, the system provides users with a more natural and realistic love simulation experience, while also enabling dialogue within the virtual store and responses that reflect the user's emotions.

[0486] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0487] Step 1:

[0488] Users start the dedicated application on their smartphone and use the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies). The input data is temporarily recorded on the device.

[0489] Input: User's appearance and personality settings

[0490] Output: Recorded setting information data

[0491] Step 2:

[0492] The device sends the setting information entered by the user to the server. The server uses the generative AI model based on the received setting information to generate image data of the virtual partner. The generated image data is then sent back from the server to the device.

[0493] Input: Setting information data

[0494] Output: Image data of virtual partner

[0495] Step 3:

[0496] The terminal that acquires the image data of the virtual partner displays the image to the user, who can then talk to the displayed virtual partner.

[0497] Input: Image data of virtual partner

[0498] Output: Image displayed to the user

[0499] Step 4:

[0500] When a user speaks to a virtual partner, the device records the speech as text data and sends it to the server. The server analyzes the received speech data and generates an appropriate response text using a generative AI model. The generated response text is then sent from the server to the device.

[0501] Input: User's comment text data

[0502] Output: Virtual partner's response text data

[0503] Step 5:

[0504] The terminal displays the virtual partner's response text data received from the server to the user, and the server simultaneously stores this exchange as a conversation history.

[0505] Input: Virtual partner's response text data

[0506] Output: Display response text to user, record conversation history

[0507] Step 6:

[0508] The user's facial expression data is acquired using the smartphone camera, and the acquired data is analyzed using emotion recognition means. Based on the analysis results, the user's emotions are recognized and emotion data is generated.

[0509] Input: User's facial expression data

[0510] Output: User emotion data

[0511] Step 7:

[0512] The server uses the emotion data to input prompt sentences into the generative AI model, which generates a response that matches the user's emotion. The generated response is then sent from the server to the device, which then displays the response to the user.

[0513] Input: User emotion data, prompt sentence

[0514] Output: Emotion-adjusted text data of the virtual partner's responses, displayed to the user

[0515] Step 8:

[0516] When a conversation with a user takes place in a virtual store, the virtual partner will have a natural conversation based on a scenario of actions in the virtual store, product introductions, etc. The server generates a response based on this scenario and sends it to the terminal, providing a realistic experience in the virtual store.

[0517] Input: Scenario information in the virtual store, user dialogue text data

[0518] Output: Text data of the virtual partner's response based on the scenario, displayed to the user

[0519] These processing steps allow users to enjoy natural and emotionally responsive interactions with their ideal virtual partner, and also provide a realistic experience within the virtual store.

[0520] 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.

[0521] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0522] 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.

[0523] [Second embodiment]

[0524] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0525] 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.

[0526] 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).

[0527] 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.

[0528] 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.

[0529] 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).

[0530] 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.

[0531] 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.

[0532] 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.

[0533] 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.

[0534] 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.

[0535] 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."

[0536] ---

[0537] This invention is a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game, and interact with them through natural conversation. This system includes a generation means, a display means, and a communication means, and is realized through a user interface.

[0538] Entering configuration information

[0539] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies), which generates setting information according to the user's preferences.

[0540] Creating a Virtual Partner

[0541] The device sends the setting information entered by the user to the server. The server uses image generation AI based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[0542] Conversation initiation and memory

[0543] The user talks to the virtual partner created on the device, for example, asking, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server.

[0544] The server analyzes the received user speech data and uses a generation AI to generate an appropriate response text. For example, a response such as "Hello! I went running today. How was it?" is generated. This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[0545] Ongoing exchanges

[0546] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. The server generates continuous, natural conversation responses based on the conversation history. For example, in response to the user's question, "How was your run yesterday?", the server responds, "I ran 5km yesterday. It felt great!" In this way, the conversations between the user and the virtual partner are accumulated, enabling more intimate communication.

[0547] Specific examples

[0548] 1. Example of user settings

[0549] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[0550] 2. Example of Virtual Partner Generation

[0551] Terminal: Sends configuration information to the server.

[0552] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[0553] Terminal: displays the generated image to the user.

[0554] 3. Example conversation

[0555] User: Asks the generated partner, "How was your run yesterday?"

[0556] Terminal: Sends the user's question to the server.

[0557] Server: Based on the conversation history, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[0558] Terminal: displays the response to the user.

[0559] In this way, the system can provide users with a more natural and realistic dating simulation experience.

[0560] ---

[0561] The processing flow will be explained below.

[0562] ---

[0563] Step 1:

[0564] Launching the application

[0565] User: Launches a dedicated application on the device.

[0566] Terminal: Displays the main screen of the application.

[0567] Step 2:

[0568] Ideal partner setting

[0569] Terminal: Displays an interface for the user to input their ideal appearance (hairstyle, eye color, height, etc.) and personality (kindness, humor, knowledge, etc.).

[0570] User: Follow the interface and enter the configuration information of your ideal partner.

[0571] Terminal: Manages the entered setting information.

[0572] Step 3:

[0573] Sending configuration information

[0574] Terminal: The setting information entered by the user is sent to the server in JSON format.

[0575] Step 4:

[0576] Receiving a Partner Generation Request

[0577] Server: Receives the setting information (JSON data) sent from the device.

[0578] Step 5:

[0579] Calling image generation AI

[0580] Server: Based on the received setting information, the image generation AI is called and an image of a partner with the ideal appearance is generated.

[0581] Step 6:

[0582] Sending the generated results

[0583] Server: Sends the generated partner image data back to the device.

[0584] Step 7:

[0585] Displaying partner images

[0586] Terminal: Displays the received image data to the user.

[0587] Step 8:

[0588] Start a conversation

[0589] User: Talk to the generated partner through the device.

[0590] Terminal: Records user comments as text data.

[0591] Step 9:

[0592] Sending conversation data

[0593] Terminal: Sends recorded user speech data to the server.

[0594] Step 10:

[0595] Generating conversational responses

[0596] Server: Analyzes the received user speech data and generates appropriate response text using a generative AI model.

[0597] Step 11:

[0598] Sending a Generate Response

[0599] Server: Sends the generated response text to the terminal.

[0600] Step 12:

[0601] Viewing the response

[0602] Terminal: Displays the response text received from the server to the user.

[0603] Step 13:

[0604] Save conversation history

[0605] Server: Stores the conversation history between the user and the partner in a database.

[0606] Step 14:

[0607] Re-login

[0608] User: Relaunches the application on a daily basis and continues the conversation with the partner.

[0609] Device: Requests user information and past conversation history from the server.

[0610] Step 15:

[0611] Retrieving conversation history

[0612] Server: Retrieves the user's conversation history from the database and sends it to the terminal.

[0613] Step 16:

[0614] Use of history

[0615] Device: Displays the received conversation history on the screen, allowing the user to review past interactions.

[0616] Step 17:

[0617] Continuing Conversation

[0618] User: Continue a new conversation with your partner while referring to your conversation history.

[0619] Server: Receives new user utterances and uses stored history to generate more natural responses.

[0620] Step 18:

[0621] Generating a continuation response

[0622] Server: Again generates a conversation response and sends it to the terminal.

[0623] Terminal: displays the generated response to the user.

[0624] ---

[0625] The above is a detailed explanation of the system program processing divided into specific steps.

[0626] Example 1

[0627] 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."

[0628] Conventional dating simulation games have had difficulty in flexibly generating characters according to user preferences. They also have had issues with not being able to realize natural conversations, limiting the user experience. Furthermore, they lacked a mechanism for deepening relationships with users through ongoing conversations.

[0629] 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.

[0630] In this invention, the server includes means for allowing a user to input ideal appearance and personality setting information, means for transmitting the input appearance and personality setting information to the server, means for generating a virtual partner based on the input appearance and personality setting information, means for receiving image data of the generated virtual partner from the server, means for displaying image data of the generated virtual partner, means for recording user utterances on the terminal and transmitting them to the server, communication means for storing a conversation history with the user and providing natural conversation using a generative AI model, means for receiving conversation responses generated from the server, means for displaying the received conversation responses, and means for providing continuous conversation based on the past conversation history, thereby enabling character generation according to user preferences and natural conversation exchange.

[0631] "User" refers to a person who utilizes the system to generate and interact with an ideal virtual partner.

[0632] "Terminal" refers to a device operated by a user that runs dedicated applications to generate and interact with virtual partners.

[0633] "Server" refers to a central control device that receives setting information sent by a user, generates a virtual partner, and responds to conversations.

[0634] "Ideal appearance and personality setting information" refers to information that the user specifically inputs about the appearance and personality traits that the user desires in a virtual partner.

[0635] "Virtual partner" refers to a fictional character that is generated based on the user's setting information.

[0636] "Generative AI model" refers to artificial intelligence (AI) technology that generates images and conversational responses of virtual partners based on user settings.

[0637] A "prompt sentence" is text information input to a generative AI model to provide instructions on the virtual partner's characteristics and conversation content.

[0638] "Image Data" refers to data in digital form that represents a visual representation of a virtual partner generated by a generative AI model.

[0639] "Utterance data" refers to the recorded text of what the user says to the virtual partner.

[0640] "Conversation history" refers to a record of past interactions between a user and a virtual partner.

[0641] "Communication means" refers to the functions and processes necessary for natural interaction between the user and the virtual partner.

[0642] "Continuous conversation" refers to an ongoing dialogue between a virtual partner and a user based on past dialogue history.

[0643] This invention is a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game, and interact with them through natural conversation. This system includes a generation means, a display means, and a communication means, and is realized through a user interface.

[0644] Entering configuration information

[0645] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies). For example, the user may set a partner who is "black hair, blue eyes, 180cm tall, athletic," and "kind and humorous." This generates setting information that matches the user's preferences.

[0646] Creating a Virtual Partner

[0647] The device sends the setting information entered by the user to the server. The server uses an image generation AI (e.g., DALL-E, Stable Diffusion) based on the received setting information to generate image data for the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[0648] Conversation initiation and memory

[0649] The user speaks to the virtual partner generated on the device. For example, they might ask, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI (e.g., GPT-3). For example, a response might be generated such as, "Hello! I went for a run today. How was it for you?" This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[0650] Ongoing exchanges

[0651] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. The server generates continuous, natural conversation responses based on the conversation history. For example, if the user asks, "How was your run yesterday?", the server may respond, based on the past conversation history, with, "I ran 5km yesterday. It felt great!" In this way, the conversation between the user and the virtual partner is accumulated, enabling more intimate communication.

[0652] Specific examples

[0653] 1. Example of user settings

[0654] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[0655] 2. Example of Virtual Partner Generation

[0656] Terminal: Sends configuration information to the server.

[0657] Server: Image generation AI (e.g., Stable Diffusion) generates an image of the virtual partner based on the configuration information and sends it to the device.

[0658] Terminal: displays the generated image to the user.

[0659] 3. Example conversation

[0660] User: Asks the generated partner, "How was your run yesterday?"

[0661] Terminal: Sends the user's question to the server.

[0662] Server: Based on the conversation history, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[0663] Terminal: displays the response to the user.

[0664] In this way, the system can provide users with a more natural and realistic dating simulation experience.

[0665] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0666] Step 1:

[0667] The user launches the dedicated application on the device. At this time, an interface appears on the device's display, allowing the user to input the appearance and personality settings of their ideal virtual partner. Through this interface, the user inputs settings that suit their preferences. Specific inputs include "black hair, blue eyes, an athletic man who is 180 cm tall," as well as "kind and humorous." This input information is temporarily recorded on the device.

[0668] Step 2:

[0669] The device sends the setting information entered by the user to the server. The transmitted data includes the appearance and personality setting information entered by the user. When the server receives this setting information, it automatically prepares to input the setting information as a prompt to the image generation AI (e.g., DALL-E, Stable Diffusion). This prompt includes the specific characteristics desired by the user.

[0670] Step 3:

[0671] The server uses image generation AI based on the received setting information to generate image data of a virtual partner. A prompt such as "black hair, blue eyes, 180cm tall, athletic, kind and humorous" is input into the generation AI model. The image generation AI outputs an image of a partner with the specified characteristics according to this prompt. This image data is generated on the server side.

[0672] Step 4:

[0673] The generated image data of the virtual partner is sent from the server to the terminal. The terminal displays the received image data on the user interface. This display allows the user to check the visual appearance of the virtual partner based on the information set by the user.

[0674] Step 5:

[0675] The user starts a conversation with the virtual partner generated on the terminal. For example, the user enters "Hello, how was your day?" This utterance is recorded as text data on the terminal. The recorded text data is then sent by the terminal to the server.

[0676] Step 6:

[0677] The server analyzes the received user utterance data and calls a generative AI model (e.g., GPT-3). The utterance data is input to the generative AI model as a prompt sentence. For example, the user asks the virtual partner, "Hello, how was your day?" The generative AI model generates an appropriate response text (e.g., "Hello! I went for a run today. How was it for you?"). This response text is generated by the server.

[0678] Step 7:

[0679] The server sends the generated response to the terminal, which displays the received response text on the user interface, allowing the user to check the response from the virtual partner.

[0680] Step 8:

[0681] The server stores a conversation history with the user, including what the user said and the responses generated, allowing future conversations to reference past interactions.

[0682] Step 9:

[0683] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the conversation history, the server generates continuous, natural conversation responses. For example, in response to the question, "How was your run yesterday?", the server responds, "I ran 5km yesterday. It felt great!" This response text is generated and sent to the device.

[0684] Step 10:

[0685] The device then displays the received response on the user interface, allowing the user to enjoy a continuous dialogue based on the past conversation history.

[0686] As described above, this system can provide users with a more natural and realistic dating simulation experience.

[0687] (Application example 1)

[0688] 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."

[0689] Current food delivery services face the challenge of providing personalized suggestions that fully take into account the user's individual preferences and background information, resulting in a limited user experience. In particular, providing more intimate and effective services to users through personalized suggestions in food delivery is a challenge.

[0690] 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.

[0691] In this invention, the server includes means for allowing a user to input information on ideal appearance and personality settings, means for generating a virtual partner based on the input information on appearance and personality settings, means for storing a conversation history with the user and providing natural interaction, and means for making delivery suggestions based on the user's order information and conversation history, thereby enabling personalized delivery suggestions to be made to the user.

[0692] A "user" is someone who uses the system to interact with their ideal virtual partner and order and customize food.

[0693] "Appearance setting information" is information about the virtual partner's appearance, such as hairstyle, eye color, height, and build, set by the user.

[0694] "Personality setting information" is information about the inner qualities of the virtual partner set by the user, such as kindness, humor, knowledge, hobbies, etc.

[0695] A "virtual partner" is a digital character that is generated based on the user's settings information and with which the user can interact.

[0696] The "generation means" is a technology that has a function for generating a virtual partner based on information input by the user.

[0697] "Communication means" refers to technology that provides a function for realizing natural conversation between a virtual partner and a user and storing the conversation history.

[0698] "Order information" refers to information about the content that a user inputs when ordering or customizing food.

[0699] "Delivery Suggestion" is a function that suggests optimal foods and services to users based on their order information and conversation history.

[0700] A "generative AI model" is an artificial intelligence algorithm that generates images and responses of virtual partners based on the user's settings and conversations.

[0701] A "prompt" is an instruction or question that is input to a generative AI model to obtain a specific output.

[0702] This invention is a system that allows users to create a virtual partner with ideal appearance and personality, interact with them through natural conversation, and provide personalized suggestions for food delivery services. The system includes the following main means:

[0703] 1. Enter your user settings

[0704] The user starts a dedicated application installed on their smartphone and uses the interface to set the appearance (e.g., hairstyle, eye color, height, physique, etc.) and personality (e.g., kindness, humor, knowledge, hobbies, etc.) of their ideal virtual partner. This generates setting information.

[0705] 2. Generation of Virtual Partners

[0706] The smartphone sends the setting information entered by the user to the server. The server uses the generative AI model based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the smartphone and displayed to the user.

[0707] 3. Initiating and remembering conversations

[0708] The user speaks to the virtual partner generated on the device. For example, they might ask, "Good evening, what should I eat today?" The user's utterances are recorded as text data on the smartphone and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI model. For example, a response might be generated such as, "Why don't you order pizza today? We have recommended toppings." This generated response is sent to the smartphone and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[0709] 4. Continuous communication and suggestions

[0710] When the user launches the application again and continues the conversation with the virtual partner, the smartphone retrieves the user's past conversation history from the server. Based on the conversation history, the server provides delivery suggestions along with continuous, natural conversational responses. For example, in response to a user's question, "How was the pizza yesterday?", the server responds with, "Was the pizza delicious yesterday? Why not try the side dish next time?" In this way, more intimate and personalized suggestions are possible based on the user's preferences and past ordering history.

[0711] Hardware and software used

[0712] Hardware: Smartphone

[0713] Software: Python, OpenAI's GPT-3, image generation API

[0714] Specific examples

[0715] 1. Example of user settings

[0716] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[0717] 2. Example of Virtual Partner Generation

[0718] Smartphone: Sends configuration information to the server.

[0719] Server: Using a generative AI model, it generates an image of the virtual partner based on the settings information and sends it to the smartphone.

[0720] Smartphone: The generated image is displayed to the user.

[0721] 3. Example conversation

[0722] User: "I'm craving pizza today. What do you recommend?"

[0723] Smartphone: Sends the user's question to the server.

[0724] Server: Based on the conversation history, it generates a response such as, "You've been ordering Margherita pizza lately. Why not try a slightly spicy Diavolo today?" and sends it to your smartphone.

[0725] Smartphone: Display the response to the user.

[0726] Prompt Sentence Examples

[0727] "Generate natural conversational responses for your virtual partner based on the following text: User: I'm craving pizza today. What do you recommend? Virtual partner: You've been ordering Margherita pizzas lately. How about trying a slightly spicy Diavolo today?"

[0728] In this way, the system can provide users with personalized delivery suggestions as well as a more natural and realistic communication experience.

[0729] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0730] Step 1: The user launches a dedicated application on their smartphone. This application allows the user to input the appearance and personality settings of their ideal virtual partner through a user interface. Input data includes hairstyle, eye color, height, physique, kindness, humor, knowledge, hobbies, etc. The input information is then recorded on the device.

[0731] Step 2: The device sends the setting information entered by the user to the server. The data is sent to the server using a communication means. The server analyzes the received data and converts it into an appropriate format. This formatted data is provided as input to the image generation AI model.

[0732] Step 3: The server uses the image generation AI model based on the received data to generate image data of the virtual partner. The image generation AI model generates an image of the virtual partner based on the user's settings, and the generated image data is temporarily stored on the server. The generated data is then sent back to the device.

[0733] Step 4: The terminal displays the image data of the generated virtual partner received from the server on the user interface. The user can check the image of the generated virtual partner. Here, the virtual partner and the user can interact with each other.

[0734] Step 5: The user speaks to the virtual partner generated on the device. For example, the user types, "Hello, what should I eat today?" The user's speech is recorded as text data on the device and then sent to the server. The device sends the user's speech data to the server in text format.

[0735] Step 6: The server analyzes the received user utterance data and inputs it into the generative AI model to generate an appropriate response. Prompt sentences include "User: Hello, what should I eat today?" The generative AI model generates a response text based on the prompt sentence. For example, a response such as "How about ordering pizza today?" is generated. This generated response data is sent to the device.

[0736] Step 7: The terminal displays the response data received from the server on the user interface. The user can check the virtual partner's response and continue the conversation. At the same time, the server stores this exchange as a conversation history.

[0737] Step 8: When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the user's past conversation history, the server provides continuous, natural conversational responses, such as food delivery suggestions. For example, in response to the user's question, "How was the pizza yesterday?", a response such as "Was the pizza delicious yesterday? Why not try the side dish today?" is generated. This response is also sent to the device and displayed.

[0738] 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.

[0739] ---

[0740] This invention combines a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game and interact with them through natural conversation, with an emotion engine that recognizes the user's emotions. This system includes generation means, display means, communication means, and the emotion engine, and is realized through a user interface.

[0741] Entering configuration information

[0742] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies), which generates setting information according to the user's preferences.

[0743] Creating a Virtual Partner

[0744] The device sends the setting information entered by the user to the server. The server uses image generation AI based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[0745] Conversation initiation and memory

[0746] The user talks to the virtual partner created on the device, for example, asking, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server.

[0747] The server analyzes the received user speech data and uses a generation AI to generate an appropriate response text. For example, a response such as "Hello! I went for a walk today. How was it?" is generated. This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[0748] User Emotion Recognition

[0749] The emotion engine recognizes emotions from the user's speech and facial expression data. For example, if the user is smiling while speaking, the emotion "joy" is recognized. This allows the virtual partner's response to be adjusted to match the user's emotion. For example, if the user is angry, the virtual partner can ask, "Is something wrong?"

[0750] Ongoing exchanges

[0751] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the conversation history, the server uses an emotion engine to generate continuous, natural conversation responses. For example, if the user previously said "I'm tired," the server remembers this and generates a response such as "Did you sleep well last night?" In this way, the conversations between the user and the virtual partner are accumulated, enabling more intimate communication.

[0752] Specific examples

[0753] 1. Example of user settings

[0754] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[0755] 2. Example of Virtual Partner Generation

[0756] Terminal: Sends configuration information to the server.

[0757] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[0758] Terminal: displays the generated image to the user.

[0759] 3. Example conversation

[0760] User: Asks the generated partner, "How was your run yesterday?"

[0761] Terminal: Sends the user's question to the server.

[0762] Server: Based on the conversation history and emotion engine, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[0763] Terminal: displays the response to the user.

[0764] 4. Emotion recognition example

[0765] User: Smile while talking to your virtual partner.

[0766] Device: Sends the user's smile to the emotion engine via the camera function.

[0767] Server: The emotion engine recognizes "joy" and generates a response based on that.

[0768] In this way, the system provides the user with a more natural and realistic dating simulation experience, while also realizing responses that correspond to the user's emotions.

[0769] The processing flow will be explained below.

[0770] ---

[0771] Step 1:

[0772] Launching the application

[0773] User: Launches a dedicated application on the device.

[0774] Terminal: Displays the main screen of the application.

[0775] Step 2:

[0776] Ideal partner setting

[0777] Terminal: Displays an interface for the user to input their ideal appearance (hairstyle, eye color, height, etc.) and personality (kindness, humor, knowledge, etc.).

[0778] User: Follow the interface and enter the configuration information of your ideal partner.

[0779] Terminal: Manages the entered setting information.

[0780] Step 3:

[0781] Sending configuration information

[0782] Terminal: The setting information entered by the user is sent to the server in JSON format.

[0783] Step 4:

[0784] Receiving a Partner Generation Request

[0785] Server: Receives the setting information (JSON data) sent from the device.

[0786] Step 5:

[0787] Calling image generation AI

[0788] Server: Calls the image generation AI based on the received setting information and generates an image of a partner with the ideal appearance.

[0789] Step 6:

[0790] Sending the generated results

[0791] Server: Sends the generated partner image data back to the device.

[0792] Step 7:

[0793] Displaying partner images

[0794] Terminal: Displays the received image data to the user.

[0795] Step 8:

[0796] Start a conversation

[0797] User: Talk to the generated partner through the device.

[0798] Terminal: Records user comments as text data.

[0799] Step 9:

[0800] Sending conversation data

[0801] Terminal: Sends recorded user speech data to the server.

[0802] Step 10:

[0803] Generating conversational responses

[0804] Server: Analyzes the received user speech data and generates appropriate response text using a generative AI model.

[0805] Step 11:

[0806] User Emotion Recognition

[0807] Terminal: Collects the user's facial expression data using an accessible camera function and sends it to the emotion engine.

[0808] Server: The emotion engine recognizes emotions (e.g., joy, anger, sadness) based on the user's speech and facial expression data.

[0809] Step 12:

[0810] Response adjustment

[0811] Server: Adjusts the generated response text based on the user's perceived emotions. For example, if the user is determined to be tired, it generates a gentle response such as "Thank you for your hard work. Maybe you should take a rest today."

[0812] Step 13:

[0813] Sending a Generate Response

[0814] Server: Sends the tailored response text to the device.

[0815] Step 14:

[0816] Viewing the response

[0817] Terminal: Displays the response text received from the server to the user.

[0818] Step 15:

[0819] Save conversation history

[0820] Server: Stores the conversation history and recognized emotion data of the user and partner in a database.

[0821] Step 16:

[0822] Re-login

[0823] User: Relaunches the application on a daily basis and continues the conversation with the partner.

[0824] Terminal: Requests user information, past conversation history, and emotion data from the server.

[0825] Step 17:

[0826] Retrieving conversation history

[0827] Server: Retrieves the user's conversation history and emotion data from the database and sends them to the device.

[0828] Step 18:

[0829] Use of history

[0830] Terminal: Displays the received conversation history and emotion history on the screen, allowing the user to check past interactions and emotional states.

[0831] Step 19:

[0832] Continuing Conversation

[0833] User: Continue a new conversation with your partner while referring to the conversation history and emotion history.

[0834] Server: Receives new user utterances and uses stored history to generate more natural responses.

[0835] Step 20:

[0836] Generating a continuation response

[0837] Server: Again generates a conversation response and sends it to the terminal.

[0838] Terminal: displays the generated response to the user.

[0839] ---

[0840] The above is a detailed explanation of the program processing of a system that combines an emotion engine, broken down into specific steps.

[0841] Example 2

[0842] 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."

[0843] In conventional dating simulation systems, it was difficult for users to create their ideal virtual partner and engage in continuous interaction. Furthermore, the system lacked a realistic experience because it did not provide responses based on the user's emotions. Furthermore, it lacked a means to conduct natural, continuous dialogue based on past conversation history.

[0844] The specification processing 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 means for allowing the user to input ideal appearance and personality setting information, generation means for generating a virtual partner based on the input appearance and personality setting information, communication means for storing utterances made by the user to the generated virtual partner and providing natural interactions, emotion recognition means for collecting facial expressions and voice data of the user and recognizing emotions, and means for adjusting the responses of the virtual partner based on the emotion recognition results. This enables the user to have continuous, natural conversations with their ideal virtual partner according to their emotions.

[0845] "User" refers to an individual who uses the dating simulation system.

[0846] "Ideal appearance" refers to information about the appearance of a virtual partner set by the user.

[0847] "Personality setting information" refers to information about the personality and characteristics of the virtual partner set by the user.

[0848] "Virtual partner" refers to a digital character that is generated based on information set by the user.

[0849] "Generation means" refers to a function that generates a virtual partner based on setting information input by the user.

[0850] "Communication means" refers to a function that stores conversation history with the user and provides natural interaction.

[0851] "Emotion recognition means" refers to a function for collecting facial expressions and voice data of the user and recognizing emotions.

[0852] "Adjustment means" refers to the ability to adjust the virtual partner's responses based on perceived emotions.

[0853] "Server" refers to a central control unit that manages user preferences and conversation history, and provides virtual partner generation and response.

[0854] "Terminal" refers to a device through which a user accesses and operates the system.

[0855] "Conversation history" refers to data that records past interactions between a user and a virtual partner.

[0856] "Continuous interaction" refers to continuous and natural dialogue based on past conversation history.

[0857] "Response according to emotions" refers to a response from a virtual partner that is generated taking into account the user's emotions.

[0858] "Natural interaction" refers to dialogue that flows like a human conversation.

[0859] This invention combines a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game and interact with them through natural conversation, with an emotion engine that recognizes the user's emotions. This system includes generation means, display means, communication means, and the emotion engine, and is realized through a user interface.

[0860] Entering configuration information

[0861] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies), which generates setting information according to the user's preferences.

[0862] Creating a Virtual Partner

[0863] The device sends the setting information entered by the user to the server. The server uses an image generation AI model (e.g., DALL-E or GAN) based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[0864] Conversation initiation and memory

[0865] The user speaks to the virtual partner generated on the device. For example, they might ask, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI (e.g., GPT-4). For example, a response might be generated such as, "Hello! I went for a walk today. How was it for you?" This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[0866] User Emotion Recognition

[0867] The emotion engine recognizes emotions from the user's speech and facial expression data. For example, if the user is smiling while speaking, the emotion "joy" is recognized. This allows the virtual partner's response to be adjusted to match the user's emotion. For example, if the user is angry, the virtual partner can ask, "Is something wrong?"

[0868] Ongoing exchanges

[0869] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the conversation history, the server uses an emotion engine to generate continuous, natural conversation responses. For example, if the user previously said "I'm tired," the server remembers this and generates a response such as "Did you sleep well last night?" In this way, the conversations between the user and the virtual partner are accumulated, enabling more intimate communication.

[0870] Specific examples

[0871] 1. Example of user settings

[0872] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[0873] 2. Example of Virtual Partner Generation

[0874] Terminal: Sends configuration information to the server.

[0875] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[0876] Terminal: displays the generated image to the user.

[0877] 3. Example conversation

[0878] User: Asks the generated partner, "How was your run yesterday?"

[0879] Terminal: Sends the user's question to the server.

[0880] Server: Based on the conversation history and emotion engine, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[0881] Terminal: displays the response to the user.

[0882] 4. Emotion recognition example

[0883] User: Smile while talking to your virtual partner.

[0884] Device: Sends the user's smile to the emotion engine via the camera function.

[0885] Server: The emotion engine recognizes "joy" and generates a response based on that.

[0886] In this way, the system provides the user with a more natural and realistic love simulation experience, while also realizing responses that correspond to the user's emotions.

[0887] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0888] Step 1:

[0889] The user launches the dedicated application on their device and inputs their ideal appearance and personality through the interface. For example, they can select a character with black hair, blue eyes, a height of 180cm, an athletic body, and a kind and humorous personality. This input data is then saved on the device.

[0890] Input: User's ideal appearance and personality setting information (e.g., black hair, blue eyes, height 180 cm, athletic, kind, humorous)

[0891] Output: JSON data of configuration information

[0892] Specific behavior:

[0893] The user enters configuration information on the initial screen of the app.

[0894] The terminal converts the input data into JSON format and prepares it for the API request.

[0895] Step 2:

[0896] The device sends the setting information entered by the user to the server. The server uses an image generation AI model (e.g., GAN) based on the received setting information to generate image data of a virtual partner. The generated virtual partner data is then sent back to the device and displayed to the user.

[0897] Input: JSON data of setting information

[0898] Output: Image data of virtual partner

[0899] Specific behavior:

[0900] The device sends the configuration information to the server's API endpoint via a POST request.

[0901] The server inputs the prompt statement "A sportsman with black hair, blue eyes, and a height of 180 cm" into the generative AI model and generates image data.

[0902] The terminal displays the received image data on the user's screen.

[0903] Step 3:

[0904] The user speaks to the generated virtual partner via text or voice. For example, they might say, "Hello, how was your day?" The user's speech is recorded as text data on the device and sent to the server. The server analyzes the received user speech data, generates an appropriate response text using a generative AI model (e.g., GPT-4), and sends it back to the device. The device then displays the response to the user.

[0905] Input: User-spoken text (e.g., "Hello, how was your day?")

[0906] Output: Virtual partner's response text (e.g., "Hi! I went for a walk today. How was it for you?")

[0907] Specific behavior:

[0908] The user types "Hi, how was your day?" into the text box.

[0909] The device sends the entered text data to the server's API endpoint.

[0910] The server inputs a prompt sentence into the generative AI model and sends the generated response text back to the terminal.

[0911] The terminal displays the generated response to the user.

[0912] Step 4:

[0913] The device captures the user's facial expressions and voice data using a camera and microphone and sends it to the server, which then uses an emotion recognition engine to recognize the user's emotions from the captured data and adjusts the virtual partner's responses based on the results.

[0914] Input: User facial expression images or voice data

[0915] Output: Emotion recognition results and tailored response text

[0916] Specific behavior:

[0917] The user smiles during the conversation.

[0918] The device captures the user's facial expressions with a camera and sends them to the server.

[0919] The server analyzes the captured data using an emotion recognition engine, recognizes the emotion "joy," and generates a response based on the result: "You look happy. Did something good happen?"

[0920] The terminal displays the generated response to the user.

[0921] Step 5:

[0922] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the past conversation history from the server. Based on the conversation history, the server uses the generative AI model and emotion engine to generate continuous, natural-sounding conversation responses and send them to the device. The device then displays the responses to the user.

[0923] Input: User ID, past conversation history

[0924] Output: Natural conversational response text

[0925] Specific behavior:

[0926] The user restarts the app and types, "I'm curious to know what happened next from yesterday."

[0927] The device sends the user ID to the server and requests past conversation history.

[0928] The server references the conversation history and generates a response such as, "You said you were tired. Did you get enough rest?"

[0929] The terminal displays the generated response to the user.

[0930] The above are the processing steps of the program for this system.

[0931] (Application example 2)

[0932] 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."

[0933] The present invention relates to a system that allows users to have natural conversations with a virtual partner that reflects the user's ideal appearance and personality, and provides responses that correspond to the user's emotions. Conventional systems lack the ability to recognize the user's emotions, making it difficult to respond to emotions in real time. There has also been a demand for a system that enables a more realistic experience by expanding the interaction scene with the virtual partner to a virtual store. The objective of this system is to provide an environment in which users can enjoy deeper interactions in virtual space.

[0934] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0935] In this invention, the server includes means for allowing a user to input ideal appearance and personality setting information, means for generating a virtual partner based on the input appearance and personality setting information, means for recognizing emotions from the user's facial expression data, and means for realizing a dialogue between the generated virtual partner and the user in a virtual store. This not only allows the user to enjoy natural dialogue with their ideal virtual partner, but also enables a realistic experience in the virtual store, and makes it possible to provide responses that correspond to the user's emotions.

[0936] "Means enabling users to input ideal appearance and personality setting information" refers to a function that provides an interface for users to specifically customize the appearance and personality of their virtual partner based on their own preferences.

[0937] The "generation means for generating a virtual partner based on input appearance and personality setting information" refers to an algorithm and system for automatically generating the appearance and personality of a virtual partner based on setting information provided by the user.

[0938] "A communication method that remembers conversation history with the user and provides natural interactions" is a system that records the content of past conversations the user has had with a virtual partner and enables more natural and continuous conversations based on that history.

[0939] The "emotion recognition means for recognizing emotions from user's facial expression data" is a function that analyzes the user's facial expressions in real time and identifies the user's current emotional state (such as joy or sadness) from those expressions.

[0940] "Means for enabling interaction between the generated virtual partner and the user within a virtual store" refers to a function that enables direct interaction between the virtual partner and the user within a virtual space, and an example of such a space is a virtual store.

[0941] "Means for generating virtual partner responses using a generative AI model" refers to methods and systems for using a generative AI model (e.g., GPT-3) to generate virtual partner responses to user input.

[0942] "Means for inputting prompt sentences into a generative AI model to obtain an appropriate response" refers to the process of creating a text sentence (prompt sentence) to query the generative AI model so that the virtual partner can respond appropriately to what the user says, and obtaining a response based on that.

[0943] MODE FOR CARRYING OUT THE INVENTION

[0944] This invention combines a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game and interact with them through natural conversation, with an emotion engine that recognizes the user's emotions. This system includes generation means, display means, communication means, emotion recognition means, and means for realizing dialogue within a virtual store, and is realized through a user interface.

[0945] composition

[0946] The system consists of the following elements:

[0947] 1. User interface: An interface where the user inputs information about their ideal appearance and personality.

[0948] 2. Generator: A generative AI model for generating virtual partners based on input information.

[0949] 3. Display means: a display device for displaying an image of the virtual partner to the user.

[0950] 4. Communication tools: A generative AI model that remembers conversation history with the user and provides natural interactions.

[0951] 5. Emotion recognition means: A camera and analysis engine for recognizing emotions from the user's facial expression data.

[0952] 6. Means for realizing interaction within a virtual store: An environment that enables interaction within a virtual space.

[0953] Example Details

[0954] Entering configuration information

[0955] Users launch a dedicated application on their smartphone and use the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies).

[0956] Creating a Virtual Partner

[0957] The device sends the setting information entered by the user to the server. The server uses a generative AI model based on the received setting information to generate image data of a virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[0958] Conversation initiation and memory

[0959] The user speaks to the virtual partner generated on the device. For example, they might ask, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI model. For example, a response might be "Hello! I went for a walk today. How was it for you?" This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[0960] User Emotion Recognition

[0961] The emotion recognition means uses the smartphone's camera to acquire data on the user's facial expressions, and the analysis engine uses that data to recognize the user's emotions. For example, if the user is smiling while speaking, the emotion "joy" is recognized. This allows the virtual partner's response to be adjusted to match the user's emotions. For example, if the user is angry, the virtual partner can ask, "Is something wrong?"

[0962] Interactions in a virtual store

[0963] Users can enjoy interacting with virtual partners in a virtual store. In the virtual store, the virtual partners can introduce products to users and they can enjoy the virtual store together. This allows users to feel a more realistic experience in the virtual space.

[0964] Specific examples of use

[0965] 1. Example of user settings:

[0966] Through the application, users select a partner who is "black-haired, blue-eyed, 180cm tall, athletic," and "kind and humorous."

[0967] 2. Example of Virtual Partner Generation:

[0968] Terminal: Sends configuration information to the server.

[0969] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[0970] Terminal: displays the generated image to the user.

[0971] 3. Example conversation:

[0972] User: "Hi, how was your day?"

[0973] Server: Based on the conversation history and the generative AI model, it generates a response such as "Hello! I went for a walk today. How was it?" and sends it to the device.

[0974] 4. Emotion Recognition Example:

[0975] User: Smile while talking to your virtual partner.

[0976] Server: The emotion recognition engine recognizes "happiness" and generates a response based on that.

[0977] Example prompt for a generative AI model:

[0978] "Generate an image of a person with black hair, blue eyes, and a height of 180 cm, who has a kind and humorous personality."

[0979] In this way, the system provides users with a more natural and realistic love simulation experience, while also enabling dialogue within the virtual store and responses that reflect the user's emotions.

[0980] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0981] Step 1:

[0982] Users start the dedicated application on their smartphone and use the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies). The input data is temporarily recorded on the device.

[0983] Input: User's appearance and personality settings

[0984] Output: Recorded setting information data

[0985] Step 2:

[0986] The device sends the setting information entered by the user to the server. The server uses the generative AI model based on the received setting information to generate image data of the virtual partner. The generated image data is then sent back from the server to the device.

[0987] Input: Setting information data

[0988] Output: Image data of virtual partner

[0989] Step 3:

[0990] The terminal that acquires the image data of the virtual partner displays the image to the user, who can then talk to the displayed virtual partner.

[0991] Input: Image data of virtual partner

[0992] Output: Image displayed to the user

[0993] Step 4:

[0994] When a user speaks to a virtual partner, the device records the speech as text data and sends it to the server. The server analyzes the received speech data and generates an appropriate response text using a generative AI model. The generated response text is then sent from the server to the device.

[0995] Input: User's comment text data

[0996] Output: Virtual partner's response text data

[0997] Step 5:

[0998] The terminal displays the virtual partner's response text data received from the server to the user, and the server simultaneously stores this exchange as a conversation history.

[0999] Input: Virtual partner's response text data

[1000] Output: Display response text to user, record conversation history

[1001] Step 6:

[1002] The user's facial expression data is acquired using the smartphone camera, and the acquired data is analyzed using emotion recognition means. Based on the analysis results, the user's emotions are recognized and emotion data is generated.

[1003] Input: User's facial expression data

[1004] Output: User emotion data

[1005] Step 7:

[1006] The server uses the emotion data to input prompt sentences into the generative AI model, which generates a response that matches the user's emotion. The generated response is then sent from the server to the device, which then displays the response to the user.

[1007] Input: User emotion data, prompt sentence

[1008] Output: Emotion-adjusted text data of the virtual partner's responses, displayed to the user

[1009] Step 8:

[1010] When a conversation with a user takes place in a virtual store, the virtual partner will have a natural conversation based on a scenario of actions in the virtual store, product introductions, etc. The server generates a response based on this scenario and sends it to the terminal, providing a realistic experience in the virtual store.

[1011] Input: Scenario information in the virtual store, user dialogue text data

[1012] Output: Text data of the virtual partner's response based on the scenario, displayed to the user

[1013] These processing steps allow users to enjoy natural and emotionally responsive interactions with their ideal virtual partner, and also provide a realistic experience within the virtual store.

[1014] 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.

[1015] 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.

[1016] 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.

[1017] [Third embodiment]

[1018] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1019] 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.

[1020] 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).

[1021] 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.

[1022] 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.

[1023] 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).

[1024] 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.

[1025] 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.

[1026] 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.

[1027] 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.

[1028] 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.

[1029] 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."

[1030] ---

[1031] This invention is a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game, and interact with them through natural conversation. This system includes a generation means, a display means, and a communication means, and is realized through a user interface.

[1032] Entering configuration information

[1033] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies), which generates setting information according to the user's preferences.

[1034] Creating a Virtual Partner

[1035] The device sends the setting information entered by the user to the server. The server uses image generation AI based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[1036] Conversation initiation and memory

[1037] The user talks to the virtual partner created on the device, for example, asking, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server.

[1038] The server analyzes the received user speech data and uses a generation AI to generate an appropriate response text. For example, a response such as "Hello! I went running today. How was it?" is generated. This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[1039] Ongoing exchanges

[1040] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. The server generates continuous, natural conversation responses based on the conversation history. For example, in response to the user's question, "How was your run yesterday?", the server responds, "I ran 5km yesterday. It felt great!" In this way, the conversations between the user and the virtual partner are accumulated, enabling more intimate communication.

[1041] Specific examples

[1042] 1. Example of user settings

[1043] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[1044] 2. Example of Virtual Partner Generation

[1045] Terminal: Sends configuration information to the server.

[1046] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[1047] Terminal: displays the generated image to the user.

[1048] 3. Example conversation

[1049] User: Asks the generated partner, "How was your run yesterday?"

[1050] Terminal: Sends the user's question to the server.

[1051] Server: Based on the conversation history, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[1052] Terminal: displays the response to the user.

[1053] In this way, the system can provide users with a more natural and realistic dating simulation experience.

[1054] ---

[1055] The processing flow will be explained below.

[1056] ---

[1057] Step 1:

[1058] Launching the application

[1059] User: Launches a dedicated application on the device.

[1060] Terminal: Displays the main screen of the application.

[1061] Step 2:

[1062] Ideal partner setting

[1063] Terminal: Displays an interface for the user to input their ideal appearance (hairstyle, eye color, height, etc.) and personality (kindness, humor, knowledge, etc.).

[1064] User: Follow the interface and enter the configuration information of your ideal partner.

[1065] Terminal: Manages the entered setting information.

[1066] Step 3:

[1067] Sending configuration information

[1068] Terminal: The setting information entered by the user is sent to the server in JSON format.

[1069] Step 4:

[1070] Receiving a Partner Generation Request

[1071] Server: Receives the setting information (JSON data) sent from the device.

[1072] Step 5:

[1073] Calling image generation AI

[1074] Server: Based on the received setting information, the image generation AI is called and an image of a partner with the ideal appearance is generated.

[1075] Step 6:

[1076] Sending the generated results

[1077] Server: Sends the generated partner image data back to the device.

[1078] Step 7:

[1079] Displaying partner images

[1080] Terminal: Displays the received image data to the user.

[1081] Step 8:

[1082] Start a conversation

[1083] User: Talk to the generated partner through the device.

[1084] Terminal: Records user comments as text data.

[1085] Step 9:

[1086] Sending conversation data

[1087] Terminal: Sends recorded user speech data to the server.

[1088] Step 10:

[1089] Generating conversational responses

[1090] Server: Analyzes the received user speech data and generates appropriate response text using a generative AI model.

[1091] Step 11:

[1092] Sending a Generate Response

[1093] Server: Sends the generated response text to the terminal.

[1094] Step 12:

[1095] Viewing the response

[1096] Terminal: Displays the response text received from the server to the user.

[1097] Step 13:

[1098] Save conversation history

[1099] Server: Stores the conversation history between the user and the partner in a database.

[1100] Step 14:

[1101] Re-login

[1102] User: Relaunches the application on a daily basis and continues the conversation with the partner.

[1103] Device: Requests user information and past conversation history from the server.

[1104] Step 15:

[1105] Retrieving conversation history

[1106] Server: Retrieves the user's conversation history from the database and sends it to the terminal.

[1107] Step 16:

[1108] Use of history

[1109] Device: Displays the received conversation history on the screen, allowing the user to review past interactions.

[1110] Step 17:

[1111] Continuing Conversation

[1112] User: Continue a new conversation with your partner while referring to your conversation history.

[1113] Server: Receives new user utterances and uses stored history to generate more natural responses.

[1114] Step 18:

[1115] Generating a continuation response

[1116] Server: Again generates a conversation response and sends it to the terminal.

[1117] Terminal: displays the generated response to the user.

[1118] ---

[1119] The above is a detailed explanation of the system program processing divided into specific steps.

[1120] Example 1

[1121] 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."

[1122] Conventional dating simulation games have had difficulty in flexibly generating characters according to user preferences. They also have had issues with not being able to realize natural conversations, limiting the user experience. Furthermore, they lacked a mechanism for deepening relationships with users through ongoing conversations.

[1123] 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.

[1124] In this invention, the server includes means for allowing a user to input ideal appearance and personality setting information, means for transmitting the input appearance and personality setting information to the server, means for generating a virtual partner based on the input appearance and personality setting information, means for receiving image data of the generated virtual partner from the server, means for displaying image data of the generated virtual partner, means for recording user utterances on the terminal and transmitting them to the server, communication means for storing a conversation history with the user and providing natural conversation using a generative AI model, means for receiving conversation responses generated from the server, means for displaying the received conversation responses, and means for providing continuous conversation based on the past conversation history, thereby enabling character generation according to user preferences and natural conversation exchange.

[1125] "User" refers to a person who utilizes the system to generate and interact with an ideal virtual partner.

[1126] "Terminal" refers to a device operated by a user that runs dedicated applications to generate and interact with virtual partners.

[1127] "Server" refers to a central control device that receives setting information sent by a user, generates a virtual partner, and responds to conversations.

[1128] "Ideal appearance and personality setting information" refers to information that the user specifically inputs about the appearance and personality traits that the user desires in a virtual partner.

[1129] "Virtual partner" refers to a fictional character that is generated based on the user's setting information.

[1130] "Generative AI model" refers to artificial intelligence (AI) technology that generates images and conversational responses of virtual partners based on user settings.

[1131] A "prompt sentence" is text information input to a generative AI model to provide instructions on the virtual partner's characteristics and conversation content.

[1132] "Image Data" refers to data in digital form that represents a visual representation of a virtual partner generated by a generative AI model.

[1133] "Utterance data" refers to the recorded text of what the user says to the virtual partner.

[1134] "Conversation history" refers to a record of past interactions between a user and a virtual partner.

[1135] "Communication means" refers to the functions and processes necessary for natural interaction between the user and the virtual partner.

[1136] "Continuous conversation" refers to an ongoing dialogue between a virtual partner and a user based on past dialogue history.

[1137] This invention is a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game, and interact with them through natural conversation. This system includes a generation means, a display means, and a communication means, and is realized through a user interface.

[1138] Entering configuration information

[1139] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies). For example, the user may set a partner who is "black hair, blue eyes, 180cm tall, athletic," and "kind and humorous." This generates setting information that matches the user's preferences.

[1140] Creating a Virtual Partner

[1141] The device sends the setting information entered by the user to the server. The server uses an image generation AI (e.g., DALL-E, Stable Diffusion) based on the received setting information to generate image data for the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[1142] Conversation initiation and memory

[1143] The user speaks to the virtual partner generated on the device. For example, they might ask, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI (e.g., GPT-3). For example, a response might be generated such as, "Hello! I went for a run today. How was it for you?" This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[1144] Ongoing exchanges

[1145] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. The server generates continuous, natural conversation responses based on the conversation history. For example, if the user asks, "How was your run yesterday?", the server may respond, based on the past conversation history, with, "I ran 5km yesterday. It felt great!" In this way, the conversation between the user and the virtual partner is accumulated, enabling more intimate communication.

[1146] Specific examples

[1147] 1. Example of user settings

[1148] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[1149] 2. Example of Virtual Partner Generation

[1150] Terminal: Sends configuration information to the server.

[1151] Server: Image generation AI (e.g., Stable Diffusion) generates an image of the virtual partner based on the configuration information and sends it to the device.

[1152] Terminal: displays the generated image to the user.

[1153] 3. Example conversation

[1154] User: Asks the generated partner, "How was your run yesterday?"

[1155] Terminal: Sends the user's question to the server.

[1156] Server: Based on the conversation history, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[1157] Terminal: displays the response to the user.

[1158] In this way, the system can provide users with a more natural and realistic dating simulation experience.

[1159] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1160] Step 1:

[1161] The user launches the dedicated application on the device. At this time, an interface appears on the device's display, allowing the user to input the appearance and personality settings of their ideal virtual partner. Through this interface, the user inputs settings that suit their preferences. Specific inputs include "black hair, blue eyes, an athletic man who is 180 cm tall," as well as "kind and humorous." This input information is temporarily recorded on the device.

[1162] Step 2:

[1163] The device sends the setting information entered by the user to the server. The transmitted data includes the appearance and personality setting information entered by the user. When the server receives this setting information, it automatically prepares to input the setting information as a prompt to the image generation AI (e.g., DALL-E, Stable Diffusion). This prompt includes the specific characteristics desired by the user.

[1164] Step 3:

[1165] The server uses image generation AI based on the received setting information to generate image data of a virtual partner. A prompt such as "black hair, blue eyes, 180cm tall, athletic, kind and humorous" is input into the generation AI model. The image generation AI outputs an image of a partner with the specified characteristics according to this prompt. This image data is generated on the server side.

[1166] Step 4:

[1167] The generated image data of the virtual partner is sent from the server to the terminal. The terminal displays the received image data on the user interface. This display allows the user to check the visual appearance of the virtual partner based on the information set by the user.

[1168] Step 5:

[1169] The user starts a conversation with the virtual partner generated on the terminal. For example, the user enters "Hello, how was your day?" This utterance is recorded as text data on the terminal. The recorded text data is then sent by the terminal to the server.

[1170] Step 6:

[1171] The server analyzes the received user utterance data and calls a generative AI model (e.g., GPT-3). The utterance data is input to the generative AI model as a prompt sentence. For example, the user asks the virtual partner, "Hello, how was your day?" The generative AI model generates an appropriate response text (e.g., "Hello! I went for a run today. How was it for you?"). This response text is generated by the server.

[1172] Step 7:

[1173] The server sends the generated response to the terminal, which displays the received response text on the user interface, allowing the user to check the response from the virtual partner.

[1174] Step 8:

[1175] The server stores a conversation history with the user, including what the user said and the responses generated, allowing future conversations to reference past interactions.

[1176] Step 9:

[1177] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the conversation history, the server generates continuous, natural conversation responses. For example, in response to the question, "How was your run yesterday?", the server responds, "I ran 5km yesterday. It felt great!" This response text is generated and sent to the device.

[1178] Step 10:

[1179] The device then displays the received response on the user interface, allowing the user to enjoy a continuous dialogue based on the past conversation history.

[1180] As described above, this system can provide users with a more natural and realistic dating simulation experience.

[1181] (Application example 1)

[1182] 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."

[1183] Current food delivery services face the challenge of providing personalized suggestions that fully take into account the user's individual preferences and background information, resulting in a limited user experience. In particular, providing more intimate and effective services to users through personalized suggestions in food delivery is a challenge.

[1184] 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.

[1185] In this invention, the server includes means for allowing a user to input information on ideal appearance and personality settings, means for generating a virtual partner based on the input information on appearance and personality settings, means for storing a conversation history with the user and providing natural interaction, and means for making delivery suggestions based on the user's order information and conversation history, thereby enabling personalized delivery suggestions to be made to the user.

[1186] A "user" is someone who uses the system to interact with their ideal virtual partner and order and customize food.

[1187] "Appearance setting information" is information about the virtual partner's appearance, such as hairstyle, eye color, height, and build, set by the user.

[1188] "Personality setting information" is information about the inner qualities of the virtual partner set by the user, such as kindness, humor, knowledge, hobbies, etc.

[1189] A "virtual partner" is a digital character that is generated based on the user's settings information and with which the user can interact.

[1190] The "generation means" is a technology that has a function for generating a virtual partner based on information input by the user.

[1191] "Communication means" refers to technology that provides a function for realizing natural conversation between a virtual partner and a user and storing the conversation history.

[1192] "Order information" refers to information about the content that a user inputs when ordering or customizing food.

[1193] "Delivery Suggestion" is a function that suggests optimal foods and services to users based on their order information and conversation history.

[1194] A "generative AI model" is an artificial intelligence algorithm that generates images and responses of virtual partners based on the user's settings and conversations.

[1195] A "prompt" is an instruction or question that is input to a generative AI model to obtain a specific output.

[1196] This invention is a system that allows users to create a virtual partner with ideal appearance and personality, interact with them through natural conversation, and provide personalized suggestions for food delivery services. The system includes the following main means:

[1197] 1. Enter your user settings

[1198] The user starts a dedicated application installed on their smartphone and uses the interface to set the appearance (e.g., hairstyle, eye color, height, physique, etc.) and personality (e.g., kindness, humor, knowledge, hobbies, etc.) of their ideal virtual partner. This generates setting information.

[1199] 2. Generation of Virtual Partners

[1200] The smartphone sends the setting information entered by the user to the server. The server uses the generative AI model based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the smartphone and displayed to the user.

[1201] 3. Initiating and remembering conversations

[1202] The user speaks to the virtual partner generated on the device. For example, they might ask, "Good evening, what should I eat today?" The user's utterances are recorded as text data on the smartphone and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI model. For example, a response might be generated such as, "Why don't you order pizza today? We have recommended toppings." This generated response is sent to the smartphone and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[1203] 4. Continuous communication and suggestions

[1204] When the user launches the application again and continues the conversation with the virtual partner, the smartphone retrieves the user's past conversation history from the server. Based on the conversation history, the server provides delivery suggestions along with continuous, natural conversational responses. For example, in response to a user's question, "How was the pizza yesterday?", the server responds with, "Was the pizza delicious yesterday? Why not try the side dish next time?" In this way, more intimate and personalized suggestions are possible based on the user's preferences and past ordering history.

[1205] Hardware and software used

[1206] Hardware: Smartphone

[1207] Software: Python, OpenAI's GPT-3, image generation API

[1208] Specific examples

[1209] 1. Example of user settings

[1210] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[1211] 2. Example of Virtual Partner Generation

[1212] Smartphone: Sends configuration information to the server.

[1213] Server: Using a generative AI model, it generates an image of the virtual partner based on the settings information and sends it to the smartphone.

[1214] Smartphone: The generated image is displayed to the user.

[1215] 3. Example conversation

[1216] User: "I'm craving pizza today. What do you recommend?"

[1217] Smartphone: Sends the user's question to the server.

[1218] Server: Based on the conversation history, it generates a response such as, "You've been ordering Margherita pizza lately. Why not try a slightly spicy Diavolo today?" and sends it to your smartphone.

[1219] Smartphone: Display the response to the user.

[1220] Prompt Sentence Examples

[1221] "Generate natural conversational responses for your virtual partner based on the following text: User: I'm craving pizza today. What do you recommend? Virtual partner: You've been ordering Margherita pizzas lately. How about trying a slightly spicy Diavolo today?"

[1222] In this way, the system can provide users with personalized delivery suggestions as well as a more natural and realistic communication experience.

[1223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1224] Step 1: The user launches a dedicated application on their smartphone. This application allows the user to input the appearance and personality settings of their ideal virtual partner through a user interface. Input data includes hairstyle, eye color, height, physique, kindness, humor, knowledge, hobbies, etc. The input information is then recorded on the device.

[1225] Step 2: The device sends the setting information entered by the user to the server. The data is sent to the server using a communication means. The server analyzes the received data and converts it into an appropriate format. This formatted data is provided as input to the image generation AI model.

[1226] Step 3: The server uses the image generation AI model based on the received data to generate image data of the virtual partner. The image generation AI model generates an image of the virtual partner based on the user's settings, and the generated image data is temporarily stored on the server. The generated data is then sent back to the device.

[1227] Step 4: The terminal displays the image data of the generated virtual partner received from the server on the user interface. The user can check the image of the generated virtual partner. Here, the virtual partner and the user can interact with each other.

[1228] Step 5: The user speaks to the virtual partner generated on the device. For example, the user types, "Hello, what should I eat today?" The user's speech is recorded as text data on the device and then sent to the server. The device sends the user's speech data to the server in text format.

[1229] Step 6: The server analyzes the received user utterance data and inputs it into the generative AI model to generate an appropriate response. Prompt sentences include "User: Hello, what should I eat today?" The generative AI model generates a response text based on the prompt sentence. For example, a response such as "How about ordering pizza today?" is generated. This generated response data is sent to the device.

[1230] Step 7: The terminal displays the response data received from the server on the user interface. The user can check the virtual partner's response and continue the conversation. At the same time, the server stores this exchange as a conversation history.

[1231] Step 8: When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the user's past conversation history, the server provides continuous, natural conversational responses, such as food delivery suggestions. For example, in response to the user's question, "How was the pizza yesterday?", a response such as "Was the pizza delicious yesterday? Why not try the side dish today?" is generated. This response is also sent to the device and displayed.

[1232] 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.

[1233] ---

[1234] This invention combines a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game and interact with them through natural conversation, with an emotion engine that recognizes the user's emotions. This system includes generation means, display means, communication means, and the emotion engine, and is realized through a user interface.

[1235] Entering configuration information

[1236] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies), which generates setting information according to the user's preferences.

[1237] Creating a Virtual Partner

[1238] The device sends the setting information entered by the user to the server. The server uses image generation AI based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[1239] Conversation initiation and memory

[1240] The user talks to the virtual partner created on the device, for example, asking, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server.

[1241] The server analyzes the received user speech data and uses a generation AI to generate an appropriate response text. For example, a response such as "Hello! I went for a walk today. How was it?" is generated. This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[1242] User Emotion Recognition

[1243] The emotion engine recognizes emotions from the user's speech and facial expression data. For example, if the user is smiling while speaking, the emotion "joy" is recognized. This allows the virtual partner's response to be adjusted to match the user's emotion. For example, if the user is angry, the virtual partner can ask, "Is something wrong?"

[1244] Ongoing exchanges

[1245] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the conversation history, the server uses an emotion engine to generate continuous, natural conversation responses. For example, if the user previously said "I'm tired," the server remembers this and generates a response such as "Did you sleep well last night?" In this way, the conversations between the user and the virtual partner are accumulated, enabling more intimate communication.

[1246] Specific examples

[1247] 1. Example of user settings

[1248] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[1249] 2. Example of Virtual Partner Generation

[1250] Terminal: Sends configuration information to the server.

[1251] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[1252] Terminal: displays the generated image to the user.

[1253] 3. Example conversation

[1254] User: Asks the generated partner, "How was your run yesterday?"

[1255] Terminal: Sends the user's question to the server.

[1256] Server: Based on the conversation history and emotion engine, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[1257] Terminal: displays the response to the user.

[1258] 4. Emotion recognition example

[1259] User: Smile while talking to your virtual partner.

[1260] Device: Sends the user's smile to the emotion engine via the camera function.

[1261] Server: The emotion engine recognizes "joy" and generates a response based on that.

[1262] In this way, the system provides the user with a more natural and realistic dating simulation experience, while also realizing responses that correspond to the user's emotions.

[1263] The processing flow will be explained below.

[1264] ---

[1265] Step 1:

[1266] Launching the application

[1267] User: Launches a dedicated application on the device.

[1268] Terminal: Displays the main screen of the application.

[1269] Step 2:

[1270] Ideal partner setting

[1271] Terminal: Displays an interface for the user to input their ideal appearance (hairstyle, eye color, height, etc.) and personality (kindness, humor, knowledge, etc.).

[1272] User: Follow the interface and enter the configuration information of your ideal partner.

[1273] Terminal: Manages the entered setting information.

[1274] Step 3:

[1275] Sending configuration information

[1276] Terminal: The setting information entered by the user is sent to the server in JSON format.

[1277] Step 4:

[1278] Receiving a Partner Generation Request

[1279] Server: Receives the setting information (JSON data) sent from the device.

[1280] Step 5:

[1281] Calling image generation AI

[1282] Server: Calls the image generation AI based on the received setting information and generates an image of a partner with the ideal appearance.

[1283] Step 6:

[1284] Sending the generated results

[1285] Server: Sends the generated partner image data back to the device.

[1286] Step 7:

[1287] Displaying partner images

[1288] Terminal: Displays the received image data to the user.

[1289] Step 8:

[1290] Start a conversation

[1291] User: Talk to the generated partner through the device.

[1292] Terminal: Records user comments as text data.

[1293] Step 9:

[1294] Sending conversation data

[1295] Terminal: Sends recorded user speech data to the server.

[1296] Step 10:

[1297] Generating conversational responses

[1298] Server: Analyzes the received user speech data and generates appropriate response text using a generative AI model.

[1299] Step 11:

[1300] User Emotion Recognition

[1301] Terminal: Collects the user's facial expression data using an accessible camera function and sends it to the emotion engine.

[1302] Server: The emotion engine recognizes emotions (e.g., joy, anger, sadness) based on the user's speech and facial expression data.

[1303] Step 12:

[1304] Response adjustment

[1305] Server: Adjusts the generated response text based on the user's perceived emotions. For example, if the user is determined to be tired, it generates a gentle response such as "Thank you for your hard work. Maybe you should take a rest today."

[1306] Step 13:

[1307] Sending a Generate Response

[1308] Server: Sends the tailored response text to the device.

[1309] Step 14:

[1310] Viewing the response

[1311] Terminal: Displays the response text received from the server to the user.

[1312] Step 15:

[1313] Save conversation history

[1314] Server: Stores the conversation history and recognized emotion data of the user and partner in a database.

[1315] Step 16:

[1316] Re-login

[1317] User: Relaunches the application on a daily basis and continues the conversation with the partner.

[1318] Terminal: Requests user information, past conversation history, and emotion data from the server.

[1319] Step 17:

[1320] Retrieving conversation history

[1321] Server: Retrieves the user's conversation history and emotion data from the database and sends them to the device.

[1322] Step 18:

[1323] Use of history

[1324] Terminal: Displays the received conversation history and emotion history on the screen, allowing the user to check past interactions and emotional states.

[1325] Step 19:

[1326] Continuing Conversation

[1327] User: Continue a new conversation with your partner while referring to the conversation history and emotion history.

[1328] Server: Receives new user utterances and uses stored history to generate more natural responses.

[1329] Step 20:

[1330] Generating a continuation response

[1331] Server: Again generates a conversation response and sends it to the terminal.

[1332] Terminal: displays the generated response to the user.

[1333] ---

[1334] The above is a detailed explanation of the program processing of a system that combines an emotion engine, broken down into specific steps.

[1335] Example 2

[1336] 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."

[1337] In conventional dating simulation systems, it was difficult for users to create their ideal virtual partner and engage in continuous interaction. Furthermore, the system lacked a realistic experience because it did not provide responses based on the user's emotions. Furthermore, it lacked a means to conduct natural, continuous dialogue based on past conversation history.

[1338] The specification processing 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 means for allowing the user to input ideal appearance and personality setting information, generation means for generating a virtual partner based on the input appearance and personality setting information, communication means for storing utterances made by the user to the generated virtual partner and providing natural interactions, emotion recognition means for collecting facial expressions and voice data of the user and recognizing emotions, and means for adjusting the responses of the virtual partner based on the emotion recognition results. This enables the user to have continuous, natural conversations with their ideal virtual partner according to their emotions.

[1339] "User" refers to an individual who uses the dating simulation system.

[1340] "Ideal appearance" refers to information about the appearance of a virtual partner set by the user.

[1341] "Personality setting information" refers to information about the personality and characteristics of the virtual partner set by the user.

[1342] "Virtual partner" refers to a digital character that is generated based on information set by the user.

[1343] "Generation means" refers to a function that generates a virtual partner based on setting information input by the user.

[1344] "Communication means" refers to a function that stores conversation history with the user and provides natural interaction.

[1345] "Emotion recognition means" refers to a function for collecting facial expressions and voice data of the user and recognizing emotions.

[1346] "Adjustment means" refers to the ability to adjust the virtual partner's responses based on perceived emotions.

[1347] "Server" refers to a central control unit that manages user preferences and conversation history, and provides virtual partner generation and response.

[1348] "Terminal" refers to a device through which a user accesses and operates the system.

[1349] "Conversation history" refers to data that records past interactions between a user and a virtual partner.

[1350] "Continuous interaction" refers to continuous and natural dialogue based on past conversation history.

[1351] "Response according to emotions" refers to a response from a virtual partner that is generated taking into account the user's emotions.

[1352] "Natural interaction" refers to dialogue that flows like a human conversation.

[1353] This invention combines a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game and interact with them through natural conversation, with an emotion engine that recognizes the user's emotions. This system includes generation means, display means, communication means, and the emotion engine, and is realized through a user interface.

[1354] Entering configuration information

[1355] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies), which generates setting information according to the user's preferences.

[1356] Creating a Virtual Partner

[1357] The device sends the setting information entered by the user to the server. The server uses an image generation AI model (e.g., DALL-E or GAN) based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[1358] Conversation initiation and memory

[1359] The user speaks to the virtual partner generated on the device. For example, they might ask, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI (e.g., GPT-4). For example, a response might be generated such as, "Hello! I went for a walk today. How was it for you?" This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[1360] User Emotion Recognition

[1361] The emotion engine recognizes emotions from the user's speech and facial expression data. For example, if the user is smiling while speaking, the emotion "joy" is recognized. This allows the virtual partner's response to be adjusted to match the user's emotion. For example, if the user is angry, the virtual partner can ask, "Is something wrong?"

[1362] Ongoing exchanges

[1363] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the conversation history, the server uses an emotion engine to generate continuous, natural conversation responses. For example, if the user previously said "I'm tired," the server remembers this and generates a response such as "Did you sleep well last night?" In this way, the conversations between the user and the virtual partner are accumulated, enabling more intimate communication.

[1364] Specific examples

[1365] 1. Example of user settings

[1366] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[1367] 2. Example of Virtual Partner Generation

[1368] Terminal: Sends configuration information to the server.

[1369] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[1370] Terminal: displays the generated image to the user.

[1371] 3. Example conversation

[1372] User: Asks the generated partner, "How was your run yesterday?"

[1373] Terminal: Sends the user's question to the server.

[1374] Server: Based on the conversation history and emotion engine, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[1375] Terminal: displays the response to the user.

[1376] 4. Emotion recognition example

[1377] User: Smile while talking to your virtual partner.

[1378] Device: Sends the user's smile to the emotion engine via the camera function.

[1379] Server: The emotion engine recognizes "joy" and generates a response based on that.

[1380] In this way, the system provides the user with a more natural and realistic love simulation experience, while also realizing responses that correspond to the user's emotions.

[1381] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1382] Step 1:

[1383] The user launches the dedicated application on their device and inputs their ideal appearance and personality through the interface. For example, they can select a character with black hair, blue eyes, a height of 180cm, an athletic body, and a kind and humorous personality. This input data is then saved on the device.

[1384] Input: User's ideal appearance and personality setting information (e.g., black hair, blue eyes, height 180 cm, athletic, kind, humorous)

[1385] Output: JSON data of configuration information

[1386] Specific behavior:

[1387] The user enters configuration information on the initial screen of the app.

[1388] The terminal converts the input data into JSON format and prepares it for the API request.

[1389] Step 2:

[1390] The device sends the setting information entered by the user to the server. The server uses an image generation AI model (e.g., GAN) based on the received setting information to generate image data of a virtual partner. The generated virtual partner data is then sent back to the device and displayed to the user.

[1391] Input: JSON data of setting information

[1392] Output: Image data of virtual partner

[1393] Specific behavior:

[1394] The device sends the configuration information to the server's API endpoint via a POST request.

[1395] The server inputs the prompt statement "A sportsman with black hair, blue eyes, and a height of 180 cm" into the generative AI model and generates image data.

[1396] The terminal displays the received image data on the user's screen.

[1397] Step 3:

[1398] The user speaks to the generated virtual partner via text or voice. For example, they might say, "Hello, how was your day?" The user's speech is recorded as text data on the device and sent to the server. The server analyzes the received user speech data, generates an appropriate response text using a generative AI model (e.g., GPT-4), and sends it back to the device. The device then displays the response to the user.

[1399] Input: User-spoken text (e.g., "Hello, how was your day?")

[1400] Output: Virtual partner's response text (e.g., "Hi! I went for a walk today. How was it for you?")

[1401] Specific behavior:

[1402] The user types "Hi, how was your day?" into the text box.

[1403] The device sends the entered text data to the server's API endpoint.

[1404] The server inputs a prompt sentence into the generative AI model and sends the generated response text back to the terminal.

[1405] The terminal displays the generated response to the user.

[1406] Step 4:

[1407] The device captures the user's facial expressions and voice data using a camera and microphone and sends it to the server, which then uses an emotion recognition engine to recognize the user's emotions from the captured data and adjusts the virtual partner's responses based on the results.

[1408] Input: User facial expression images or voice data

[1409] Output: Emotion recognition results and tailored response text

[1410] Specific behavior:

[1411] The user smiles during the conversation.

[1412] The device captures the user's facial expressions with a camera and sends them to the server.

[1413] The server analyzes the captured data using an emotion recognition engine, recognizes the emotion "joy," and generates a response based on the result: "You look happy. Did something good happen?"

[1414] The terminal displays the generated response to the user.

[1415] Step 5:

[1416] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the past conversation history from the server. Based on the conversation history, the server uses the generative AI model and emotion engine to generate continuous, natural-sounding conversation responses and send them to the device. The device then displays the responses to the user.

[1417] Input: User ID, past conversation history

[1418] Output: Natural conversational response text

[1419] Specific behavior:

[1420] The user restarts the app and types, "I'm curious to know what happened next from yesterday."

[1421] The device sends the user ID to the server and requests past conversation history.

[1422] The server references the conversation history and generates a response such as, "You said you were tired. Did you get enough rest?"

[1423] The terminal displays the generated response to the user.

[1424] The above are the processing steps of the program for this system.

[1425] (Application example 2)

[1426] 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."

[1427] The present invention relates to a system that allows users to have natural conversations with a virtual partner that reflects the user's ideal appearance and personality, and provides responses that correspond to the user's emotions. Conventional systems lack the ability to recognize the user's emotions, making it difficult to respond to emotions in real time. There has also been a demand for a system that enables a more realistic experience by expanding the interaction scene with the virtual partner to a virtual store. The objective of this system is to provide an environment in which users can enjoy deeper interactions in virtual space.

[1428] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1429] In this invention, the server includes means for allowing a user to input ideal appearance and personality setting information, means for generating a virtual partner based on the input appearance and personality setting information, means for recognizing emotions from the user's facial expression data, and means for realizing a dialogue between the generated virtual partner and the user in a virtual store. This not only allows the user to enjoy natural dialogue with their ideal virtual partner, but also enables a realistic experience in the virtual store, and makes it possible to provide responses that correspond to the user's emotions.

[1430] "Means enabling users to input ideal appearance and personality setting information" refers to a function that provides an interface for users to specifically customize the appearance and personality of their virtual partner based on their own preferences.

[1431] The "generation means for generating a virtual partner based on input appearance and personality setting information" refers to an algorithm and system for automatically generating the appearance and personality of a virtual partner based on setting information provided by the user.

[1432] "A communication method that remembers conversation history with the user and provides natural interactions" is a system that records the content of past conversations the user has had with a virtual partner and enables more natural and continuous conversations based on that history.

[1433] The "emotion recognition means for recognizing emotions from user's facial expression data" is a function that analyzes the user's facial expressions in real time and identifies the user's current emotional state (such as joy or sadness) from those expressions.

[1434] "Means for enabling interaction between the generated virtual partner and the user within a virtual store" refers to a function that enables direct interaction between the virtual partner and the user within a virtual space, and an example of such a space is a virtual store.

[1435] "Means for generating virtual partner responses using a generative AI model" refers to methods and systems for using a generative AI model (e.g., GPT-3) to generate virtual partner responses to user input.

[1436] "Means for inputting prompt sentences into a generative AI model to obtain an appropriate response" refers to the process of creating a text sentence (prompt sentence) to query the generative AI model so that the virtual partner can respond appropriately to what the user says, and obtaining a response based on that.

[1437] MODE FOR CARRYING OUT THE INVENTION

[1438] This invention combines a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game and interact with them through natural conversation, with an emotion engine that recognizes the user's emotions. This system includes generation means, display means, communication means, emotion recognition means, and means for realizing dialogue within a virtual store, and is realized through a user interface.

[1439] composition

[1440] The system consists of the following elements:

[1441] 1. User interface: An interface where the user inputs information about their ideal appearance and personality.

[1442] 2. Generator: A generative AI model for generating virtual partners based on input information.

[1443] 3. Display means: a display device for displaying an image of the virtual partner to the user.

[1444] 4. Communication tools: A generative AI model that remembers conversation history with the user and provides natural interactions.

[1445] 5. Emotion recognition means: A camera and analysis engine for recognizing emotions from the user's facial expression data.

[1446] 6. Means for realizing interaction within a virtual store: An environment that enables interaction within a virtual space.

[1447] Example Details

[1448] Entering configuration information

[1449] Users launch a dedicated application on their smartphone and use the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies).

[1450] Creating a Virtual Partner

[1451] The device sends the setting information entered by the user to the server. The server uses a generative AI model based on the received setting information to generate image data of a virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[1452] Conversation initiation and memory

[1453] The user speaks to the virtual partner generated on the device. For example, they might ask, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI model. For example, a response might be "Hello! I went for a walk today. How was it for you?" This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[1454] User Emotion Recognition

[1455] The emotion recognition means uses the smartphone's camera to acquire data on the user's facial expressions, and the analysis engine uses that data to recognize the user's emotions. For example, if the user is smiling while speaking, the emotion "joy" is recognized. This allows the virtual partner's response to be adjusted to match the user's emotions. For example, if the user is angry, the virtual partner can ask, "Is something wrong?"

[1456] Interactions in a virtual store

[1457] Users can enjoy interacting with virtual partners in a virtual store. In the virtual store, the virtual partners can introduce products to users and they can enjoy the virtual store together. This allows users to feel a more realistic experience in the virtual space.

[1458] Specific examples of use

[1459] 1. Example of user settings:

[1460] Through the application, users select a partner who is "black-haired, blue-eyed, 180cm tall, athletic," and "kind and humorous."

[1461] 2. Example of Virtual Partner Generation:

[1462] Terminal: Sends configuration information to the server.

[1463] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[1464] Terminal: displays the generated image to the user.

[1465] 3. Example conversation:

[1466] User: "Hi, how was your day?"

[1467] Server: Based on the conversation history and the generative AI model, it generates a response such as "Hello! I went for a walk today. How was it?" and sends it to the device.

[1468] 4. Emotion Recognition Example:

[1469] User: Smile while talking to your virtual partner.

[1470] Server: The emotion recognition engine recognizes "happiness" and generates a response based on that.

[1471] Example prompt for a generative AI model:

[1472] "Generate an image of a person with black hair, blue eyes, and a height of 180 cm, who has a kind and humorous personality."

[1473] In this way, the system provides users with a more natural and realistic love simulation experience, while also enabling dialogue within the virtual store and responses that reflect the user's emotions.

[1474] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1475] Step 1:

[1476] Users start the dedicated application on their smartphone and use the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies). The input data is temporarily recorded on the device.

[1477] Input: User's appearance and personality settings

[1478] Output: Recorded setting information data

[1479] Step 2:

[1480] The device sends the setting information entered by the user to the server. The server uses the generative AI model based on the received setting information to generate image data of the virtual partner. The generated image data is then sent back from the server to the device.

[1481] Input: Setting information data

[1482] Output: Image data of virtual partner

[1483] Step 3:

[1484] The terminal that acquires the image data of the virtual partner displays the image to the user, who can then talk to the displayed virtual partner.

[1485] Input: Image data of virtual partner

[1486] Output: Image displayed to the user

[1487] Step 4:

[1488] When a user speaks to a virtual partner, the device records the speech as text data and sends it to the server. The server analyzes the received speech data and generates an appropriate response text using a generative AI model. The generated response text is then sent from the server to the device.

[1489] Input: User's comment text data

[1490] Output: Virtual partner's response text data

[1491] Step 5:

[1492] The terminal displays the virtual partner's response text data received from the server to the user, and the server simultaneously stores this exchange as a conversation history.

[1493] Input: Virtual partner's response text data

[1494] Output: Display response text to user, record conversation history

[1495] Step 6:

[1496] The user's facial expression data is acquired using the smartphone camera, and the acquired data is analyzed using emotion recognition means. Based on the analysis results, the user's emotions are recognized and emotion data is generated.

[1497] Input: User's facial expression data

[1498] Output: User emotion data

[1499] Step 7:

[1500] The server uses the emotion data to input prompt sentences into the generative AI model, which generates a response that matches the user's emotion. The generated response is then sent from the server to the device, which then displays the response to the user.

[1501] Input: User emotion data, prompt sentence

[1502] Output: Emotion-adjusted text data of the virtual partner's responses, displayed to the user

[1503] Step 8:

[1504] When a conversation with a user takes place in a virtual store, the virtual partner will have a natural conversation based on a scenario of actions in the virtual store, product introductions, etc. The server generates a response based on this scenario and sends it to the terminal, providing a realistic experience in the virtual store.

[1505] Input: Scenario information in the virtual store, user dialogue text data

[1506] Output: Text data of the virtual partner's response based on the scenario, displayed to the user

[1507] These processing steps allow users to enjoy natural and emotionally responsive interactions with their ideal virtual partner, and also provide a realistic experience within the virtual store.

[1508] 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.

[1509] 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.

[1510] 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.

[1511] [Fourth embodiment]

[1512] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1513] 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.

[1514] 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).

[1515] 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.

[1516] 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.

[1517] 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).

[1518] 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.

[1519] 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.

[1520] 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.

[1521] 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.

[1522] 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.

[1523] 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.

[1524] 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."

[1525] ---

[1526] This invention is a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game, and interact with them through natural conversation. This system includes a generation means, a display means, and a communication means, and is realized through a user interface.

[1527] Entering configuration information

[1528] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies), which generates setting information according to the user's preferences.

[1529] Creating a Virtual Partner

[1530] The device sends the setting information entered by the user to the server. The server uses image generation AI based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[1531] Conversation initiation and memory

[1532] The user talks to the virtual partner created on the device, for example, asking, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server.

[1533] The server analyzes the received user speech data and uses a generation AI to generate an appropriate response text. For example, a response such as "Hello! I went running today. How was it?" is generated. This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[1534] Ongoing exchanges

[1535] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. The server generates continuous, natural conversation responses based on the conversation history. For example, in response to the user's question, "How was your run yesterday?", the server responds, "I ran 5km yesterday. It felt great!" In this way, the conversations between the user and the virtual partner are accumulated, enabling more intimate communication.

[1536] Specific examples

[1537] 1. Example of user settings

[1538] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[1539] 2. Example of Virtual Partner Generation

[1540] Terminal: Sends configuration information to the server.

[1541] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[1542] Terminal: displays the generated image to the user.

[1543] 3. Example conversation

[1544] User: Asks the generated partner, "How was your run yesterday?"

[1545] Terminal: Sends the user's question to the server.

[1546] Server: Based on the conversation history, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[1547] Terminal: displays the response to the user.

[1548] In this way, the system can provide users with a more natural and realistic dating simulation experience.

[1549] ---

[1550] The processing flow will be explained below.

[1551] ---

[1552] Step 1:

[1553] Launching the application

[1554] User: Launches a dedicated application on the device.

[1555] Terminal: Displays the main screen of the application.

[1556] Step 2:

[1557] Ideal partner setting

[1558] Terminal: Displays an interface for the user to input their ideal appearance (hairstyle, eye color, height, etc.) and personality (kindness, humor, knowledge, etc.).

[1559] User: Follow the interface and enter the configuration information of your ideal partner.

[1560] Terminal: Manages the entered setting information.

[1561] Step 3:

[1562] Sending configuration information

[1563] Terminal: The setting information entered by the user is sent to the server in JSON format.

[1564] Step 4:

[1565] Receiving a Partner Generation Request

[1566] Server: Receives the setting information (JSON data) sent from the device.

[1567] Step 5:

[1568] Calling image generation AI

[1569] Server: Based on the received setting information, the image generation AI is called and an image of a partner with the ideal appearance is generated.

[1570] Step 6:

[1571] Sending the generated results

[1572] Server: Sends the generated partner image data back to the device.

[1573] Step 7:

[1574] Displaying partner images

[1575] Terminal: Displays the received image data to the user.

[1576] Step 8:

[1577] Start a conversation

[1578] User: Talk to the generated partner through the device.

[1579] Terminal: Records user comments as text data.

[1580] Step 9:

[1581] Sending conversation data

[1582] Terminal: Sends recorded user speech data to the server.

[1583] Step 10:

[1584] Generating conversational responses

[1585] Server: Analyzes the received user speech data and generates appropriate response text using a generative AI model.

[1586] Step 11:

[1587] Sending a Generate Response

[1588] Server: Sends the generated response text to the terminal.

[1589] Step 12:

[1590] Viewing the response

[1591] Terminal: Displays the response text received from the server to the user.

[1592] Step 13:

[1593] Save conversation history

[1594] Server: Stores the conversation history between the user and the partner in a database.

[1595] Step 14:

[1596] Re-login

[1597] User: Relaunches the application on a daily basis and continues the conversation with the partner.

[1598] Device: Requests user information and past conversation history from the server.

[1599] Step 15:

[1600] Retrieving conversation history

[1601] Server: Retrieves the user's conversation history from the database and sends it to the terminal.

[1602] Step 16:

[1603] Use of history

[1604] Device: Displays the received conversation history on the screen, allowing the user to review past interactions.

[1605] Step 17:

[1606] Continuing Conversation

[1607] User: Continue a new conversation with your partner while referring to your conversation history.

[1608] Server: Receives new user utterances and uses stored history to generate more natural responses.

[1609] Step 18:

[1610] Generating a continuation response

[1611] Server: Again generates a conversation response and sends it to the terminal.

[1612] Terminal: displays the generated response to the user.

[1613] ---

[1614] The above is a detailed explanation of the system program processing divided into specific steps.

[1615] Example 1

[1616] 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."

[1617] Conventional dating simulation games have had difficulty in flexibly generating characters according to user preferences. They also have had issues with not being able to realize natural conversations, limiting the user experience. Furthermore, they lacked a mechanism for deepening relationships with users through ongoing conversations.

[1618] 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.

[1619] In this invention, the server includes means for allowing a user to input ideal appearance and personality setting information, means for transmitting the input appearance and personality setting information to the server, means for generating a virtual partner based on the input appearance and personality setting information, means for receiving image data of the generated virtual partner from the server, means for displaying image data of the generated virtual partner, means for recording user utterances on the terminal and transmitting them to the server, communication means for storing a conversation history with the user and providing natural conversation using a generative AI model, means for receiving conversation responses generated from the server, means for displaying the received conversation responses, and means for providing continuous conversation based on the past conversation history, thereby enabling character generation according to user preferences and natural conversation exchange.

[1620] "User" refers to a person who utilizes the system to generate and interact with an ideal virtual partner.

[1621] "Terminal" refers to a device operated by a user that runs dedicated applications to generate and interact with virtual partners.

[1622] "Server" refers to a central control device that receives setting information sent by a user, generates a virtual partner, and responds to conversations.

[1623] "Ideal appearance and personality setting information" refers to information that the user specifically inputs about the appearance and personality traits that the user desires in a virtual partner.

[1624] "Virtual partner" refers to a fictional character that is generated based on the user's setting information.

[1625] "Generative AI model" refers to artificial intelligence (AI) technology that generates images and conversational responses of virtual partners based on user settings.

[1626] A "prompt sentence" is text information input to a generative AI model to provide instructions on the virtual partner's characteristics and conversation content.

[1627] "Image Data" refers to data in digital form that represents a visual representation of a virtual partner generated by a generative AI model.

[1628] "Utterance data" refers to the recorded text of what the user says to the virtual partner.

[1629] "Conversation history" refers to a record of past interactions between a user and a virtual partner.

[1630] "Communication means" refers to the functions and processes necessary for natural interaction between the user and the virtual partner.

[1631] "Continuous conversation" refers to an ongoing dialogue between a virtual partner and a user based on past dialogue history.

[1632] This invention is a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game, and interact with them through natural conversation. This system includes a generation means, a display means, and a communication means, and is realized through a user interface.

[1633] Entering configuration information

[1634] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies). For example, the user may set a partner who is "black hair, blue eyes, 180cm tall, athletic," and "kind and humorous." This generates setting information that matches the user's preferences.

[1635] Creating a Virtual Partner

[1636] The device sends the setting information entered by the user to the server. The server uses an image generation AI (e.g., DALL-E, Stable Diffusion) based on the received setting information to generate image data for the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[1637] Conversation initiation and memory

[1638] The user speaks to the virtual partner generated on the device. For example, they might ask, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI (e.g., GPT-3). For example, a response might be generated such as, "Hello! I went for a run today. How was it for you?" This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[1639] Ongoing exchanges

[1640] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. The server generates continuous, natural conversation responses based on the conversation history. For example, if the user asks, "How was your run yesterday?", the server may respond, based on the past conversation history, with, "I ran 5km yesterday. It felt great!" In this way, the conversation between the user and the virtual partner is accumulated, enabling more intimate communication.

[1641] Specific examples

[1642] 1. Example of user settings

[1643] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[1644] 2. Example of Virtual Partner Generation

[1645] Terminal: Sends configuration information to the server.

[1646] Server: Image generation AI (e.g., Stable Diffusion) generates an image of the virtual partner based on the configuration information and sends it to the device.

[1647] Terminal: displays the generated image to the user.

[1648] 3. Example conversation

[1649] User: Asks the generated partner, "How was your run yesterday?"

[1650] Terminal: Sends the user's question to the server.

[1651] Server: Based on the conversation history, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[1652] Terminal: displays the response to the user.

[1653] In this way, the system can provide users with a more natural and realistic dating simulation experience.

[1654] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1655] Step 1:

[1656] The user launches the dedicated application on the device. At this time, an interface appears on the device's display, allowing the user to input the appearance and personality settings of their ideal virtual partner. Through this interface, the user inputs settings that suit their preferences. Specific inputs include "black hair, blue eyes, an athletic man who is 180 cm tall," as well as "kind and humorous." This input information is temporarily recorded on the device.

[1657] Step 2:

[1658] The device sends the setting information entered by the user to the server. The transmitted data includes the appearance and personality setting information entered by the user. When the server receives this setting information, it automatically prepares to input the setting information as a prompt to the image generation AI (e.g., DALL-E, Stable Diffusion). This prompt includes the specific characteristics desired by the user.

[1659] Step 3:

[1660] The server uses image generation AI based on the received setting information to generate image data of a virtual partner. A prompt such as "black hair, blue eyes, 180cm tall, athletic, kind and humorous" is input into the generation AI model. The image generation AI outputs an image of a partner with the specified characteristics according to this prompt. This image data is generated on the server side.

[1661] Step 4:

[1662] The generated image data of the virtual partner is sent from the server to the terminal. The terminal displays the received image data on the user interface. This display allows the user to check the visual appearance of the virtual partner based on the information set by the user.

[1663] Step 5:

[1664] The user starts a conversation with the virtual partner generated on the terminal. For example, the user enters "Hello, how was your day?" This utterance is recorded as text data on the terminal. The recorded text data is then sent by the terminal to the server.

[1665] Step 6:

[1666] The server analyzes the received user utterance data and calls a generative AI model (e.g., GPT-3). The utterance data is input to the generative AI model as a prompt sentence. For example, the user asks the virtual partner, "Hello, how was your day?" The generative AI model generates an appropriate response text (e.g., "Hello! I went for a run today. How was it for you?"). This response text is generated by the server.

[1667] Step 7:

[1668] The server sends the generated response to the terminal, which displays the received response text on the user interface, allowing the user to check the response from the virtual partner.

[1669] Step 8:

[1670] The server stores a conversation history with the user, including what the user said and the responses generated, allowing future conversations to reference past interactions.

[1671] Step 9:

[1672] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the conversation history, the server generates continuous, natural conversation responses. For example, in response to the question, "How was your run yesterday?", the server responds, "I ran 5km yesterday. It felt great!" This response text is generated and sent to the device.

[1673] Step 10:

[1674] The device then displays the received response on the user interface, allowing the user to enjoy a continuous dialogue based on the past conversation history.

[1675] As described above, this system can provide users with a more natural and realistic dating simulation experience.

[1676] (Application example 1)

[1677] 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."

[1678] Current food delivery services face the challenge of providing personalized suggestions that fully take into account the user's individual preferences and background information, resulting in a limited user experience. In particular, providing more intimate and effective services to users through personalized suggestions in food delivery is a challenge.

[1679] 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.

[1680] In this invention, the server includes means for allowing a user to input information on ideal appearance and personality settings, means for generating a virtual partner based on the input information on appearance and personality settings, means for storing a conversation history with the user and providing natural interaction, and means for making delivery suggestions based on the user's order information and conversation history, thereby enabling personalized delivery suggestions to be made to the user.

[1681] A "user" is someone who uses the system to interact with their ideal virtual partner and order and customize food.

[1682] "Appearance setting information" is information about the virtual partner's appearance, such as hairstyle, eye color, height, and build, set by the user.

[1683] "Personality setting information" is information about the inner qualities of the virtual partner set by the user, such as kindness, humor, knowledge, hobbies, etc.

[1684] A "virtual partner" is a digital character that is generated based on the user's settings information and with which the user can interact.

[1685] The "generation means" is a technology that has a function for generating a virtual partner based on information input by the user.

[1686] "Communication means" refers to technology that provides a function for realizing natural conversation between a virtual partner and a user and storing the conversation history.

[1687] "Order information" refers to information about the content that a user inputs when ordering or customizing food.

[1688] "Delivery Suggestion" is a function that suggests optimal foods and services to users based on their order information and conversation history.

[1689] A "generative AI model" is an artificial intelligence algorithm that generates images and responses of virtual partners based on the user's settings and conversations.

[1690] A "prompt" is an instruction or question that is input to a generative AI model to obtain a specific output.

[1691] This invention is a system that allows users to create a virtual partner with ideal appearance and personality, interact with them through natural conversation, and provide personalized suggestions for food delivery services. The system includes the following main means:

[1692] 1. Enter your user settings

[1693] The user starts a dedicated application installed on their smartphone and uses the interface to set the appearance (e.g., hairstyle, eye color, height, physique, etc.) and personality (e.g., kindness, humor, knowledge, hobbies, etc.) of their ideal virtual partner. This generates setting information.

[1694] 2. Generation of Virtual Partners

[1695] The smartphone sends the setting information entered by the user to the server. The server uses the generative AI model based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the smartphone and displayed to the user.

[1696] 3. Initiating and remembering conversations

[1697] The user speaks to the virtual partner generated on the device. For example, they might ask, "Good evening, what should I eat today?" The user's utterances are recorded as text data on the smartphone and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI model. For example, a response might be generated such as, "Why don't you order pizza today? We have recommended toppings." This generated response is sent to the smartphone and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[1698] 4. Continuous communication and suggestions

[1699] When the user launches the application again and continues the conversation with the virtual partner, the smartphone retrieves the user's past conversation history from the server. Based on the conversation history, the server provides delivery suggestions along with continuous, natural conversational responses. For example, in response to a user's question, "How was the pizza yesterday?", the server responds with, "Was the pizza delicious yesterday? Why not try the side dish next time?" In this way, more intimate and personalized suggestions are possible based on the user's preferences and past ordering history.

[1700] Hardware and software used

[1701] Hardware: Smartphone

[1702] Software: Python, OpenAI's GPT-3, image generation API

[1703] Specific examples

[1704] 1. Example of user settings

[1705] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[1706] 2. Example of Virtual Partner Generation

[1707] Smartphone: Sends configuration information to the server.

[1708] Server: Using a generative AI model, it generates an image of the virtual partner based on the settings information and sends it to the smartphone.

[1709] Smartphone: The generated image is displayed to the user.

[1710] 3. Example conversation

[1711] User: "I'm craving pizza today. What do you recommend?"

[1712] Smartphone: Sends the user's question to the server.

[1713] Server: Based on the conversation history, it generates a response such as, "You've been ordering Margherita pizza lately. Why not try a slightly spicy Diavolo today?" and sends it to your smartphone.

[1714] Smartphone: Display the response to the user.

[1715] Prompt Sentence Examples

[1716] "Generate natural conversational responses for your virtual partner based on the following text: User: I'm craving pizza today. What do you recommend? Virtual partner: You've been ordering Margherita pizzas lately. How about trying a slightly spicy Diavolo today?"

[1717] In this way, the system can provide users with personalized delivery suggestions as well as a more natural and realistic communication experience.

[1718] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1719] Step 1: The user launches a dedicated application on their smartphone. This application allows the user to input the appearance and personality settings of their ideal virtual partner through a user interface. Input data includes hairstyle, eye color, height, physique, kindness, humor, knowledge, hobbies, etc. The input information is then recorded on the device.

[1720] Step 2: The device sends the setting information entered by the user to the server. The data is sent to the server using a communication means. The server analyzes the received data and converts it into an appropriate format. This formatted data is provided as input to the image generation AI model.

[1721] Step 3: The server uses the image generation AI model based on the received data to generate image data of the virtual partner. The image generation AI model generates an image of the virtual partner based on the user's settings, and the generated image data is temporarily stored on the server. The generated data is then sent back to the device.

[1722] Step 4: The terminal displays the image data of the generated virtual partner received from the server on the user interface. The user can check the image of the generated virtual partner. Here, the virtual partner and the user can interact with each other.

[1723] Step 5: The user speaks to the virtual partner generated on the device. For example, the user types, "Hello, what should I eat today?" The user's speech is recorded as text data on the device and then sent to the server. The device sends the user's speech data to the server in text format.

[1724] Step 6: The server analyzes the received user utterance data and inputs it into the generative AI model to generate an appropriate response. Prompt sentences include "User: Hello, what should I eat today?" The generative AI model generates a response text based on the prompt sentence. For example, a response such as "How about ordering pizza today?" is generated. This generated response data is sent to the device.

[1725] Step 7: The terminal displays the response data received from the server on the user interface. The user can check the virtual partner's response and continue the conversation. At the same time, the server stores this exchange as a conversation history.

[1726] Step 8: When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the user's past conversation history, the server provides continuous, natural conversational responses, such as food delivery suggestions. For example, in response to the user's question, "How was the pizza yesterday?", a response such as "Was the pizza delicious yesterday? Why not try the side dish today?" is generated. This response is also sent to the device and displayed.

[1727] 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.

[1728] ---

[1729] This invention combines a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game and interact with them through natural conversation, with an emotion engine that recognizes the user's emotions. This system includes generation means, display means, communication means, and the emotion engine, and is realized through a user interface.

[1730] Entering configuration information

[1731] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies), which generates setting information according to the user's preferences.

[1732] Creating a Virtual Partner

[1733] The device sends the setting information entered by the user to the server. The server uses image generation AI based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[1734] Conversation initiation and memory

[1735] The user talks to the virtual partner created on the device, for example, asking, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server.

[1736] The server analyzes the received user speech data and uses a generation AI to generate an appropriate response text. For example, a response such as "Hello! I went for a walk today. How was it?" is generated. This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[1737] User Emotion Recognition

[1738] The emotion engine recognizes emotions from the user's speech and facial expression data. For example, if the user is smiling while speaking, the emotion "joy" is recognized. This allows the virtual partner's response to be adjusted to match the user's emotion. For example, if the user is angry, the virtual partner can ask, "Is something wrong?"

[1739] Ongoing exchanges

[1740] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the conversation history, the server uses an emotion engine to generate continuous, natural conversation responses. For example, if the user previously said "I'm tired," the server remembers this and generates a response such as "Did you sleep well last night?" In this way, the conversations between the user and the virtual partner are accumulated, enabling more intimate communication.

[1741] Specific examples

[1742] 1. Example of user settings

[1743] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[1744] 2. Example of Virtual Partner Generation

[1745] Terminal: Sends configuration information to the server.

[1746] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[1747] Terminal: displays the generated image to the user.

[1748] 3. Example conversation

[1749] User: Asks the generated partner, "How was your run yesterday?"

[1750] Terminal: Sends the user's question to the server.

[1751] Server: Based on the conversation history and emotion engine, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[1752] Terminal: displays the response to the user.

[1753] 4. Emotion recognition example

[1754] User: Smile while talking to your virtual partner.

[1755] Device: Sends the user's smile to the emotion engine via the camera function.

[1756] Server: The emotion engine recognizes "joy" and generates a response based on that.

[1757] In this way, the system provides the user with a more natural and realistic dating simulation experience, while also realizing responses that correspond to the user's emotions.

[1758] The processing flow will be explained below.

[1759] ---

[1760] Step 1:

[1761] Launching the application

[1762] User: Launches a dedicated application on the device.

[1763] Terminal: Displays the main screen of the application.

[1764] Step 2:

[1765] Ideal partner setting

[1766] Terminal: Displays an interface for the user to input their ideal appearance (hairstyle, eye color, height, etc.) and personality (kindness, humor, knowledge, etc.).

[1767] User: Follow the interface and enter the configuration information of your ideal partner.

[1768] Terminal: Manages the entered setting information.

[1769] Step 3:

[1770] Sending configuration information

[1771] Terminal: The setting information entered by the user is sent to the server in JSON format.

[1772] Step 4:

[1773] Receiving a Partner Generation Request

[1774] Server: Receives the setting information (JSON data) sent from the device.

[1775] Step 5:

[1776] Calling image generation AI

[1777] Server: Calls the image generation AI based on the received setting information and generates an image of a partner with the ideal appearance.

[1778] Step 6:

[1779] Sending the generated results

[1780] Server: Sends the generated partner image data back to the device.

[1781] Step 7:

[1782] Displaying partner images

[1783] Terminal: Displays the received image data to the user.

[1784] Step 8:

[1785] Start a conversation

[1786] User: Talk to the generated partner through the device.

[1787] Terminal: Records user comments as text data.

[1788] Step 9:

[1789] Sending conversation data

[1790] Terminal: Sends recorded user speech data to the server.

[1791] Step 10:

[1792] Generating conversational responses

[1793] Server: Analyzes the received user speech data and generates appropriate response text using a generative AI model.

[1794] Step 11:

[1795] User Emotion Recognition

[1796] Terminal: Collects the user's facial expression data using an accessible camera function and sends it to the emotion engine.

[1797] Server: The emotion engine recognizes emotions (e.g., joy, anger, sadness) based on the user's speech and facial expression data.

[1798] Step 12:

[1799] Response adjustment

[1800] Server: Adjusts the generated response text based on the user's perceived emotions. For example, if the user is determined to be tired, it generates a gentle response such as "Thank you for your hard work. Maybe you should take a rest today."

[1801] Step 13:

[1802] Sending a Generate Response

[1803] Server: Sends the tailored response text to the device.

[1804] Step 14:

[1805] Viewing the response

[1806] Terminal: Displays the response text received from the server to the user.

[1807] Step 15:

[1808] Save conversation history

[1809] Server: Stores the conversation history and recognized emotion data of the user and partner in a database.

[1810] Step 16:

[1811] Re-login

[1812] User: Relaunches the application on a daily basis and continues the conversation with the partner.

[1813] Terminal: Requests user information, past conversation history, and emotion data from the server.

[1814] Step 17:

[1815] Retrieving conversation history

[1816] Server: Retrieves the user's conversation history and emotion data from the database and sends them to the device.

[1817] Step 18:

[1818] Use of history

[1819] Terminal: Displays the received conversation history and emotion history on the screen, allowing the user to check past interactions and emotional states.

[1820] Step 19:

[1821] Continuing Conversation

[1822] User: Continue a new conversation with your partner while referring to the conversation history and emotion history.

[1823] Server: Receives new user utterances and uses stored history to generate more natural responses.

[1824] Step 20:

[1825] Generating a continuation response

[1826] Server: Again generates a conversation response and sends it to the terminal.

[1827] Terminal: displays the generated response to the user.

[1828] ---

[1829] The above is a detailed explanation of the program processing of a system that combines an emotion engine, broken down into specific steps.

[1830] Example 2

[1831] 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."

[1832] In conventional dating simulation systems, it was difficult for users to create their ideal virtual partner and engage in continuous interaction. Furthermore, the system lacked a realistic experience because it did not provide responses based on the user's emotions. Furthermore, it lacked a means to conduct natural, continuous dialogue based on past conversation history.

[1833] The specification processing 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 means for allowing the user to input ideal appearance and personality setting information, generation means for generating a virtual partner based on the input appearance and personality setting information, communication means for storing utterances made by the user to the generated virtual partner and providing natural interactions, emotion recognition means for collecting facial expressions and voice data of the user and recognizing emotions, and means for adjusting the responses of the virtual partner based on the emotion recognition results. This enables the user to have continuous, natural conversations with their ideal virtual partner according to their emotions.

[1834] "User" refers to an individual who uses the dating simulation system.

[1835] "Ideal appearance" refers to information about the appearance of a virtual partner set by the user.

[1836] "Personality setting information" refers to information about the personality and characteristics of the virtual partner set by the user.

[1837] "Virtual partner" refers to a digital character that is generated based on information set by the user.

[1838] "Generation means" refers to a function that generates a virtual partner based on setting information input by the user.

[1839] "Communication means" refers to a function that stores conversation history with the user and provides natural interaction.

[1840] "Emotion recognition means" refers to a function for collecting facial expressions and voice data of the user and recognizing emotions.

[1841] "Adjustment means" refers to the ability to adjust the virtual partner's responses based on perceived emotions.

[1842] "Server" refers to a central control unit that manages user preferences and conversation history, and provides virtual partner generation and response.

[1843] "Terminal" refers to a device through which a user accesses and operates the system.

[1844] "Conversation history" refers to data that records past interactions between a user and a virtual partner.

[1845] "Continuous interaction" refers to continuous and natural dialogue based on past conversation history.

[1846] "Response according to emotions" refers to a response from a virtual partner that is generated taking into account the user's emotions.

[1847] "Natural interaction" refers to dialogue that flows like a human conversation.

[1848] This invention combines a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game and interact with them through natural conversation, with an emotion engine that recognizes the user's emotions. This system includes generation means, display means, communication means, and the emotion engine, and is realized through a user interface.

[1849] Entering configuration information

[1850] The user starts the dedicated application on the device and uses the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies), which generates setting information according to the user's preferences.

[1851] Creating a Virtual Partner

[1852] The device sends the setting information entered by the user to the server. The server uses an image generation AI model (e.g., DALL-E or GAN) based on the received setting information to generate image data of the virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[1853] Conversation initiation and memory

[1854] The user speaks to the virtual partner generated on the device. For example, they might ask, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI (e.g., GPT-4). For example, a response might be generated such as, "Hello! I went for a walk today. How was it for you?" This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[1855] User Emotion Recognition

[1856] The emotion engine recognizes emotions from the user's speech and facial expression data. For example, if the user is smiling while speaking, the emotion "joy" is recognized. This allows the virtual partner's response to be adjusted to match the user's emotion. For example, if the user is angry, the virtual partner can ask, "Is something wrong?"

[1857] Ongoing exchanges

[1858] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the user's past conversation history from the server. Based on the conversation history, the server uses an emotion engine to generate continuous, natural conversation responses. For example, if the user previously said "I'm tired," the server remembers this and generates a response such as "Did you sleep well last night?" In this way, the conversations between the user and the virtual partner are accumulated, enabling more intimate communication.

[1859] Specific examples

[1860] 1. Example of user settings

[1861] User: Through the application, the user selects a partner who is "black haired, blue eyes, 180cm tall, athletic" and "kind and humorous."

[1862] 2. Example of Virtual Partner Generation

[1863] Terminal: Sends configuration information to the server.

[1864] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[1865] Terminal: displays the generated image to the user.

[1866] 3. Example conversation

[1867] User: Asks the generated partner, "How was your run yesterday?"

[1868] Terminal: Sends the user's question to the server.

[1869] Server: Based on the conversation history and emotion engine, it generates a response such as "I ran 5km yesterday. It felt great!" and sends it to the device.

[1870] Terminal: displays the response to the user.

[1871] 4. Emotion recognition example

[1872] User: Smile while talking to your virtual partner.

[1873] Device: Sends the user's smile to the emotion engine via the camera function.

[1874] Server: The emotion engine recognizes "joy" and generates a response based on that.

[1875] In this way, the system provides the user with a more natural and realistic love simulation experience, while also realizing responses that correspond to the user's emotions.

[1876] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1877] Step 1:

[1878] The user launches the dedicated application on their device and inputs their ideal appearance and personality through the interface. For example, they can select a character with black hair, blue eyes, a height of 180cm, an athletic body, and a kind and humorous personality. This input data is then saved on the device.

[1879] Input: User's ideal appearance and personality setting information (e.g., black hair, blue eyes, height 180 cm, athletic, kind, humorous)

[1880] Output: JSON data of configuration information

[1881] Specific behavior:

[1882] The user enters configuration information on the initial screen of the app.

[1883] The terminal converts the input data into JSON format and prepares it for the API request.

[1884] Step 2:

[1885] The device sends the setting information entered by the user to the server. The server uses an image generation AI model (e.g., GAN) based on the received setting information to generate image data of a virtual partner. The generated virtual partner data is then sent back to the device and displayed to the user.

[1886] Input: JSON data of setting information

[1887] Output: Image data of virtual partner

[1888] Specific behavior:

[1889] The device sends the configuration information to the server's API endpoint via a POST request.

[1890] The server inputs the prompt statement "A sportsman with black hair, blue eyes, and a height of 180 cm" into the generative AI model and generates image data.

[1891] The terminal displays the received image data on the user's screen.

[1892] Step 3:

[1893] The user speaks to the generated virtual partner via text or voice. For example, they might say, "Hello, how was your day?" The user's speech is recorded as text data on the device and sent to the server. The server analyzes the received user speech data, generates an appropriate response text using a generative AI model (e.g., GPT-4), and sends it back to the device. The device then displays the response to the user.

[1894] Input: User-spoken text (e.g., "Hello, how was your day?")

[1895] Output: Virtual partner's response text (e.g., "Hi! I went for a walk today. How was it for you?")

[1896] Specific behavior:

[1897] The user types "Hi, how was your day?" into the text box.

[1898] The device sends the entered text data to the server's API endpoint.

[1899] The server inputs a prompt sentence into the generative AI model and sends the generated response text back to the terminal.

[1900] The terminal displays the generated response to the user.

[1901] Step 4:

[1902] The device captures the user's facial expressions and voice data using a camera and microphone and sends it to the server, which then uses an emotion recognition engine to recognize the user's emotions from the captured data and adjusts the virtual partner's responses based on the results.

[1903] Input: User facial expression images or voice data

[1904] Output: Emotion recognition results and tailored response text

[1905] Specific behavior:

[1906] The user smiles during the conversation.

[1907] The device captures the user's facial expressions with a camera and sends them to the server.

[1908] The server analyzes the captured data using an emotion recognition engine, recognizes the emotion "joy," and generates a response based on the result: "You look happy. Did something good happen?"

[1909] The terminal displays the generated response to the user.

[1910] Step 5:

[1911] When the user launches the application again and continues the conversation with the virtual partner, the device retrieves the past conversation history from the server. Based on the conversation history, the server uses the generative AI model and emotion engine to generate continuous, natural-sounding conversation responses and send them to the device. The device then displays the responses to the user.

[1912] Input: User ID, past conversation history

[1913] Output: Natural conversational response text

[1914] Specific behavior:

[1915] The user restarts the app and types, "I'm curious to know what happened next from yesterday."

[1916] The device sends the user ID to the server and requests past conversation history.

[1917] The server references the conversation history and generates a response such as, "You said you were tired. Did you get enough rest?"

[1918] The terminal displays the generated response to the user.

[1919] The above are the processing steps of the program for this system.

[1920] (Application example 2)

[1921] 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."

[1922] The present invention relates to a system that allows users to have natural conversations with a virtual partner that reflects the user's ideal appearance and personality, and provides responses that correspond to the user's emotions. Conventional systems lack the ability to recognize the user's emotions, making it difficult to respond to emotions in real time. There has also been a demand for a system that enables a more realistic experience by expanding the interaction scene with the virtual partner to a virtual store. The objective of this system is to provide an environment in which users can enjoy deeper interactions in virtual space.

[1923] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1924] In this invention, the server includes means for allowing a user to input ideal appearance and personality setting information, means for generating a virtual partner based on the input appearance and personality setting information, means for recognizing emotions from the user's facial expression data, and means for realizing a dialogue between the generated virtual partner and the user in a virtual store. This not only allows the user to enjoy natural dialogue with their ideal virtual partner, but also enables a realistic experience in the virtual store, and makes it possible to provide responses that correspond to the user's emotions.

[1925] "Means enabling users to input ideal appearance and personality setting information" refers to a function that provides an interface for users to specifically customize the appearance and personality of their virtual partner based on their own preferences.

[1926] The "generation means for generating a virtual partner based on input appearance and personality setting information" refers to an algorithm and system for automatically generating the appearance and personality of a virtual partner based on setting information provided by the user.

[1927] "A communication method that remembers conversation history with the user and provides natural interactions" is a system that records the content of past conversations the user has had with a virtual partner and enables more natural and continuous conversations based on that history.

[1928] The "emotion recognition means for recognizing emotions from user's facial expression data" is a function that analyzes the user's facial expressions in real time and identifies the user's current emotional state (such as joy or sadness) from those expressions.

[1929] "Means for enabling interaction between the generated virtual partner and the user within a virtual store" refers to a function that enables direct interaction between the virtual partner and the user within a virtual space, and an example of such a space is a virtual store.

[1930] "Means for generating virtual partner responses using a generative AI model" refers to methods and systems for using a generative AI model (e.g., GPT-3) to generate virtual partner responses to user input.

[1931] "Means for inputting prompt sentences into a generative AI model to obtain an appropriate response" refers to the process of creating a text sentence (prompt sentence) to query the generative AI model so that the virtual partner can respond appropriately to what the user says, and obtaining a response based on that.

[1932] MODE FOR CARRYING OUT THE INVENTION

[1933] This invention combines a system that allows users to create a virtual partner with their ideal appearance and personality in a dating simulation game and interact with them through natural conversation, with an emotion engine that recognizes the user's emotions. This system includes generation means, display means, communication means, emotion recognition means, and means for realizing dialogue within a virtual store, and is realized through a user interface.

[1934] composition

[1935] The system consists of the following elements:

[1936] 1. User interface: An interface where the user inputs information about their ideal appearance and personality.

[1937] 2. Generator: A generative AI model for generating virtual partners based on input information.

[1938] 3. Display means: a display device for displaying an image of the virtual partner to the user.

[1939] 4. Communication tools: A generative AI model that remembers conversation history with the user and provides natural interactions.

[1940] 5. Emotion recognition means: A camera and analysis engine for recognizing emotions from the user's facial expression data.

[1941] 6. Means for realizing interaction within a virtual store: An environment that enables interaction within a virtual space.

[1942] Example Details

[1943] Entering configuration information

[1944] Users launch a dedicated application on their smartphone and use the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies).

[1945] Creating a Virtual Partner

[1946] The device sends the setting information entered by the user to the server. The server uses a generative AI model based on the received setting information to generate image data of a virtual partner. This generated virtual partner data is sent back to the device and displayed to the user.

[1947] Conversation initiation and memory

[1948] The user speaks to the virtual partner generated on the device. For example, they might ask, "Hello, how was your day?" The user's utterances are recorded as text data on the device and sent to the server. The server analyzes the received user utterance data and generates an appropriate response text using a generative AI model. For example, a response might be "Hello! I went for a walk today. How was it for you?" This generated response is sent to the device and displayed to the user. At the same time, the server stores this exchange as a conversation history.

[1949] User Emotion Recognition

[1950] The emotion recognition means uses the smartphone's camera to acquire data on the user's facial expressions, and the analysis engine uses that data to recognize the user's emotions. For example, if the user is smiling while speaking, the emotion "joy" is recognized. This allows the virtual partner's response to be adjusted to match the user's emotions. For example, if the user is angry, the virtual partner can ask, "Is something wrong?"

[1951] Interactions in a virtual store

[1952] Users can enjoy interacting with virtual partners in a virtual store. In the virtual store, the virtual partners can introduce products to users and they can enjoy the virtual store together. This allows users to feel a more realistic experience in the virtual space.

[1953] Specific examples of use

[1954] 1. Example of user settings:

[1955] Through the application, users select a partner who is "black-haired, blue-eyed, 180cm tall, athletic," and "kind and humorous."

[1956] 2. Example of Virtual Partner Generation:

[1957] Terminal: Sends configuration information to the server.

[1958] Server: The image generation AI generates an image of the virtual partner based on the setting information and sends it to the device.

[1959] Terminal: displays the generated image to the user.

[1960] 3. Example conversation:

[1961] User: "Hi, how was your day?"

[1962] Server: Based on the conversation history and the generative AI model, it generates a response such as "Hello! I went for a walk today. How was it?" and sends it to the device.

[1963] 4. Emotion Recognition Example:

[1964] User: Smile while talking to your virtual partner.

[1965] Server: The emotion recognition engine recognizes "happiness" and generates a response based on that.

[1966] Example prompt for a generative AI model:

[1967] "Generate an image of a person with black hair, blue eyes, and a height of 180 cm, who has a kind and humorous personality."

[1968] In this way, the system provides users with a more natural and realistic love simulation experience, while also enabling dialogue within the virtual store and responses that reflect the user's emotions.

[1969] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1970] Step 1:

[1971] Users start the dedicated application on their smartphone and use the interface to input their ideal appearance (e.g., hairstyle, eye color, height, physique) and personality (e.g., kindness, humor, knowledge, hobbies). The input data is temporarily recorded on the device.

[1972] Input: User's appearance and personality settings

[1973] Output: Recorded setting information data

[1974] Step 2:

[1975] The device sends the setting information entered by the user to the server. The server uses the generative AI model based on the received setting information to generate image data of the virtual partner. The generated image data is then sent back from the server to the device.

[1976] Input: Setting information data

[1977] Output: Image data of virtual partner

[1978] Step 3:

[1979] The terminal that acquires the image data of the virtual partner displays the image to the user, who can then talk to the displayed virtual partner.

[1980] Input: Image data of virtual partner

[1981] Output: Image displayed to the user

[1982] Step 4:

[1983] When a user speaks to a virtual partner, the device records the speech as text data and sends it to the server. The server analyzes the received speech data and generates an appropriate response text using a generative AI model. The generated response text is then sent from the server to the device.

[1984] Input: User's comment text data

[1985] Output: Virtual partner's response text data

[1986] Step 5:

[1987] The terminal displays the virtual partner's response text data received from the server to the user, and the server simultaneously stores this exchange as a conversation history.

[1988] Input: Virtual partner's response text data

[1989] Output: Display response text to user, record conversation history

[1990] Step 6:

[1991] The user's facial expression data is acquired using the smartphone camera, and the acquired data is analyzed using emotion recognition means. Based on the analysis results, the user's emotions are recognized and emotion data is generated.

[1992] Input: User's facial expression data

[1993] Output: User emotion data

[1994] Step 7:

[1995] The server uses the emotion data to input prompt sentences into the generative AI model, which generates a response that matches the user's emotion. The generated response is then sent from the server to the device, which then displays the response to the user.

[1996] Input: User emotion data, prompt sentence

[1997] Output: Emotion-adjusted text data of the virtual partner's responses, displayed to the user

[1998] Step 8:

[1999] When a conversation with a user takes place in a virtual store, the virtual partner will have a natural conversation based on a scenario of actions in the virtual store, product introductions, etc. The server generates a response based on this scenario and sends it to the terminal, providing a realistic experience in the virtual store.

[2000] Input: Scenario information in the virtual store, user dialogue text data

[2001] Output: Text data of the virtual partner's response based on the scenario, displayed to the user

[2002] These processing steps allow users to enjoy natural and emotionally responsive interactions with their ideal virtual partner, and also provide a realistic experience within the virtual store.

[2003] 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.

[2004] 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.

[2005] 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.

[2006] 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.

[2007] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2008] 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.

[2009] 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).

[2010] 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.

[2011] 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."

[2012] 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.

[2013] 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).

[2014] 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.

[2015] 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.

[2016] 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.

[2017] 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.

[2018] 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.

[2019] 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.

[2020] 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.

[2021] 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.

[2022] 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.

[2023] 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.

[2024] The following is further disclosed regarding the above embodiment.

[2025] ---

[2026] (Claim 1)

[2027] means for allowing a user to input ideal appearance and personality setting information;

[2028] A generating means for generating a virtual partner based on input appearance and personality setting information;

[2029] A communication means that stores conversation history with the user and provides natural interaction;

[2030] A system including:

[2031] (Claim 2)

[2032] 10. The system of claim 1, further comprising means for displaying an image of the generated virtual partner.

[2033] (Claim 3)

[2034] means for transmitting information set by a user to a server;

[2035] means for receiving image data and conversation responses of the generated virtual partner from the server;

[2036] The system of claim 1 further comprising:

[2037] (Claim 4)

[2038] 10. The system of claim 1, further comprising means for utilizing a conversation history to provide ongoing, natural conversational responses based on a conversation with the generated virtual partner.

[2039] "Example 1"

[2040] (Claim 1)

[2041] means for allowing a user to input ideal appearance and personality setting information;

[2042] means for transmitting the input appearance and personality setting information to a server;

[2043] means for generating a virtual partner based on input appearance and personality setting information;

[2044] means for receiving image data of the generated virtual partner from a server;

[2045] A means for displaying image data of the generated virtual partner;

[2046] A means for recording user utterances on a terminal and transmitting the recorded utterances to a server;

[2047] A communication method that memorizes conversation history with users and provides natural interactions using generative AI models;

[2048] means for receiving a generated conversational response from the server;

[2049] means for displaying received conversation responses;

[2050] a means for providing ongoing conversation based on past conversation history;

[2051] A system including:

[2052] (Claim 2)

[2053] The system of claim 1, characterized in that it uses a generative AI model to generate an image of a virtual partner.

[2054] (Claim 3)

[2055] The system of claim 1, characterized in that it uses a generative AI model to generate responses based on the received conversation history.

[2056] "Application Example 1"

[2057] (Claim 1)

[2058] means for allowing a user to input ideal appearance and personality setting information;

[2059] A generating means for generating a virtual partner based on input appearance and personality setting information;

[2060] A communication means that stores conversation history with the user and provides natural interaction;

[2061] A means for making delivery suggestions based on the user's order information and conversation history;

[2062] A system including:

[2063] (Claim 2)

[2064] 10. The system of claim 1, further comprising means for displaying an image of the generated virtual partner.

[2065] (Claim 3)

[2066] means for transmitting information set by a user to a server;

[2067] means for receiving image data and conversation responses of the generated virtual partner from the server;

[2068] means for displaying the order information and delivery suggestions retrieved from the server;

[2069] The system of claim 1 further comprising:

[2070] "Example 2: Combining Emotion Engines"

[2071] (Claim 1)

[2072] means for allowing a user to input ideal appearance and personality setting information;

[2073] A generating means for generating a virtual partner based on input appearance and personality setting information;

[2074] A communication means for storing utterances made by a user to the generated virtual partner and providing natural interactions;

[2075] emotion recognition means for recognizing emotions by collecting facial expressions and voice data of a user;

[2076] a means for adjusting the virtual partner's response based on the emotion recognition result;

[2077] A system including:

[2078] (Claim 2)

[2079] 10. The system of claim 1, further comprising means for displaying an image of the generated virtual partner.

[2080] (Claim 3)

[2081] means for transmitting information set by a user to a server;

[2082] means for receiving image data and conversation responses of the generated virtual partner from the server;

[2083] A means to provide ongoing interaction based on past conversation history;

[2084] The system of claim 1 further comprising:

[2085] "Application example 2 when combining emotion engines"

[2086] (Claim 1)

[2087] means for allowing a user to input ideal appearance and personality setting information;

[2088] A generating means for generating a virtual partner based on input appearance and personality setting information;

[2089] A communication means that stores conversation history with the user and provides natural interaction;

[2090] emotion recognition means for recognizing emotions from facial expression data of a user;

[2091] A means for realizing a dialogue between the generated virtual partner and the user in the virtual store;

[2092] A system including:

[2093] (Claim 2)

[2094] 10. The system of claim 1, further comprising means for displaying an image of the generated virtual partner.

[2095] (Claim 3)

[2096] means for transmitting information set by a user to a server;

[2097] means for receiving image data and conversation responses of the generated virtual partner from the server;

[2098] means for generating responses of the virtual partner using a generative AI model;

[2099] A means of inputting prompts into a generative AI model to obtain an appropriate response; and

[2100] The system of claim 1 further comprising: [Explanation of symbols]

[2101] 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 allowing a user to input ideal appearance and personality setting information; A generating means for generating a virtual partner based on input appearance and personality setting information; A communication means that stores conversation history with the user and provides natural interaction; A system including:

2. 10. The system of claim 1, further comprising means for displaying an image of the generated virtual partner.

3. means for transmitting information set by a user to a server; means for receiving image data and conversation responses of the generated virtual partner from the server; The system of claim 1 further comprising:

4. The system of claim 1 , further comprising means for utilizing a conversation history to provide continuous, natural conversational responses based on a conversation with the generated virtual partner.

Images