system

Abstract

We provide the system. [Solution] A generation means for generating the appearance and voice of a virtual character based on user selection, A communication means that provides communication with the generated virtual character, A recording means that records the conversation history between the user and the virtual character and provides a continuous conversation experience, A control means for deleting the user's conversation history and virtual character information and stopping communication based on the termination of the communication contract, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, many people lack someone with whom they can freely talk about their daily worries and complaints. Such a situation is a factor leading to the accumulation of individual stress and the deterioration of mental health. Also, for communication service providers, improving the customer contract renewal rate and preventing contract termination are issues. In order to solve these problems, there is a demand for providing a system in which a user can continuously talk with a virtual character of their preference.

Means for Solving the Problems

[0005] This invention provides a means for generating the appearance and voice of a virtual character by utilizing a generative AI model based on user selection. It also enables recording the history of conversations between the generated virtual character and the user, providing a continuous conversational experience. Furthermore, the invention proposes a system that includes control means for deleting the conversation history and virtual character information and suspending service use when the user cancels their communication contract. This system is expected to provide users with an experience that contributes to stress relief, and encourage communication service providers to promote contract continuation.

[0006] A "user" is a person who uses this system to customize a virtual character and engage in conversations with them.

[0007] A "virtual character" is a digital partner that is generated based on the user's choices and engages in conversations with the user.

[0008] "Generation means" refers to a part of a system that has the function of generating the appearance and voice of a virtual character based on user input data.

[0009] "Communication means" refers to functions for sending and receiving information such as messages and voice between the user and the virtual character.

[0010] "Recording means" refers to a part of a system that has the function of saving the conversation history between the user and the virtual character.

[0011] "Control measures" refer to a part of a system that has the function of deleting information about virtual characters and stopping service provision upon termination of a communication contract.

[0012] "Cloud" refers to a group of remote servers that provide data and services via the internet. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the 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.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0027] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is implemented as a system that enables users to enjoy continuous communication through a virtual character of their choice. This system provides the ability to customize the appearance and voice of the virtual character based on the user's choices, thereby realizing a continuous conversational experience with the user.

[0035] Character generation process

[0036] The user begins customizing a virtual character through the application. The user can select attributes such as eye color, hairstyle, and voice pitch. The device receives this selection information and sends it to the server. The server uses an AI generative model to generate the virtual character's face and voice based on the input data and saves this data to the cloud. Next, the server sends the generated virtual character to the device and displays it on the user's screen.

[0037] Conversation with a virtual character

[0038] The user enters a message into the chat screen to begin a conversation with a virtual character. The device receives this message and sends it to the server. The server generates a response using an AI conversation model, considering an appropriate reply based on the user's request. The generated response is then presented to the user through the device. The conversation history is always saved in the cloud by the server and referenced during subsequent conversations.

[0039] Service termination management

[0040] When a user cancels their communication contract, a cancellation notification is sent from the device to the server, and the information is updated. The server then triggers the complete deletion of the user's conversation history and character settings information from the cloud. As a result, the service is discontinued, and the user loses access to the system.

[0041] As a concrete example, suppose a user selects a "male character with a gentle voice" and starts a conversation with that character by asking, "How was your day?" In this case, the server can generate a response such as, "That's wonderful. What happened?" based on the conversation history. Through such interactions, users can receive emotional support through conversations with virtual characters.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The user launches the app and accesses the virtual character customization screen. The user sets their preferred attributes using an interface that allows them to select eye color, hairstyle, voice pitch, and more.

[0045] Step 2:

[0046] The device collects user customization information as data. This data is organized in JSON format and ready to be sent to the server.

[0047] Step 3:

[0048] The server inputs the customization information received from the terminal into the AI ​​generation model. Based on the input data, the server generates an image and voice of a virtual character and temporarily stores them in the cloud.

[0049] Step 4:

[0050] The server sends the generated virtual character data back to the terminal. Based on the received data, the terminal displays the virtual character on the user's screen.

[0051] Step 5:

[0052] To begin a conversation with a virtual character, the user types a message into the chat screen and sends it.

[0053] Step 6:

[0054] The device sends the user's message to the server. The message data is converted into an API format for communication with the server.

[0055] Step 7:

[0056] The server inputs the received message into an AI conversation model and generates a response corresponding to the user's message. The server also refers to past conversation history to create a personalized response.

[0057] Step 8:

[0058] The server sends the generated response back to the terminal, which then displays the response on the user's chat screen. The user then continues the conversation with the virtual character through this process.

[0059] Step 9:

[0060] The server saves the conversation history between the user and the virtual character to the cloud. This allows the user to refer to past conversations during subsequent conversations.

[0061] Step 10:

[0062] When a user cancels their communication contract, the device notifies the server of the cancellation information.

[0063] Step 11:

[0064] Upon receiving the cancellation information, the server deletes the user's conversation history and character settings from the cloud. The service is then shut down, and user access is restricted.

[0065] (Example 1)

[0066] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0067] Conventional virtual character interaction systems have struggled to dynamically generate the visual and auditory attributes of virtual characters based on user input, and have lacked sufficient recording and management capabilities to provide a continuous and consistent interaction experience. Furthermore, a lack of mechanisms to safely and reliably delete user data upon termination of a communication contract was a significant challenge.

[0068] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0069] In this invention, the server includes generation means for generating visual and auditory attributes of a virtual character based on user selection, communication means for providing interaction with the generated virtual character, and generation means for generating responses in response to user input using a learning model. This enables the user to obtain a dynamic and personalized interaction experience. Furthermore, by appropriately managing the interaction history and user information and securely deleting it upon termination of the communication contract, privacy protection can be enhanced.

[0070] "Generation means" refers to a device or software that has the function of generating the visual and auditory attributes of a virtual character based on the user's selection.

[0071] "Communication means" refers to the systems and network infrastructure used to provide interaction between the generated virtual character and the user.

[0072] "Recording means" refers to devices and technologies that record the history of conversations between a user and a virtual character and use that information to provide a continuous conversational experience.

[0073] "Control means" refers to a mechanism or process for deleting the user's dialogue history and virtual character information and stopping the dialogue based on the termination of the communication contract.

[0074] A "learning model" is an artificial intelligence technology used to generate responses in response to user input, and refers to a set of algorithms and devices that improve their performance based on data.

[0075] "Display means" refers to devices or software used to transmit information about the generated virtual character to the user's display device and visualize it on the screen.

[0076] "Management means" refers to a system or mechanism for properly saving and deleting conversation history using online storage.

[0077] This invention enables users to generate characters tailored to their individual preferences and enjoy continuous interaction with virtual characters through an interactive system. Specific embodiments will be described below.

[0078] First, the user begins customizing their virtual character using a dedicated application. The user can select attributes such as eye color, hairstyle, and voice pitch to suit their preferences. For example, a user might choose a character with "blue eyes and a high-pitched voice." The device collects this selection information and sends it to the server.

[0079] The server uses an AI generative model based on the received information to generate visual and auditory attributes for a virtual character. Machine learning libraries such as TENSORFLOW® and PyTorch are used. The generated character data is securely stored in cloud storage, and the server sends it to the user's terminal to visualize the character on a display device.

[0080] The user initiates a conversation with a virtual character through a chat screen. For example, they can enter a message such as, "What did you do today?" The device sends this message to the server, which uses a generative AI model to generate a response appropriate to the message. Possible models include ChatGPT®. This response is displayed to the user through the device, and the conversation is completed. The conversation history is stored in the cloud by the server and used to facilitate future conversations.

[0081] When a communication contract ends, the user sends a cancellation notice through their device. The server receives this notice and completely deletes the user's conversation history and character settings information stored in cloud storage. This restricts future access.

[0082] This system is compatible with various devices and enables flexible operation. It promotes a natural and engaging interaction experience with virtual characters to provide users with a sense of psychological security.

[0083] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0084] Step 1:

[0085] The user launches the application and accesses the virtual character customization screen. The user selects eye color, hairstyle, and voice pitch. The input is the user's selection information, which is sent to the terminal. The terminal aggregates this information and sends it to the server. The output is the completion of sending the selection information to the server.

[0086] Step 2:

[0087] The server analyzes user selection information received from the terminal. The input is user selection information, and an AI generative model is used to generate the visual and auditory attributes of a virtual character. Data processing involves information analysis and generation by the AI ​​model. The output is the data of the generated virtual character.

[0088] Step 3:

[0089] Data for a virtual character generated from the server is sent to the terminal. The input is the generated character data, which the terminal receives and displays on its display device. The output is the virtual character displayed on the user's screen.

[0090] Step 4:

[0091] The user initiates a conversation with a virtual character through a chat screen. For example, they might type, "How was your day?" The input is the user's message, and the device sends this information to the server. The output indicates that the message has been successfully sent to the server.

[0092] Step 5:

[0093] When the server receives a message from a user, it uses a generative AI model to generate an appropriate response. The input consists of the user's message and past conversation history. Data processing involves message analysis and response generation by the AI ​​model. The output is the generated response.

[0094] Step 6:

[0095] The response generated by the server is sent to the terminal and presented to the user. The input is the generated response, which the terminal displays on the user's screen. The output is the response presented to the user.

[0096] Step 7:

[0097] When a user cancels their communication contract, a cancellation notification is sent from the device to the server. The input is the cancellation notification, and the server receives this notification. The output is a confirmation that the cancellation notification has been received.

[0098] Step 8:

[0099] Upon receiving a cancellation notice, the server deletes the user's conversation history and character settings information stored in the cloud. The input is the trigger information for the cancellation procedure, and the data processing is the deletion process of the stored data. The output is the completion of the complete deletion of the user data.

[0100] (Application Example 1)

[0101] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0102] Existing virtual character systems limit user communication to simple conversations, failing to adequately provide information and content recommendations based on individual preferences. This makes it difficult to broadly support the entertainment experiences users desire.

[0103] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0104] In this invention, the server includes generation means for generating the appearance and voice of a virtual character based on user selection, information provision means for providing information and recommending entertainment to the user through the generated virtual character, and communication means for providing communication with the generated virtual character. This makes it possible to provide information and content tailored to the user's preferences in real time, enhancing the individualized entertainment experience.

[0105] A "user" refers to a person who uses the system and is the entity that receives communication and information through virtual characters.

[0106] A "virtual character" is a digital personality generated based on user choices, and it serves the role of communication and information provision.

[0107] "Generation means" refers to the process or device for creating the appearance and voice of a virtual character based on user input.

[0108] "Information provision means" refers to a function or device that recommends information and content tailored to the individual preferences of a user through a virtual character.

[0109] "Communication means" refers to methods and devices that enable two-way communication between the user and the virtual character.

[0110] "Recording means" refers to processes and devices for saving conversation history and related information between a user and a virtual character.

[0111] "Control means" refers to a function or device for managing user information based on the termination of a communication contract and deleting data as necessary.

[0112] The system used to implement this application consists of server, terminal, and user elements.

[0113] The server receives character attribute selection information entered by the user through the terminal and uses a generative AI model to generate data for the appearance and voice of a virtual character. The generated data is stored in cloud storage and sent to the terminal. In this process, the server executes Python programs and uses PyTorch / TensorFlow, etc., for data processing.

[0114] The terminal receives virtual character data sent from the server and displays it on the user interface. The user can then begin interacting with the virtual character via voice or text. In entertainment information provision, the server suggests relevant content through information provision means in response to user input requests and returns the results to the terminal in real time.

[0115] For example, if a user types "Tell me about the latest action movie," the server analyzes the user's past preferences and viewing history and recommends a suitable movie. A concrete example of a prompt would be if a user typed "Tell me about a good science fiction novel," to which a virtual character would respond, "A recent noteworthy work is XX. Are you interested in the content?"

[0116] In this way, the system can enhance the user's entertainment experience through information provision and personalized recommendations via virtual characters.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The user begins customizing a virtual character on a device such as a smartphone. Through the device's interface, the user selects and inputs multiple attributes, such as eye color, hairstyle, and voice pitch. This selection information is then transmitted as digital data to the server by the device.

[0120] Step 2:

[0121] The server receives selection information from the terminal as input and uses an AI generative model to generate appearance and voice data for a virtual character. In practice, frameworks such as PyTorch and TensorFlow are used for processing this data. The generated digital data is stored in cloud storage and sent from the server to the terminal.

[0122] Step 3:

[0123] The terminal receives virtual character data sent from the server and displays it to the user. Rendering technology is used for this display, allowing the user to visually encounter a customized character.

[0124] Step 4:

[0125] The user begins interacting with the displayed virtual character via voice or text. When the user types a text message such as "Tell me the latest movies" into the device, the device sends that message to the server.

[0126] Step 5:

[0127] The server receives a message from the user as input and uses natural language processing to generate a response based on the prompt. Using a generative AI model, the server processes relevant content based on the user's preferences and history and outputs recommended information. The generated information is sent to the terminal.

[0128] Step 6:

[0129] The terminal presents the user with information received from the server. For example, in movie recommendations, a virtual character will deliver a generated prompt message to the user via voice or text, saying, "Our recommended movie is XX." This allows the user to receive entertainment information through the virtual character.

[0130] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0131] This invention is implemented as a system that not only allows users to continuously enjoy communication with their preferred virtual character, but also enables dialogue that takes into account their emotional state during that time. This system analyzes the user's emotions using an emotion engine and adaptively adjusts the virtual character's responses and actions based on that information.

[0132] Character and emotional interaction

[0133] When a user begins a conversation with a virtual character, the device collects the user's voice and text input in real time. The user's input is analyzed by an emotion engine to identify their emotional state. For example, if a user says, "I'm busy and tired," the emotion engine recognizes the user's emotion as "fatigue."

[0134] The server receives this emotional information and adjusts the AI ​​conversation model's response. Specifically, if it detects that the user is tired, the virtual character generates an empathetic response such as, "You've had a tough day. Get some rest." This response is then presented to the user through the device.

[0135] Managing conversation history and sentiment data

[0136] The server stores user-virtual character interactions and detected emotion information in a cloud-based database. This data is used to provide a more personalized experience in subsequent interactions. For example, if the user's "fatigue" is frequently detected in previous conversations, the virtual character will periodically respond with inquiries about the user's well-being.

[0137] Service and data lifecycle management

[0138] If a user cancels their communication contract, the device sends information to the server indicating that continued use is no longer possible. Based on this, the server completely deletes the conversation history, emotion data, and character setting information stored in the cloud. The service is immediately terminated, and the user ends their interaction with the virtual character.

[0139] This system dynamically changes its response in accordance with the user's emotions, providing a simulated experience of social interaction and designed to allow users to receive psychological support. In addition, it has a mechanism in place to protect privacy through the proper management of data, including emotional information, and to ensure that information is reliably deleted when the contract is terminated.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] The user launches the app and accesses the chat function with the virtual character. The user enters a message in the text input field displayed on the screen and presses the send button.

[0143] Step 2:

[0144] The terminal receives user input messages and sends them to the server as voice or text data. This data is processed in real time, enabling rapid communication.

[0145] Step 3:

[0146] The server passes the received message to the emotion engine, which performs sentiment analysis. The emotion engine analyzes keywords and context in the message to identify the user's emotional state (e.g., joy, anger, sadness, relief).

[0147] Step 4:

[0148] The server adjusts the response generated by the AI ​​conversation model based on emotional information obtained from the emotion engine. For example, if the user says "I'm tired," the response would be something like "Get some rest."

[0149] Step 5:

[0150] The server sends a pre-arranged response message to the terminal. The terminal displays the received message on the user's chat screen.

[0151] Step 6:

[0152] The server stores the user's interaction history with the virtual character, as well as detected emotion data, in the cloud. This allows the system to accumulate data on the user's state over time and use it as context for future interactions.

[0153] Step 7:

[0154] If the user wishes to continue the conversation with the virtual character, the process from step 1 is repeated. Various responses based on emotional information allow for a more human-like and enjoyable continuation of the conversation with the virtual character.

[0155] Step 8:

[0156] When a user cancels their communication contract, that information is sent from the device to the server. Upon receiving the cancellation notification, the server terminates the service while protecting privacy by deleting the relevant conversation history and sentiment data from the cloud.

[0157] (Example 2)

[0158] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0159] In recent years, there has been a growing demand for systems that provide users with personalized experiences through interaction with virtual characters. However, existing systems often struggle to accurately reflect the user's emotional state, resulting in monotonous and inefficient conversations. Furthermore, the proper management of users' personal information and emotional data, as well as the protection of their privacy, are also important issues. This invention aims to solve these problems and provide users with a more natural and emotionally resonant conversational experience.

[0160] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0161] In this invention, the server includes means for generating the appearance and voice of a virtual character based on user selection, means for collecting user input and performing sentiment analysis, and means for generating responses of the virtual character using a generative AI model. This enables the generation of customized responses that take into account the user's emotional state.

[0162] A "user" refers to someone who interacts with a virtual character and utilizes the system in the process.

[0163] A "virtual character" refers to a digital entity created by a computer program that mimics a person or living being, generated for the purpose of interacting with users.

[0164] "Appearance" refers to the visual characteristics and design of a virtual character.

[0165] "Voice" refers to the information of words and voices spoken by virtual characters.

[0166] "Generation means" refers to methods or devices for creating the appearance and voice of a virtual character based on user selections.

[0167] "Communication means" refers to methods and devices for exchanging information between virtual characters and users.

[0168] "Recording means" refers to a device or method that has the function of saving the conversation history between the user and the virtual character and retrieving it as needed.

[0169] "Control means" refers to a device or method that evaluates based on specific conditions, such as the termination of a communication contract, and performs the necessary processing.

[0170] A "terminal" refers to an electronic device used by a user to interact with a virtual character.

[0171] "Emotion analysis" refers to a technical method for identifying a user's emotional state from their input information.

[0172] A "generative AI model" refers to an algorithm or program that generates responses from a virtual character based on the user's emotions.

[0173] A "prompt statement" refers to an input statement used to instruct a generative AI model to generate a desired response.

[0174] "Cloud" is a general term for computer resources and services provided via the internet.

[0175] This invention is a system that allows users to have a deep, emotionally responsive dialogue experience through conversations with a virtual character. Based on voice and text data provided by the user, this system uses an emotion engine to analyze the user's emotional state and then uses a generative AI model to generate responses from the virtual character based on the results.

[0176] First, the user speaks to a virtual character using their device. The device uses voice processing software to convert the user's voice into text data and sends it to the emotion engine. The emotion engine uses natural language processing technology to identify the user's emotional state from their input and recognize it as a specific emotion such as "fatigue" or "joy."

[0177] Next, the server sends a prompt to the generative AI model based on the received emotional information. This prompt might be written in the form of, for example, "How should the virtual character respond when the user is complaining of fatigue?" The generative AI model analyzes the prompt and generates a response that is empathetic to the user's emotions. The server sends this response to the terminal, which then presents the response to the user.

[0178] This allows users to experience dynamic, emotion-based dialogue. For example, if a user says, "I'm busy and tired," the virtual character might respond with something like, "You've had a tough day. Take a good rest," providing empathy and reassurance. The system also uses a cloud-based database to save conversation history and emotion data, which can then be used to improve future interactions.

[0179] This design allows the system to provide psychological support to users while ensuring the proper management of personal data.

[0180] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0181] Step 1:

[0182] The user speaks to a virtual character through the device or enters text. In the case of voice input, the device uses speech processing software to convert this audio into text data. At this stage, the input is the user's raw voice or text data, and the output is text data obtained through speech recognition. Specifically, the microphone captures the audio, and that data is instantly converted into text.

[0183] Step 2:

[0184] The device sends this text data to the emotion engine. The emotion engine uses natural language processing techniques to analyze keywords and expressions in the text and identify the user's emotional state. The input is text data, and the output is the identified emotional state (e.g., "fatigue" or "joy"). Specifically, the emotion engine analyzes the text and compares it with a pre-trained emotion database to determine the emotion.

[0185] Step 3:

[0186] The terminal sends identified emotion data to the server. The server uses the received emotion data to create and send a prompt to a generative AI model. The prompt might be written as, "How should the virtual character respond when the user is feeling 'fatigued'?" The input is emotion data, and the output is the prompt generated based on it. Specifically, a prompt generation algorithm runs within the server.

[0187] Step 4:

[0188] The generative AI model analyzes the prompt text and generates an appropriate response. The generated response is then presented as a dialogue between virtual characters. The input is the prompt text, and the output is the response text that the user will see and hear. For example, the AI ​​model can create empathetic responses such as, "You had a tough day. Get some rest."

[0189] Step 5:

[0190] The server sends this generated response to the terminal and presents it to the user. The terminal uses speech synthesis software to output the response as audio or displays it as text on its screen. The input is the generated response, and the output is the audio or visualized text that the user experiences. Specifically, the speaker outputs the response as audio, or the text is displayed on the screen.

[0191] Step 6:

[0192] The server stores the content and sentiment data of conversations in a cloud database. This data is used to provide a personalized experience in subsequent conversations. The input is conversation history data, and the output is updated and saved database entries. Specifically, a database management system runs in the backend to organize and store the data.

[0193] (Application Example 2)

[0194] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0195] In modern information exchange experiences using information processing devices, responses that take user emotions into consideration are often lacking. Therefore, there is a need for means to accurately analyze the emotions users feel and provide appropriate support based on that analysis. Furthermore, properly managing user conversation records and emotion analysis information, and protecting privacy, are also crucial issues.

[0196] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0197] In this invention, the server includes an analysis means for analyzing the user's emotions and adjusting the response according to the analyzed emotions, a support means for providing support based on the user's emotions during information exchange, and a management means for managing the storage and deletion of conversation records using an information processing infrastructure. This enables the provision of flexible responses and support according to the user's emotions, realizing a more personalized information exchange experience.

[0198] A "user" refers to an individual who uses a system or information processing device.

[0199] "Visual information" refers to virtual images and characters generated based on user selections, and is information that includes visual elements.

[0200] "Auditory information" refers to virtual voices and sounds generated as acoustic signals, and is information that includes auditory elements.

[0201] "Generation means" refers to devices or systems that generate visual or audio information based on user selections.

[0202] "Communication means" refers to the means of exchanging information between the user and visual information, and includes devices and protocols that enable interaction.

[0203] "Conversation record" refers to the history of information exchange between the user and visual information.

[0204] "Recording means" refers to devices or systems used to save conversation records and utilize them for future, ongoing information provision experiences.

[0205] "Control means" refers to devices or systems that delete user conversation records and visual information and terminate information exchange upon termination of a communication contract.

[0206] "Analysis means" refers to devices or systems that analyze the user's emotions and adjust the response of visual information according to the analysis results.

[0207] "Support measures" refer to devices and systems that provide appropriate support based on the user's emotions.

[0208] An "information processing device" refers to a terminal or device used to process and display information.

[0209] "Information processing infrastructure" refers to the infrastructure, including clouds and servers, used for managing data storage and deletion.

[0210] The system of this invention aims to generate visual and auditory information that takes into account the user's emotional state, and to improve the user's information exchange experience. This system is implemented using the following hardware and software.

[0211] The server uses an emotion engine to analyze voice or text input from the user. This process utilizes a speech analysis library such as Google® Cloud Speech-to-Text API. Based on the analyzed emotion data, the server generates a response through an AI conversation model (e.g., ChatGPT-4®). This process uses a generative AI model to provide emotion-adaptive responses.

[0212] The terminal receives input from the user and sends that information to the server. It also receives responses from the server and displays them on the information processing device to present them to the user as visual and audio information. Smartphones are commonly used as the information processing device for this purpose.

[0213] Users continuously exchange information with the system through dialogue. For example, if the system analyzes information indicating that the user is feeling stressed, it will present a supportive message such as, "Thank you for your hard work. We have some tips to help you relax on your next shopping trip."

[0214] For example, if a user in a cafe says, "I've been so busy lately, I'm exhausted," the system recognizes this emotion and makes a positive suggestion such as, "Why not try a new latte on a day like that?"

[0215] An example of a prompt for a generative AI model would be: "If a user says they are tired, what refreshing methods can you suggest? Please provide some ideas for relaxing the mind and body."

[0216] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0217] Step 1:

[0218] The device collects the user's voice or text input. The input data, consisting of words and voice that reflect the user's emotions, is transmitted to the server in real time.

[0219] Step 2:

[0220] The server analyzes user input data using a speech analysis library (e.g., Google Cloud Speech-to-Text API). During this process, calculations are performed to convert speech and text data into emotional data, identifying the user's emotional state. The output is index data indicating the emotional state.

[0221] Step 3:

[0222] The server provides an AI generator (e.g., ChatGPT-4) with the user's emotional state as input and generates an appropriate response for the user. At this stage, a prompt that takes the emotional state into account is sent to the AI ​​generator. The output is a personalized response message tailored to the user.

[0223] Step 4:

[0224] The server sends a generated response message to the terminal. This message includes positive suggestions and support messages tailored to the user's emotional state.

[0225] Step 5:

[0226] The terminal presents the response message received from the server to the user as visual or audio information. Output is information conveyed to the user through a screen or audio output device.

[0227] Step 6:

[0228] The user receives the presented information and decides on their next action. The user's response is collected as new input, returning to step 1, to improve future information exchange experiences.

[0229] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0230] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0231] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0232] [Second Embodiment]

[0233] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0234] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0235] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0236] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0237] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0238] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0239] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0240] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0241] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0242] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0243] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0244] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0245] This invention is implemented as a system that enables users to enjoy continuous communication through a virtual character of their choice. This system provides the ability to customize the appearance and voice of the virtual character based on the user's choices, thereby realizing a continuous conversational experience with the user.

[0246] Character generation process

[0247] The user begins customizing a virtual character through the application. The user can select attributes such as eye color, hairstyle, and voice pitch. The device receives this selection information and sends it to the server. The server uses an AI generative model to generate the virtual character's face and voice based on the input data and saves this data to the cloud. Next, the server sends the generated virtual character to the device and displays it on the user's screen.

[0248] Conversation with a virtual character

[0249] The user enters a message into the chat screen to begin a conversation with a virtual character. The device receives this message and sends it to the server. The server generates a response using an AI conversation model, considering an appropriate reply based on the user's request. The generated response is then presented to the user through the device. The conversation history is always saved in the cloud by the server and referenced during subsequent conversations.

[0250] Service termination management

[0251] When a user cancels their communication contract, a cancellation notification is sent from the device to the server, and the information is updated. The server then triggers the complete deletion of the user's conversation history and character settings information from the cloud. As a result, the service is discontinued, and the user loses access to the system.

[0252] As a concrete example, suppose a user selects a "male character with a gentle voice" and starts a conversation with that character by asking, "How was your day?" In this case, the server can generate a response such as, "That's wonderful. What happened?" based on the conversation history. Through such interactions, users can receive emotional support through conversations with virtual characters.

[0253] The following describes the processing flow.

[0254] Step 1:

[0255] The user launches the app and accesses the virtual character customization screen. The user sets their preferred attributes using an interface that allows them to select eye color, hairstyle, voice pitch, and more.

[0256] Step 2:

[0257] The device collects user customization information as data. This data is organized in JSON format and ready to be sent to the server.

[0258] Step 3:

[0259] The server inputs the customization information received from the terminal into the AI ​​generation model. Based on the input data, the server generates an image and voice of a virtual character and temporarily stores them in the cloud.

[0260] Step 4:

[0261] The server sends the generated virtual character data back to the terminal. Based on the received data, the terminal displays the virtual character on the user's screen.

[0262] Step 5:

[0263] To begin a conversation with a virtual character, the user types a message into the chat screen and sends it.

[0264] Step 6:

[0265] The device sends the user's message to the server. The message data is converted into an API format for communication with the server.

[0266] Step 7:

[0267] The server inputs the received message into an AI conversation model and generates a response corresponding to the user's message. The server also refers to past conversation history to create a personalized response.

[0268] Step 8:

[0269] The server sends the generated response back to the terminal, which then displays the response on the user's chat screen. The user then continues the conversation with the virtual character through this process.

[0270] Step 9:

[0271] The server saves the conversation history between the user and the virtual character to the cloud. This allows the user to refer to past conversations during subsequent conversations.

[0272] Step 10:

[0273] When a user cancels their communication contract, the device notifies the server of the cancellation information.

[0274] Step 11:

[0275] Upon receiving the cancellation information, the server deletes the user's conversation history and character settings from the cloud. The service is then shut down, and user access is restricted.

[0276] (Example 1)

[0277] Next, we will describe Example 1. 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."

[0278] Conventional virtual character interaction systems have struggled to dynamically generate the visual and auditory attributes of virtual characters based on user input, and have lacked sufficient recording and management capabilities to provide a continuous and consistent interaction experience. Furthermore, a lack of mechanisms to safely and reliably delete user data upon termination of a communication contract was a significant challenge.

[0279] 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.

[0280] In this invention, the server includes a generation means for generating visual and auditory attributes of a virtual character based on a user's selection, a communication means for providing interaction with the generated virtual character, and a generation means for generating a response according to a user's input using a learning model. Thereby, the user can obtain a dynamic and personalized interaction experience. Also, by appropriately managing the interaction history and user information and securely deleting them at the end of the communication contract, the improvement of privacy protection can be achieved.

[0281] The "generation means" refers to a device or software having a function of generating visual and auditory attributes of a virtual character based on a user's selection.

[0282] The "communication means" refers to a system or network infrastructure used to provide interaction between the generated virtual character and the user.

[0283] The "recording means" refers to a device or technology for recording the interaction history between the user and the virtual character and using it to assist in providing a continuous interaction experience.

[0284] / The "control means" refers to a mechanism or process for deleting the user's interaction history and virtual character information and stopping the interaction based on the end of the communication contract.

[0285] The "learning model" refers to an artificial intelligence technology used to generate a response according to a user's input, and refers to a collection of algorithms and devices that improve their own performance based on data.

[0286] The "display means" refers to a device or software used to transmit information of the generated virtual character to the user's display device and visualize it on the screen.

[0287] The "management means" refers to a system or mechanism for appropriately storing and deleting conversation histories using online storage.

[0288] This invention enables a user to generate a character that suits their individual preferences and continuously enjoy conversations by using an interactive system with a virtual character. Here, specific embodiments will be described.

[0289] First, the user starts customizing a virtual character using a dedicated application. The user can select attributes such as eye color, hairstyle, and voice pitch according to their preferences. For example, the user can select a character with "blue eyes and a high-pitched voice". The terminal collects this selection information and sends it to the server.

[0290] Based on the received information, the server utilizes an AI generation model to generate visual and auditory attributes of the virtual character. Machine learning libraries such as TensorFlow and PyTorch are used. The generated character data is securely stored in cloud storage, and the server visualizes the character on the display device by sending this to the user's terminal.

[0291] The user starts a conversation with the virtual character from the chat screen. For example, a message such as "What did you do today?" can be input. The terminal sends this message to the server, and the server uses the generation AI model to generate a response suitable for this message. Models such as ChatGPT can be considered. This response is displayed to the user through the terminal, and a conversation is established. The conversation history is stored in the cloud by the server and used for the next conversation.

[0292] When a communication contract ends, the user sends a cancellation notice through their device. The server receives this notice and completely deletes the user's conversation history and character settings information stored in cloud storage. This restricts future access.

[0293] This system is compatible with various devices and enables flexible operation. It promotes a natural and engaging interaction experience with virtual characters to provide users with a sense of psychological security.

[0294] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0295] Step 1:

[0296] The user launches the application and accesses the virtual character customization screen. The user selects eye color, hairstyle, and voice pitch. The input is the user's selection information, which is sent to the terminal. The terminal aggregates this information and sends it to the server. The output is the completion of sending the selection information to the server.

[0297] Step 2:

[0298] The server analyzes user selection information received from the terminal. The input is user selection information, and an AI generative model is used to generate the visual and auditory attributes of a virtual character. Data processing involves information analysis and generation by the AI ​​model. The output is the data of the generated virtual character.

[0299] Step 3:

[0300] Data for a virtual character generated from the server is sent to the terminal. The input is the generated character data, which the terminal receives and displays on its display device. The output is the virtual character displayed on the user's screen.

[0301] Step 4:

[0302] The user starts a conversation with the virtual character through the chat screen. For example, the user enters "How was your day today?". The input is the user's message, and the terminal sends this information to the server. The output is the completion of sending the message to the server.

[0303] Step 5:

[0304] When the server receives the message from the user, it uses the generation AI model to generate an appropriate response. The input is the user's message and the past conversation history. The data operation is the message analysis and response generation by the AI model. The output is the generated response text.

[0305] Step 6:

[0306] The response text generated by the server is sent to the terminal and presented to the user. The input is the generated response text, and the terminal displays this on the user's screen. The output is the response content presented to the user.

[0307] Step 7:

[0308] When the user cancels the communication contract, a cancellation notice is sent from the terminal to the server. The input is the cancellation notice, and the server receives this notice. The output is the receipt confirmation of the cancellation notice.

[0309] Step 8:

[0310] Triggered by the cancellation notice, the server deletes the user's conversation history and character setting information stored in the cloud. The input is the trigger information for the cancellation procedure, and the data processing is the deletion process of the storage data. The output is the complete deletion of the user data.

[0311] (Application Example 1)

[0312] <000098_3>Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0313] Existing virtual character systems limit user communication to simple conversations, failing to adequately provide information and content recommendations based on individual preferences. This makes it difficult to broadly support the entertainment experiences users desire.

[0314] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0315] In this invention, the server includes generation means for generating the appearance and voice of a virtual character based on user selection, information provision means for providing information and recommending entertainment to the user through the generated virtual character, and communication means for providing communication with the generated virtual character. This makes it possible to provide information and content tailored to the user's preferences in real time, enhancing the individualized entertainment experience.

[0316] A "user" refers to a person who uses the system and is the entity that receives communication and information through virtual characters.

[0317] A "virtual character" is a digital personality generated based on user choices, and it serves the role of communication and information provision.

[0318] "Generation means" refers to the process or device for creating the appearance and voice of a virtual character based on user input.

[0319] "Information provision means" refers to a function or device that recommends information and content tailored to the individual preferences of a user through a virtual character.

[0320] "Communication means" refers to methods and devices that enable two-way communication between the user and the virtual character.

[0321] "Recording means" refers to processes and devices for saving conversation history and related information between a user and a virtual character.

[0322] "Control means" refers to a function or device for managing user information based on the termination of a communication contract and deleting data as necessary.

[0323] The system used to implement this application consists of server, terminal, and user elements.

[0324] The server receives character attribute selection information entered by the user through the terminal and uses a generative AI model to generate data for the appearance and voice of a virtual character. The generated data is stored in cloud storage and sent to the terminal. In this process, the server executes Python programs and uses PyTorch / TensorFlow, etc., for data processing.

[0325] The terminal receives virtual character data sent from the server and displays it on the user interface. The user can then begin interacting with the virtual character via voice or text. In entertainment information provision, the server suggests relevant content through information provision means in response to user input requests and returns the results to the terminal in real time.

[0326] For example, if a user types "Tell me about the latest action movie," the server analyzes the user's past preferences and viewing history and recommends a suitable movie. A concrete example of a prompt would be if a user typed "Tell me about a good science fiction novel," to which a virtual character would respond, "A recent noteworthy work is XX. Are you interested in the content?"

[0327] In this way, the system can enhance the user's entertainment experience through information provision and personalized recommendations via virtual characters.

[0328] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0329] Step 1:

[0330] The user begins customizing a virtual character on a device such as a smartphone. Through the device's interface, the user selects and inputs multiple attributes, such as eye color, hairstyle, and voice pitch. This selection information is then transmitted as digital data to the server by the device.

[0331] Step 2:

[0332] The server receives selection information from the terminal as input and uses an AI generative model to generate appearance and voice data for a virtual character. In practice, frameworks such as PyTorch and TensorFlow are used for processing this data. The generated digital data is stored in cloud storage and sent from the server to the terminal.

[0333] Step 3:

[0334] The terminal receives virtual character data sent from the server and displays it to the user. Rendering technology is used for this display, allowing the user to visually encounter a customized character.

[0335] Step 4:

[0336] The user begins interacting with the displayed virtual character via voice or text. When the user types a text message such as "Tell me the latest movies" into the device, the device sends that message to the server.

[0337] Step 5:

[0338] The server receives a message from the user as input and uses natural language processing to generate a response based on the prompt. Using a generative AI model, the server processes relevant content based on the user's preferences and history and outputs recommended information. The generated information is sent to the terminal.

[0339] Step 6:

[0340] The terminal presents the user with information received from the server. For example, in movie recommendations, a virtual character will deliver a generated prompt message to the user via voice or text, saying, "Our recommended movie is XX." This allows the user to receive entertainment information through the virtual character.

[0341] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0342] This invention is implemented as a system that not only allows users to continuously enjoy communication with their preferred virtual character, but also enables dialogue that takes into account their emotional state during that time. This system analyzes the user's emotions using an emotion engine and adaptively adjusts the virtual character's responses and actions based on that information.

[0343] Character and emotional interaction

[0344] When a user begins a conversation with a virtual character, the device collects the user's voice and text input in real time. The user's input is analyzed by an emotion engine to identify their emotional state. For example, if a user says, "I'm busy and tired," the emotion engine recognizes the user's emotion as "fatigue."

[0345] The server receives this emotional information and adjusts the AI ​​conversation model's response. Specifically, if it detects that the user is tired, the virtual character generates an empathetic response such as, "You've had a tough day. Get some rest." This response is then presented to the user through the device.

[0346] Managing conversation history and sentiment data

[0347] The server stores user-virtual character interactions and detected emotion information in a cloud-based database. This data is used to provide a more personalized experience in subsequent interactions. For example, if the user's "fatigue" is frequently detected in previous conversations, the virtual character will periodically respond with inquiries about the user's well-being.

[0348] Service and data lifecycle management

[0349] If a user cancels their communication contract, the device sends information to the server indicating that continued use is no longer possible. Based on this, the server completely deletes the conversation history, emotion data, and character setting information stored in the cloud. The service is immediately terminated, and the user ends their interaction with the virtual character.

[0350] This system dynamically changes its response in accordance with the user's emotions, providing a simulated experience of social interaction and designed to allow users to receive psychological support. In addition, it has a mechanism in place to protect privacy through the proper management of data, including emotional information, and to ensure that information is reliably deleted when the contract is terminated.

[0351] The following describes the processing flow.

[0352] Step 1:

[0353] The user launches the app and accesses the chat function with the virtual character. The user enters a message in the text input field displayed on the screen and presses the send button.

[0354] Step 2:

[0355] The terminal receives user input messages and sends them to the server as voice or text data. This data is processed in real time, enabling rapid communication.

[0356] Step 3:

[0357] The server passes the received message to the emotion engine, which performs sentiment analysis. The emotion engine analyzes keywords and context in the message to identify the user's emotional state (e.g., joy, anger, sadness, relief).

[0358] Step 4:

[0359] The server adjusts the response generated by the AI ​​conversation model based on emotional information obtained from the emotion engine. For example, if the user says "I'm tired," the response would be something like "Get some rest."

[0360] Step 5:

[0361] The server sends a pre-arranged response message to the terminal. The terminal displays the received message on the user's chat screen.

[0362] Step 6:

[0363] The server stores the user's interaction history with the virtual character, as well as detected emotion data, in the cloud. This allows the system to accumulate data on the user's state over time and use it as context for future interactions.

[0364] Step 7:

[0365] If the user wishes to continue the conversation with the virtual character, the process from step 1 is repeated. Various responses based on emotional information allow for a more human-like and enjoyable continuation of the conversation with the virtual character.

[0366] Step 8:

[0367] When a user cancels their communication contract, that information is sent from the device to the server. Upon receiving the cancellation notification, the server terminates the service while protecting privacy by deleting the relevant conversation history and sentiment data from the cloud.

[0368] (Example 2)

[0369] Next, we will describe Example 2. 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".

[0370] In recent years, there has been a growing demand for systems that provide users with personalized experiences through interaction with virtual characters. However, existing systems often struggle to accurately reflect the user's emotional state, resulting in monotonous and inefficient conversations. Furthermore, the proper management of users' personal information and emotional data, as well as the protection of their privacy, are also important issues. This invention aims to solve these problems and provide users with a more natural and emotionally resonant conversational experience.

[0371] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0372] In this invention, the server includes means for generating the appearance and voice of a virtual character based on user selection, means for collecting user input and performing sentiment analysis, and means for generating responses of the virtual character using a generative AI model. This enables the generation of customized responses that take into account the user's emotional state.

[0373] A "user" refers to someone who interacts with a virtual character and utilizes the system in the process.

[0374] A "virtual character" refers to a digital entity created by a computer program that mimics a person or living being, generated for the purpose of interacting with users.

[0375] "Appearance" refers to the visual characteristics and design of a virtual character.

[0376] "Voice" refers to the information of words and voices spoken by virtual characters.

[0377] "Generation means" refers to methods or devices for creating the appearance and voice of a virtual character based on user selections.

[0378] "Communication means" refers to methods and devices for exchanging information between virtual characters and users.

[0379] "Recording means" refers to a device or method that has the function of saving the conversation history between the user and the virtual character and retrieving it as needed.

[0380] "Control means" refers to a device or method that evaluates based on specific conditions, such as the termination of a communication contract, and performs the necessary processing.

[0381] A "terminal" refers to an electronic device used by a user to interact with a virtual character.

[0382] "Emotion analysis" refers to a technical method for identifying a user's emotional state from their input information.

[0383] A "generative AI model" refers to an algorithm or program that generates responses from a virtual character based on the user's emotions.

[0384] A "prompt statement" refers to an input statement used to instruct a generative AI model to generate a desired response.

[0385] "Cloud" is a general term for computer resources and services provided via the internet.

[0386] This invention is a system that allows users to have a deep, emotionally responsive dialogue experience through conversations with a virtual character. Based on voice and text data provided by the user, this system uses an emotion engine to analyze the user's emotional state and then uses a generative AI model to generate responses from the virtual character based on the results.

[0387] First, the user speaks to a virtual character using their device. The device uses voice processing software to convert the user's voice into text data and sends it to the emotion engine. The emotion engine uses natural language processing technology to identify the user's emotional state from their input and recognize it as a specific emotion such as "fatigue" or "joy."

[0388] Next, the server sends a prompt to the generative AI model based on the received emotional information. This prompt might be written in the form of, for example, "How should the virtual character respond when the user is complaining of fatigue?" The generative AI model analyzes the prompt and generates a response that is empathetic to the user's emotions. The server sends this response to the terminal, which then presents the response to the user.

[0389] This allows users to experience dynamic, emotion-based dialogue. For example, if a user says, "I'm busy and tired," the virtual character might respond with something like, "You've had a tough day. Take a good rest," providing empathy and reassurance. The system also uses a cloud-based database to save conversation history and emotion data, which can then be used to improve future interactions.

[0390] This design allows the system to provide psychological support to users while ensuring the proper management of personal data.

[0391] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0392] Step 1:

[0393] The user speaks to a virtual character through the device or enters text. In the case of voice input, the device uses speech processing software to convert this audio into text data. At this stage, the input is the user's raw voice or text data, and the output is text data obtained through speech recognition. Specifically, the microphone captures the audio, and that data is instantly converted into text.

[0394] Step 2:

[0395] The device sends this text data to the emotion engine. The emotion engine uses natural language processing techniques to analyze keywords and expressions in the text and identify the user's emotional state. The input is text data, and the output is the identified emotional state (e.g., "fatigue" or "joy"). Specifically, the emotion engine analyzes the text and compares it with a pre-trained emotion database to determine the emotion.

[0396] Step 3:

[0397] The terminal sends identified emotion data to the server. The server uses the received emotion data to create and send a prompt to a generative AI model. The prompt might be written as, "How should the virtual character respond when the user is feeling 'fatigued'?" The input is emotion data, and the output is the prompt generated based on it. Specifically, a prompt generation algorithm runs within the server.

[0398] Step 4:

[0399] The generative AI model analyzes the prompt text and generates an appropriate response. The generated response is then presented as a dialogue between virtual characters. The input is the prompt text, and the output is the response text that the user will see and hear. For example, the AI ​​model can create empathetic responses such as, "You had a tough day. Get some rest."

[0400] Step 5:

[0401] The server sends this generated response to the terminal and presents it to the user. The terminal uses speech synthesis software to output the response as audio or displays it as text on its screen. The input is the generated response, and the output is the audio or visualized text that the user experiences. Specifically, the speaker outputs the response as audio, or the text is displayed on the screen.

[0402] Step 6:

[0403] The server stores the content and sentiment data of conversations in a cloud database. This data is used to provide a personalized experience in subsequent conversations. The input is conversation history data, and the output is updated and saved database entries. Specifically, a database management system runs in the backend to organize and store the data.

[0404] (Application Example 2)

[0405] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0406] In modern information exchange experiences using information processing devices, responses that take user emotions into consideration are often lacking. Therefore, there is a need for means to accurately analyze the emotions users feel and provide appropriate support based on that analysis. Furthermore, properly managing user conversation records and emotion analysis information, and protecting privacy, are also crucial issues.

[0407] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0408] In this invention, the server includes an analysis means for analyzing the user's emotions and adjusting the response according to the analyzed emotions, a support means for providing support based on the user's emotions during information exchange, and a management means for managing the storage and deletion of conversation records using an information processing infrastructure. This enables the provision of flexible responses and support according to the user's emotions, realizing a more personalized information exchange experience.

[0409] A "user" refers to an individual who uses a system or information processing device.

[0410] "Visual information" refers to virtual images and characters generated based on user selections, and is information that includes visual elements.

[0411] "Auditory information" refers to virtual voices and sounds generated as acoustic signals, and is information that includes auditory elements.

[0412] "Generation means" refers to devices or systems that generate visual or audio information based on user selections.

[0413] "Communication means" refers to the means of exchanging information between the user and visual information, and includes devices and protocols that enable interaction.

[0414] "Conversation record" refers to the history of information exchange between the user and visual information.

[0415] "Recording means" refers to devices or systems used to save conversation records and utilize them for future, ongoing information provision experiences.

[0416] "Control means" refers to devices or systems that delete user conversation records and visual information and terminate information exchange upon termination of a communication contract.

[0417] "Analysis means" refers to devices or systems that analyze the user's emotions and adjust the response of visual information according to the analysis results.

[0418] "Support measures" refer to devices and systems that provide appropriate support based on the user's emotions.

[0419] An "information processing device" refers to a terminal or device used to process and display information.

[0420] "Information processing infrastructure" refers to the infrastructure, including clouds and servers, used for managing data storage and deletion.

[0421] The system of this invention aims to generate visual and auditory information that takes into account the user's emotional state, and to improve the user's information exchange experience. This system is implemented using the following hardware and software.

[0422] The server uses an emotion engine to analyze voice or text input from the user. This process utilizes a speech analysis library such as the Google Cloud Speech-to-Text API. Based on the analyzed emotion data, the server generates a response through an AI conversation model (e.g., ChatGPT-4). This process uses a generative AI model to provide emotion-adaptive responses.

[0423] The terminal receives input from the user and sends that information to the server. It also receives responses from the server and displays them on the information processing device to present them to the user as visual and audio information. Smartphones are commonly used as the information processing device for this purpose.

[0424] Users continuously exchange information with the system through dialogue. For example, if the system analyzes information indicating that the user is feeling stressed, it will present a supportive message such as, "Thank you for your hard work. We have some tips to help you relax on your next shopping trip."

[0425] For example, if a user in a cafe says, "I've been so busy lately, I'm exhausted," the system recognizes this emotion and makes a positive suggestion such as, "Why not try a new latte on a day like that?"

[0426] An example of a prompt for a generative AI model would be: "If a user says they are tired, what refreshing methods can you suggest? Please provide some ideas for relaxing the mind and body."

[0427] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0428] Step 1:

[0429] The device collects the user's voice or text input. The input data, consisting of words and voice that reflect the user's emotions, is transmitted to the server in real time.

[0430] Step 2:

[0431] The server analyzes user input data using a speech analysis library (e.g., Google Cloud Speech-to-Text API). During this process, calculations are performed to convert speech and text data into emotional data, identifying the user's emotional state. The output is index data indicating the emotional state.

[0432] Step 3:

[0433] The server provides an AI generator (e.g., ChatGPT-4) with the user's emotional state as input and generates an appropriate response for the user. At this stage, a prompt that takes the emotional state into account is sent to the AI ​​generator. The output is a personalized response message tailored to the user.

[0434] Step 4:

[0435] The server sends a generated response message to the terminal. This message includes positive suggestions and support messages tailored to the user's emotional state.

[0436] Step 5:

[0437] The terminal presents the response message received from the server to the user as visual or audio information. Output is information conveyed to the user through a screen or audio output device.

[0438] Step 6:

[0439] The user receives the presented information and decides on their next action. The user's response is collected as new input, returning to step 1, to improve future information exchange experiences.

[0440] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0441] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0442] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0443] [Third Embodiment]

[0444] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0445] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0446] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0447] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0448] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0449] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0450] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0451] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0452] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0453] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0454] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0455] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0456] This invention is implemented as a system that enables users to enjoy continuous communication through a virtual character of their choice. This system provides the ability to customize the appearance and voice of the virtual character based on the user's choices, thereby realizing a continuous conversational experience with the user.

[0457] Character generation process

[0458] The user begins customizing a virtual character through the application. The user can select attributes such as eye color, hairstyle, and voice pitch. The device receives this selection information and sends it to the server. The server uses an AI generative model to generate the virtual character's face and voice based on the input data and saves this data to the cloud. Next, the server sends the generated virtual character to the device and displays it on the user's screen.

[0459] Conversation with a virtual character

[0460] The user enters a message into the chat screen to begin a conversation with a virtual character. The device receives this message and sends it to the server. The server generates a response using an AI conversation model, considering an appropriate reply based on the user's request. The generated response is then presented to the user through the device. The conversation history is always saved in the cloud by the server and referenced during subsequent conversations.

[0461] Service termination management

[0462] When a user cancels their communication contract, a cancellation notification is sent from the device to the server, and the information is updated. The server then triggers the complete deletion of the user's conversation history and character settings information from the cloud. As a result, the service is discontinued, and the user loses access to the system.

[0463] As a concrete example, suppose a user selects a "male character with a gentle voice" and starts a conversation with that character by asking, "How was your day?" In this case, the server can generate a response such as, "That's wonderful. What happened?" based on the conversation history. Through such interactions, users can receive emotional support through conversations with virtual characters.

[0464] The following describes the processing flow.

[0465] Step 1:

[0466] The user launches the app and accesses the virtual character customization screen. The user sets their preferred attributes using an interface that allows them to select eye color, hairstyle, voice pitch, and more.

[0467] Step 2:

[0468] The device collects user customization information as data. This data is organized in JSON format and ready to be sent to the server.

[0469] Step 3:

[0470] The server inputs the customization information received from the terminal into the AI ​​generation model. Based on the input data, the server generates an image and voice of a virtual character and temporarily stores them in the cloud.

[0471] Step 4:

[0472] The server sends the generated virtual character data back to the terminal. Based on the received data, the terminal displays the virtual character on the user's screen.

[0473] Step 5:

[0474] To begin a conversation with a virtual character, the user types a message into the chat screen and sends it.

[0475] Step 6:

[0476] The device sends the user's message to the server. The message data is converted into an API format for communication with the server.

[0477] Step 7:

[0478] The server inputs the received message into an AI conversation model and generates a response corresponding to the user's message. The server also refers to past conversation history to create a personalized response.

[0479] Step 8:

[0480] The server sends the generated response back to the terminal, which then displays the response on the user's chat screen. The user then continues the conversation with the virtual character through this process.

[0481] Step 9:

[0482] The server saves the conversation history between the user and the virtual character to the cloud. This allows the user to refer to past conversations during subsequent conversations.

[0483] Step 10:

[0484] When a user cancels their communication contract, the device notifies the server of the cancellation information.

[0485] Step 11:

[0486] Upon receiving the cancellation information, the server deletes the user's conversation history and character settings from the cloud. The service is then shut down, and user access is restricted.

[0487] (Example 1)

[0488] Next, we will describe Example 1. 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."

[0489] Conventional virtual character interaction systems have struggled to dynamically generate the visual and auditory attributes of virtual characters based on user input, and have lacked sufficient recording and management capabilities to provide a continuous and consistent interaction experience. Furthermore, a lack of mechanisms to safely and reliably delete user data upon termination of a communication contract was a significant challenge.

[0490] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0491] In this invention, the server includes generation means for generating visual and auditory attributes of a virtual character based on user selection, communication means for providing interaction with the generated virtual character, and generation means for generating responses in response to user input using a learning model. This enables the user to obtain a dynamic and personalized interaction experience. Furthermore, by appropriately managing the interaction history and user information and securely deleting it upon termination of the communication contract, privacy protection can be enhanced.

[0492] "Generation means" refers to a device or software that has the function of generating the visual and auditory attributes of a virtual character based on the user's selection.

[0493] "Communication means" refers to the systems and network infrastructure used to provide interaction between the generated virtual character and the user.

[0494] "Recording means" refers to devices and technologies that record the history of conversations between a user and a virtual character and use that information to provide a continuous conversational experience.

[0495] "Control means" refers to a mechanism or process for deleting the user's dialogue history and virtual character information and stopping the dialogue based on the termination of the communication contract.

[0496] A "learning model" is an artificial intelligence technology used to generate responses in response to user input, and refers to a set of algorithms and devices that improve their performance based on data.

[0497] "Display means" refers to devices or software used to transmit information about the generated virtual character to the user's display device and visualize it on the screen.

[0498] "Management means" refers to a system or mechanism for properly saving and deleting conversation history using online storage.

[0499] This invention enables users to generate characters tailored to their individual preferences and enjoy continuous interaction with virtual characters through an interactive system. Specific embodiments will be described below.

[0500] First, the user begins customizing their virtual character using a dedicated application. The user can select attributes such as eye color, hairstyle, and voice pitch to suit their preferences. For example, a user might choose a character with "blue eyes and a high-pitched voice." The device collects this selection information and sends it to the server.

[0501] The server uses an AI generative model based on the received information to generate visual and auditory attributes for a virtual character. Machine learning libraries such as TensorFlow and PyTorch are used. The generated character data is securely stored in cloud storage, and the server sends it to the user's terminal to visualize the character on a display device.

[0502] The user initiates a conversation with a virtual character through a chat screen. For example, they can type a message such as, "What did you do today?" The device sends this message to the server, which uses a generative AI model to generate a suitable response. Possible models include ChatGPT. This response is displayed to the user through the device, and the conversation is completed. The conversation history is stored in the cloud by the server and used to facilitate future conversations.

[0503] When a communication contract ends, the user sends a cancellation notice through their device. The server receives this notice and completely deletes the user's conversation history and character settings information stored in cloud storage. This restricts future access.

[0504] This system is compatible with various devices and enables flexible operation. It promotes a natural and engaging interaction experience with virtual characters to provide users with a sense of psychological security.

[0505] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0506] Step 1:

[0507] The user launches the application and accesses the virtual character customization screen. The user selects eye color, hairstyle, and voice pitch. The input is the user's selection information, which is sent to the terminal. The terminal aggregates this information and sends it to the server. The output is the completion of sending the selection information to the server.

[0508] Step 2:

[0509] The server analyzes user selection information received from the terminal. The input is user selection information, and an AI generative model is used to generate the visual and auditory attributes of a virtual character. Data processing involves information analysis and generation by the AI ​​model. The output is the data of the generated virtual character.

[0510] Step 3:

[0511] Data for a virtual character generated from the server is sent to the terminal. The input is the generated character data, which the terminal receives and displays on its display device. The output is the virtual character displayed on the user's screen.

[0512] Step 4:

[0513] The user initiates a conversation with a virtual character through a chat screen. For example, they might type, "How was your day?" The input is the user's message, and the device sends this information to the server. The output indicates that the message has been successfully sent to the server.

[0514] Step 5:

[0515] When the server receives a message from a user, it uses a generative AI model to generate an appropriate response. The input consists of the user's message and past conversation history. Data processing involves message analysis and response generation by the AI ​​model. The output is the generated response.

[0516] Step 6:

[0517] The response generated by the server is sent to the terminal and presented to the user. The input is the generated response, which the terminal displays on the user's screen. The output is the response presented to the user.

[0518] Step 7:

[0519] When a user cancels their communication contract, a cancellation notification is sent from the device to the server. The input is the cancellation notification, and the server receives this notification. The output is a confirmation that the cancellation notification has been received.

[0520] Step 8:

[0521] Upon receiving a cancellation notice, the server deletes the user's conversation history and character settings information stored in the cloud. The input is the trigger information for the cancellation procedure, and the data processing is the deletion process of the stored data. The output is the completion of the complete deletion of the user data.

[0522] (Application Example 1)

[0523] Next, we will explain Application Example 1. In the following explanation, 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."

[0524] Existing virtual character systems limit user communication to simple conversations, failing to adequately provide information and content recommendations based on individual preferences. This makes it difficult to broadly support the entertainment experiences users desire.

[0525] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0526] In this invention, the server includes generation means for generating the appearance and voice of a virtual character based on user selection, information provision means for providing information and recommending entertainment to the user through the generated virtual character, and communication means for providing communication with the generated virtual character. This makes it possible to provide information and content tailored to the user's preferences in real time, enhancing the individualized entertainment experience.

[0527] A "user" refers to a person who uses the system and is the entity that receives communication and information through virtual characters.

[0528] A "virtual character" is a digital personality generated based on user choices, and it serves the role of communication and information provision.

[0529] "Generation means" refers to the process or device for creating the appearance and voice of a virtual character based on user input.

[0530] "Information provision means" refers to a function or device that recommends information and content tailored to the individual preferences of a user through a virtual character.

[0531] "Communication means" refers to methods and devices that enable two-way communication between the user and the virtual character.

[0532] "Recording means" refers to processes and devices for saving conversation history and related information between a user and a virtual character.

[0533] "Control means" refers to a function or device for managing user information based on the termination of a communication contract and deleting data as necessary.

[0534] The system used to implement this application consists of server, terminal, and user elements.

[0535] The server receives character attribute selection information entered by the user through the terminal and uses a generative AI model to generate data for the appearance and voice of a virtual character. The generated data is stored in cloud storage and sent to the terminal. In this process, the server executes Python programs and uses PyTorch / TensorFlow, etc., for data processing.

[0536] The terminal receives virtual character data sent from the server and displays it on the user interface. The user can then begin interacting with the virtual character via voice or text. In entertainment information provision, the server suggests relevant content through information provision means in response to user input requests and returns the results to the terminal in real time.

[0537] For example, if a user types "Tell me about the latest action movie," the server analyzes the user's past preferences and viewing history and recommends a suitable movie. A concrete example of a prompt would be if a user typed "Tell me about a good science fiction novel," to which a virtual character would respond, "A recent noteworthy work is XX. Are you interested in the content?"

[0538] In this way, the system can enhance the user's entertainment experience through information provision and personalized recommendations via virtual characters.

[0539] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0540] Step 1:

[0541] The user begins customizing a virtual character on a device such as a smartphone. Through the device's interface, the user selects and inputs multiple attributes, such as eye color, hairstyle, and voice pitch. This selection information is then transmitted as digital data to the server by the device.

[0542] Step 2:

[0543] The server receives selection information from the terminal as input and uses an AI generative model to generate appearance and voice data for a virtual character. In practice, frameworks such as PyTorch and TensorFlow are used for processing this data. The generated digital data is stored in cloud storage and sent from the server to the terminal.

[0544] Step 3:

[0545] The terminal receives virtual character data sent from the server and displays it to the user. Rendering technology is used for this display, allowing the user to visually encounter a customized character.

[0546] Step 4:

[0547] The user begins interacting with the displayed virtual character via voice or text. When the user types a text message such as "Tell me the latest movies" into the device, the device sends that message to the server.

[0548] Step 5:

[0549] The server receives a message from the user as input and uses natural language processing to generate a response based on the prompt. Using a generative AI model, the server processes relevant content based on the user's preferences and history and outputs recommended information. The generated information is sent to the terminal.

[0550] Step 6:

[0551] The terminal presents the user with information received from the server. For example, in movie recommendations, a virtual character will deliver a generated prompt message to the user via voice or text, saying, "Our recommended movie is XX." This allows the user to receive entertainment information through the virtual character.

[0552] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0553] This invention is implemented as a system that not only allows users to continuously enjoy communication with their preferred virtual character, but also enables dialogue that takes into account their emotional state during that time. This system analyzes the user's emotions using an emotion engine and adaptively adjusts the virtual character's responses and actions based on that information.

[0554] Character and emotional interaction

[0555] When a user begins a conversation with a virtual character, the device collects the user's voice and text input in real time. The user's input is analyzed by an emotion engine to identify their emotional state. For example, if a user says, "I'm busy and tired," the emotion engine recognizes the user's emotion as "fatigue."

[0556] The server receives this emotional information and adjusts the AI ​​conversation model's response. Specifically, if it detects that the user is tired, the virtual character generates an empathetic response such as, "You've had a tough day. Get some rest." This response is then presented to the user through the device.

[0557] Managing conversation history and sentiment data

[0558] The server stores user-virtual character interactions and detected emotion information in a cloud-based database. This data is used to provide a more personalized experience in subsequent interactions. For example, if the user's "fatigue" is frequently detected in previous conversations, the virtual character will periodically respond with inquiries about the user's well-being.

[0559] Service and data lifecycle management

[0560] If a user cancels their communication contract, the device sends information to the server indicating that continued use is no longer possible. Based on this, the server completely deletes the conversation history, emotion data, and character setting information stored in the cloud. The service is immediately terminated, and the user ends their interaction with the virtual character.

[0561] This system dynamically changes its response in accordance with the user's emotions, providing a simulated experience of social interaction and designed to allow users to receive psychological support. In addition, it has a mechanism in place to protect privacy through the proper management of data, including emotional information, and to ensure that information is reliably deleted when the contract is terminated.

[0562] The following describes the processing flow.

[0563] Step 1:

[0564] The user launches the app and accesses the chat function with the virtual character. The user enters a message in the text input field displayed on the screen and presses the send button.

[0565] Step 2:

[0566] The terminal receives user input messages and sends them to the server as voice or text data. This data is processed in real time, enabling rapid communication.

[0567] Step 3:

[0568] The server passes the received message to the emotion engine, which performs sentiment analysis. The emotion engine analyzes keywords and context in the message to identify the user's emotional state (e.g., joy, anger, sadness, relief).

[0569] Step 4:

[0570] The server adjusts the response generated by the AI ​​conversation model based on emotional information obtained from the emotion engine. For example, if the user says "I'm tired," the response would be something like "Get some rest."

[0571] Step 5:

[0572] The server sends a pre-arranged response message to the terminal. The terminal displays the received message on the user's chat screen.

[0573] Step 6:

[0574] The server stores the user's interaction history with the virtual character, as well as detected emotion data, in the cloud. This allows the system to accumulate data on the user's state over time and use it as context for future interactions.

[0575] Step 7:

[0576] If the user wishes to continue the conversation with the virtual character, the process from step 1 is repeated. Various responses based on emotional information allow for a more human-like and enjoyable continuation of the conversation with the virtual character.

[0577] Step 8:

[0578] When a user cancels their communication contract, that information is sent from the device to the server. Upon receiving the cancellation notification, the server terminates the service while protecting privacy by deleting the relevant conversation history and sentiment data from the cloud.

[0579] (Example 2)

[0580] Next, we will describe Example 2. 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."

[0581] In recent years, there has been a growing demand for systems that provide users with personalized experiences through interaction with virtual characters. However, existing systems often struggle to accurately reflect the user's emotional state, resulting in monotonous and inefficient conversations. Furthermore, the proper management of users' personal information and emotional data, as well as the protection of their privacy, are also important issues. This invention aims to solve these problems and provide users with a more natural and emotionally resonant conversational experience.

[0582] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0583] In this invention, the server includes means for generating the appearance and voice of a virtual character based on user selection, means for collecting user input and performing sentiment analysis, and means for generating responses of the virtual character using a generative AI model. This enables the generation of customized responses that take into account the user's emotional state.

[0584] A "user" refers to someone who interacts with a virtual character and utilizes the system in the process.

[0585] A "virtual character" refers to a digital entity created by a computer program that mimics a person or living being, generated for the purpose of interacting with users.

[0586] "Appearance" refers to the visual characteristics and design of a virtual character.

[0587] "Voice" refers to the information of words and voices spoken by virtual characters.

[0588] "Generation means" refers to methods or devices for creating the appearance and voice of a virtual character based on user selections.

[0589] "Communication means" refers to methods and devices for exchanging information between virtual characters and users.

[0590] "Recording means" refers to a device or method that has the function of saving the conversation history between the user and the virtual character and retrieving it as needed.

[0591] "Control means" refers to a device or method that evaluates based on specific conditions, such as the termination of a communication contract, and performs the necessary processing.

[0592] A "terminal" refers to an electronic device used by a user to interact with a virtual character.

[0593] "Emotion analysis" refers to a technical method for identifying a user's emotional state from their input information.

[0594] A "generative AI model" refers to an algorithm or program that generates responses from a virtual character based on the user's emotions.

[0595] A "prompt statement" refers to an input statement used to instruct a generative AI model to generate a desired response.

[0596] "Cloud" is a general term for computer resources and services provided via the internet.

[0597] This invention is a system that allows users to have a deep, emotionally responsive dialogue experience through conversations with a virtual character. Based on voice and text data provided by the user, this system uses an emotion engine to analyze the user's emotional state and then uses a generative AI model to generate responses from the virtual character based on the results.

[0598] First, the user speaks to a virtual character using their device. The device uses voice processing software to convert the user's voice into text data and sends it to the emotion engine. The emotion engine uses natural language processing technology to identify the user's emotional state from their input and recognize it as a specific emotion such as "fatigue" or "joy."

[0599] Next, the server sends a prompt to the generative AI model based on the received emotional information. This prompt might be written in the form of, for example, "How should the virtual character respond when the user is complaining of fatigue?" The generative AI model analyzes the prompt and generates a response that is empathetic to the user's emotions. The server sends this response to the terminal, which then presents the response to the user.

[0600] This allows users to experience dynamic, emotion-based dialogue. For example, if a user says, "I'm busy and tired," the virtual character might respond with something like, "You've had a tough day. Take a good rest," providing empathy and reassurance. The system also uses a cloud-based database to save conversation history and emotion data, which can then be used to improve future interactions.

[0601] This design allows the system to provide psychological support to users while ensuring the proper management of personal data.

[0602] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0603] Step 1:

[0604] The user speaks to a virtual character through the device or enters text. In the case of voice input, the device uses speech processing software to convert this audio into text data. At this stage, the input is the user's raw voice or text data, and the output is text data obtained through speech recognition. Specifically, the microphone captures the audio, and that data is instantly converted into text.

[0605] Step 2:

[0606] The device sends this text data to the emotion engine. The emotion engine uses natural language processing techniques to analyze keywords and expressions in the text and identify the user's emotional state. The input is text data, and the output is the identified emotional state (e.g., "fatigue" or "joy"). Specifically, the emotion engine analyzes the text and compares it with a pre-trained emotion database to determine the emotion.

[0607] Step 3:

[0608] The terminal sends identified emotion data to the server. The server uses the received emotion data to create and send a prompt to a generative AI model. The prompt might be written as, "How should the virtual character respond when the user is feeling 'fatigued'?" The input is emotion data, and the output is the prompt generated based on it. Specifically, a prompt generation algorithm runs within the server.

[0609] Step 4:

[0610] The generative AI model analyzes the prompt text and generates an appropriate response. The generated response is then presented as a dialogue between virtual characters. The input is the prompt text, and the output is the response text that the user will see and hear. For example, the AI ​​model can create empathetic responses such as, "You had a tough day. Get some rest."

[0611] Step 5:

[0612] The server sends this generated response to the terminal and presents it to the user. The terminal uses speech synthesis software to output the response as audio or displays it as text on its screen. The input is the generated response, and the output is the audio or visualized text that the user experiences. Specifically, the speaker outputs the response as audio, or the text is displayed on the screen.

[0613] Step 6:

[0614] The server stores the content and sentiment data of conversations in a cloud database. This data is used to provide a personalized experience in subsequent conversations. The input is conversation history data, and the output is updated and saved database entries. Specifically, a database management system runs in the backend to organize and store the data.

[0615] (Application Example 2)

[0616] Next, we will explain application example 2. In the following explanation, 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."

[0617] In modern information exchange experiences using information processing devices, responses that take user emotions into consideration are often lacking. Therefore, there is a need for means to accurately analyze the emotions users feel and provide appropriate support based on that analysis. Furthermore, properly managing user conversation records and emotion analysis information, and protecting privacy, are also crucial issues.

[0618] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0619] In this invention, the server includes an analysis means for analyzing the user's emotions and adjusting the response according to the analyzed emotions, a support means for providing support based on the user's emotions during information exchange, and a management means for managing the storage and deletion of conversation records using an information processing infrastructure. This enables the provision of flexible responses and support according to the user's emotions, realizing a more personalized information exchange experience.

[0620] A "user" refers to an individual who uses a system or information processing device.

[0621] "Visual information" refers to virtual images and characters generated based on user selections, and is information that includes visual elements.

[0622] "Auditory information" refers to virtual voices and sounds generated as acoustic signals, and is information that includes auditory elements.

[0623] "Generation means" refers to devices or systems that generate visual or audio information based on user selections.

[0624] "Communication means" refers to the means of exchanging information between the user and visual information, and includes devices and protocols that enable interaction.

[0625] "Conversation record" refers to the history of information exchange between the user and visual information.

[0626] "Recording means" refers to devices or systems used to save conversation records and utilize them for future, ongoing information provision experiences.

[0627] "Control means" refers to devices or systems that delete user conversation records and visual information and terminate information exchange upon termination of a communication contract.

[0628] "Analysis means" refers to devices or systems that analyze the user's emotions and adjust the response of visual information according to the analysis results.

[0629] "Support measures" refer to devices and systems that provide appropriate support based on the user's emotions.

[0630] An "information processing device" refers to a terminal or device used to process and display information.

[0631] "Information processing infrastructure" refers to the infrastructure, including clouds and servers, used for managing data storage and deletion.

[0632] The system of this invention aims to generate visual and auditory information that takes into account the user's emotional state, and to improve the user's information exchange experience. This system is implemented using the following hardware and software.

[0633] The server uses an emotion engine to analyze voice or text input from the user. This process utilizes a speech analysis library such as the Google Cloud Speech-to-Text API. Based on the analyzed emotion data, the server generates a response through an AI conversation model (e.g., ChatGPT-4). This process uses a generative AI model to provide emotion-adaptive responses.

[0634] The terminal receives input from the user and sends that information to the server. It also receives responses from the server and displays them on the information processing device to present them to the user as visual and audio information. Smartphones are commonly used as the information processing device for this purpose.

[0635] Users continuously exchange information with the system through dialogue. For example, if the system analyzes information indicating that the user is feeling stressed, it will present a supportive message such as, "Thank you for your hard work. We have some tips to help you relax on your next shopping trip."

[0636] For example, if a user in a cafe says, "I've been so busy lately, I'm exhausted," the system recognizes this emotion and makes a positive suggestion such as, "Why not try a new latte on a day like that?"

[0637] An example of a prompt for a generative AI model would be: "If a user says they are tired, what refreshing methods can you suggest? Please provide some ideas for relaxing the mind and body."

[0638] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0639] Step 1:

[0640] The device collects the user's voice or text input. The input data, consisting of words and voice that reflect the user's emotions, is transmitted to the server in real time.

[0641] Step 2:

[0642] The server analyzes user input data using a speech analysis library (e.g., Google Cloud Speech-to-Text API). During this process, calculations are performed to convert speech and text data into emotional data, identifying the user's emotional state. The output is index data indicating the emotional state.

[0643] Step 3:

[0644] The server provides an AI generator (e.g., ChatGPT-4) with the user's emotional state as input and generates an appropriate response for the user. At this stage, a prompt that takes the emotional state into account is sent to the AI ​​generator. The output is a personalized response message tailored to the user.

[0645] Step 4:

[0646] The server sends a generated response message to the terminal. This message includes positive suggestions and support messages tailored to the user's emotional state.

[0647] Step 5:

[0648] The terminal presents the response message received from the server to the user as visual or audio information. Output is information conveyed to the user through a screen or audio output device.

[0649] Step 6:

[0650] The user receives the presented information and decides on their next action. The user's response is collected as new input, returning to step 1, to improve future information exchange experiences.

[0651] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0652] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0653] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0654] [Fourth Embodiment]

[0655] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0656] As shown in Figure 7, the 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.

[0657] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0658] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0659] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0660] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0661] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0662] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0663] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0664] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0665] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0666] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0667] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0668] This invention is implemented as a system that enables users to enjoy continuous communication through a virtual character of their choice. This system provides the ability to customize the appearance and voice of the virtual character based on the user's choices, thereby realizing a continuous conversational experience with the user.

[0669] Character generation process

[0670] The user begins customizing a virtual character through the application. The user can select attributes such as eye color, hairstyle, and voice pitch. The device receives this selection information and sends it to the server. The server uses an AI generative model to generate the virtual character's face and voice based on the input data and saves this data to the cloud. Next, the server sends the generated virtual character to the device and displays it on the user's screen.

[0671] Conversation with a virtual character

[0672] The user enters a message into the chat screen to begin a conversation with a virtual character. The device receives this message and sends it to the server. The server generates a response using an AI conversation model, considering an appropriate reply based on the user's request. The generated response is then presented to the user through the device. The conversation history is always saved in the cloud by the server and referenced during subsequent conversations.

[0673] Service termination management

[0674] When a user cancels their communication contract, a cancellation notification is sent from the device to the server, and the information is updated. The server then triggers the complete deletion of the user's conversation history and character settings information from the cloud. As a result, the service is discontinued, and the user loses access to the system.

[0675] As a concrete example, suppose a user selects a "male character with a gentle voice" and starts a conversation with that character by asking, "How was your day?" In this case, the server can generate a response such as, "That's wonderful. What happened?" based on the conversation history. Through such interactions, users can receive emotional support through conversations with virtual characters.

[0676] The following describes the processing flow.

[0677] Step 1:

[0678] The user launches the app and accesses the virtual character customization screen. The user sets their preferred attributes using an interface that allows them to select eye color, hairstyle, voice pitch, and more.

[0679] Step 2:

[0680] The device collects user customization information as data. This data is organized in JSON format and ready to be sent to the server.

[0681] Step 3:

[0682] The server inputs the customization information received from the terminal into the AI ​​generation model. Based on the input data, the server generates an image and voice of a virtual character and temporarily stores them in the cloud.

[0683] Step 4:

[0684] The server sends the generated virtual character data back to the terminal. Based on the received data, the terminal displays the virtual character on the user's screen.

[0685] Step 5:

[0686] To begin a conversation with a virtual character, the user types a message into the chat screen and sends it.

[0687] Step 6:

[0688] The device sends the user's message to the server. The message data is converted into an API format for communication with the server.

[0689] Step 7:

[0690] The server inputs the received message into an AI conversation model and generates a response corresponding to the user's message. The server also refers to past conversation history to create a personalized response.

[0691] Step 8:

[0692] The server sends the generated response back to the terminal, which then displays the response on the user's chat screen. The user then continues the conversation with the virtual character through this process.

[0693] Step 9:

[0694] The server saves the conversation history between the user and the virtual character to the cloud. This allows the user to refer to past conversations during subsequent conversations.

[0695] Step 10:

[0696] When a user cancels their communication contract, the device notifies the server of the cancellation information.

[0697] Step 11:

[0698] Upon receiving the cancellation information, the server deletes the user's conversation history and character settings from the cloud. The service is then shut down, and user access is restricted.

[0699] (Example 1)

[0700] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0701] Conventional virtual character interaction systems have struggled to dynamically generate the visual and auditory attributes of virtual characters based on user input, and have lacked sufficient recording and management capabilities to provide a continuous and consistent interaction experience. Furthermore, a lack of mechanisms to safely and reliably delete user data upon termination of a communication contract was a significant challenge.

[0702] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0703] In this invention, the server includes generation means for generating visual and auditory attributes of a virtual character based on user selection, communication means for providing interaction with the generated virtual character, and generation means for generating responses in response to user input using a learning model. This enables the user to obtain a dynamic and personalized interaction experience. Furthermore, by appropriately managing the interaction history and user information and securely deleting it upon termination of the communication contract, privacy protection can be enhanced.

[0704] "Generation means" refers to a device or software that has the function of generating the visual and auditory attributes of a virtual character based on the user's selection.

[0705] "Communication means" refers to the systems and network infrastructure used to provide interaction between the generated virtual character and the user.

[0706] "Recording means" refers to devices and technologies that record the history of conversations between a user and a virtual character and use that information to provide a continuous conversational experience.

[0707] "Control means" refers to a mechanism or process for deleting the user's dialogue history and virtual character information and stopping the dialogue based on the termination of the communication contract.

[0708] A "learning model" is an artificial intelligence technology used to generate responses in response to user input, and refers to a set of algorithms and devices that improve their performance based on data.

[0709] "Display means" refers to devices or software used to transmit information about the generated virtual character to the user's display device and visualize it on the screen.

[0710] "Management means" refers to a system or mechanism for properly saving and deleting conversation history using online storage.

[0711] This invention enables users to generate characters tailored to their individual preferences and enjoy continuous interaction with virtual characters through an interactive system. Specific embodiments will be described below.

[0712] First, the user begins customizing their virtual character using a dedicated application. The user can select attributes such as eye color, hairstyle, and voice pitch to suit their preferences. For example, a user might choose a character with "blue eyes and a high-pitched voice." The device collects this selection information and sends it to the server.

[0713] The server uses an AI generative model based on the received information to generate visual and auditory attributes for a virtual character. Machine learning libraries such as TensorFlow and PyTorch are used. The generated character data is securely stored in cloud storage, and the server sends it to the user's terminal to visualize the character on a display device.

[0714] The user initiates a conversation with a virtual character through a chat screen. For example, they can type a message such as, "What did you do today?" The device sends this message to the server, which uses a generative AI model to generate a suitable response. Possible models include ChatGPT. This response is displayed to the user through the device, and the conversation is completed. The conversation history is stored in the cloud by the server and used to facilitate future conversations.

[0715] When a communication contract ends, the user sends a cancellation notice through their device. The server receives this notice and completely deletes the user's conversation history and character settings information stored in cloud storage. This restricts future access.

[0716] This system is compatible with various devices and enables flexible operation. It promotes a natural and engaging interaction experience with virtual characters to provide users with a sense of psychological security.

[0717] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0718] Step 1:

[0719] The user launches the application and accesses the virtual character customization screen. The user selects eye color, hairstyle, and voice pitch. The input is the user's selection information, which is sent to the terminal. The terminal aggregates this information and sends it to the server. The output is the completion of sending the selection information to the server.

[0720] Step 2:

[0721] The server analyzes user selection information received from the terminal. The input is user selection information, and an AI generative model is used to generate the visual and auditory attributes of a virtual character. Data processing involves information analysis and generation by the AI ​​model. The output is the data of the generated virtual character.

[0722] Step 3:

[0723] Data for a virtual character generated from the server is sent to the terminal. The input is the generated character data, which the terminal receives and displays on its display device. The output is the virtual character displayed on the user's screen.

[0724] Step 4:

[0725] The user initiates a conversation with a virtual character through a chat screen. For example, they might type, "How was your day?" The input is the user's message, and the device sends this information to the server. The output indicates that the message has been successfully sent to the server.

[0726] Step 5:

[0727] When the server receives a message from a user, it uses a generative AI model to generate an appropriate response. The input consists of the user's message and past conversation history. Data processing involves message analysis and response generation by the AI ​​model. The output is the generated response.

[0728] Step 6:

[0729] The response generated by the server is sent to the terminal and presented to the user. The input is the generated response, which the terminal displays on the user's screen. The output is the response presented to the user.

[0730] Step 7:

[0731] When a user cancels their communication contract, a cancellation notification is sent from the device to the server. The input is the cancellation notification, and the server receives this notification. The output is a confirmation that the cancellation notification has been received.

[0732] Step 8:

[0733] Upon receiving a cancellation notice, the server deletes the user's conversation history and character settings information stored in the cloud. The input is the trigger information for the cancellation procedure, and the data processing is the deletion process of the stored data. The output is the completion of the complete deletion of the user data.

[0734] (Application Example 1)

[0735] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0736] Existing virtual character systems limit user communication to simple conversations, failing to adequately provide information and content recommendations based on individual preferences. This makes it difficult to broadly support the entertainment experiences users desire.

[0737] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0738] In this invention, the server includes generation means for generating the appearance and voice of a virtual character based on user selection, information provision means for providing information and recommending entertainment to the user through the generated virtual character, and communication means for providing communication with the generated virtual character. This makes it possible to provide information and content tailored to the user's preferences in real time, enhancing the individualized entertainment experience.

[0739] A "user" refers to a person who uses the system and is the entity that receives communication and information through virtual characters.

[0740] A "virtual character" is a digital personality generated based on user choices, and it serves the role of communication and information provision.

[0741] "Generation means" refers to the process or device for creating the appearance and voice of a virtual character based on user input.

[0742] "Information provision means" refers to a function or device that recommends information and content tailored to the individual preferences of a user through a virtual character.

[0743] "Communication means" refers to methods and devices that enable two-way communication between the user and the virtual character.

[0744] "Recording means" refers to processes and devices for saving conversation history and related information between a user and a virtual character.

[0745] "Control means" refers to a function or device for managing user information based on the termination of a communication contract and deleting data as necessary.

[0746] The system used to implement this application consists of server, terminal, and user elements.

[0747] The server receives character attribute selection information entered by the user through the terminal and uses a generative AI model to generate data for the appearance and voice of a virtual character. The generated data is stored in cloud storage and sent to the terminal. In this process, the server executes Python programs and uses PyTorch / TensorFlow, etc., for data processing.

[0748] The terminal receives virtual character data sent from the server and displays it on the user interface. The user can then begin interacting with the virtual character via voice or text. In entertainment information provision, the server suggests relevant content through information provision means in response to user input requests and returns the results to the terminal in real time.

[0749] For example, if a user types "Tell me about the latest action movie," the server analyzes the user's past preferences and viewing history and recommends a suitable movie. A concrete example of a prompt would be if a user typed "Tell me about a good science fiction novel," to which a virtual character would respond, "A recent noteworthy work is XX. Are you interested in the content?"

[0750] In this way, the system can enhance the user's entertainment experience through information provision and personalized recommendations via virtual characters.

[0751] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0752] Step 1:

[0753] The user begins customizing a virtual character on a device such as a smartphone. Through the device's interface, the user selects and inputs multiple attributes, such as eye color, hairstyle, and voice pitch. This selection information is then transmitted as digital data to the server by the device.

[0754] Step 2:

[0755] The server receives selection information from the terminal as input and uses an AI generative model to generate appearance and voice data for a virtual character. In practice, frameworks such as PyTorch and TensorFlow are used for processing this data. The generated digital data is stored in cloud storage and sent from the server to the terminal.

[0756] Step 3:

[0757] The terminal receives virtual character data sent from the server and displays it to the user. Rendering technology is used for this display, allowing the user to visually encounter a customized character.

[0758] Step 4:

[0759] The user begins interacting with the displayed virtual character via voice or text. When the user types a text message such as "Tell me the latest movies" into the device, the device sends that message to the server.

[0760] Step 5:

[0761] The server receives a message from the user as input and uses natural language processing to generate a response based on the prompt. Using a generative AI model, the server processes relevant content based on the user's preferences and history and outputs recommended information. The generated information is sent to the terminal.

[0762] Step 6:

[0763] The terminal presents the user with information received from the server. For example, in movie recommendations, a virtual character will deliver a generated prompt message to the user via voice or text, saying, "Our recommended movie is XX." This allows the user to receive entertainment information through the virtual character.

[0764] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0765] This invention is implemented as a system that not only allows users to continuously enjoy communication with their preferred virtual character, but also enables dialogue that takes into account their emotional state during that time. This system analyzes the user's emotions using an emotion engine and adaptively adjusts the virtual character's responses and actions based on that information.

[0766] Character and emotional interaction

[0767] When a user begins a conversation with a virtual character, the device collects the user's voice and text input in real time. The user's input is analyzed by an emotion engine to identify their emotional state. For example, if a user says, "I'm busy and tired," the emotion engine recognizes the user's emotion as "fatigue."

[0768] The server receives this emotional information and adjusts the AI ​​conversation model's response. Specifically, if it detects that the user is tired, the virtual character generates an empathetic response such as, "You've had a tough day. Get some rest." This response is then presented to the user through the device.

[0769] Managing conversation history and sentiment data

[0770] The server stores user-virtual character interactions and detected emotion information in a cloud-based database. This data is used to provide a more personalized experience in subsequent interactions. For example, if the user's "fatigue" is frequently detected in previous conversations, the virtual character will periodically respond with inquiries about the user's well-being.

[0771] Service and data lifecycle management

[0772] If a user cancels their communication contract, the device sends information to the server indicating that continued use is no longer possible. Based on this, the server completely deletes the conversation history, emotion data, and character setting information stored in the cloud. The service is immediately terminated, and the user ends their interaction with the virtual character.

[0773] This system dynamically changes its response in accordance with the user's emotions, providing a simulated experience of social interaction and designed to allow users to receive psychological support. In addition, it has a mechanism in place to protect privacy through the proper management of data, including emotional information, and to ensure that information is reliably deleted when the contract is terminated.

[0774] The following describes the processing flow.

[0775] Step 1:

[0776] The user launches the app and accesses the chat function with the virtual character. The user enters a message in the text input field displayed on the screen and presses the send button.

[0777] Step 2:

[0778] The terminal receives user input messages and sends them to the server as voice or text data. This data is processed in real time, enabling rapid communication.

[0779] Step 3:

[0780] The server passes the received message to the emotion engine, which performs sentiment analysis. The emotion engine analyzes keywords and context in the message to identify the user's emotional state (e.g., joy, anger, sadness, relief).

[0781] Step 4:

[0782] The server adjusts the response generated by the AI ​​conversation model based on emotional information obtained from the emotion engine. For example, if the user says "I'm tired," the response would be something like "Get some rest."

[0783] Step 5:

[0784] The server sends a pre-arranged response message to the terminal. The terminal displays the received message on the user's chat screen.

[0785] Step 6:

[0786] The server stores the user's interaction history with the virtual character, as well as detected emotion data, in the cloud. This allows the system to accumulate data on the user's state over time and use it as context for future interactions.

[0787] Step 7:

[0788] If the user wishes to continue the conversation with the virtual character, the process from step 1 is repeated. Various responses based on emotional information allow for a more human-like and enjoyable continuation of the conversation with the virtual character.

[0789] Step 8:

[0790] When a user cancels their communication contract, that information is sent from the device to the server. Upon receiving the cancellation notification, the server terminates the service while protecting privacy by deleting the relevant conversation history and sentiment data from the cloud.

[0791] (Example 2)

[0792] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0793] In recent years, there has been a growing demand for systems that provide users with personalized experiences through interaction with virtual characters. However, existing systems often struggle to accurately reflect the user's emotional state, resulting in monotonous and inefficient conversations. Furthermore, the proper management of users' personal information and emotional data, as well as the protection of their privacy, are also important issues. This invention aims to solve these problems and provide users with a more natural and emotionally resonant conversational experience.

[0794] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0795] In this invention, the server includes means for generating the appearance and voice of a virtual character based on user selection, means for collecting user input and performing sentiment analysis, and means for generating responses of the virtual character using a generative AI model. This enables the generation of customized responses that take into account the user's emotional state.

[0796] A "user" refers to someone who interacts with a virtual character and utilizes the system in the process.

[0797] A "virtual character" refers to a digital entity created by a computer program that mimics a person or living being, generated for the purpose of interacting with users.

[0798] "Appearance" refers to the visual characteristics and design of a virtual character.

[0799] "Voice" refers to the information of words and voices spoken by virtual characters.

[0800] "Generation means" refers to methods or devices for creating the appearance and voice of a virtual character based on user selections.

[0801] "Communication means" refers to methods and devices for exchanging information between virtual characters and users.

[0802] "Recording means" refers to a device or method that has the function of saving the conversation history between the user and the virtual character and retrieving it as needed.

[0803] "Control means" refers to a device or method that evaluates based on specific conditions, such as the termination of a communication contract, and performs the necessary processing.

[0804] A "terminal" refers to an electronic device used by a user to interact with a virtual character.

[0805] "Emotion analysis" refers to a technical method for identifying a user's emotional state from their input information.

[0806] A "generative AI model" refers to an algorithm or program that generates responses from a virtual character based on the user's emotions.

[0807] A "prompt statement" refers to an input statement used to instruct a generative AI model to generate a desired response.

[0808] "Cloud" is a general term for computer resources and services provided via the internet.

[0809] This invention is a system that allows users to have a deep, emotionally responsive dialogue experience through conversations with a virtual character. Based on voice and text data provided by the user, this system uses an emotion engine to analyze the user's emotional state and then uses a generative AI model to generate responses from the virtual character based on the results.

[0810] First, the user speaks to a virtual character using their device. The device uses voice processing software to convert the user's voice into text data and sends it to the emotion engine. The emotion engine uses natural language processing technology to identify the user's emotional state from their input and recognize it as a specific emotion such as "fatigue" or "joy."

[0811] Next, the server sends a prompt to the generative AI model based on the received emotional information. This prompt might be written in the form of, for example, "How should the virtual character respond when the user is complaining of fatigue?" The generative AI model analyzes the prompt and generates a response that is empathetic to the user's emotions. The server sends this response to the terminal, which then presents the response to the user.

[0812] This allows users to experience dynamic, emotion-based dialogue. For example, if a user says, "I'm busy and tired," the virtual character might respond with something like, "You've had a tough day. Take a good rest," providing empathy and reassurance. The system also uses a cloud-based database to save conversation history and emotion data, which can then be used to improve future interactions.

[0813] This design allows the system to provide psychological support to users while ensuring the proper management of personal data.

[0814] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0815] Step 1:

[0816] The user speaks to a virtual character through the device or enters text. In the case of voice input, the device uses speech processing software to convert this audio into text data. At this stage, the input is the user's raw voice or text data, and the output is text data obtained through speech recognition. Specifically, the microphone captures the audio, and that data is instantly converted into text.

[0817] Step 2:

[0818] The device sends this text data to the emotion engine. The emotion engine uses natural language processing techniques to analyze keywords and expressions in the text and identify the user's emotional state. The input is text data, and the output is the identified emotional state (e.g., "fatigue" or "joy"). Specifically, the emotion engine analyzes the text and compares it with a pre-trained emotion database to determine the emotion.

[0819] Step 3:

[0820] The terminal sends identified emotion data to the server. The server uses the received emotion data to create and send a prompt to a generative AI model. The prompt might be written as, "How should the virtual character respond when the user is feeling 'fatigued'?" The input is emotion data, and the output is the prompt generated based on it. Specifically, a prompt generation algorithm runs within the server.

[0821] Step 4:

[0822] The generative AI model analyzes the prompt text and generates an appropriate response. The generated response is then presented as a dialogue between virtual characters. The input is the prompt text, and the output is the response text that the user will see and hear. For example, the AI ​​model can create empathetic responses such as, "You had a tough day. Get some rest."

[0823] Step 5:

[0824] The server sends this generated response to the terminal and presents it to the user. The terminal uses speech synthesis software to output the response as audio or displays it as text on its screen. The input is the generated response, and the output is the audio or visualized text that the user experiences. Specifically, the speaker outputs the response as audio, or the text is displayed on the screen.

[0825] Step 6:

[0826] The server stores the content and sentiment data of conversations in a cloud database. This data is used to provide a personalized experience in subsequent conversations. The input is conversation history data, and the output is updated and saved database entries. Specifically, a database management system runs in the backend to organize and store the data.

[0827] (Application Example 2)

[0828] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0829] In modern information exchange experiences using information processing devices, responses that take user emotions into consideration are often lacking. Therefore, there is a need for means to accurately analyze the emotions users feel and provide appropriate support based on that analysis. Furthermore, properly managing user conversation records and emotion analysis information, and protecting privacy, are also crucial issues.

[0830] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0831] In this invention, the server includes an analysis means for analyzing the user's emotions and adjusting the response according to the analyzed emotions, a support means for providing support based on the user's emotions during information exchange, and a management means for managing the storage and deletion of conversation records using an information processing infrastructure. This enables the provision of flexible responses and support according to the user's emotions, realizing a more personalized information exchange experience.

[0832] A "user" refers to an individual who uses a system or information processing device.

[0833] "Visual information" refers to virtual images and characters generated based on user selections, and is information that includes visual elements.

[0834] "Auditory information" refers to virtual voices and sounds generated as acoustic signals, and is information that includes auditory elements.

[0835] "Generation means" refers to devices or systems that generate visual or audio information based on user selections.

[0836] "Communication means" refers to the means of exchanging information between the user and visual information, and includes devices and protocols that enable interaction.

[0837] "Conversation record" refers to the history of information exchange between the user and visual information.

[0838] "Recording means" refers to devices or systems used to save conversation records and utilize them for future, ongoing information provision experiences.

[0839] "Control means" refers to devices or systems that delete user conversation records and visual information and terminate information exchange upon termination of a communication contract.

[0840] "Analysis means" refers to devices or systems that analyze the user's emotions and adjust the response of visual information according to the analysis results.

[0841] "Support measures" refer to devices and systems that provide appropriate support based on the user's emotions.

[0842] An "information processing device" refers to a terminal or device used to process and display information.

[0843] "Information processing infrastructure" refers to the infrastructure, including clouds and servers, used for managing data storage and deletion.

[0844] The system of this invention aims to generate visual and auditory information that takes into account the user's emotional state, and to improve the user's information exchange experience. This system is implemented using the following hardware and software.

[0845] The server uses an emotion engine to analyze voice or text input from the user. This process utilizes a speech analysis library such as the Google Cloud Speech-to-Text API. Based on the analyzed emotion data, the server generates a response through an AI conversation model (e.g., ChatGPT-4). This process uses a generative AI model to provide emotion-adaptive responses.

[0846] The terminal receives input from the user and sends that information to the server. It also receives responses from the server and displays them on the information processing device to present them to the user as visual and audio information. Smartphones are commonly used as the information processing device for this purpose.

[0847] Users continuously exchange information with the system through dialogue. For example, if the system analyzes information indicating that the user is feeling stressed, it will present a supportive message such as, "Thank you for your hard work. We have some tips to help you relax on your next shopping trip."

[0848] For example, if a user in a cafe says, "I've been so busy lately, I'm exhausted," the system recognizes this emotion and makes a positive suggestion such as, "Why not try a new latte on a day like that?"

[0849] An example of a prompt for a generative AI model would be: "If a user says they are tired, what refreshing methods can you suggest? Please provide some ideas for relaxing the mind and body."

[0850] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0851] Step 1:

[0852] The device collects the user's voice or text input. The input data, consisting of words and voice that reflect the user's emotions, is transmitted to the server in real time.

[0853] Step 2:

[0854] The server analyzes user input data using a speech analysis library (e.g., Google Cloud Speech-to-Text API). During this process, calculations are performed to convert speech and text data into emotional data, identifying the user's emotional state. The output is index data indicating the emotional state.

[0855] Step 3:

[0856] The server provides an AI generator (e.g., ChatGPT-4) with the user's emotional state as input and generates an appropriate response for the user. At this stage, a prompt that takes the emotional state into account is sent to the AI ​​generator. The output is a personalized response message tailored to the user.

[0857] Step 4:

[0858] The server sends a generated response message to the terminal. This message includes positive suggestions and support messages tailored to the user's emotional state.

[0859] Step 5:

[0860] The terminal presents the response message received from the server to the user as visual or audio information. Output is information conveyed to the user through a screen or audio output device.

[0861] Step 6:

[0862] The user receives the presented information and decides on their next action. The user's response is collected as new input, returning to step 1, to improve future information exchange experiences.

[0863] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0864] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0865] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0866] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0867] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0868] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0869] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0870] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0871] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0872] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0873] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0874] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0875] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0876] 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.

[0877] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0878] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0879] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0880] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0881] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0882] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0883] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0884] The following is further disclosed regarding the embodiments described above.

[0885] (Claim 1)

[0886] A generation means for generating the appearance and voice of a virtual character based on user selection,

[0887] A communication means that provides communication with the generated virtual character,

[0888] A recording means that records the conversation history between the user and the virtual character and provides a continuous conversation experience,

[0889] A control means for deleting the user's conversation history and virtual character information and stopping communication based on the termination of the communication contract,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, further comprising display means for transmitting and displaying information of a generated virtual character to a user's terminal.

[0893] (Claim 3)

[0894] The system according to claim 1, further comprising a management means for managing the saving and deletion of conversation history using the cloud.

[0895] "Example 1"

[0896] (Claim 1)

[0897] A generation means for generating visual and auditory attributes of a virtual character based on user selection,

[0898] A means of communication that provides interaction with a generated virtual character,

[0899] A recording means for recording the history of conversations between a user and a virtual character, and for providing a continuous conversational experience,

[0900] A control means that deletes the user's dialogue history and virtual character information and stops the dialogue based on the termination of the communication contract,

[0901] A generation means that generates a response in accordance with user input using a learning model,

[0902] A system that includes this.

[0903] (Claim 2)

[0904] The system according to claim 1, further comprising display means for transmitting and displaying information of a generated virtual character on a user's display device.

[0905] (Claim 3)

[0906] The system according to claim 1, further comprising a management means for managing the saving and deletion of dialogue history using online storage.

[0907] "Application Example 1"

[0908] (Claim 1)

[0909] A generation means for generating the appearance and voice of a virtual character based on user selection,

[0910] An information provision method that provides information to users and recommends entertainment through generated virtual characters,

[0911] A communication means that provides communication with the generated virtual character,

[0912] A recording means that records the conversation history between the user and the virtual character and provides a continuous conversation experience,

[0913] A control means for deleting the user's conversation history and virtual character information and stopping communication based on the termination of the communication contract,

[0914] A system that includes this.

[0915] (Claim 2)

[0916] The system according to claim 1, further comprising display means for transmitting and displaying information of a generated virtual character to a user's terminal.

[0917] (Claim 3)

[0918] The system according to claim 1, further comprising a management means for managing the saving and deletion of conversation history using the cloud.

[0919] "Example 2 of combining an emotion engine"

[0920] (Claim 1)

[0921] Means for generating the appearance and voice of a virtual character based on user selection,

[0922] A means of providing communication between the generated virtual character and the user,

[0923] A means for collecting user input and performing sentiment analysis,

[0924] A means of generating responses for a virtual character using a generative AI model based on analyzed emotional data,

[0925] A means of recording conversation history and emotional data between the user and the virtual character, and providing a continuous conversational experience.

[0926] Based on the termination of the communication contract, a means to delete all recorded data and virtual character information and stop communication,

[0927] A system that includes this.

[0928] (Claim 2)

[0929] The system according to claim 1, further comprising means for transmitting and displaying information of a generated virtual character on a user's device.

[0930] (Claim 3)

[0931] The system according to claim 1, further comprising means for managing the storage and deletion of conversation history and sentiment data using network resources.

[0932] "Application example 2 when combining with an emotional engine"

[0933] (Claim 1)

[0934] A generation means that generates visual and audio information based on user selection,

[0935] A communication means that provides information exchange with generated visual information,

[0936] A recording means for saving conversation records between the user and visual information, and for providing a continuous information delivery experience,

[0937] A control means that deletes the user's conversation records and visual information and terminates information exchange based on the termination of the communication contract,

[0938] An analytical means that analyzes the user's emotions and adjusts the response according to the analyzed emotions,

[0939] A support mechanism that provides user-based support during information exchange,

[0940] A system that includes this.

[0941] (Claim 2)

[0942] The system according to claim 1, further comprising display means for transmitting and displaying generated visual information to a user's information processing device.

[0943] (Claim 3)

[0944] The system according to claim 1, further comprising a management means for managing the storage and deletion of conversation records using an information processing infrastructure. [Explanation of symbols]

[0945] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A generation means for generating the appearance and voice of a virtual character based on user selection, A communication means that provides communication with the generated virtual character, A recording means that records the conversation history between the user and the virtual character and provides a continuous conversation experience, A control means for deleting the user's conversation history and virtual character information and stopping communication based on the termination of the communication contract, A system that includes this.

2. The system according to claim 1, further comprising display means for transmitting and displaying information of a generated virtual character to a user's terminal.

3. The system according to claim 1, further comprising a management means for managing the saving and deletion of conversation history using the cloud.

Images