System
The system simplifies AI agent configuration by allowing users to create and use customizable AI agents through questionnaires and presets, addressing the complexity of conventional methods and enhancing user experience.
Patent Information
- Application Number
- JP2024119001
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-07-24
- Publication Date
- 2026-02-05
AI Technical Summary
Conventional AI agent configuration is time-consuming and cumbersome, requiring users to manually set character appearance, personality, and functions, making it difficult to change and adapt to individual needs, and limiting the provision of personalized AI agents.
A system that allows users to easily create customized AI agents by answering questionnaires or selecting presets, generating AI agents based on user preferences, and installing them on devices, enabling flexible use and support in daily life.
Enables users to quickly generate and switch between AI agents that meet their preferences, providing convenient and customizable support for daily activities.
Smart Images

Figure 2026017940000001_ABST
Abstract
Description
[Technical Field]
[0001] The technology of the present disclosure relates to a system. [Background technology]
[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]
[0004] Conventional AI agent configuration requires a great deal of time and effort, making it difficult for users to use. For example, users must individually decide the character's appearance, personality, and function settings, making this a cumbersome process. Furthermore, once an agent has been configured, it is not easy to change it, and it is not possible to flexibly change it to meet the user's needs. Furthermore, existing systems make it difficult to provide official AI agents using specific characters. There is a need for a system that solves these problems and allows users to easily create and use AI agents that suit their preferences. [Means for solving the problem]
[0005] This invention solves the above-mentioned problems by providing a means for receiving information by a user answering a simple questionnaire or selecting preset settings, a means for analyzing the received user information and generating an AI agent based on the user's preferences and needs, and a means for transmitting the generated AI agent to the user's device and installing and executing it. This system allows users to use customized AI agents with minimal effort. It also provides a means for displaying a list of multiple preset AI agents, allowing users to select and purchase their preferred AI agent from among them. This allows users to easily switch between agents once they have been set up, enabling flexible support in daily life.
[0006] "User" refers to any individual or entity that uses the System or Services.
[0007] "Survey" means a survey-style document or data entry form that contains questions about a user's preferences or needs.
[0008] "Preset" refers to pre-defined options or settings that are prepared in advance for users to easily select and apply.
[0009] "User Information" refers to information about personal preferences and desired functionality provided by a User through surveys or preset settings.
[0010] "Analysis" refers to the process of interpreting, classifying, and organizing acquired data into usable information.
[0011] "AI agent" refers to a virtual character or program that uses artificial intelligence to perform tasks at the user's request.
[0012] "Generation" refers to the process of creating a new AI agent based on user information.
[0013] "Terminal" refers to a device (e.g., a smartphone or PC) that a user directly operates and on which an AI agent is installed and executed.
[0014] "Transmission" refers to the act of moving data or information from one point to another.
[0015] "Installation" refers to the process of placing a system or software on a terminal and setting it up for use.
[0016] "Running" refers to the act of running an installed system or software and making its functions available.
[0017] "Store" means an online platform or in-app marketplace where Users can select from and purchase multiple AI agents.
[0018] "Supporting daily life" refers to functions that support users' daily activities and plans, such as providing weather forecasts, suggesting optimal routes for commuting to work or school, and setting reminders. [Brief explanation of the drawings]
[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6]FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION
[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.
[0021] First, the terms used in the following description will be explained.
[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).
[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.
[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.
[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.
[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."
[0027] [First embodiment]
[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.
[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.
[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).
[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.
[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.
[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.
[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.
[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.
[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.
[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.
[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0040] This invention provides a system that allows users to easily use customized AI agents. This system generates AI agents that meet individual needs by allowing users to select and answer questionnaires or presets. The specific operations of each stakeholder (user, terminal, server) are explained below.
[0041] User operations
[0042] Enter information
[0043] First, the user accesses a questionnaire form and preset selection screen provided on the device. The questionnaire includes questions such as "favorite character" and "necessary functions," and the user answers these. The preset settings also allow the user to select from several pre-prepared agents.
[0044] Agent Selection and Purchasing
[0045] The user can view a list of multiple preset agents provided in the store, and can select and purchase an agent that suits his or her preference.
[0046] Device behavior
[0047] Providing an input interface
[0048] The device displays a questionnaire form or a preset selection screen where the user can enter information. After the user has completed the input, the information is sent to the server.
[0049] Installing and Running the Agent
[0050] The device installs the customized AI agent data received from the server and performs initial setup so that the user can use it immediately. After installation, the agent is executed and notifies the user.
[0051] Server Operation
[0052] Receiving and storing user information
[0053] The server receives the user information sent from the terminal and stores it in a database.
[0054] Generating AI agents
[0055] The server analyzes the stored user information and customizes the AI agent based on that data, generating an agent that reflects the user's preferences and desired functions.
[0056] Sending Agents
[0057] The server sends the data of the generated customized AI agent to the terminal.
[0058] Specific examples
[0059] For example, suppose user C wants a new customized AI agent. User C launches the app on their device and accesses the survey form. They select "dog" as their favorite character and "weather forecast" and "reminder settings" as their desired functions.
[0060] Next, when User C sends information, the device sends the data to the server. The server receives this information and stores it in a database. The server analyzes the stored information and generates an AI agent based on User C's preferences. The generated agent includes the "appearance of the dog character" and "weather forecast and reminder setting functions."
[0061] The server then sends the agent data to the device, which receives and installs it. Once the installation is complete, the device runs the agent and notifies User C. User C can use this agent to receive support for daily activities such as checking the weather forecast and setting reminders.
[0062] In this way, the system of the present invention provides users with convenient and easily customizable AI agents. Furthermore, by using presets and a store, users can easily obtain agents that suit their preferences.
[0063] The processing flow will be explained below.
[0064] Step 1:
[0065] Device: When the user launches the app, a survey form or preset selection screen is displayed.
[0066] Step 2:
[0067] User: Access the survey form and answer questions such as "Favorite character" and "Desired functions." Alternatively, select your preferred agent from a list of preset agents.
[0068] Step 3:
[0069] Terminal: After the user has completed their input or selection, they press the send button, which sends the information to the server.
[0070] Step 4:
[0071] Server: Receives user information sent from the device and stores it in a database. The stored information includes the user ID, answers, selected presets, etc.
[0072] Step 5:
[0073] Server: Analyzes saved user information and generates a customized AI agent based on the user's preferences and needs. For example, if a user selects "dog" as their favorite character, an agent with the appearance and voice of that character will be generated.
[0074] Step 6:
[0075] Server: Prepares the data of the generated AI agent and prepares it for transmission to the terminal.
[0076] Step 7:
[0077] Server: Sends customized AI agent data to the device, including appearance, function settings, and required initial setup information.
[0078] Step 8:
[0079] Terminal: Installs the received agent data. The installation process includes extracting the data and registering it in the system.
[0080] Step 9:
[0081] Terminal: Performing initial agent configuration, for example, applying a setting to enable the weather forecast function on the user's terminal.
[0082] Step 10:
[0083] Terminal: Starts the AI agent and notifies the user when it is ready.
[0084] Step 11:
[0085] User: Starts interacting with the AI agent that is activated on the device. For example, they can ask the agent, "What's the weather like today?" and the agent will provide a weather forecast.
[0086] Step 12:
[0087] Agent (running on the device): Provides ongoing support for the user's everyday requests. This is an ongoing process and can include a variety of functions, such as setting reminders or optimizing commute routes.
[0088] The above is the specific process flow for users to use a customized AI agent.
[0089] Example 1
[0090] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0091] Existing AI agent systems make it difficult for users to easily customize agents to suit their preferences and needs. Furthermore, the process is often cumbersome, resulting in a poor user experience. Furthermore, agent customization is limited, making it difficult to meet diverse user needs. The objective of this invention is to solve these problems and provide a system that allows users to more easily use highly customized AI agents.
[0092] 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.
[0093] In this invention, the server includes a means for receiving information from a user by answering a simple questionnaire or selecting preset settings, a means for analyzing the received user information and generating a customized AI agent using a generative AI model based on the user's preferences and needs, and a means for transmitting the generated AI agent to the user's terminal and installing and executing it, thereby enabling the user to easily use an AI agent that suits their preferences and needs.
[0094] "User" refers to any individual or legal entity that uses the system and customizes an AI agent to suit their preferences and needs through questionnaires and presets.
[0095] A "survey" refers to a form containing questions to gather user preferences and needs.
[0096] "Presets" refers to options that provide multiple pre-configured AI agent configurations and capabilities.
[0097] "Means for receiving" refers to the method or process by which the system receives information entered by the user.
[0098] "Means for analyzing" refers to the methods and algorithms used to process received user information and understand the user's preferences and needs.
[0099] "Generative AI models" refer to machine learning models and natural language processing models that generate customized AI agents based on user information.
[0100] A "customized AI agent" refers to an AI agent that is specially created to reflect the user's preferences and needs.
[0101] "Terminal" refers to the hardware or device through which a user accesses the system and installs and runs customized AI agents.
[0102] "Transmission means" refers to the method or process for transmitting data of the generated AI agent from the server to the terminal.
[0103] "Installation and execution means" refers to the method or process for installing a customized AI agent on a device and running it for use by the user.
[0104] "Various functions to support the user's daily life" refers to the functions and services provided by a customized AI agent to assist the user in their daily life.
[0105] This invention provides a system that allows users to easily use customized AI agents. This system generates AI agents that meet individual needs by allowing users to select and answer questionnaires or presets. The specific operations of each stakeholder (server, terminal, user) are explained in detail below.
[0106] User operations
[0107] First, users access a questionnaire form and preset selection screen provided on their smartphone, tablet, or PC. The questionnaire includes questions such as "favorite character" and "necessary functions," and the user answers these. The preset settings also allow users to choose from several pre-prepared agents.
[0108] As a specific example, user A opens a questionnaire form and selects "dragon" as his / her "favorite character" and "to-do list management" as his / her "necessary function."
[0109] Server Operation
[0110] The server receives the user information sent from the device and stores it in a database in JSON format.
[0111] Next, the server analyzes the stored user information and generates a customized AI agent using a generative AI model (e.g., GPT-4). Specifically, it generates an AI agent using the following prompt sentence:
[0112] User's favorite character: Dragon
[0113] Required feature: To-do list management
[0114] Generate customized AI agents based on this information.
[0115] The server then sends the generated customized AI agent data to the terminal, again in JSON format.
[0116] Device behavior
[0117] The device receives the customized AI agent data sent from the server, installs it, and performs initial setup. After installation, the agent runs and notifies the user.
[0118] As a concrete example, the device installs an agent with the "appearance of a dragon character" and "to-do list management function" for User A. After the installation is complete, the device notifies the user that "the agent has been installed."
[0119] Using an agent
[0120] Users can use the installed customized agents to perform various tasks. For example, user A, who is managing his to-do list, asks the agent, "What's on my schedule for today?" The agent responds, "I have three meetings today."
[0121] Hardware and software used
[0122] Devices: Smartphones, tablets, PCs
[0123] Server: Cloud server (e.g. AWS, Google Cloud, Azure)
[0124] Software: Web applications for implementing survey forms and preset selection screens, and machine learning models (e.g., GPT-4) for generating AI agents.
[0125] In this way, the system of the present invention provides users with convenient and easily customizable AI agents. Users can easily use agents with functions based on their individual needs. Furthermore, by using presets and a store, users can easily obtain agents that suit their preferences.
[0126] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0127] Step 1:
[0128] Enter user information
[0129] Users log in to the system using a terminal. After logging in, they can access a questionnaire form and a preset selection screen. Here, users input their favorite character and required functions. For example, User A selects "dragon" as his "favorite character" and "to-do list management" as his "required function."
[0130] Input: User survey data
[0131] Output: User data in JSON format
[0132] Step 2:
[0133] Sending information
[0134] The device sends the information entered by the user to the server, in JSON format.
[0135] Input: User data in JSON format
[0136] Output: User data sent to the server
[0137] Step 3:
[0138] Receiving and storing user information
[0139] The server receives the information sent from the terminal and stores it in a database.
[0140] Input: User data in JSON format
[0141] Output: User information stored in the database
[0142] Step 4:
[0143] Generating AI agents
[0144] The server analyzes the stored user information and generates a customized AI agent using a generative AI model (e.g., GPT-4). Specifically, it generates an AI agent using the following prompt:
[0145] User's favorite character: Dragon
[0146] Required feature: To-do list management
[0147] Generate customized AI agents based on this information.
[0148] Input: User information stored in the database
[0149] Output: Customized agent data in JSON format
[0150] Step 5:
[0151] Sending Agent Information
[0152] The server sends the generated customized agent data to the device, again in JSON format.
[0153] Input: Customized agent data in JSON format
[0154] Output: Agent data sent to the terminal
[0155] Step 6:
[0156] Installing and Running the Agent
[0157] The device receives the customized AI agent data sent from the server, installs it, and performs initial setup. After installation, the agent runs and notifies the user.
[0158] Input: Customized agent data in JSON format
[0159] Output: An installed and running AI agent.
[0160] Step 7:
[0161] Using an agent
[0162] Users can use the installed customized agents to perform various tasks. For example, user A asks the agent, "What's on my schedule for today?" to manage his to-do list. The agent responds, "I have three meetings today."
[0163] Input: User operation instructions
[0164] Output: Response from the agent
[0165] (Application example 1)
[0166] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0167] Conventional food delivery services have the drawback of requiring users to select different restaurants and menus each time, and not providing optimal suggestions that fit individual preferences or schedules. Furthermore, in order to accommodate specific requirements (such as allergy information or specific types of cuisine), users must perform detailed searches and confirmations each time, which is cumbersome.
[0168] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.
[0169] In this invention, the server includes means for receiving information from a user by answering a simple questionnaire or selecting preset settings, means for analyzing the received user information and generating an AI agent based on the user's preferences and needs, means for transmitting the generated AI agent to the user's terminal and installing and executing it, and means for providing the user with recommended information optimized for a specific category (e.g., food delivery) based on the analyzed information, thereby enabling the provision of an optimal food delivery service based on the user's individual preferences and schedule.
[0170] The "questionnaire" is a question-type input means for the user to input individual preferences and required functions.
[0171] "Preset" refers to pre-defined options and settings that users can choose from.
[0172] "User Information" is data about individual preferences and needs provided by a user through surveys or preset selections.
[0173] An "AI agent" is a virtual assistant that provides assistance and services to users through a customized program based on their preferences and needs.
[0174] "Food delivery" is a service that delivers dishes or food selected by the user to a specified location.
[0175] A "generative AI model" refers to an algorithm or program that generates a customized AI agent based on user information.
[0176] A "prompt" is a form of recommendation or instruction that an AI agent provides to a user.
[0177] This invention relates to a system that allows users to easily use customized AI agents. The core of this system is the exchange and analysis of data between the user, terminal, and server.
[0178] System Program
[0179] User operations
[0180] The user first accesses a questionnaire form or preset selection screen provided on the device. The questionnaire includes the user's preferences and desired functions (for example, "favorite type of food," "delivery frequency," etc.), and the user answers them. The preset settings allow the user to choose from pre-prepared options. This information is sent from the device to the server.
[0181] Server Operation
[0182] The server receives the information sent by the user and stores it in a database. The stored data is then analyzed using a generative AI model. This analysis generates a customized AI agent based on the user's preferences and needs. The generated AI agent includes, for example, recommendation information and notification functions suitable for a specific category (food delivery). Finally, the server sends the generated AI agent's data to the device.
[0183] Device behavior
[0184] The device then installs the customized AI agent data received from the server, making it immediately available to the user. After installation, the agent provides support for the user in their daily lives, such as recommending specific restaurants based on the user's preferences and providing ordering prompts.
[0185] Hardware and software used
[0186] Hardware:
[0187] Smartphone
[0188] Server machine
[0189] software:
[0190] Flask (Python framework)
[0191] Generative AI model (an algorithm that analyzes user information and generates a customized AI agent)
[0192] Database management system (storing user information)
[0193] This allows users to use a food delivery agent optimized for their individual needs by filling out a simple questionnaire or selecting presets.
[0194] Specific examples
[0195] For example, if a user enters "favorite cuisine (e.g., Chinese food)" and "delivery frequency (twice a week)" on the survey screen, the server analyzes this data and generates a customized agent that provides recommended restaurants and delivery times that suit the user's needs. This agent then displays a prompt to the user such as, "We have three Chinese restaurants A, B, and C that suit your tastes. When would you like your next delivery?"
[0196] Example prompt sentence:
[0197] "Based on your food preferences, we'd like to recommend Chinese restaurant A, restaurant B, and restaurant C. When would you like your next delivery?"
[0198] In this way, the system of the present invention provides the optimal food delivery service that matches the user's preferences.
[0199] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0200] Step 1:
[0201] The user accesses a questionnaire form or preset selection screen provided on the terminal, where they answer questions such as "Favorite type of food" and "Delivery frequency." The entered information is collected by the terminal as user information and sent to the server.
[0202] Step 2:
[0203] The server receives the user information sent from the device and temporarily stores it in a database. At this point, the input format is data such as JSON or XML. The stored information is used for analysis.
[0204] Step 3:
[0205] The server uses a generative AI model to analyze the stored user information. Specifically, it extracts data patterns based on the user's preferences and needs and generates a customized AI agent. This generation process involves processing and calculating the data (e.g., statistical analysis and clustering) to create agent data containing optimal recommendations.
[0206] Step 4:
[0207] The server sends the generated customized AI agent data to the device in a format such as JSON or binary. The device converts this data into an installable format and installs it as a working application.
[0208] Step 5:
[0209] The device will then begin running the installed AI agent, which the user can then control to receive assistance with daily activities, such as food recommendations and ordering prompts based on the user's preferences.
[0210] Step 6:
[0211] The user operates based on prompts provided by the AI agent. For example, they may receive instructions such as, "There are three Chinese restaurants A, B, and C that suit your tastes. When would you like your next delivery?" The user then selects the delivery time and confirms the order.
[0212] In this way, a customized food delivery service is provided based on the user's preferences and needs.
[0213] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.
[0214] This invention improves the quality of responses and support to users by combining an emotion engine with a system that allows users to easily use customized AI agents. The specific operations of each stakeholder (user, terminal, server) are explained below.
[0215] User operations
[0216] Enter information
[0217] First, the user accesses a questionnaire form and preset selection screen provided on the device. The questionnaire includes questions such as "favorite character" and "necessary functions," and the user answers these. The preset settings also allow the user to select from several pre-prepared agents.
[0218] Agent Selection and Purchasing
[0219] The user can check a list of multiple preset agents provided in the store, select an agent that suits his / her taste, and purchase it.
[0220] Device behavior
[0221] Providing an input interface
[0222] The device displays a questionnaire form or a preset selection screen where the user can enter information. After the user has completed the input, the information is sent to the server.
[0223] Use of emotion engine
[0224] The terminal provides the user's voice, facial expression, and text data to the emotion engine, which analyzes this data to detect the user's emotional state.
[0225] Installing and Running the Agent
[0226] The device installs the customized AI agent data received from the server and performs initial setup so that the user can use it immediately. After installation, the agent is executed and notifies the user.
[0227] Server Operation
[0228] Receiving and storing user information
[0229] The server receives the user information sent from the device and stores it in a database, including the user ID, answers, and selected presets.
[0230] Generating AI agents
[0231] The server analyzes the stored user information and customizes the AI agent based on that data, generating an agent based on the user's preferences, desired functionality, and emotional state.
[0232] Sending Agents
[0233] The server sends the data of the generated customized AI agent to the terminal.
[0234] Specific examples
[0235] For example, suppose User D wants a new customized AI agent. User D launches the app on their device and accesses the survey form. They select "cat" as their favorite character and "weather forecast" and "reminder settings" as their desired functions.
[0236] Next, when User D sends information, the device sends the data to the server. The server receives this information and stores it in a database. The server analyzes the stored information and generates an AI agent based on User D's preferences. The generated agent includes the cat character's appearance and the ability to set weather forecasts and reminders.
[0237] The device also uses an emotion engine to analyze the user's voice and facial expressions to detect their emotional state. For example, if the emotion engine recognizes "sadness" in User D's voice, the agent will respond in a gentle manner.
[0238] The server then sends the agent data to the device, which receives and installs it. Once installation is complete, the device executes the agent and notifies User D. User D can then use this agent to receive support for daily activities such as checking the weather forecast and setting reminders.
[0239] Furthermore, the agent dynamically adjusts its dialogue and behavior according to the emotional state of user D, providing continuous support. For example, if user D says, "I'm feeling down today," the agent will suggest, "Shall we do something fun to change your mood?"
[0240] In this way, the system of the present invention not only provides users with a convenient and easily customizable AI agent, but also uses an emotion engine to achieve high-quality dialogue that responds to the user's emotions.
[0241] The processing flow will be explained below.
[0242] Step 1:
[0243] Device: When the user launches the app, a survey form or preset selection screen is displayed.
[0244] Step 2:
[0245] User: Access the survey form and answer questions such as "Favorite character" and "Desired functions." Alternatively, select your preferred agent from a list of preset agents.
[0246] Step 3:
[0247] Terminal: After the user has completed their input or selection, they press the send button, which sends the information to the server.
[0248] Step 4:
[0249] Server: Receives user information sent from the device and stores it in a database. The stored information includes the user ID, answers, selected presets, etc.
[0250] Step 5:
[0251] Server: Analyzes saved user information and generates a customized AI agent based on the user's preferences and needs. For example, if a user selects a favorite character, "cat," an agent with the character's appearance and voice will be generated.
[0252] Step 6:
[0253] Server: Prepares the data of the generated AI agent and prepares it for transmission to the terminal.
[0254] Step 7:
[0255] Server: Sends customized AI agent data to the device, including appearance, function settings, and required initial setup information.
[0256] Step 8:
[0257] Terminal: Installs the received agent data. The installation process includes extracting the data and registering it in the system.
[0258] Step 9:
[0259] Terminal: Performing initial agent configuration, for example, applying a setting to enable the weather forecast function on the user's terminal.
[0260] Step 10:
[0261] Terminal: Starts the AI agent and notifies the user when it is ready.
[0262] Step 11:
[0263] User: Starts interacting with the AI agent that is activated on the device. For example, they can ask the agent, "What's the weather like today?" and the agent will provide a weather forecast.
[0264] Step 12:
[0265] Terminal: When a user is using an active agent, emotional data of the user is collected using voice input and camera functions.
[0266] Step 13:
[0267] Device: The emotion engine analyzes the collected emotional data and identifies the user's emotional state. For example, it can detect "happiness" or "sadness" from the user's tone of voice and facial expressions.
[0268] Step 14:
[0269] Terminal: Dynamically adjusts the AI agent's responses and behavior based on emotional data analyzed by the emotion engine. For example, if the user expresses "sadness," the agent will ask, "Is there anything you're worried about?"
[0270] Step 15:
[0271] Agent (running on the device): Provides ongoing support for the user's everyday requests. For example, if the user says, "Set a reminder," the agent responds, "Reminder set."
[0272] Step 16:
[0273] Device: Records emotional data analyzed by the emotion engine and learns the user's emotional tendencies over time.
[0274] Step 17:
[0275] Server: The server periodically collects and analyzes the user's emotional data and customizes the service to reflect the user's emotional tendencies. For example, if the user frequently feels "stressed," the agent will proactively make suggestions to help them relax.
[0276] In this way, the system of the present invention not only provides users with a convenient and easily customizable AI agent, but also uses an emotion engine to achieve high-quality dialogue that responds to the user's emotions.
[0277] Example 2
[0278] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0279] Conventional AI agent systems have difficulty fully meeting the individual needs and preferences of users, and few systems can flexibly respond to the user's emotional state. As a result, interactions with users tend to be unnatural, often resulting in low user satisfaction. Furthermore, customization using unique characters and the provision of multifunctional agents are insufficient, leaving them lacking in support for everyday life.
[0280] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for receiving information when a user accesses a simple input form and answers a questionnaire or selects a preset setting, a means for the terminal to collect the information and send it to the server, a means for analyzing the received user information and using a generative AI model to generate an AI agent based on the user's preferences and required functions, and a means for sending the generated AI agent data to the terminal and installing and executing it. This makes it possible to generate and install an AI agent that is highly personalized for the user, thereby realizing advanced dialogue that responds to the user's needs and emotional state.
[0281] The "information input form" is an interface that allows the user to answer questionnaires and select preset settings.
[0282] A "server" is a device or system that receives, stores, and analyzes information sent by a user, generates an AI agent, and sends it to a terminal.
[0283] A "terminal" is a device for users to input information and is a device for installing and executing generated AI agents.
[0284] An "emotion engine" is software or a device that analyzes a user's voice, facial expression, and text data to detect their emotional state.
[0285] A "generative AI model" is an algorithm or machine learning model for generating customized AI agents based on user information.
[0286] "Agent data" refers to the configuration information and program data of the generated AI agent.
[0287] The "questionnaire" is a questionnaire containing questions about the user's preferences and required functions.
[0288] "Presets" are the settings and function patterns of multiple AI agents that have been set up in advance.
[0289] "Installation" refers to the process of incorporating the AI agent's programs and settings into the device.
[0290] "Execution" means running the installed AI agent and interacting with and supporting the user.
[0291] "User information" refers to questionnaires and preset setting data entered by the user, as well as data on emotional states analyzed by the emotion engine.
[0292] This invention is a system that allows users to easily use customized AI agents. This system is composed of a terminal, a server, and an emotion engine. The specific operations of each stakeholder (user, terminal, server) are explained below.
[0293] User operations
[0294] Enter information
[0295] First, the user accesses the input form or preset selection screen provided on the device using a web browser or dedicated application. For example, the user answers questions such as "favorite character" or "necessary functions" in a questionnaire.
[0296] Agent Selection and Purchasing
[0297] The user can select and purchase an agent that suits their preferences from the displayed list of preset agents, allowing the user to easily select a customized agent.
[0298] Device behavior
[0299] Providing an input interface
[0300] The device displays an input form or preset selection screen to the user, and after the user completes the input, it uses HTML and JavaScript to send the data to the server.
[0301] Use of emotion engine
[0302] The device collects the user's voice and facial expression data and sends it to an emotion engine such as Affectiva or IBM Watson Tone Analyzer. The emotion engine analyzes this data to detect the user's emotional state. For example, if a user says, "I'm tired today," this information is analyzed by the emotion engine.
[0303] Installing and Running the Agent
[0304] The device installs the customized AI agent data received from the server, runs a Python script to install the agent, and notifies the user when it is complete, allowing the agent to be used immediately.
[0305] Server Operation
[0306] Receiving and storing user information
[0307] The server receives the user information sent from the device. For example, it receives the data using a REST API and stores it in a database (MySQL or PostgreSQL). The stored information includes the user ID, answers, selected presets, etc.
[0308] Generating AI agents
[0309] The server analyzes the stored user information and generates an AI agent using a generative AI model such as OpenAI's GPT-4. The server customizes the agent based on the user's preferences, required features, and emotional state. This generation process uses prompts such as:
[0310] Prompt Sentence Examples
[0311] 1. "The user's favorite character is a cat, and they need weather forecasts and reminder settings. Create a customized AI agent configuration based on this."
[0312] 2. "Sadness was detected from the user's voice analysis. Please add a kind response for the user."
[0313] Sending Agents
[0314] The server sends the generated AI agent data to the device, which then receives it using the REST API.
[0315] Specific examples
[0316] For example, consider the case where User D wants a new customized AI agent. User D starts the app on his / her device, accesses the questionnaire form, and selects "cat as favorite character" and "weather forecast and reminder setting as required functions." The device collects this information and sends it to the server. The server receives the information and stores it in a database. The server then analyzes the received information and generates an AI agent with the appearance of a cat character and the functions of weather forecast and reminder setting. The generated agent data is sent to the device, which receives it and installs it. After installation is complete, the device notifies User D, who can then begin using the agent.
[0317] Furthermore, if User D says, "I'm feeling depressed today," the emotion engine analyzes this and sends the data to the server. The server then changes the agent's response settings based on the additional prompts, providing a friendly response to User D. In this way, the system can provide a personalized agent for the user and achieve high-quality dialogue that responds to the user's emotional state.
[0318] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0319] Step 1: User launches application
[0320] The user launches a dedicated application or web browser on the device and accesses an input form or preset selection screen. A form is displayed asking for input such as the character of their choice and the functions they require. The user answers these questions and the information is sent to the device.
[0321] Step 2: Collect and submit input data
[0322] The device collects the survey data and preset setting data entered by the user and sends it to the server. Specifically, the data entered in the HTML form is sent to the server via the REST API using JavaScript with the POST method. The survey data and preset settings are input, and a notification of completion of transmission to the server is sent as output.
[0323] Step 3: Receiving and storing user information
[0324] The server receives user information sent from the device and stores it in a database. Specifically, it processes the received data using Python scripts and a database engine (MySQL or PostgreSQL). The inputs are survey data and preset settings, and the output is the data saved in the database.
[0325] Step 4: Collect and send emotion data
[0326] The device collects the user's voice and facial expression data and sends it to the emotion engine. For example, if the user says, "I'm tired today," the device records that voice and sends it to the emotion engine (Affectiva or IBM Watson Tone Analyzer). The input is the user's voice data and facial expression data, and the output is the result sent to the emotion engine.
[0327] Step 5: Emotional state analysis and notification
[0328] The emotion engine analyzes the voice data and facial expression data received from the user to detect the user's emotional state. Specifically, the emotion engine's algorithm analyzes the data and identifies the user's emotional state (e.g., sadness or joy). The voice data and facial expression data are sent as input, and the detected emotional state is sent as output to the server.
[0329] Step 6: Generate an AI agent
[0330] The server analyzes the stored user information and emotional state data obtained from the emotion engine to generate an AI agent specialized for the user. OpenAI's GPT-4 is used as the generative AI model. The server customizes the agent based on the user's preferences, required functions, and emotional state. For example, it generates an agent with a "cat character appearance" and "weather forecast and reminder setting functions." User information and emotional state data are obtained as input, and agent configuration information and program data are obtained as output.
[0331] Step 7: Submit and install the agent
[0332] The server sends the generated customized AI agent data to the device. The data is then sent again via a REST API, and the device receives and installs it. For example, a Python script can install the agent and notify the user when it's complete. The agent data is received from the server as input, and a notification of installation completion is sent to the device as output.
[0333] Step 8: Run the agent and notify the user
[0334] The device runs the installed AI agent and notifies the user. For example, the AI agent starts on the device and notifies the user, "The agent installation is complete and it's ready to use." The input is the installed AI agent, and the output is the agent launch and a notification to the user.
[0335] Step 9: Agent support for daily life
[0336] Users use the agent to receive support in their daily lives, such as checking the weather forecast or setting reminders. The agent adjusts its dialogue and behavior appropriately according to the user's emotional state. For example, if the user says, "I'm feeling down today," the agent might suggest, "Shall we do something fun to cheer you up?" The inputs are the user's statements and emotional state data, and the output is the agent's response and the provision of support functions.
[0337] (Application example 2)
[0338] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0339] Conventional content distribution services lacked a function to recommend content that was tailored to the user's emotional state, making it difficult to provide users with the optimal entertainment experience. In particular, content recommendations were often inappropriate for users because they could not respond to the user's mood or emotions. As a result, users often spent a lot of time and effort finding the optimal content, which often led to a decrease in satisfaction with the service.
[0340] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving information when the user answers a simple questionnaire or selects a preset setting, means for analyzing the received user information and generating an AI agent based on the user's preferences and needs, means for transmitting the generated AI agent to the user's terminal and installing and executing it, and means for analyzing the user's emotional state in real time and recommending videos and music according to that emotional state. This makes it possible to automatically recommend optimal content that matches the user's emotional state.
[0341] A "questionnaire" is a question-type input means for a user to input their preferences and needs.
[0342] "Preset" refers to a set of agents and functions that have been set up in advance, and allows the user to easily customize the system by selecting one of them.
[0343] "User Information" refers to data about a user's preferences and needs collected through questionnaires and preset selections.
[0344] "Analysis" is an information processing process that identifies the user's preferences and needs from the received user information and generates an appropriate AI agent.
[0345] An "AI agent" is software equipped with artificial intelligence that responds to user instructions and requests and provides various functions.
[0346] "Terminal" refers to a device used by a user, such as a computer or smartphone.
[0347] "Emotional state" is information indicating the psychological state of the user obtained from facial expressions, voice, and text data.
[0348] "Real-time" refers to the time-based responsiveness of responding and responding immediately to user actions and inputs.
[0349] "Recommendation" is the act of suggesting optimal content based on a user's preferences and emotional state.
[0350] "Moving image" is viewable information content that includes a sequence of images and sound.
[0351] "Music" is information content that can be enjoyed auditorily, consisting of melody, harmony, and rhythm.
[0352] A "system" is a set of devices and software that combine multiple means to achieve a specific function.
[0353] The present invention relates to a system for allowing a user to receive optimal content according to his / her emotional state. Detailed embodiments are described below.
[0354] Overall system configuration
[0355] The present invention mainly comprises the following three elements:
[0356] 1. Server: Stores and analyzes user information, generates and transmits customized AI agents.
[0357] 2. Terminal: Provides an interface for users to input information and analyzes the user's emotional state using an emotion engine.
[0358] 3. User: Customize your agent by answering surveys and selecting presets.
[0359] Program operation explanation
[0360] Hardware and software used
[0361] Hardware: Smartphones, servers
[0362] Software: Python, requests library, transformers library, Hypothesis sentiment analysis and recommendation engine module (SentimentAnalyzer, ContentRecommender)
[0363] Data flow
[0364] 1. User Action:
[0365] Users access a questionnaire form using their smartphones and enter their preferences and desired features, and the information is sent to the server.
[0366] 2. Server operation:
[0367] The server receives and analyzes user information. Based on the analysis results, it generates a customized AI agent that matches the user's preferences and needs. The generated agent is then sent to the user's device.
[0368] 3. Device operation:
[0369] The device then installs and runs the received AI agent, analyzes the user's emotional state in real time, and recommends appropriate content (videos and music) based on that emotion.
[0370] As part of the specific processing steps, the device passes the user's voice input and text to the "SentimentAnalyzer" to analyze their emotions. Based on the results, the "ContentRecommender" selects the most appropriate content and presents it to the user.
[0371] Specific examples
[0372] For example, User A accesses a questionnaire form, selects "cat" as his / her favorite character, and selects "video recommendation" and "music recommendation" as required functions. This information is sent to the server, which generates a customized AI agent based on User A's preferences and sends it to the device. The device installs it, and if User A enters "I'm feeling depressed today," the emotion analysis engine recognizes "sadness," and the recommendation engine suggests uplifting content based on that.
[0373] Prompt Sentence Examples
[0374] User: I'm feeling down today.
[0375] System: The emotion analysis engine has detected "sadness." We will recommend music and videos that will uplift your mood.
[0376] In this way, the present invention can realize high-quality content recommendations that correspond to the user's emotional state.
[0377] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0378] Step 1:
[0379] The user accesses the questionnaire form and enters their preferences and required functions. At this time, the user uses their smartphone to select, for example, "cat" as their "favorite character" and selects "video recommendations" and "music recommendations" as "required functions." The input data is sent to the server in JSON format.
[0380] Input: Survey content selected by the user (preferences, required features)
[0381] Output: User information sent to the server (JSON format data)
[0382] Step 2:
[0383] The server receives the user information and stores it in a database. This process records the user's ID, preferences, and required functions in the database. The server then analyzes the received user information and generates an AI agent based on the user's preferences and needs.
[0384] Input: User information sent from the device (JSON format data)
[0385] Output: User information stored in a database, customized AI agent
[0386] Step 3:
[0387] The server sends the generated AI agent data to the user's device. The device receives this data and installs the AI agent. Once the installation is complete, the AI agent is set up to be immediately available for use.
[0388] Input: AI agent data generated by the server
[0389] Output: AI agent installed on the device
[0390] Step 4:
[0391] The device receives the user's voice input and text data and sends it to a sentiment analysis engine (SentimentAnalyzer). The sentiment analysis engine analyzes the input data and identifies the user's emotional state. The analysis results are output as an emotional state, such as "sadness," "joy," or "anger."
[0392] Input: User voice input or text data
[0393] Output: Parsed user's emotional state (e.g. "sadness")
[0394] Step 5:
[0395] The device receives the emotion analysis results and passes them to a recommendation engine (ContentRecommender). The recommendation engine generates a list of recommended videos and music based on the user's emotional state. For example, if the user's emotion is analyzed as "sadness," it will recommend uplifting music and fun videos. These recommendation results are then presented to the user on the device.
[0396] Input: Emotional state from the emotion analysis engine (e.g. "sadness")
[0397] Output: A list of content recommendations based on emotional state
[0398] Step 6:
[0399] The user checks the recommendation list on the device and selects the content they want to watch. The device then starts playing the selected content, providing the user with a viewing experience.
[0400] Input: Content selected from the recommended list
[0401] Output: The content that started playing (video or music)
[0402] In this way, through each step, the user can receive the most suitable content depending on their emotional state, thereby improving the user's entertainment experience.
[0403] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.
[0404] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[0405] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.
[0406] [Second embodiment]
[0407] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.
[0408] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.
[0409] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).
[0410] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.
[0411] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.
[0412] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).
[0413] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.
[0414] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.
[0415] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.
[0416] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.
[0417] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[0418] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."
[0419] This invention provides a system that allows users to easily use customized AI agents. This system generates AI agents that meet individual needs by allowing users to select and answer questionnaires or presets. The specific operations of each stakeholder (user, terminal, server) are explained below.
[0420] User operations
[0421] Enter information
[0422] First, the user accesses a questionnaire form and preset selection screen provided on the device. The questionnaire includes questions such as "favorite character" and "necessary functions," and the user answers these. The preset settings also allow the user to select from several pre-prepared agents.
[0423] Agent Selection and Purchasing
[0424] The user can view a list of multiple preset agents provided in the store, and can select and purchase an agent that suits his or her preference.
[0425] Device behavior
[0426] Providing an input interface
[0427] The device displays a questionnaire form or a preset selection screen where the user can enter information. After the user has completed the input, the information is sent to the server.
[0428] Installing and Running the Agent
[0429] The device installs the customized AI agent data received from the server and performs initial setup so that the user can use it immediately. After installation, the agent is executed and notifies the user.
[0430] Server Operation
[0431] Receiving and storing user information
[0432] The server receives the user information sent from the terminal and stores it in a database.
[0433] Generating AI agents
[0434] The server analyzes the stored user information and customizes the AI agent based on that data, generating an agent that reflects the user's preferences and desired functions.
[0435] Sending Agents
[0436] The server sends the data of the generated customized AI agent to the terminal.
[0437] Specific examples
[0438] For example, suppose user C wants a new customized AI agent. User C launches the app on their device and accesses the survey form. They select "dog" as their favorite character and "weather forecast" and "reminder settings" as their desired functions.
[0439] Next, when User C sends information, the device sends the data to the server. The server receives this information and stores it in a database. The server analyzes the stored information and generates an AI agent based on User C's preferences. The generated agent includes the "appearance of the dog character" and "weather forecast and reminder setting functions."
[0440] The server then sends the agent data to the device, which receives and installs it. Once the installation is complete, the device runs the agent and notifies User C. User C can use this agent to receive support for daily activities such as checking the weather forecast and setting reminders.
[0441] In this way, the system of the present invention provides users with convenient and easily customizable AI agents. Furthermore, by using presets and a store, users can easily obtain agents that suit their preferences.
[0442] The processing flow will be explained below.
[0443] Step 1:
[0444] Device: When the user launches the app, a survey form or preset selection screen is displayed.
[0445] Step 2:
[0446] User: Access the survey form and answer questions such as "Favorite character" and "Desired functions." Alternatively, select your preferred agent from a list of preset agents.
[0447] Step 3:
[0448] Terminal: After the user has completed their input or selection, they press the send button, which sends the information to the server.
[0449] Step 4:
[0450] Server: Receives user information sent from the device and stores it in a database. The stored information includes the user ID, answers, selected presets, etc.
[0451] Step 5:
[0452] Server: Analyzes saved user information and generates a customized AI agent based on the user's preferences and needs. For example, if a user selects "dog" as their favorite character, an agent with the appearance and voice of that character will be generated.
[0453] Step 6:
[0454] Server: Prepares the data of the generated AI agent and prepares it for transmission to the terminal.
[0455] Step 7:
[0456] Server: Sends customized AI agent data to the device, including appearance, function settings, and required initial setup information.
[0457] Step 8:
[0458] Terminal: Installs the received agent data. The installation process includes extracting the data and registering it in the system.
[0459] Step 9:
[0460] Terminal: Performing initial agent configuration, for example, applying a setting to enable the weather forecast function on the user's terminal.
[0461] Step 10:
[0462] Terminal: Starts the AI agent and notifies the user when it is ready.
[0463] Step 11:
[0464] User: Starts interacting with the AI agent that is activated on the device. For example, they can ask the agent, "What's the weather like today?" and the agent will provide a weather forecast.
[0465] Step 12:
[0466] Agent (running on the device): Provides ongoing support for the user's everyday requests. This is an ongoing process and can include a variety of functions, such as setting reminders or optimizing commute routes.
[0467] The above is the specific process flow for users to use a customized AI agent.
[0468] Example 1
[0469] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."
[0470] Existing AI agent systems make it difficult for users to easily customize agents to suit their preferences and needs. Furthermore, the process is often cumbersome, resulting in a poor user experience. Furthermore, agent customization is limited, making it difficult to meet diverse user needs. The objective of this invention is to solve these problems and provide a system that allows users to more easily use highly customized AI agents.
[0471] 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.
[0472] In this invention, the server includes a means for receiving information from a user by answering a simple questionnaire or selecting preset settings, a means for analyzing the received user information and generating a customized AI agent using a generative AI model based on the user's preferences and needs, and a means for transmitting the generated AI agent to the user's terminal and installing and executing it, thereby enabling the user to easily use an AI agent that suits their preferences and needs.
[0473] "User" refers to any individual or legal entity that uses the system and customizes an AI agent to suit their preferences and needs through questionnaires and presets.
[0474] A "survey" refers to a form containing questions to gather user preferences and needs.
[0475] "Presets" refers to options that provide multiple pre-configured AI agent configurations and capabilities.
[0476] "Means for receiving" refers to the method or process by which the system receives information entered by the user.
[0477] "Means for analyzing" refers to the methods and algorithms used to process received user information and understand the user's preferences and needs.
[0478] "Generative AI models" refer to machine learning models and natural language processing models that generate customized AI agents based on user information.
[0479] A "customized AI agent" refers to an AI agent that is specially created to reflect the user's preferences and needs.
[0480] "Terminal" refers to the hardware or device through which a user accesses the system and installs and runs customized AI agents.
[0481] "Transmission means" refers to the method or process for transmitting data of the generated AI agent from the server to the terminal.
[0482] "Installation and execution means" refers to the method or process for installing a customized AI agent on a device and running it for use by the user.
[0483] "Various functions to support the user's daily life" refers to the functions and services provided by a customized AI agent to assist the user in their daily life.
[0484] This invention provides a system that allows users to easily use customized AI agents. This system generates AI agents that meet individual needs by allowing users to select and answer questionnaires or presets. The specific operations of each stakeholder (server, terminal, user) are explained in detail below.
[0485] User operations
[0486] First, users access a questionnaire form and preset selection screen provided on their smartphone, tablet, or PC. The questionnaire includes questions such as "favorite character" and "necessary functions," and the user answers these. The preset settings also allow users to choose from several pre-prepared agents.
[0487] As a specific example, user A opens a questionnaire form and selects "dragon" as his / her "favorite character" and "to-do list management" as his / her "necessary function."
[0488] Server Operation
[0489] The server receives the user information sent from the device and stores it in a database in JSON format.
[0490] Next, the server analyzes the stored user information and generates a customized AI agent using a generative AI model (e.g., GPT-4). Specifically, it generates an AI agent using the following prompt sentence:
[0491] User's favorite character: Dragon
[0492] Required feature: To-do list management
[0493] Generate customized AI agents based on this information.
[0494] The server then sends the generated customized AI agent data to the terminal, again in JSON format.
[0495] Device behavior
[0496] The device receives the customized AI agent data sent from the server, installs it, and performs initial setup. After installation, the agent runs and notifies the user.
[0497] As a concrete example, the device installs an agent with the "appearance of a dragon character" and "to-do list management function" for User A. After the installation is complete, the device notifies the user that "the agent has been installed."
[0498] Using an agent
[0499] Users can use the installed customized agents to perform various tasks. For example, user A, who is managing his to-do list, asks the agent, "What's on my schedule for today?" The agent responds, "I have three meetings today."
[0500] Hardware and software used
[0501] Devices: Smartphones, tablets, PCs
[0502] Server: Cloud server (e.g. AWS, Google Cloud, Azure)
[0503] Software: Web applications for implementing survey forms and preset selection screens, and machine learning models (e.g., GPT-4) for generating AI agents.
[0504] In this way, the system of the present invention provides users with convenient and easily customizable AI agents. Users can easily use agents with functions based on their individual needs. Furthermore, by using presets and a store, users can easily obtain agents that suit their preferences.
[0505] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0506] Step 1:
[0507] Enter user information
[0508] Users log in to the system using a terminal. After logging in, they can access a questionnaire form and a preset selection screen. Here, users input their favorite character and required functions. For example, User A selects "dragon" as his "favorite character" and "to-do list management" as his "required function."
[0509] Input: User survey data
[0510] Output: User data in JSON format
[0511] Step 2:
[0512] Sending information
[0513] The device sends the information entered by the user to the server, in JSON format.
[0514] Input: User data in JSON format
[0515] Output: User data sent to the server
[0516] Step 3:
[0517] Receiving and storing user information
[0518] The server receives the information sent from the terminal and stores it in a database.
[0519] Input: User data in JSON format
[0520] Output: User information stored in the database
[0521] Step 4:
[0522] Generating AI agents
[0523] The server analyzes the stored user information and generates a customized AI agent using a generative AI model (e.g., GPT-4). Specifically, it generates an AI agent using the following prompt:
[0524] User's favorite character: Dragon
[0525] Required feature: To-do list management
[0526] Generate customized AI agents based on this information.
[0527] Input: User information stored in the database
[0528] Output: Customized agent data in JSON format
[0529] Step 5:
[0530] Sending Agent Information
[0531] The server sends the generated customized agent data to the device, again in JSON format.
[0532] Input: Customized agent data in JSON format
[0533] Output: Agent data sent to the terminal
[0534] Step 6:
[0535] Installing and Running the Agent
[0536] The device receives the customized AI agent data sent from the server, installs it, and performs initial setup. After installation, the agent runs and notifies the user.
[0537] Input: Customized agent data in JSON format
[0538] Output: An installed and running AI agent.
[0539] Step 7:
[0540] Using an agent
[0541] Users can use the installed customized agents to perform various tasks. For example, user A asks the agent, "What's on my schedule for today?" to manage his to-do list. The agent responds, "I have three meetings today."
[0542] Input: User operation instructions
[0543] Output: Response from the agent
[0544] (Application example 1)
[0545] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."
[0546] Conventional food delivery services have the drawback of requiring users to select different restaurants and menus each time, and not providing optimal suggestions that fit individual preferences or schedules. Furthermore, in order to accommodate specific requirements (such as allergy information or specific types of cuisine), users must perform detailed searches and confirmations each time, which is cumbersome.
[0547] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.
[0548] In this invention, the server includes means for receiving information from a user by answering a simple questionnaire or selecting preset settings, means for analyzing the received user information and generating an AI agent based on the user's preferences and needs, means for transmitting the generated AI agent to the user's terminal and installing and executing it, and means for providing the user with recommended information optimized for a specific category (e.g., food delivery) based on the analyzed information, thereby enabling the provision of an optimal food delivery service based on the user's individual preferences and schedule.
[0549] The "questionnaire" is a question-type input means for the user to input individual preferences and required functions.
[0550] "Preset" refers to pre-defined options and settings that users can choose from.
[0551] "User Information" is data about individual preferences and needs provided by a user through surveys or preset selections.
[0552] An "AI agent" is a virtual assistant that provides assistance and services to users through a customized program based on their preferences and needs.
[0553] "Food delivery" is a service that delivers dishes or food selected by the user to a specified location.
[0554] A "generative AI model" refers to an algorithm or program that generates a customized AI agent based on user information.
[0555] A "prompt" is a form of recommendation or instruction that an AI agent provides to a user.
[0556] This invention relates to a system that allows users to easily use customized AI agents. The core of this system is the exchange and analysis of data between the user, terminal, and server.
[0557] System Program
[0558] User operations
[0559] The user first accesses a questionnaire form or preset selection screen provided on the device. The questionnaire includes the user's preferences and desired functions (for example, "favorite type of food," "delivery frequency," etc.), and the user answers them. The preset settings allow the user to choose from pre-prepared options. This information is sent from the device to the server.
[0560] Server Operation
[0561] The server receives the information sent by the user and stores it in a database. The stored data is then analyzed using a generative AI model. This analysis generates a customized AI agent based on the user's preferences and needs. The generated AI agent includes, for example, recommendation information and notification functions suitable for a specific category (food delivery). Finally, the server sends the generated AI agent's data to the device.
[0562] Device behavior
[0563] The device then installs the customized AI agent data received from the server, making it immediately available to the user. After installation, the agent provides support for the user in their daily lives, such as recommending specific restaurants based on the user's preferences and providing ordering prompts.
[0564] Hardware and software used
[0565] Hardware:
[0566] Smartphone
[0567] Server machine
[0568] software:
[0569] Flask (Python framework)
[0570] Generative AI model (an algorithm that analyzes user information and generates a customized AI agent)
[0571] Database management system (storing user information)
[0572] This allows users to use a food delivery agent optimized for their individual needs by filling out a simple questionnaire or selecting presets.
[0573] Specific examples
[0574] For example, if a user enters "favorite cuisine (e.g., Chinese food)" and "delivery frequency (twice a week)" on the survey screen, the server analyzes this data and generates a customized agent that provides recommended restaurants and delivery times that suit the user's needs. This agent then displays a prompt to the user such as, "We have three Chinese restaurants A, B, and C that suit your tastes. When would you like your next delivery?"
[0575] Example prompt sentence:
[0576] "Based on your food preferences, we'd like to recommend Chinese restaurant A, restaurant B, and restaurant C. When would you like your next delivery?"
[0577] In this way, the system of the present invention provides the optimal food delivery service that matches the user's preferences.
[0578] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0579] Step 1:
[0580] The user accesses a questionnaire form or preset selection screen provided on the terminal, where they answer questions such as "Favorite type of food" and "Delivery frequency." The entered information is collected by the terminal as user information and sent to the server.
[0581] Step 2:
[0582] The server receives the user information sent from the device and temporarily stores it in a database. At this point, the input format is data such as JSON or XML. The stored information is used for analysis.
[0583] Step 3:
[0584] The server uses a generative AI model to analyze the stored user information. Specifically, it extracts data patterns based on the user's preferences and needs and generates a customized AI agent. This generation process involves processing and calculating the data (e.g., statistical analysis and clustering) to create agent data containing optimal recommendations.
[0585] Step 4:
[0586] The server sends the generated customized AI agent data to the device in a format such as JSON or binary. The device converts this data into an installable format and installs it as a working application.
[0587] Step 5:
[0588] The device will then begin running the installed AI agent, which the user can then control to receive assistance with daily activities, such as food recommendations and ordering prompts based on the user's preferences.
[0589] Step 6:
[0590] The user operates based on prompts provided by the AI agent. For example, they may receive instructions such as, "There are three Chinese restaurants A, B, and C that suit your tastes. When would you like your next delivery?" The user then selects the delivery time and confirms the order.
[0591] In this way, a customized food delivery service is provided based on the user's preferences and needs.
[0592] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.
[0593] This invention improves the quality of responses and support to users by combining an emotion engine with a system that allows users to easily use customized AI agents. The specific operations of each stakeholder (user, terminal, server) are explained below.
[0594] User operations
[0595] Enter information
[0596] First, the user accesses a questionnaire form and preset selection screen provided on the device. The questionnaire includes questions such as "favorite character" and "necessary functions," and the user answers these. The preset settings also allow the user to select from several pre-prepared agents.
[0597] Agent Selection and Purchasing
[0598] The user can check a list of multiple preset agents provided in the store, select an agent that suits his / her taste, and purchase it.
[0599] Device behavior
[0600] Providing an input interface
[0601] The device displays a questionnaire form or a preset selection screen where the user can enter information. After the user has completed the input, the information is sent to the server.
[0602] Use of emotion engine
[0603] The terminal provides the user's voice, facial expression, and text data to the emotion engine, which analyzes this data to detect the user's emotional state.
[0604] Installing and Running the Agent
[0605] The device installs the customized AI agent data received from the server and performs initial setup so that the user can use it immediately. After installation, the agent is executed and notifies the user.
[0606] Server Operation
[0607] Receiving and storing user information
[0608] The server receives the user information sent from the device and stores it in a database, including the user ID, answers, and selected presets.
[0609] Generating AI agents
[0610] The server analyzes the stored user information and customizes the AI agent based on that data, generating an agent based on the user's preferences, desired functionality, and emotional state.
[0611] Sending Agents
[0612] The server sends the data of the generated customized AI agent to the terminal.
[0613] Specific examples
[0614] For example, suppose User D wants a new customized AI agent. User D launches the app on their device and accesses the survey form. They select "cat" as their favorite character and "weather forecast" and "reminder settings" as their desired functions.
[0615] Next, when User D sends information, the device sends the data to the server. The server receives this information and stores it in a database. The server analyzes the stored information and generates an AI agent based on User D's preferences. The generated agent includes the cat character's appearance and the ability to set weather forecasts and reminders.
[0616] The device also uses an emotion engine to analyze the user's voice and facial expressions to detect their emotional state. For example, if the emotion engine recognizes "sadness" in User D's voice, the agent will respond in a gentle manner.
[0617] The server then sends the agent data to the device, which receives and installs it. Once installation is complete, the device executes the agent and notifies User D. User D can then use this agent to receive support for daily activities such as checking the weather forecast and setting reminders.
[0618] Furthermore, the agent dynamically adjusts its dialogue and behavior according to the emotional state of user D, providing continuous support. For example, if user D says, "I'm feeling down today," the agent will suggest, "Shall we do something fun to change your mood?"
[0619] In this way, the system of the present invention not only provides users with a convenient and easily customizable AI agent, but also uses an emotion engine to achieve high-quality dialogue that responds to the user's emotions.
[0620] The processing flow will be explained below.
[0621] Step 1:
[0622] Device: When the user launches the app, a survey form or preset selection screen is displayed.
[0623] Step 2:
[0624] User: Access the survey form and answer questions such as "Favorite character" and "Desired functions." Alternatively, select your preferred agent from a list of preset agents.
[0625] Step 3:
[0626] Terminal: After the user has completed their input or selection, they press the send button, which sends the information to the server.
[0627] Step 4:
[0628] Server: Receives user information sent from the device and stores it in a database. The stored information includes the user ID, answers, selected presets, etc.
[0629] Step 5:
[0630] Server: Analyzes saved user information and generates a customized AI agent based on the user's preferences and needs. For example, if a user selects a favorite character, "cat," an agent with the character's appearance and voice will be generated.
[0631] Step 6:
[0632] Server: Prepares the data of the generated AI agent and prepares it for transmission to the terminal.
[0633] Step 7:
[0634] Server: Sends customized AI agent data to the device, including appearance, function settings, and required initial setup information.
[0635] Step 8:
[0636] Terminal: Installs the received agent data. The installation process includes extracting the data and registering it in the system.
[0637] Step 9:
[0638] Terminal: Performing initial agent configuration, for example, applying a setting to enable the weather forecast function on the user's terminal.
[0639] Step 10:
[0640] Terminal: Starts the AI agent and notifies the user when it is ready.
[0641] Step 11:
[0642] User: Starts interacting with the AI agent that is activated on the device. For example, they can ask the agent, "What's the weather like today?" and the agent will provide a weather forecast.
[0643] Step 12:
[0644] Terminal: When a user is using an active agent, emotional data of the user is collected using voice input and camera functions.
[0645] Step 13:
[0646] Device: The emotion engine analyzes the collected emotional data and identifies the user's emotional state. For example, it can detect "happiness" or "sadness" from the user's tone of voice and facial expressions.
[0647] Step 14:
[0648] Terminal: Dynamically adjusts the AI agent's responses and behavior based on emotional data analyzed by the emotion engine. For example, if the user expresses "sadness," the agent will ask, "Is there anything you're worried about?"
[0649] Step 15:
[0650] Agent (running on the device): Provides ongoing support for the user's everyday requests. For example, if the user says, "Set a reminder," the agent responds, "Reminder set."
[0651] Step 16:
[0652] Device: Records emotional data analyzed by the emotion engine and learns the user's emotional tendencies over time.
[0653] Step 17:
[0654] Server: The server periodically collects and analyzes the user's emotional data and customizes the service to reflect the user's emotional tendencies. For example, if the user frequently feels "stressed," the agent will proactively make suggestions to help them relax.
[0655] In this way, the system of the present invention not only provides users with a convenient and easily customizable AI agent, but also uses an emotion engine to achieve high-quality dialogue that responds to the user's emotions.
[0656] Example 2
[0657] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."
[0658] Conventional AI agent systems have difficulty fully meeting the individual needs and preferences of users, and few systems can flexibly respond to the user's emotional state. As a result, interactions with users tend to be unnatural, often resulting in low user satisfaction. Furthermore, customization using unique characters and the provision of multifunctional agents are insufficient, leaving them lacking in support for everyday life.
[0659] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for receiving information when a user accesses a simple input form and answers a questionnaire or selects a preset setting, a means for the terminal to collect the information and send it to the server, a means for analyzing the received user information and using a generative AI model to generate an AI agent based on the user's preferences and required functions, and a means for sending the generated AI agent data to the terminal and installing and executing it. This makes it possible to generate and install an AI agent that is highly personalized for the user, thereby realizing advanced dialogue that responds to the user's needs and emotional state.
[0660] The "information input form" is an interface that allows the user to answer questionnaires and select preset settings.
[0661] A "server" is a device or system that receives, stores, and analyzes information sent by a user, generates an AI agent, and sends it to a terminal.
[0662] A "terminal" is a device for users to input information and is a device for installing and executing generated AI agents.
[0663] An "emotion engine" is software or a device that analyzes a user's voice, facial expression, and text data to detect their emotional state.
[0664] A "generative AI model" is an algorithm or machine learning model for generating customized AI agents based on user information.
[0665] "Agent data" refers to the configuration information and program data of the generated AI agent.
[0666] The "questionnaire" is a questionnaire containing questions about the user's preferences and required functions.
[0667] "Presets" are the settings and function patterns of multiple AI agents that have been set up in advance.
[0668] "Installation" refers to the process of incorporating the AI agent's programs and settings into the device.
[0669] "Execution" means running the installed AI agent and interacting with and supporting the user.
[0670] "User information" refers to questionnaires and preset setting data entered by the user, as well as data on emotional states analyzed by the emotion engine.
[0671] This invention is a system that allows users to easily use customized AI agents. This system is composed of a terminal, a server, and an emotion engine. The specific operations of each stakeholder (user, terminal, server) are explained below.
[0672] User operations
[0673] Enter information
[0674] First, the user accesses the input form or preset selection screen provided on the device using a web browser or dedicated application. For example, the user answers questions such as "favorite character" or "necessary functions" in a questionnaire.
[0675] Agent Selection and Purchasing
[0676] The user can select and purchase an agent that suits their preferences from the displayed list of preset agents, allowing the user to easily select a customized agent.
[0677] Device behavior
[0678] Providing an input interface
[0679] The device displays an input form or preset selection screen to the user, and after the user completes the input, it uses HTML and JavaScript to send the data to the server.
[0680] Use of emotion engine
[0681] The device collects the user's voice and facial expression data and sends it to an emotion engine such as Affectiva or IBM Watson Tone Analyzer. The emotion engine analyzes this data to detect the user's emotional state. For example, if a user says, "I'm tired today," this information is analyzed by the emotion engine.
[0682] Installing and Running the Agent
[0683] The device installs the customized AI agent data received from the server, runs a Python script to install the agent, and notifies the user when it is complete, allowing the agent to be used immediately.
[0684] Server Operation
[0685] Receiving and storing user information
[0686] The server receives the user information sent from the device. For example, it receives the data using a REST API and stores it in a database (MySQL or PostgreSQL). The stored information includes the user ID, answers, selected presets, etc.
[0687] Generating AI agents
[0688] The server analyzes the stored user information and generates an AI agent using a generative AI model such as OpenAI's GPT-4. The server customizes the agent based on the user's preferences, required features, and emotional state. This generation process uses prompts such as:
[0689] Prompt Sentence Examples
[0690] 1. "The user's favorite character is a cat, and they need weather forecasts and reminder settings. Create a customized AI agent configuration based on this."
[0691] 2. "Sadness was detected from the user's voice analysis. Please add a kind response for the user."
[0692] Sending Agents
[0693] The server sends the generated AI agent data to the device, which then receives it using the REST API.
[0694] Specific examples
[0695] For example, consider the case where User D wants a new customized AI agent. User D starts the app on his / her device, accesses the questionnaire form, and selects "cat as favorite character" and "weather forecast and reminder setting as required functions." The device collects this information and sends it to the server. The server receives the information and stores it in a database. The server then analyzes the received information and generates an AI agent with the appearance of a cat character and the functions of weather forecast and reminder setting. The generated agent data is sent to the device, which receives it and installs it. After installation is complete, the device notifies User D, who can then begin using the agent.
[0696] Furthermore, if User D says, "I'm feeling depressed today," the emotion engine analyzes this and sends the data to the server. The server then changes the agent's response settings based on the additional prompts, providing a friendly response to User D. In this way, the system can provide a personalized agent for the user and achieve high-quality dialogue that responds to the user's emotional state.
[0697] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0698] Step 1: User launches application
[0699] The user launches a dedicated application or web browser on the device and accesses an input form or preset selection screen. A form is displayed asking for input such as the character of their choice and the functions they require. The user answers these questions and the information is sent to the device.
[0700] Step 2: Collect and submit input data
[0701] The device collects the survey data and preset setting data entered by the user and sends it to the server. Specifically, the data entered in the HTML form is sent to the server via the REST API using JavaScript with the POST method. The survey data and preset settings are input, and a notification of completion of transmission to the server is sent as output.
[0702] Step 3: Receiving and storing user information
[0703] The server receives user information sent from the device and stores it in a database. Specifically, it processes the received data using Python scripts and a database engine (MySQL or PostgreSQL). The inputs are survey data and preset settings, and the output is the data saved in the database.
[0704] Step 4: Collect and send emotion data
[0705] The device collects the user's voice and facial expression data and sends it to the emotion engine. For example, if the user says, "I'm tired today," the device records that voice and sends it to the emotion engine (Affectiva or IBM Watson Tone Analyzer). The input is the user's voice data and facial expression data, and the output is the result sent to the emotion engine.
[0706] Step 5: Emotional state analysis and notification
[0707] The emotion engine analyzes the voice data and facial expression data received from the user to detect the user's emotional state. Specifically, the emotion engine's algorithm analyzes the data and identifies the user's emotional state (e.g., sadness or joy). The voice data and facial expression data are sent as input, and the detected emotional state is sent as output to the server.
[0708] Step 6: Generate an AI agent
[0709] The server analyzes the stored user information and emotional state data obtained from the emotion engine to generate an AI agent specialized for the user. OpenAI's GPT-4 is used as the generative AI model. The server customizes the agent based on the user's preferences, required functions, and emotional state. For example, it generates an agent with a "cat character appearance" and "weather forecast and reminder setting functions." User information and emotional state data are obtained as input, and agent configuration information and program data are obtained as output.
[0710] Step 7: Submit and install the agent
[0711] The server sends the generated customized AI agent data to the device. The data is then sent again via a REST API, and the device receives and installs it. For example, a Python script can install the agent and notify the user when it's complete. The agent data is received from the server as input, and a notification of installation completion is sent to the device as output.
[0712] Step 8: Run the agent and notify the user
[0713] The device runs the installed AI agent and notifies the user. For example, the AI agent starts on the device and notifies the user, "The agent installation is complete and it's ready to use." The input is the installed AI agent, and the output is the agent launch and a notification to the user.
[0714] Step 9: Agent support for daily life
[0715] Users use the agent to receive support in their daily lives, such as checking the weather forecast or setting reminders. The agent adjusts its dialogue and behavior appropriately according to the user's emotional state. For example, if the user says, "I'm feeling down today," the agent might suggest, "Shall we do something fun to cheer you up?" The inputs are the user's statements and emotional state data, and the output is the agent's response and the provision of support functions.
[0716] (Application example 2)
[0717] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."
[0718] Conventional content distribution services lacked a function to recommend content that was tailored to the user's emotional state, making it difficult to provide users with the optimal entertainment experience. In particular, content recommendations were often inappropriate for users because they could not respond to the user's mood or emotions. As a result, users often spent a lot of time and effort finding the optimal content, which often led to a decrease in satisfaction with the service.
[0719] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving information when the user answers a simple questionnaire or selects a preset setting, means for analyzing the received user information and generating an AI agent based on the user's preferences and needs, means for transmitting the generated AI agent to the user's terminal and installing and executing it, and means for analyzing the user's emotional state in real time and recommending videos and music according to that emotional state. This makes it possible to automatically recommend optimal content that matches the user's emotional state.
[0720] A "questionnaire" is a question-type input means for a user to input their preferences and needs.
[0721] "Preset" refers to a set of agents and functions that have been set up in advance, and allows the user to easily customize the system by selecting one of them.
[0722] "User Information" refers to data about a user's preferences and needs collected through questionnaires and preset selections.
[0723] "Analysis" is an information processing process that identifies the user's preferences and needs from the received user information and generates an appropriate AI agent.
[0724] An "AI agent" is software equipped with artificial intelligence that responds to user instructions and requests and provides various functions.
[0725] "Terminal" refers to a device used by a user, such as a computer or smartphone.
[0726] "Emotional state" is information indicating the psychological state of the user obtained from facial expressions, voice, and text data.
[0727] "Real-time" refers to the time-based responsiveness of responding and responding immediately to user actions and inputs.
[0728] "Recommendation" is the act of suggesting optimal content based on a user's preferences and emotional state.
[0729] "Moving image" is viewable information content that includes a sequence of images and sound.
[0730] "Music" is information content that can be enjoyed auditorily, consisting of melody, harmony, and rhythm.
[0731] A "system" is a set of devices and software that combine multiple means to achieve a specific function.
[0732] The present invention relates to a system for allowing a user to receive optimal content according to his / her emotional state. Detailed embodiments are described below.
[0733] Overall system configuration
[0734] The present invention mainly comprises the following three elements:
[0735] 1. Server: Stores and analyzes user information, generates and transmits customized AI agents.
[0736] 2. Terminal: Provides an interface for users to input information and analyzes the user's emotional state using an emotion engine.
[0737] 3. User: Customize your agent by answering surveys and selecting presets.
[0738] Program operation explanation
[0739] Hardware and software used
[0740] Hardware: Smartphones, servers
[0741] Software: Python, requests library, transformers library, Hypothesis sentiment analysis and recommendation engine module (SentimentAnalyzer, ContentRecommender)
[0742] Data flow
[0743] 1. User Action:
[0744] Users access a questionnaire form using their smartphones and enter their preferences and desired features, and the information is sent to the server.
[0745] 2. Server operation:
[0746] The server receives and analyzes user information. Based on the analysis results, it generates a customized AI agent that matches the user's preferences and needs. The generated agent is then sent to the user's device.
[0747] 3. Device operation:
[0748] The device then installs and runs the received AI agent, analyzes the user's emotional state in real time, and recommends appropriate content (videos and music) based on that emotion.
[0749] As part of the specific processing steps, the device passes the user's voice input and text to the "SentimentAnalyzer" to analyze their emotions. Based on the results, the "ContentRecommender" selects the most appropriate content and presents it to the user.
[0750] Specific examples
[0751] For example, User A accesses a questionnaire form, selects "cat" as his / her favorite character, and selects "video recommendation" and "music recommendation" as required functions. This information is sent to the server, which generates a customized AI agent based on User A's preferences and sends it to the device. The device installs it, and if User A enters "I'm feeling depressed today," the emotion analysis engine recognizes "sadness," and the recommendation engine suggests uplifting content based on that.
[0752] Prompt Sentence Examples
[0753] User: I'm feeling down today.
[0754] System: The emotion analysis engine has detected "sadness." We will recommend music and videos that will uplift your mood.
[0755] In this way, the present invention can realize high-quality content recommendations that correspond to the user's emotional state.
[0756] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0757] Step 1:
[0758] The user accesses the questionnaire form and enters their preferences and required functions. At this time, the user uses their smartphone to select, for example, "cat" as their "favorite character" and selects "video recommendations" and "music recommendations" as "required functions." The input data is sent to the server in JSON format.
[0759] Input: Survey content selected by the user (preferences, required features)
[0760] Output: User information sent to the server (JSON format data)
[0761] Step 2:
[0762] The server receives the user information and stores it in a database. This process records the user's ID, preferences, and required functions in the database. The server then analyzes the received user information and generates an AI agent based on the user's preferences and needs.
[0763] Input: User information sent from the device (JSON format data)
[0764] Output: User information stored in a database, customized AI agent
[0765] Step 3:
[0766] The server sends the generated AI agent data to the user's device. The device receives this data and installs the AI agent. Once the installation is complete, the AI agent is set up to be immediately available for use.
[0767] Input: AI agent data generated by the server
[0768] Output: AI agent installed on the device
[0769] Step 4:
[0770] The device receives the user's voice input and text data and sends it to a sentiment analysis engine (SentimentAnalyzer). The sentiment analysis engine analyzes the input data and identifies the user's emotional state. The analysis results are output as an emotional state, such as "sadness," "joy," or "anger."
[0771] Input: User voice input or text data
[0772] Output: Parsed user's emotional state (e.g. "sadness")
[0773] Step 5:
[0774] The device receives the emotion analysis results and passes them to a recommendation engine (ContentRecommender). The recommendation engine generates a list of recommended videos and music based on the user's emotional state. For example, if the user's emotion is analyzed as "sadness," it will recommend uplifting music and fun videos. These recommendation results are then presented to the user on the device.
[0775] Input: Emotional state from the emotion analysis engine (e.g. "sadness")
[0776] Output: A list of content recommendations based on emotional state
[0777] Step 6:
[0778] The user checks the recommendation list on the device and selects the content they want to watch. The device then starts playing the selected content, providing the user with a viewing experience.
[0779] Input: Content selected from the recommended list
[0780] Output: The content that started playing (video or music)
[0781] In this way, through each step, the user can receive the most suitable content depending on their emotional state, thereby improving the user's entertainment experience.
[0782] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.
[0783] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[0784] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.
[0785] [Third embodiment]
[0786] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.
[0787] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.
[0788] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).
[0789] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.
[0790] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.
[0791] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).
[0792] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.
[0793] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.
[0794] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.
[0795] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.
[0796] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[0797] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."
[0798] This invention provides a system that allows users to easily use customized AI agents. This system generates AI agents that meet individual needs by allowing users to select and answer questionnaires or presets. The specific operations of each stakeholder (user, terminal, server) are explained below.
[0799] User operations
[0800] Enter information
[0801] First, the user accesses a questionnaire form and preset selection screen provided on the device. The questionnaire includes questions such as "favorite character" and "necessary functions," and the user answers these. The preset settings also allow the user to select from several pre-prepared agents.
[0802] Agent Selection and Purchasing
[0803] The user can view a list of multiple preset agents provided in the store, and can select and purchase an agent that suits his or her preference.
[0804] Device behavior
[0805] Providing an input interface
[0806] The device displays a questionnaire form or a preset selection screen where the user can enter information. After the user has completed the input, the information is sent to the server.
[0807] Installing and Running the Agent
[0808] The device installs the customized AI agent data received from the server and performs initial setup so that the user can use it immediately. After installation, the agent is executed and notifies the user.
[0809] Server Operation
[0810] Receiving and storing user information
[0811] The server receives the user information sent from the terminal and stores it in a database.
[0812] Generating AI agents
[0813] The server analyzes the stored user information and customizes the AI agent based on that data, generating an agent that reflects the user's preferences and desired functions.
[0814] Sending Agents
[0815] The server sends the data of the generated customized AI agent to the terminal.
[0816] Specific examples
[0817] For example, suppose user C wants a new customized AI agent. User C launches the app on their device and accesses the survey form. They select "dog" as their favorite character and "weather forecast" and "reminder settings" as their desired functions.
[0818] Next, when User C sends information, the device sends the data to the server. The server receives this information and stores it in a database. The server analyzes the stored information and generates an AI agent based on User C's preferences. The generated agent includes the "appearance of the dog character" and "weather forecast and reminder setting functions."
[0819] The server then sends the agent data to the device, which receives and installs it. Once the installation is complete, the device runs the agent and notifies User C. User C can use this agent to receive support for daily activities such as checking the weather forecast and setting reminders.
[0820] In this way, the system of the present invention provides users with convenient and easily customizable AI agents. Furthermore, by using presets and a store, users can easily obtain agents that suit their preferences.
[0821] The processing flow will be explained below.
[0822] Step 1:
[0823] Device: When the user launches the app, a survey form or preset selection screen is displayed.
[0824] Step 2:
[0825] User: Access the survey form and answer questions such as "Favorite character" and "Desired functions." Alternatively, select your preferred agent from a list of preset agents.
[0826] Step 3:
[0827] Terminal: After the user has completed their input or selection, they press the send button, which sends the information to the server.
[0828] Step 4:
[0829] Server: Receives user information sent from the device and stores it in a database. The stored information includes the user ID, answers, selected presets, etc.
[0830] Step 5:
[0831] Server: Analyzes saved user information and generates a customized AI agent based on the user's preferences and needs. For example, if a user selects "dog" as their favorite character, an agent with the appearance and voice of that character will be generated.
[0832] Step 6:
[0833] Server: Prepares the data of the generated AI agent and prepares it for transmission to the terminal.
[0834] Step 7:
[0835] Server: Sends customized AI agent data to the device, including appearance, function settings, and required initial setup information.
[0836] Step 8:
[0837] Terminal: Installs the received agent data. The installation process includes extracting the data and registering it in the system.
[0838] Step 9:
[0839] Terminal: Performing initial agent configuration, for example, applying a setting to enable the weather forecast function on the user's terminal.
[0840] Step 10:
[0841] Terminal: Starts the AI agent and notifies the user when it is ready.
[0842] Step 11:
[0843] User: Starts interacting with the AI agent that is activated on the device. For example, they can ask the agent, "What's the weather like today?" and the agent will provide a weather forecast.
[0844] Step 12:
[0845] Agent (running on the device): Provides ongoing support for the user's everyday requests. This is an ongoing process and can include a variety of functions, such as setting reminders or optimizing commute routes.
[0846] The above is the specific process flow for users to use a customized AI agent.
[0847] Example 1
[0848] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."
[0849] Existing AI agent systems make it difficult for users to easily customize agents to suit their preferences and needs. Furthermore, the process is often cumbersome, resulting in a poor user experience. Furthermore, agent customization is limited, making it difficult to meet diverse user needs. The objective of this invention is to solve these problems and provide a system that allows users to more easily use highly customized AI agents.
[0850] 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.
[0851] In this invention, the server includes a means for receiving information from a user by answering a simple questionnaire or selecting preset settings, a means for analyzing the received user information and generating a customized AI agent using a generative AI model based on the user's preferences and needs, and a means for transmitting the generated AI agent to the user's terminal and installing and executing it, thereby enabling the user to easily use an AI agent that suits their preferences and needs.
[0852] "User" refers to any individual or legal entity that uses the system and customizes an AI agent to suit their preferences and needs through questionnaires and presets.
[0853] A "survey" refers to a form containing questions to gather user preferences and needs.
[0854] "Presets" refers to options that provide multiple pre-configured AI agent configurations and capabilities.
[0855] "Means for receiving" refers to the method or process by which the system receives information entered by the user.
[0856] "Means for analyzing" refers to the methods and algorithms used to process received user information and understand the user's preferences and needs.
[0857] "Generative AI models" refer to machine learning models and natural language processing models that generate customized AI agents based on user information.
[0858] A "customized AI agent" refers to an AI agent that is specially created to reflect the user's preferences and needs.
[0859] "Terminal" refers to the hardware or device through which a user accesses the system and installs and runs customized AI agents.
[0860] "Transmission means" refers to the method or process for transmitting data of the generated AI agent from the server to the terminal.
[0861] "Installation and execution means" refers to the method or process for installing a customized AI agent on a device and running it for use by the user.
[0862] "Various functions to support the user's daily life" refers to the functions and services provided by a customized AI agent to assist the user in their daily life.
[0863] This invention provides a system that allows users to easily use customized AI agents. This system generates AI agents that meet individual needs by allowing users to select and answer questionnaires or presets. The specific operations of each stakeholder (server, terminal, user) are explained in detail below.
[0864] User operations
[0865] First, users access a questionnaire form and preset selection screen provided on their smartphone, tablet, or PC. The questionnaire includes questions such as "favorite character" and "necessary functions," and the user answers these. The preset settings also allow users to choose from several pre-prepared agents.
[0866] As a specific example, user A opens a questionnaire form and selects "dragon" as his / her "favorite character" and "to-do list management" as his / her "necessary function."
[0867] Server Operation
[0868] The server receives the user information sent from the device and stores it in a database in JSON format.
[0869] Next, the server analyzes the stored user information and generates a customized AI agent using a generative AI model (e.g., GPT-4). Specifically, it generates an AI agent using the following prompt sentence:
[0870] User's favorite character: Dragon
[0871] Required feature: To-do list management
[0872] Generate customized AI agents based on this information.
[0873] The server then sends the generated customized AI agent data to the terminal, again in JSON format.
[0874] Device behavior
[0875] The device receives the customized AI agent data sent from the server, installs it, and performs initial setup. After installation, the agent runs and notifies the user.
[0876] As a concrete example, the device installs an agent with the "appearance of a dragon character" and "to-do list management function" for User A. After the installation is complete, the device notifies the user that "the agent has been installed."
[0877] Using an agent
[0878] Users can use the installed customized agents to perform various tasks. For example, user A, who is managing his to-do list, asks the agent, "What's on my schedule for today?" The agent responds, "I have three meetings today."
[0879] Hardware and software used
[0880] Devices: Smartphones, tablets, PCs
[0881] Server: Cloud server (e.g. AWS, Google Cloud, Azure)
[0882] Software: Web applications for implementing survey forms and preset selection screens, and machine learning models (e.g., GPT-4) for generating AI agents.
[0883] In this way, the system of the present invention provides users with convenient and easily customizable AI agents. Users can easily use agents with functions based on their individual needs. Furthermore, by using presets and a store, users can easily obtain agents that suit their preferences.
[0884] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0885] Step 1:
[0886] Enter user information
[0887] Users log in to the system using a terminal. After logging in, they can access a questionnaire form and a preset selection screen. Here, users input their favorite character and required functions. For example, User A selects "dragon" as his "favorite character" and "to-do list management" as his "required function."
[0888] Input: User survey data
[0889] Output: User data in JSON format
[0890] Step 2:
[0891] Sending information
[0892] The device sends the information entered by the user to the server, in JSON format.
[0893] Input: User data in JSON format
[0894] Output: User data sent to the server
[0895] Step 3:
[0896] Receiving and storing user information
[0897] The server receives the information sent from the terminal and stores it in a database.
[0898] Input: User data in JSON format
[0899] Output: User information stored in the database
[0900] Step 4:
[0901] Generating AI agents
[0902] The server analyzes the stored user information and generates a customized AI agent using a generative AI model (e.g., GPT-4). Specifically, it generates an AI agent using the following prompt:
[0903] User's favorite character: Dragon
[0904] Required feature: To-do list management
[0905] Generate customized AI agents based on this information.
[0906] Input: User information stored in the database
[0907] Output: Customized agent data in JSON format
[0908] Step 5:
[0909] Sending Agent Information
[0910] The server sends the generated customized agent data to the device, again in JSON format.
[0911] Input: Customized agent data in JSON format
[0912] Output: Agent data sent to the terminal
[0913] Step 6:
[0914] Installing and Running the Agent
[0915] The device receives the customized AI agent data sent from the server, installs it, and performs initial setup. After installation, the agent runs and notifies the user.
[0916] Input: Customized agent data in JSON format
[0917] Output: An installed and running AI agent.
[0918] Step 7:
[0919] Using an agent
[0920] Users can use the installed customized agents to perform various tasks. For example, user A asks the agent, "What's on my schedule for today?" to manage his to-do list. The agent responds, "I have three meetings today."
[0921] Input: User operation instructions
[0922] Output: Response from the agent
[0923] (Application example 1)
[0924] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."
[0925] Conventional food delivery services have the drawback of requiring users to select different restaurants and menus each time, and not providing optimal suggestions that fit individual preferences or schedules. Furthermore, in order to accommodate specific requirements (such as allergy information or specific types of cuisine), users must perform detailed searches and confirmations each time, which is cumbersome.
[0926] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.
[0927] In this invention, the server includes means for receiving information from a user by answering a simple questionnaire or selecting preset settings, means for analyzing the received user information and generating an AI agent based on the user's preferences and needs, means for transmitting the generated AI agent to the user's terminal and installing and executing it, and means for providing the user with recommended information optimized for a specific category (e.g., food delivery) based on the analyzed information, thereby enabling the provision of an optimal food delivery service based on the user's individual preferences and schedule.
[0928] The "questionnaire" is a question-type input means for the user to input individual preferences and required functions.
[0929] "Preset" refers to pre-defined options and settings that users can choose from.
[0930] "User Information" is data about individual preferences and needs provided by a user through surveys or preset selections.
[0931] An "AI agent" is a virtual assistant that provides assistance and services to users through a customized program based on their preferences and needs.
[0932] "Food delivery" is a service that delivers dishes or food selected by the user to a specified location.
[0933] A "generative AI model" refers to an algorithm or program that generates a customized AI agent based on user information.
[0934] A "prompt" is a form of recommendation or instruction that an AI agent provides to a user.
[0935] This invention relates to a system that allows users to easily use customized AI agents. The core of this system is the exchange and analysis of data between the user, terminal, and server.
[0936] System Program
[0937] User operations
[0938] The user first accesses a questionnaire form or preset selection screen provided on the device. The questionnaire includes the user's preferences and desired functions (for example, "favorite type of food," "delivery frequency," etc.), and the user answers them. The preset settings allow the user to choose from pre-prepared options. This information is sent from the device to the server.
[0939] Server Operation
[0940] The server receives the information sent by the user and stores it in a database. The stored data is then analyzed using a generative AI model. This analysis generates a customized AI agent based on the user's preferences and needs. The generated AI agent includes, for example, recommendation information and notification functions suitable for a specific category (food delivery). Finally, the server sends the generated AI agent's data to the device.
[0941] Device behavior
[0942] The device then installs the customized AI agent data received from the server, making it immediately available to the user. After installation, the agent provides support for the user in their daily lives, such as recommending specific restaurants based on the user's preferences and providing ordering prompts.
[0943] Hardware and software used
[0944] Hardware:
[0945] Smartphone
[0946] Server machine
[0947] software:
[0948] Flask (Python framework)
[0949] Generative AI model (an algorithm that analyzes user information and generates a customized AI agent)
[0950] Database management system (storing user information)
[0951] This allows users to use a food delivery agent optimized for their individual needs by filling out a simple questionnaire or selecting presets.
[0952] Specific examples
[0953] For example, if a user enters "favorite cuisine (e.g., Chinese food)" and "delivery frequency (twice a week)" on the survey screen, the server analyzes this data and generates a customized agent that provides recommended restaurants and delivery times that suit the user's needs. This agent then displays a prompt to the user such as, "We have three Chinese restaurants A, B, and C that suit your tastes. When would you like your next delivery?"
[0954] Example prompt sentence:
[0955] "Based on your food preferences, we'd like to recommend Chinese restaurant A, restaurant B, and restaurant C. When would you like your next delivery?"
[0956] In this way, the system of the present invention provides the optimal food delivery service that matches the user's preferences.
[0957] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0958] Step 1:
[0959] The user accesses a questionnaire form or preset selection screen provided on the terminal, where they answer questions such as "Favorite type of food" and "Delivery frequency." The entered information is collected by the terminal as user information and sent to the server.
[0960] Step 2:
[0961] The server receives the user information sent from the device and temporarily stores it in a database. At this point, the input format is data such as JSON or XML. The stored information is used for analysis.
[0962] Step 3:
[0963] The server uses a generative AI model to analyze the stored user information. Specifically, it extracts data patterns based on the user's preferences and needs and generates a customized AI agent. This generation process involves processing and calculating the data (e.g., statistical analysis and clustering) to create agent data containing optimal recommendations.
[0964] Step 4:
[0965] The server sends the generated customized AI agent data to the device in a format such as JSON or binary. The device converts this data into an installable format and installs it as a working application.
[0966] Step 5:
[0967] The device will then begin running the installed AI agent, which the user can then control to receive assistance with daily activities, such as food recommendations and ordering prompts based on the user's preferences.
[0968] Step 6:
[0969] The user operates based on prompts provided by the AI agent. For example, they may receive instructions such as, "There are three Chinese restaurants A, B, and C that suit your tastes. When would you like your next delivery?" The user then selects the delivery time and confirms the order.
[0970] In this way, a customized food delivery service is provided based on the user's preferences and needs.
[0971] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.
[0972] This invention improves the quality of responses and support to users by combining an emotion engine with a system that allows users to easily use customized AI agents. The specific operations of each stakeholder (user, terminal, server) are explained below.
[0973] User operations
[0974] Enter information
[0975] First, the user accesses a questionnaire form and preset selection screen provided on the device. The questionnaire includes questions such as "favorite character" and "necessary functions," and the user answers these. The preset settings also allow the user to select from several pre-prepared agents.
[0976] Agent Selection and Purchasing
[0977] The user can check a list of multiple preset agents provided in the store, select an agent that suits his / her taste, and purchase it.
[0978] Device behavior
[0979] Providing an input interface
[0980] The device displays a questionnaire form or a preset selection screen where the user can enter information. After the user has completed the input, the information is sent to the server.
[0981] Use of emotion engine
[0982] The terminal provides the user's voice, facial expression, and text data to the emotion engine, which analyzes this data to detect the user's emotional state.
[0983] Installing and Running the Agent
[0984] The device installs the customized AI agent data received from the server and performs initial setup so that the user can use it immediately. After installation, the agent is executed and notifies the user.
[0985] Server Operation
[0986] Receiving and storing user information
[0987] The server receives the user information sent from the device and stores it in a database, including the user ID, answers, and selected presets.
[0988] Generating AI agents
[0989] The server analyzes the stored user information and customizes the AI agent based on that data, generating an agent based on the user's preferences, desired functionality, and emotional state.
[0990] Sending Agents
[0991] The server sends the data of the generated customized AI agent to the terminal.
[0992] Specific examples
[0993] For example, suppose User D wants a new customized AI agent. User D launches the app on their device and accesses the survey form. They select "cat" as their favorite character and "weather forecast" and "reminder settings" as their desired functions.
[0994] Next, when User D sends information, the device sends the data to the server. The server receives this information and stores it in a database. The server analyzes the stored information and generates an AI agent based on User D's preferences. The generated agent includes the cat character's appearance and the ability to set weather forecasts and reminders.
[0995] The device also uses an emotion engine to analyze the user's voice and facial expressions to detect their emotional state. For example, if the emotion engine recognizes "sadness" in User D's voice, the agent will respond in a gentle manner.
[0996] The server then sends the agent data to the device, which receives and installs it. Once installation is complete, the device executes the agent and notifies User D. User D can then use this agent to receive support for daily activities such as checking the weather forecast and setting reminders.
[0997] Furthermore, the agent dynamically adjusts its dialogue and behavior according to the emotional state of user D, providing continuous support. For example, if user D says, "I'm feeling down today," the agent will suggest, "Shall we do something fun to change your mood?"
[0998] In this way, the system of the present invention not only provides users with a convenient and easily customizable AI agent, but also uses an emotion engine to achieve high-quality dialogue that responds to the user's emotions.
[0999] The processing flow will be explained below.
[1000] Step 1:
[1001] Device: When the user launches the app, a survey form or preset selection screen is displayed.
[1002] Step 2:
[1003] User: Access the survey form and answer questions such as "Favorite character" and "Desired functions." Alternatively, select your preferred agent from a list of preset agents.
[1004] Step 3:
[1005] Terminal: After the user has completed their input or selection, they press the send button, which sends the information to the server.
[1006] Step 4:
[1007] Server: Receives user information sent from the device and stores it in a database. The stored information includes the user ID, answers, selected presets, etc.
[1008] Step 5:
[1009] Server: Analyzes saved user information and generates a customized AI agent based on the user's preferences and needs. For example, if a user selects a favorite character, "cat," an agent with the character's appearance and voice will be generated.
[1010] Step 6:
[1011] Server: Prepares the data of the generated AI agent and prepares it for transmission to the terminal.
[1012] Step 7:
[1013] Server: Sends customized AI agent data to the device, including appearance, function settings, and required initial setup information.
[1014] Step 8:
[1015] Terminal: Installs the received agent data. The installation process includes extracting the data and registering it in the system.
[1016] Step 9:
[1017] Terminal: Performing initial agent configuration, for example, applying a setting to enable the weather forecast function on the user's terminal.
[1018] Step 10:
[1019] Terminal: Starts the AI agent and notifies the user when it is ready.
[1020] Step 11:
[1021] User: Starts interacting with the AI agent that is activated on the device. For example, they can ask the agent, "What's the weather like today?" and the agent will provide a weather forecast.
[1022] Step 12:
[1023] Terminal: When a user is using an active agent, emotional data of the user is collected using voice input and camera functions.
[1024] Step 13:
[1025] Device: The emotion engine analyzes the collected emotional data and identifies the user's emotional state. For example, it can detect "happiness" or "sadness" from the user's tone of voice and facial expressions.
[1026] Step 14:
[1027] Terminal: Dynamically adjusts the AI agent's responses and behavior based on emotional data analyzed by the emotion engine. For example, if the user expresses "sadness," the agent will ask, "Is there anything you're worried about?"
[1028] Step 15:
[1029] Agent (running on the device): Provides ongoing support for the user's everyday requests. For example, if the user says, "Set a reminder," the agent responds, "Reminder set."
[1030] Step 16:
[1031] Device: Records emotional data analyzed by the emotion engine and learns the user's emotional tendencies over time.
[1032] Step 17:
[1033] Server: The server periodically collects and analyzes the user's emotional data and customizes the service to reflect the user's emotional tendencies. For example, if the user frequently feels "stressed," the agent will proactively make suggestions to help them relax.
[1034] In this way, the system of the present invention not only provides users with a convenient and easily customizable AI agent, but also uses an emotion engine to achieve high-quality dialogue that responds to the user's emotions.
[1035] Example 2
[1036] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."
[1037] Conventional AI agent systems have difficulty fully meeting the individual needs and preferences of users, and few systems can flexibly respond to the user's emotional state. As a result, interactions with users tend to be unnatural, often resulting in low user satisfaction. Furthermore, customization using unique characters and the provision of multifunctional agents are insufficient, leaving them lacking in support for everyday life.
[1038] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for receiving information when a user accesses a simple input form and answers a questionnaire or selects a preset setting, a means for the terminal to collect the information and send it to the server, a means for analyzing the received user information and using a generative AI model to generate an AI agent based on the user's preferences and required functions, and a means for sending the generated AI agent data to the terminal and installing and executing it. This makes it possible to generate and install an AI agent that is highly personalized for the user, thereby realizing advanced dialogue that responds to the user's needs and emotional state.
[1039] The "information input form" is an interface that allows the user to answer questionnaires and select preset settings.
[1040] A "server" is a device or system that receives, stores, and analyzes information sent by a user, generates an AI agent, and sends it to a terminal.
[1041] A "terminal" is a device for users to input information and is a device for installing and executing generated AI agents.
[1042] An "emotion engine" is software or a device that analyzes a user's voice, facial expression, and text data to detect their emotional state.
[1043] A "generative AI model" is an algorithm or machine learning model for generating customized AI agents based on user information.
[1044] "Agent data" refers to the configuration information and program data of the generated AI agent.
[1045] The "questionnaire" is a questionnaire containing questions about the user's preferences and required functions.
[1046] "Presets" are the settings and function patterns of multiple AI agents that have been set up in advance.
[1047] "Installation" refers to the process of incorporating the AI agent's programs and settings into the device.
[1048] "Execution" means running the installed AI agent and interacting with and supporting the user.
[1049] "User information" refers to questionnaires and preset setting data entered by the user, as well as data on emotional states analyzed by the emotion engine.
[1050] This invention is a system that allows users to easily use customized AI agents. This system is composed of a terminal, a server, and an emotion engine. The specific operations of each stakeholder (user, terminal, server) are explained below.
[1051] User operations
[1052] Enter information
[1053] First, the user accesses the input form or preset selection screen provided on the device using a web browser or dedicated application. For example, the user answers questions such as "favorite character" or "necessary functions" in a questionnaire.
[1054] Agent Selection and Purchasing
[1055] The user can select and purchase an agent that suits their preferences from the displayed list of preset agents, allowing the user to easily select a customized agent.
[1056] Device behavior
[1057] Providing an input interface
[1058] The device displays an input form or preset selection screen to the user, and after the user completes the input, it uses HTML and JavaScript to send the data to the server.
[1059] Use of emotion engine
[1060] The device collects the user's voice and facial expression data and sends it to an emotion engine such as Affectiva or IBM Watson Tone Analyzer. The emotion engine analyzes this data to detect the user's emotional state. For example, if a user says, "I'm tired today," this information is analyzed by the emotion engine.
[1061] Installing and Running the Agent
[1062] The device installs the customized AI agent data received from the server, runs a Python script to install the agent, and notifies the user when it is complete, allowing the agent to be used immediately.
[1063] Server Operation
[1064] Receiving and storing user information
[1065] The server receives the user information sent from the device. For example, it receives the data using a REST API and stores it in a database (MySQL or PostgreSQL). The stored information includes the user ID, answers, selected presets, etc.
[1066] Generating AI agents
[1067] The server analyzes the stored user information and generates an AI agent using a generative AI model such as OpenAI's GPT-4. The server customizes the agent based on the user's preferences, required features, and emotional state. This generation process uses prompts such as:
[1068] Prompt Sentence Examples
[1069] 1. "The user's favorite character is a cat, and they need weather forecasts and reminder settings. Create a customized AI agent configuration based on this."
[1070] 2. "Sadness was detected from the user's voice analysis. Please add a kind response for the user."
[1071] Sending Agents
[1072] The server sends the generated AI agent data to the device, which then receives it using the REST API.
[1073] Specific examples
[1074] For example, consider the case where User D wants a new customized AI agent. User D starts the app on his / her device, accesses the questionnaire form, and selects "cat as favorite character" and "weather forecast and reminder setting as required functions." The device collects this information and sends it to the server. The server receives the information and stores it in a database. The server then analyzes the received information and generates an AI agent with the appearance of a cat character and the functions of weather forecast and reminder setting. The generated agent data is sent to the device, which receives it and installs it. After installation is complete, the device notifies User D, who can then begin using the agent.
[1075] Furthermore, if User D says, "I'm feeling depressed today," the emotion engine analyzes this and sends the data to the server. The server then changes the agent's response settings based on the additional prompts, providing a friendly response to User D. In this way, the system can provide a personalized agent for the user and achieve high-quality dialogue that responds to the user's emotional state.
[1076] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1077] Step 1: User launches application
[1078] The user launches a dedicated application or web browser on the device and accesses an input form or preset selection screen. A form is displayed asking for input such as the character of their choice and the functions they require. The user answers these questions and the information is sent to the device.
[1079] Step 2: Collect and submit input data
[1080] The device collects the survey data and preset setting data entered by the user and sends it to the server. Specifically, the data entered in the HTML form is sent to the server via the REST API using JavaScript with the POST method. The survey data and preset settings are input, and a notification of completion of transmission to the server is sent as output.
[1081] Step 3: Receiving and storing user information
[1082] The server receives user information sent from the device and stores it in a database. Specifically, it processes the received data using Python scripts and a database engine (MySQL or PostgreSQL). The inputs are survey data and preset settings, and the output is the data saved in the database.
[1083] Step 4: Collect and send emotion data
[1084] The device collects the user's voice and facial expression data and sends it to the emotion engine. For example, if the user says, "I'm tired today," the device records that voice and sends it to the emotion engine (Affectiva or IBM Watson Tone Analyzer). The input is the user's voice data and facial expression data, and the output is the result sent to the emotion engine.
[1085] Step 5: Emotional state analysis and notification
[1086] The emotion engine analyzes the voice data and facial expression data received from the user to detect the user's emotional state. Specifically, the emotion engine's algorithm analyzes the data and identifies the user's emotional state (e.g., sadness or joy). The voice data and facial expression data are sent as input, and the detected emotional state is sent as output to the server.
[1087] Step 6: Generate an AI agent
[1088] The server analyzes the stored user information and emotional state data obtained from the emotion engine to generate an AI agent specialized for the user. OpenAI's GPT-4 is used as the generative AI model. The server customizes the agent based on the user's preferences, required functions, and emotional state. For example, it generates an agent with a "cat character appearance" and "weather forecast and reminder setting functions." User information and emotional state data are obtained as input, and agent configuration information and program data are obtained as output.
[1089] Step 7: Submit and install the agent
[1090] The server sends the generated customized AI agent data to the device. The data is then sent again via a REST API, and the device receives and installs it. For example, a Python script can install the agent and notify the user when it's complete. The agent data is received from the server as input, and a notification of installation completion is sent to the device as output.
[1091] Step 8: Run the agent and notify the user
[1092] The device runs the installed AI agent and notifies the user. For example, the AI agent starts on the device and notifies the user, "The agent installation is complete and it's ready to use." The input is the installed AI agent, and the output is the agent launch and a notification to the user.
[1093] Step 9: Agent support for daily life
[1094] Users use the agent to receive support in their daily lives, such as checking the weather forecast or setting reminders. The agent adjusts its dialogue and behavior appropriately according to the user's emotional state. For example, if the user says, "I'm feeling down today," the agent might suggest, "Shall we do something fun to cheer you up?" The inputs are the user's statements and emotional state data, and the output is the agent's response and the provision of support functions.
[1095] (Application example 2)
[1096] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."
[1097] Conventional content distribution services lacked a function to recommend content that was tailored to the user's emotional state, making it difficult to provide users with the optimal entertainment experience. In particular, content recommendations were often inappropriate for users because they could not respond to the user's mood or emotions. As a result, users often spent a lot of time and effort finding the optimal content, which often led to a decrease in satisfaction with the service.
[1098] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving information when the user answers a simple questionnaire or selects a preset setting, means for analyzing the received user information and generating an AI agent based on the user's preferences and needs, means for transmitting the generated AI agent to the user's terminal and installing and executing it, and means for analyzing the user's emotional state in real time and recommending videos and music according to that emotional state. This makes it possible to automatically recommend optimal content that matches the user's emotional state.
[1099] A "questionnaire" is a question-type input means for a user to input their preferences and needs.
[1100] "Preset" refers to a set of agents and functions that have been set up in advance, and allows the user to easily customize the system by selecting one of them.
[1101] "User Information" refers to data about a user's preferences and needs collected through questionnaires and preset selections.
[1102] "Analysis" is an information processing process that identifies the user's preferences and needs from the received user information and generates an appropriate AI agent.
[1103] An "AI agent" is software equipped with artificial intelligence that responds to user instructions and requests and provides various functions.
[1104] "Terminal" refers to a device used by a user, such as a computer or smartphone.
[1105] "Emotional state" is information indicating the psychological state of the user obtained from facial expressions, voice, and text data.
[1106] "Real-time" refers to the time-based responsiveness of responding and responding immediately to user actions and inputs.
[1107] "Recommendation" is the act of suggesting optimal content based on a user's preferences and emotional state.
[1108] "Moving image" is viewable information content that includes a sequence of images and sound.
[1109] "Music" is information content that can be enjoyed auditorily, consisting of melody, harmony, and rhythm.
[1110] A "system" is a set of devices and software that combine multiple means to achieve a specific function.
[1111] The present invention relates to a system for allowing a user to receive optimal content according to his / her emotional state. Detailed embodiments are described below.
[1112] Overall system configuration
[1113] The present invention mainly comprises the following three elements:
[1114] 1. Server: Stores and analyzes user information, generates and transmits customized AI agents.
[1115] 2. Terminal: Provides an interface for users to input information and analyzes the user's emotional state using an emotion engine.
[1116] 3. User: Customize your agent by answering surveys and selecting presets.
[1117] Program operation explanation
[1118] Hardware and software used
[1119] Hardware: Smartphones, servers
[1120] Software: Python, requests library, transformers library, Hypothesis sentiment analysis and recommendation engine module (SentimentAnalyzer, ContentRecommender)
[1121] Data flow
[1122] 1. User Action:
[1123] Users access a questionnaire form using their smartphones and enter their preferences and desired features, and the information is sent to the server.
[1124] 2. Server operation:
[1125] The server receives and analyzes user information. Based on the analysis results, it generates a customized AI agent that matches the user's preferences and needs. The generated agent is then sent to the user's device.
[1126] 3. Device operation:
[1127] The device then installs and runs the received AI agent, analyzes the user's emotional state in real time, and recommends appropriate content (videos and music) based on that emotion.
[1128] As part of the specific processing steps, the device passes the user's voice input and text to the "SentimentAnalyzer" to analyze their emotions. Based on the results, the "ContentRecommender" selects the most appropriate content and presents it to the user.
[1129] Specific examples
[1130] For example, User A accesses a questionnaire form, selects "cat" as his / her favorite character, and selects "video recommendation" and "music recommendation" as required functions. This information is sent to the server, which generates a customized AI agent based on User A's preferences and sends it to the device. The device installs it, and if User A enters "I'm feeling depressed today," the emotion analysis engine recognizes "sadness," and the recommendation engine suggests uplifting content based on that.
[1131] Prompt Sentence Examples
[1132] User: I'm feeling down today.
[1133] System: The emotion analysis engine has detected "sadness." We will recommend music and videos that will uplift your mood.
[1134] In this way, the present invention can realize high-quality content recommendations that correspond to the user's emotional state.
[1135] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1136] Step 1:
[1137] The user accesses the questionnaire form and enters their preferences and required functions. At this time, the user uses their smartphone to select, for example, "cat" as their "favorite character" and selects "video recommendations" and "music recommendations" as "required functions." The input data is sent to the server in JSON format.
[1138] Input: Survey content selected by the user (preferences, required features)
[1139] Output: User information sent to the server (JSON format data)
[1140] Step 2:
[1141] The server receives the user information and stores it in a database. This process records the user's ID, preferences, and required functions in the database. The server then analyzes the received user information and generates an AI agent based on the user's preferences and needs.
[1142] Input: User information sent from the device (JSON format data)
[1143] Output: User information stored in a database, customized AI agent
[1144] Step 3:
[1145] The server sends the generated AI agent data to the user's device. The device receives this data and installs the AI agent. Once the installation is complete, the AI agent is set up to be immediately available for use.
[1146] Input: AI agent data generated by the server
[1147] Output: AI agent installed on the device
[1148] Step 4:
[1149] The device receives the user's voice input and text data and sends it to a sentiment analysis engine (SentimentAnalyzer). The sentiment analysis engine analyzes the input data and identifies the user's emotional state. The analysis results are output as an emotional state, such as "sadness," "joy," or "anger."
[1150] Input: User voice input or text data
[1151] Output: Parsed user's emotional state (e.g. "sadness")
[1152] Step 5:
[1153] The device receives the emotion analysis results and passes them to a recommendation engine (ContentRecommender). The recommendation engine generates a list of recommended videos and music based on the user's emotional state. For example, if the user's emotion is analyzed as "sadness," it will recommend uplifting music and fun videos. These recommendation results are then presented to the user on the device.
[1154] Input: Emotional state from the emotion analysis engine (e.g. "sadness")
[1155] Output: A list of content recommendations based on emotional state
[1156] Step 6:
[1157] The user checks the recommendation list on the device and selects the content they want to watch. The device then starts playing the selected content, providing the user with a viewing experience.
[1158] Input: Content selected from the recommended list
[1159] Output: The content that started playing (video or music)
[1160] In this way, through each step, the user can receive the most suitable content depending on their emotional state, thereby improving the user's entertainment experience.
[1161] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.
[1162] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[1163] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.
[1164] [Fourth embodiment]
[1165] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.
[1166] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.
[1167] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).
[1168] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.
[1169] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.
[1170] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).
[1171] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.
[1172] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.
[1173] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.
[1174] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.
[1175] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.
[1176] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[1177] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1178] This invention provides a system that allows users to easily use customized AI agents. This system generates AI agents that meet individual needs by allowing users to select and answer questionnaires or presets. The specific operations of each stakeholder (user, terminal, server) are explained below.
[1179] User operations
[1180] Enter information
[1181] First, the user accesses a questionnaire form and preset selection screen provided on the device. The questionnaire includes questions such as "favorite character" and "necessary functions," and the user answers these. The preset settings also allow the user to select from several pre-prepared agents.
[1182] Agent Selection and Purchasing
[1183] The user can view a list of multiple preset agents provided in the store, and can select and purchase an agent that suits his or her preference.
[1184] Device behavior
[1185] Providing an input interface
[1186] The device displays a questionnaire form or a preset selection screen where the user can enter information. After the user has completed the input, the information is sent to the server.
[1187] Installing and Running the Agent
[1188] The device installs the customized AI agent data received from the server and performs initial setup so that the user can use it immediately. After installation, the agent is executed and notifies the user.
[1189] Server Operation
[1190] Receiving and storing user information
[1191] The server receives the user information sent from the terminal and stores it in a database.
[1192] Generating AI agents
[1193] The server analyzes the stored user information and customizes the AI agent based on that data, generating an agent that reflects the user's preferences and desired functions.
[1194] Sending Agents
[1195] The server sends the data of the generated customized AI agent to the terminal.
[1196] Specific examples
[1197] For example, suppose user C wants a new customized AI agent. User C launches the app on their device and accesses the survey form. They select "dog" as their favorite character and "weather forecast" and "reminder settings" as their desired functions.
[1198] Next, when User C sends information, the device sends the data to the server. The server receives this information and stores it in a database. The server analyzes the stored information and generates an AI agent based on User C's preferences. The generated agent includes the "appearance of the dog character" and "weather forecast and reminder setting functions."
[1199] The server then sends the agent data to the device, which receives and installs it. Once the installation is complete, the device runs the agent and notifies User C. User C can use this agent to receive support for daily activities such as checking the weather forecast and setting reminders.
[1200] In this way, the system of the present invention provides users with convenient and easily customizable AI agents. Furthermore, by using presets and a store, users can easily obtain agents that suit their preferences.
[1201] The processing flow will be explained below.
[1202] Step 1:
[1203] Device: When the user launches the app, a survey form or preset selection screen is displayed.
[1204] Step 2:
[1205] User: Access the survey form and answer questions such as "Favorite character" and "Desired functions." Alternatively, select your preferred agent from a list of preset agents.
[1206] Step 3:
[1207] Terminal: After the user has completed their input or selection, they press the send button, which sends the information to the server.
[1208] Step 4:
[1209] Server: Receives user information sent from the device and stores it in a database. The stored information includes the user ID, answers, selected presets, etc.
[1210] Step 5:
[1211] Server: Analyzes saved user information and generates a customized AI agent based on the user's preferences and needs. For example, if a user selects "dog" as their favorite character, an agent with the appearance and voice of that character will be generated.
[1212] Step 6:
[1213] Server: Prepares the data of the generated AI agent and prepares it for transmission to the terminal.
[1214] Step 7:
[1215] Server: Sends customized AI agent data to the device, including appearance, function settings, and required initial setup information.
[1216] Step 8:
[1217] Terminal: Installs the received agent data. The installation process includes extracting the data and registering it in the system.
[1218] Step 9:
[1219] Terminal: Performing initial agent configuration, for example, applying a setting to enable the weather forecast function on the user's terminal.
[1220] Step 10:
[1221] Terminal: Starts the AI agent and notifies the user when it is ready.
[1222] Step 11:
[1223] User: Starts interacting with the AI agent that is activated on the device. For example, they can ask the agent, "What's the weather like today?" and the agent will provide a weather forecast.
[1224] Step 12:
[1225] Agent (running on the device): Provides ongoing support for the user's everyday requests. This is an ongoing process and can include a variety of functions, such as setting reminders or optimizing commute routes.
[1226] The above is the specific process flow for users to use a customized AI agent.
[1227] Example 1
[1228] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1229] Existing AI agent systems make it difficult for users to easily customize agents to suit their preferences and needs. Furthermore, the process is often cumbersome, resulting in a poor user experience. Furthermore, agent customization is limited, making it difficult to meet diverse user needs. The objective of this invention is to solve these problems and provide a system that allows users to more easily use highly customized AI agents.
[1230] 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.
[1231] In this invention, the server includes a means for receiving information from a user by answering a simple questionnaire or selecting preset settings, a means for analyzing the received user information and generating a customized AI agent using a generative AI model based on the user's preferences and needs, and a means for transmitting the generated AI agent to the user's terminal and installing and executing it, thereby enabling the user to easily use an AI agent that suits their preferences and needs.
[1232] "User" refers to any individual or legal entity that uses the system and customizes an AI agent to suit their preferences and needs through questionnaires and presets.
[1233] A "survey" refers to a form containing questions to gather user preferences and needs.
[1234] "Presets" refers to options that provide multiple pre-configured AI agent configurations and capabilities.
[1235] "Means for receiving" refers to the method or process by which the system receives information entered by the user.
[1236] "Means for analyzing" refers to the methods and algorithms used to process received user information and understand the user's preferences and needs.
[1237] "Generative AI models" refer to machine learning models and natural language processing models that generate customized AI agents based on user information.
[1238] A "customized AI agent" refers to an AI agent that is specially created to reflect the user's preferences and needs.
[1239] "Terminal" refers to the hardware or device through which a user accesses the system and installs and runs customized AI agents.
[1240] "Transmission means" refers to the method or process for transmitting data of the generated AI agent from the server to the terminal.
[1241] "Installation and execution means" refers to the method or process for installing a customized AI agent on a device and running it for use by the user.
[1242] "Various functions to support the user's daily life" refers to the functions and services provided by a customized AI agent to assist the user in their daily life.
[1243] This invention provides a system that allows users to easily use customized AI agents. This system generates AI agents that meet individual needs by allowing users to select and answer questionnaires or presets. The specific operations of each stakeholder (server, terminal, user) are explained in detail below.
[1244] User operations
[1245] First, users access a questionnaire form and preset selection screen provided on their smartphone, tablet, or PC. The questionnaire includes questions such as "favorite character" and "necessary functions," and the user answers these. The preset settings also allow users to choose from several pre-prepared agents.
[1246] As a specific example, user A opens a questionnaire form and selects "dragon" as his / her "favorite character" and "to-do list management" as his / her "necessary function."
[1247] Server Operation
[1248] The server receives the user information sent from the device and stores it in a database in JSON format.
[1249] Next, the server analyzes the stored user information and generates a customized AI agent using a generative AI model (e.g., GPT-4). Specifically, it generates an AI agent using the following prompt sentence:
[1250] User's favorite character: Dragon
[1251] Required feature: To-do list management
[1252] Generate customized AI agents based on this information.
[1253] The server then sends the generated customized AI agent data to the terminal, again in JSON format.
[1254] Device behavior
[1255] The device receives the customized AI agent data sent from the server, installs it, and performs initial setup. After installation, the agent runs and notifies the user.
[1256] As a concrete example, the device installs an agent with the "appearance of a dragon character" and "to-do list management function" for User A. After the installation is complete, the device notifies the user that "the agent has been installed."
[1257] Using an agent
[1258] Users can use the installed customized agents to perform various tasks. For example, user A, who is managing his to-do list, asks the agent, "What's on my schedule for today?" The agent responds, "I have three meetings today."
[1259] Hardware and software used
[1260] Devices: Smartphones, tablets, PCs
[1261] Server: Cloud server (e.g. AWS, Google Cloud, Azure)
[1262] Software: Web applications for implementing survey forms and preset selection screens, and machine learning models (e.g., GPT-4) for generating AI agents.
[1263] In this way, the system of the present invention provides users with convenient and easily customizable AI agents. Users can easily use agents with functions based on their individual needs. Furthermore, by using presets and a store, users can easily obtain agents that suit their preferences.
[1264] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1265] Step 1:
[1266] Enter user information
[1267] Users log in to the system using a terminal. After logging in, they can access a questionnaire form and a preset selection screen. Here, users input their favorite character and required functions. For example, User A selects "dragon" as his "favorite character" and "to-do list management" as his "required function."
[1268] Input: User survey data
[1269] Output: User data in JSON format
[1270] Step 2:
[1271] Sending information
[1272] The device sends the information entered by the user to the server, in JSON format.
[1273] Input: User data in JSON format
[1274] Output: User data sent to the server
[1275] Step 3:
[1276] Receiving and storing user information
[1277] The server receives the information sent from the terminal and stores it in a database.
[1278] Input: User data in JSON format
[1279] Output: User information stored in the database
[1280] Step 4:
[1281] Generating AI agents
[1282] The server analyzes the stored user information and generates a customized AI agent using a generative AI model (e.g., GPT-4). Specifically, it generates an AI agent using the following prompt:
[1283] User's favorite character: Dragon
[1284] Required feature: To-do list management
[1285] Generate customized AI agents based on this information.
[1286] Input: User information stored in the database
[1287] Output: Customized agent data in JSON format
[1288] Step 5:
[1289] Sending Agent Information
[1290] The server sends the generated customized agent data to the device, again in JSON format.
[1291] Input: Customized agent data in JSON format
[1292] Output: Agent data sent to the terminal
[1293] Step 6:
[1294] Installing and Running the Agent
[1295] The device receives the customized AI agent data sent from the server, installs it, and performs initial setup. After installation, the agent runs and notifies the user.
[1296] Input: Customized agent data in JSON format
[1297] Output: An installed and running AI agent.
[1298] Step 7:
[1299] Using an agent
[1300] Users can use the installed customized agents to perform various tasks. For example, user A asks the agent, "What's on my schedule for today?" to manage his to-do list. The agent responds, "I have three meetings today."
[1301] Input: User operation instructions
[1302] Output: Response from the agent
[1303] (Application example 1)
[1304] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1305] Conventional food delivery services have the drawback of requiring users to select different restaurants and menus each time, and not providing optimal suggestions that fit individual preferences or schedules. Furthermore, in order to accommodate specific requirements (such as allergy information or specific types of cuisine), users must perform detailed searches and confirmations each time, which is cumbersome.
[1306] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.
[1307] In this invention, the server includes means for receiving information from a user by answering a simple questionnaire or selecting preset settings, means for analyzing the received user information and generating an AI agent based on the user's preferences and needs, means for transmitting the generated AI agent to the user's terminal and installing and executing it, and means for providing the user with recommended information optimized for a specific category (e.g., food delivery) based on the analyzed information, thereby enabling the provision of an optimal food delivery service based on the user's individual preferences and schedule.
[1308] The "questionnaire" is a question-type input means for the user to input individual preferences and required functions.
[1309] "Preset" refers to pre-defined options and settings that users can choose from.
[1310] "User Information" is data about individual preferences and needs provided by a user through surveys or preset selections.
[1311] An "AI agent" is a virtual assistant that provides assistance and services to users through a customized program based on their preferences and needs.
[1312] "Food delivery" is a service that delivers dishes or food selected by the user to a specified location.
[1313] A "generative AI model" refers to an algorithm or program that generates a customized AI agent based on user information.
[1314] A "prompt" is a form of recommendation or instruction that an AI agent provides to a user.
[1315] This invention relates to a system that allows users to easily use customized AI agents. The core of this system is the exchange and analysis of data between the user, terminal, and server.
[1316] System Program
[1317] User operations
[1318] The user first accesses a questionnaire form or preset selection screen provided on the device. The questionnaire includes the user's preferences and desired functions (for example, "favorite type of food," "delivery frequency," etc.), and the user answers them. The preset settings allow the user to choose from pre-prepared options. This information is sent from the device to the server.
[1319] Server Operation
[1320] The server receives the information sent by the user and stores it in a database. The stored data is then analyzed using a generative AI model. This analysis generates a customized AI agent based on the user's preferences and needs. The generated AI agent includes, for example, recommendation information and notification functions suitable for a specific category (food delivery). Finally, the server sends the generated AI agent's data to the device.
[1321] Device behavior
[1322] The device then installs the customized AI agent data received from the server, making it immediately available to the user. After installation, the agent provides support for the user in their daily lives, such as recommending specific restaurants based on the user's preferences and providing ordering prompts.
[1323] Hardware and software used
[1324] Hardware:
[1325] Smartphone
[1326] Server machine
[1327] software:
[1328] Flask (Python framework)
[1329] Generative AI model (an algorithm that analyzes user information and generates a customized AI agent)
[1330] Database management system (storing user information)
[1331] This allows users to use a food delivery agent optimized for their individual needs by filling out a simple questionnaire or selecting presets.
[1332] Specific examples
[1333] For example, if a user enters "favorite cuisine (e.g., Chinese food)" and "delivery frequency (twice a week)" on the survey screen, the server analyzes this data and generates a customized agent that provides recommended restaurants and delivery times that suit the user's needs. This agent then displays a prompt to the user such as, "We have three Chinese restaurants A, B, and C that suit your tastes. When would you like your next delivery?"
[1334] Example prompt sentence:
[1335] "Based on your food preferences, we'd like to recommend Chinese restaurant A, restaurant B, and restaurant C. When would you like your next delivery?"
[1336] In this way, the system of the present invention provides the optimal food delivery service that matches the user's preferences.
[1337] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1338] Step 1:
[1339] The user accesses a questionnaire form or preset selection screen provided on the terminal, where they answer questions such as "Favorite type of food" and "Delivery frequency." The entered information is collected by the terminal as user information and sent to the server.
[1340] Step 2:
[1341] The server receives the user information sent from the device and temporarily stores it in a database. At this point, the input format is data such as JSON or XML. The stored information is used for analysis.
[1342] Step 3:
[1343] The server uses a generative AI model to analyze the stored user information. Specifically, it extracts data patterns based on the user's preferences and needs and generates a customized AI agent. This generation process involves processing and calculating the data (e.g., statistical analysis and clustering) to create agent data containing optimal recommendations.
[1344] Step 4:
[1345] The server sends the generated customized AI agent data to the device in a format such as JSON or binary. The device converts this data into an installable format and installs it as a working application.
[1346] Step 5:
[1347] The device will then begin running the installed AI agent, which the user can then control to receive assistance with daily activities, such as food recommendations and ordering prompts based on the user's preferences.
[1348] Step 6:
[1349] The user operates based on prompts provided by the AI agent. For example, they may receive instructions such as, "There are three Chinese restaurants A, B, and C that suit your tastes. When would you like your next delivery?" The user then selects the delivery time and confirms the order.
[1350] In this way, a customized food delivery service is provided based on the user's preferences and needs.
[1351] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.
[1352] This invention improves the quality of responses and support to users by combining an emotion engine with a system that allows users to easily use customized AI agents. The specific operations of each stakeholder (user, terminal, server) are explained below.
[1353] User operations
[1354] Enter information
[1355] First, the user accesses a questionnaire form and preset selection screen provided on the device. The questionnaire includes questions such as "favorite character" and "necessary functions," and the user answers these. The preset settings also allow the user to select from several pre-prepared agents.
[1356] Agent Selection and Purchasing
[1357] The user can check a list of multiple preset agents provided in the store, select an agent that suits his / her taste, and purchase it.
[1358] Device behavior
[1359] Providing an input interface
[1360] The device displays a questionnaire form or a preset selection screen where the user can enter information. After the user has completed the input, the information is sent to the server.
[1361] Use of emotion engine
[1362] The terminal provides the user's voice, facial expression, and text data to the emotion engine, which analyzes this data to detect the user's emotional state.
[1363] Installing and Running the Agent
[1364] The device installs the customized AI agent data received from the server and performs initial setup so that the user can use it immediately. After installation, the agent is executed and notifies the user.
[1365] Server Operation
[1366] Receiving and storing user information
[1367] The server receives the user information sent from the device and stores it in a database, including the user ID, answers, and selected presets.
[1368] Generating AI agents
[1369] The server analyzes the stored user information and customizes the AI agent based on that data, generating an agent based on the user's preferences, desired functionality, and emotional state.
[1370] Sending Agents
[1371] The server sends the data of the generated customized AI agent to the terminal.
[1372] Specific examples
[1373] For example, suppose User D wants a new customized AI agent. User D launches the app on their device and accesses the survey form. They select "cat" as their favorite character and "weather forecast" and "reminder settings" as their desired functions.
[1374] Next, when User D sends information, the device sends the data to the server. The server receives this information and stores it in a database. The server analyzes the stored information and generates an AI agent based on User D's preferences. The generated agent includes the cat character's appearance and the ability to set weather forecasts and reminders.
[1375] The device also uses an emotion engine to analyze the user's voice and facial expressions to detect their emotional state. For example, if the emotion engine recognizes "sadness" in User D's voice, the agent will respond in a gentle manner.
[1376] The server then sends the agent data to the device, which receives and installs it. Once installation is complete, the device executes the agent and notifies User D. User D can then use this agent to receive support for daily activities such as checking the weather forecast and setting reminders.
[1377] Furthermore, the agent dynamically adjusts its dialogue and behavior according to the emotional state of user D, providing continuous support. For example, if user D says, "I'm feeling down today," the agent will suggest, "Shall we do something fun to change your mood?"
[1378] In this way, the system of the present invention not only provides users with a convenient and easily customizable AI agent, but also uses an emotion engine to achieve high-quality dialogue that responds to the user's emotions.
[1379] The processing flow will be explained below.
[1380] Step 1:
[1381] Device: When the user launches the app, a survey form or preset selection screen is displayed.
[1382] Step 2:
[1383] User: Access the survey form and answer questions such as "Favorite character" and "Desired functions." Alternatively, select your preferred agent from a list of preset agents.
[1384] Step 3:
[1385] Terminal: After the user has completed their input or selection, they press the send button, which sends the information to the server.
[1386] Step 4:
[1387] Server: Receives user information sent from the device and stores it in a database. The stored information includes the user ID, answers, selected presets, etc.
[1388] Step 5:
[1389] Server: Analyzes saved user information and generates a customized AI agent based on the user's preferences and needs. For example, if a user selects a favorite character, "cat," an agent with the character's appearance and voice will be generated.
[1390] Step 6:
[1391] Server: Prepares the data of the generated AI agent and prepares it for transmission to the terminal.
[1392] Step 7:
[1393] Server: Sends customized AI agent data to the device, including appearance, function settings, and required initial setup information.
[1394] Step 8:
[1395] Terminal: Installs the received agent data. The installation process includes extracting the data and registering it in the system.
[1396] Step 9:
[1397] Terminal: Performing initial agent configuration, for example, applying a setting to enable the weather forecast function on the user's terminal.
[1398] Step 10:
[1399] Terminal: Starts the AI agent and notifies the user when it is ready.
[1400] Step 11:
[1401] User: Starts interacting with the AI agent that is activated on the device. For example, they can ask the agent, "What's the weather like today?" and the agent will provide a weather forecast.
[1402] Step 12:
[1403] Terminal: When a user is using an active agent, emotional data of the user is collected using voice input and camera functions.
[1404] Step 13:
[1405] Device: The emotion engine analyzes the collected emotional data and identifies the user's emotional state. For example, it can detect "happiness" or "sadness" from the user's tone of voice and facial expressions.
[1406] Step 14:
[1407] Terminal: Dynamically adjusts the AI agent's responses and behavior based on emotional data analyzed by the emotion engine. For example, if the user expresses "sadness," the agent will ask, "Is there anything you're worried about?"
[1408] Step 15:
[1409] Agent (running on the device): Provides ongoing support for the user's everyday requests. For example, if the user says, "Set a reminder," the agent responds, "Reminder set."
[1410] Step 16:
[1411] Device: Records emotional data analyzed by the emotion engine and learns the user's emotional tendencies over time.
[1412] Step 17:
[1413] Server: The server periodically collects and analyzes the user's emotional data and customizes the service to reflect the user's emotional tendencies. For example, if the user frequently feels "stressed," the agent will proactively make suggestions to help them relax.
[1414] In this way, the system of the present invention not only provides users with a convenient and easily customizable AI agent, but also uses an emotion engine to achieve high-quality dialogue that responds to the user's emotions.
[1415] Example 2
[1416] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1417] Conventional AI agent systems have difficulty fully meeting the individual needs and preferences of users, and few systems can flexibly respond to the user's emotional state. As a result, interactions with users tend to be unnatural, often resulting in low user satisfaction. Furthermore, customization using unique characters and the provision of multifunctional agents are insufficient, leaving them lacking in support for everyday life.
[1418] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a means for receiving information when a user accesses a simple input form and answers a questionnaire or selects a preset setting, a means for the terminal to collect the information and send it to the server, a means for analyzing the received user information and using a generative AI model to generate an AI agent based on the user's preferences and required functions, and a means for sending the generated AI agent data to the terminal and installing and executing it. This makes it possible to generate and install an AI agent that is highly personalized for the user, thereby realizing advanced dialogue that responds to the user's needs and emotional state.
[1419] The "information input form" is an interface that allows the user to answer questionnaires and select preset settings.
[1420] A "server" is a device or system that receives, stores, and analyzes information sent by a user, generates an AI agent, and sends it to a terminal.
[1421] A "terminal" is a device for users to input information and is a device for installing and executing generated AI agents.
[1422] An "emotion engine" is software or a device that analyzes a user's voice, facial expression, and text data to detect their emotional state.
[1423] A "generative AI model" is an algorithm or machine learning model for generating customized AI agents based on user information.
[1424] "Agent data" refers to the configuration information and program data of the generated AI agent.
[1425] The "questionnaire" is a questionnaire containing questions about the user's preferences and required functions.
[1426] "Presets" are the settings and function patterns of multiple AI agents that have been set up in advance.
[1427] "Installation" refers to the process of incorporating the AI agent's programs and settings into the device.
[1428] "Execution" means running the installed AI agent and interacting with and supporting the user.
[1429] "User information" refers to questionnaires and preset setting data entered by the user, as well as data on emotional states analyzed by the emotion engine.
[1430] This invention is a system that allows users to easily use customized AI agents. This system is composed of a terminal, a server, and an emotion engine. The specific operations of each stakeholder (user, terminal, server) are explained below.
[1431] User operations
[1432] Enter information
[1433] First, the user accesses the input form or preset selection screen provided on the device using a web browser or dedicated application. For example, the user answers questions such as "favorite character" or "necessary functions" in a questionnaire.
[1434] Agent Selection and Purchasing
[1435] The user can select and purchase an agent that suits their preferences from the displayed list of preset agents, allowing the user to easily select a customized agent.
[1436] Device behavior
[1437] Providing an input interface
[1438] The device displays an input form or preset selection screen to the user, and after the user completes the input, it uses HTML and JavaScript to send the data to the server.
[1439] Use of emotion engine
[1440] The device collects the user's voice and facial expression data and sends it to an emotion engine such as Affectiva or IBM Watson Tone Analyzer. The emotion engine analyzes this data to detect the user's emotional state. For example, if a user says, "I'm tired today," this information is analyzed by the emotion engine.
[1441] Installing and Running the Agent
[1442] The device installs the customized AI agent data received from the server, runs a Python script to install the agent, and notifies the user when it is complete, allowing the agent to be used immediately.
[1443] Server Operation
[1444] Receiving and storing user information
[1445] The server receives the user information sent from the device. For example, it receives the data using a REST API and stores it in a database (MySQL or PostgreSQL). The stored information includes the user ID, answers, selected presets, etc.
[1446] Generating AI agents
[1447] The server analyzes the stored user information and generates an AI agent using a generative AI model such as OpenAI's GPT-4. The server customizes the agent based on the user's preferences, required features, and emotional state. This generation process uses prompts such as:
[1448] Prompt Sentence Examples
[1449] 1. "The user's favorite character is a cat, and they need weather forecasts and reminder settings. Create a customized AI agent configuration based on this."
[1450] 2. "Sadness was detected from the user's voice analysis. Please add a kind response for the user."
[1451] Sending Agents
[1452] The server sends the generated AI agent data to the device, which then receives it using the REST API.
[1453] Specific examples
[1454] For example, consider the case where User D wants a new customized AI agent. User D starts the app on his / her device, accesses the questionnaire form, and selects "cat as favorite character" and "weather forecast and reminder setting as required functions." The device collects this information and sends it to the server. The server receives the information and stores it in a database. The server then analyzes the received information and generates an AI agent with the appearance of a cat character and the functions of weather forecast and reminder setting. The generated agent data is sent to the device, which receives it and installs it. After installation is complete, the device notifies User D, who can then begin using the agent.
[1455] Furthermore, if User D says, "I'm feeling depressed today," the emotion engine analyzes this and sends the data to the server. The server then changes the agent's response settings based on the additional prompts, providing a friendly response to User D. In this way, the system can provide a personalized agent for the user and achieve high-quality dialogue that responds to the user's emotional state.
[1456] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1457] Step 1: User launches application
[1458] The user launches a dedicated application or web browser on the device and accesses an input form or preset selection screen. A form is displayed asking for input such as the character of their choice and the functions they require. The user answers these questions and the information is sent to the device.
[1459] Step 2: Collect and submit input data
[1460] The device collects the survey data and preset setting data entered by the user and sends it to the server. Specifically, the data entered in the HTML form is sent to the server via the REST API using JavaScript with the POST method. The survey data and preset settings are input, and a notification of completion of transmission to the server is sent as output.
[1461] Step 3: Receiving and storing user information
[1462] The server receives user information sent from the device and stores it in a database. Specifically, it processes the received data using Python scripts and a database engine (MySQL or PostgreSQL). The inputs are survey data and preset settings, and the output is the data saved in the database.
[1463] Step 4: Collect and send emotion data
[1464] The device collects the user's voice and facial expression data and sends it to the emotion engine. For example, if the user says, "I'm tired today," the device records that voice and sends it to the emotion engine (Affectiva or IBM Watson Tone Analyzer). The input is the user's voice data and facial expression data, and the output is the result sent to the emotion engine.
[1465] Step 5: Emotional state analysis and notification
[1466] The emotion engine analyzes the voice data and facial expression data received from the user to detect the user's emotional state. Specifically, the emotion engine's algorithm analyzes the data and identifies the user's emotional state (e.g., sadness or joy). The voice data and facial expression data are sent as input, and the detected emotional state is sent as output to the server.
[1467] Step 6: Generate an AI agent
[1468] The server analyzes the stored user information and emotional state data obtained from the emotion engine to generate an AI agent specialized for the user. OpenAI's GPT-4 is used as the generative AI model. The server customizes the agent based on the user's preferences, required functions, and emotional state. For example, it generates an agent with a "cat character appearance" and "weather forecast and reminder setting functions." User information and emotional state data are obtained as input, and agent configuration information and program data are obtained as output.
[1469] Step 7: Submit and install the agent
[1470] The server sends the generated customized AI agent data to the device. The data is then sent again via a REST API, and the device receives and installs it. For example, a Python script can install the agent and notify the user when it's complete. The agent data is received from the server as input, and a notification of installation completion is sent to the device as output.
[1471] Step 8: Run the agent and notify the user
[1472] The device runs the installed AI agent and notifies the user. For example, the AI agent starts on the device and notifies the user, "The agent installation is complete and it's ready to use." The input is the installed AI agent, and the output is the agent launch and a notification to the user.
[1473] Step 9: Agent support for daily life
[1474] Users use the agent to receive support in their daily lives, such as checking the weather forecast or setting reminders. The agent adjusts its dialogue and behavior appropriately according to the user's emotional state. For example, if the user says, "I'm feeling down today," the agent might suggest, "Shall we do something fun to cheer you up?" The inputs are the user's statements and emotional state data, and the output is the agent's response and the provision of support functions.
[1475] (Application example 2)
[1476] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1477] Conventional content distribution services lacked a function to recommend content that was tailored to the user's emotional state, making it difficult to provide users with the optimal entertainment experience. In particular, content recommendations were often inappropriate for users because they could not respond to the user's mood or emotions. As a result, users often spent a lot of time and effort finding the optimal content, which often led to a decrease in satisfaction with the service.
[1478] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving information when the user answers a simple questionnaire or selects a preset setting, means for analyzing the received user information and generating an AI agent based on the user's preferences and needs, means for transmitting the generated AI agent to the user's terminal and installing and executing it, and means for analyzing the user's emotional state in real time and recommending videos and music according to that emotional state. This makes it possible to automatically recommend optimal content that matches the user's emotional state.
[1479] A "questionnaire" is a question-type input means for a user to input their preferences and needs.
[1480] "Preset" refers to a set of agents and functions that have been set up in advance, and allows the user to easily customize the system by selecting one of them.
[1481] "User Information" refers to data about a user's preferences and needs collected through questionnaires and preset selections.
[1482] "Analysis" is an information processing process that identifies the user's preferences and needs from the received user information and generates an appropriate AI agent.
[1483] An "AI agent" is software equipped with artificial intelligence that responds to user instructions and requests and provides various functions.
[1484] "Terminal" refers to a device used by a user, such as a computer or smartphone.
[1485] "Emotional state" is information indicating the psychological state of the user obtained from facial expressions, voice, and text data.
[1486] "Real-time" refers to the time-based responsiveness of responding and responding immediately to user actions and inputs.
[1487] "Recommendation" is the act of suggesting optimal content based on a user's preferences and emotional state.
[1488] "Moving image" is viewable information content that includes a sequence of images and sound.
[1489] "Music" is information content that can be enjoyed auditorily, consisting of melody, harmony, and rhythm.
[1490] A "system" is a set of devices and software that combine multiple means to achieve a specific function.
[1491] The present invention relates to a system for allowing a user to receive optimal content according to his / her emotional state. Detailed embodiments are described below.
[1492] Overall system configuration
[1493] The present invention mainly comprises the following three elements:
[1494] 1. Server: Stores and analyzes user information, generates and transmits customized AI agents.
[1495] 2. Terminal: Provides an interface for users to input information and analyzes the user's emotional state using an emotion engine.
[1496] 3. User: Customize your agent by answering surveys and selecting presets.
[1497] Program operation explanation
[1498] Hardware and software used
[1499] Hardware: Smartphones, servers
[1500] Software: Python, requests library, transformers library, Hypothesis sentiment analysis and recommendation engine module (SentimentAnalyzer, ContentRecommender)
[1501] Data flow
[1502] 1. User Action:
[1503] Users access a questionnaire form using their smartphones and enter their preferences and desired features, and the information is sent to the server.
[1504] 2. Server operation:
[1505] The server receives and analyzes user information. Based on the analysis results, it generates a customized AI agent that matches the user's preferences and needs. The generated agent is then sent to the user's device.
[1506] 3. Device operation:
[1507] The device then installs and runs the received AI agent, analyzes the user's emotional state in real time, and recommends appropriate content (videos and music) based on that emotion.
[1508] As part of the specific processing steps, the device passes the user's voice input and text to the "SentimentAnalyzer" to analyze their emotions. Based on the results, the "ContentRecommender" selects the most appropriate content and presents it to the user.
[1509] Specific examples
[1510] For example, User A accesses a questionnaire form, selects "cat" as his / her favorite character, and selects "video recommendation" and "music recommendation" as required functions. This information is sent to the server, which generates a customized AI agent based on User A's preferences and sends it to the device. The device installs it, and if User A enters "I'm feeling depressed today," the emotion analysis engine recognizes "sadness," and the recommendation engine suggests uplifting content based on that.
[1511] Prompt Sentence Examples
[1512] User: I'm feeling down today.
[1513] System: The emotion analysis engine has detected "sadness." We will recommend music and videos that will uplift your mood.
[1514] In this way, the present invention can realize high-quality content recommendations that correspond to the user's emotional state.
[1515] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1516] Step 1:
[1517] The user accesses the questionnaire form and enters their preferences and required functions. At this time, the user uses their smartphone to select, for example, "cat" as their "favorite character" and selects "video recommendations" and "music recommendations" as "required functions." The input data is sent to the server in JSON format.
[1518] Input: Survey content selected by the user (preferences, required features)
[1519] Output: User information sent to the server (JSON format data)
[1520] Step 2:
[1521] The server receives the user information and stores it in a database. This process records the user's ID, preferences, and required functions in the database. The server then analyzes the received user information and generates an AI agent based on the user's preferences and needs.
[1522] Input: User information sent from the device (JSON format data)
[1523] Output: User information stored in a database, customized AI agent
[1524] Step 3:
[1525] The server sends the generated AI agent data to the user's device. The device receives this data and installs the AI agent. Once the installation is complete, the AI agent is set up to be immediately available for use.
[1526] Input: AI agent data generated by the server
[1527] Output: AI agent installed on the device
[1528] Step 4:
[1529] The device receives the user's voice input and text data and sends it to a sentiment analysis engine (SentimentAnalyzer). The sentiment analysis engine analyzes the input data and identifies the user's emotional state. The analysis results are output as an emotional state, such as "sadness," "joy," or "anger."
[1530] Input: User voice input or text data
[1531] Output: Parsed user's emotional state (e.g. "sadness")
[1532] Step 5:
[1533] The device receives the emotion analysis results and passes them to a recommendation engine (ContentRecommender). The recommendation engine generates a list of recommended videos and music based on the user's emotional state. For example, if the user's emotion is analyzed as "sadness," it will recommend uplifting music and fun videos. These recommendation results are then presented to the user on the device.
[1534] Input: Emotional state from the emotion analysis engine (e.g. "sadness")
[1535] Output: A list of content recommendations based on emotional state
[1536] Step 6:
[1537] The user checks the recommendation list on the device and selects the content they want to watch. The device then starts playing the selected content, providing the user with a viewing experience.
[1538] Input: Content selected from the recommended list
[1539] Output: The content that started playing (video or music)
[1540] In this way, through each step, the user can receive the most suitable content depending on their emotional state, thereby improving the user's entertainment experience.
[1541] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.
[1542] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[1543] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.
[1544] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.
[1545] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.
[1546] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.
[1547] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).
[1548] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.
[1549] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."
[1550] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.
[1551] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).
[1552] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.
[1553] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.
[1554] 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.
[1555] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.
[1556] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.
[1557] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.
[1558] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.
[1559] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.
[1560] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.
[1561] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.
[1562] The following is further disclosed regarding the above embodiment.
[1563] (Claim 1)
[1564] a means for the user to receive that information by answering a short survey or selecting preset settings;
[1565] A means for analyzing the received user information and generating an AI agent based on the user's preferences and needs;
[1566] A means for transmitting the generated AI agent to a user's terminal, and installing and executing the agent;
[1567] A system including:
[1568] (Claim 2)
[1569] 10. The system of claim 1, further comprising means for displaying a list of a plurality of preset AI agents to a user, allowing the user to select and purchase a preferred AI agent.
[1570] (Claim 3)
[1571] 10. The system of claim 1, further comprising means for providing various functions for the customized AI agent to support the user's daily life.
[1572] "Example 1"
[1573] (Claim 1)
[1574] a means for the user to receive that information by answering a short survey or selecting preset settings;
[1575] means for analyzing the received user information and generating a customized AI agent using a generative AI model based on the user's preferences and needs;
[1576] A means for transmitting the generated AI agent to a user's terminal, and installing and executing the agent;
[1577] A system including:
[1578] (Claim 2)
[1579] 10. The system of claim 1, further comprising means for displaying a list of a plurality of preset AI agents to a user, allowing the user to select and purchase a preferred AI agent.
[1580] (Claim 3)
[1581] 10. The system of claim 1, further comprising means for providing various functions for the customized AI agent to support the user's daily life.
[1582] "Application Example 1"
[1583] (Claim 1)
[1584] a means for the user to receive that information by answering a short survey or selecting preset settings;
[1585] A means for analyzing the received user information and generating an AI agent based on the user's preferences and needs;
[1586] A means for transmitting the generated AI agent to a user's terminal, and installing and executing the agent;
[1587] A means for providing users with recommended information optimized for a specific category (e.g., food delivery) based on the analyzed information;
[1588] A system including:
[1589] (Claim 2)
[1590] 10. The system of claim 1, further comprising means for displaying a list of a plurality of preset AI agents to a user, allowing the user to select and purchase a preferred AI agent.
[1591] (Claim 3)
[1592] 10. The system of claim 1, further comprising means for providing various functions for the customized AI agent to support the user's daily life.
[1593] (Claim 4)
[1594] 10. The system of claim 1, further comprising means for providing a questionnaire for a user to select a category of preferences (e.g., type of cuisine or frequency of delivery) and generate optimized information.
[1595] (Claim 5)
[1596] 10. The system of claim 1, further comprising means for the generated AI agent to provide appropriate recommended information in the form of prompt sentences based on the user's preferences.
[1597] "Example 2: Combining Emotion Engines"
[1598] (Claim 1)
[1599] a means for users to receive that information by accessing a simple form, answering a survey, or selecting a preset setting;
[1600] means for the terminal to collect and transmit the information to a server;
[1601] A means for using a generative AI model to analyze the received user information and generate an AI agent based on the user's preferences and required functions;
[1602] A means for transmitting the generated AI agent data to a terminal, and installing and executing the data;
[1603] A system including:
[1604] (Claim 2)
[1605] 10. The system of claim 1, further comprising means for collecting and analyzing the user's voice, facial expression, and text data using an emotion engine to detect the user's emotional state, and dynamically adjusting the agent's dialogue content based on the results.
[1606] (Claim 3)
[1607] The system of claim 1 further comprising means for providing a customized AI agent with various functions to support the user's daily life, including specific character appearances, weather forecasts, and reminder settings.
[1608] "Application example 2 when combining emotion engines"
[1609] (Claim 1)
[1610] a means for the user to receive that information by answering a short survey or selecting preset settings;
[1611] A means for analyzing the received user information and generating an AI agent based on the user's preferences and needs;
[1612] A means for transmitting the generated AI agent to a user's terminal, and installing and executing the agent;
[1613] A means for analyzing a user's emotional state in real time and recommending videos and music according to the emotional state;
[1614] A system including:
[1615] (Claim 2)
[1616] 10. The system of claim 1, further comprising means for displaying a list of a plurality of preset AI agents to a user, allowing the user to select and purchase a preferred AI agent.
[1617] (Claim 3)
[1618] 10. The system of claim 1, further comprising means for providing various functions for the customized AI agent to support the user's daily life. [Explanation of symbols]
[1619] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>
Claims
1. a means for the user to receive that information by answering a short survey or selecting preset settings; A means for analyzing the received user information and generating an AI agent based on the user's preferences and needs; A means for transmitting the generated AI agent to a user's terminal, and installing and executing the agent; A system including:
2. 2. The system according to claim 1, further comprising means for displaying a list of a plurality of preset AI agents to a user, allowing the user to select and purchase a preferred AI agent.
3. 10. The system of claim 1, further comprising means for providing various functions for the customized AI agent to support the user's daily life.
Citation Information
Patent Citations
Persona chatbot control method and system
JP2022180282A