System
A system using generative AI to create virtual characters addresses social isolation in elderly and unmarried individuals by managing health and promoting social connections, enhancing their quality of life.
Patent Information
- Application Number
- JP2024120463
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2026-02-05
AI Technical Summary
The increasing number of elderly and unmarried individuals living alone has led to a rise in social loneliness and inadequate mental health care services, necessitating systems that can manage physical and mental health and foster social connections.
A system utilizing generative artificial intelligence to create virtual characters resembling close friends or family members, which manages health status through input and analysis, provides advice, and supports social connections by recommending local events and facilitating participation.
The system effectively manages physical and mental health, alleviates loneliness, and enhances social connections for elderly and unmarried individuals, improving their quality of life.
Smart Images

Figure 2026019054000001_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] ---
[0005] In recent years, the number of elderly people and unmarried people living alone has increased, and social loneliness has become a problem. While online shopping and meal delivery services are available, mental health care services are still insufficient. Therefore, there is a need for systems that can alleviate loneliness, manage physical and mental health, and foster social connections. [Means for solving the problem]
[0006] In this invention, basic information about the user is collected using a means for providing an information input form and a means for transmitting and storing user information. Then, a sense of psychological security is provided to the user through a means for generating virtual characters that resemble close friends or family members using a generative artificial intelligence. Furthermore, the system continuously manages the user's physical and mental health status and provides appropriate advice using a means for inputting and transmitting health status and a means for analyzing health data and generating advice. Furthermore, the system supports the user in building social connections through a means for collecting local event information and recommending events to the user and a means for supporting event participation. This can improve the user's quality of life and alleviate the problem of social loneliness.
[0007] ---
[0008] The "information input form" is an interface that allows the user to input necessary information such as basic information and health status.
[0009] "User Information" is information that personally identifies a user, such as the user's name, age, health status, preferences, etc.
[0010] "Generative AI" is AI that uses machine learning and deep learning technologies to dynamically generate specific people or characters.
[0011] A "virtual character" is a fictitious character that resembles a close friend or family member and is displayed on the user interface.
[0012] A "user interface" is a visual interface through which a user interacts with a system.
[0013] "Health status" refers to information that indicates an individual's physical and mental state, such as body temperature, blood pressure, heart rate, and mood.
[0014] "Health data" refers to data including the health status entered by the user and the analysis results thereof.
[0015] "Advice" is instructions or suggestions provided to the user based on the analysis of health data.
[0016] "Local event information" is information about events held in the local area or community that the user can participate in.
[0017] "Support for event participation" means providing support for users to apply for and participate in local events.
[0018] --- [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] ---
[0041] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. In this system, users enter their own information into an information input form, and the system supports daily health management and participation in local events through a virtual character generated based on that information.
[0042] 1. User registration and initial settings
[0043] The process begins when the user installs and launches the "Soba de Mimamoru" app. After launching the app, the device displays a form for entering user information. The user enters the necessary information, such as name, age, health condition, and hobbies, and clicks the submit button. The device then sends the entered information to the server, completing user registration. Based on the user information, the server uses generative artificial intelligence to generate a virtual character modeled after a close friend or family member, and sends the virtual character to the device for display.
[0044] 2. Daily health management
[0045] The device displays a health check form every day. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and clicks the submit button. The device then sends the entered health information to the server. The server uses AI to analyze the health data and generates advice based on it. The advice generated is sent to the device and communicated to the user through the virtual character's UI. For example, the advice might be, "Your blood pressure is a little high, so try to limit your salt intake."
[0046] 3. Supporting social connections
[0047] The server collects information about local and social events, such as nearby walking clubs and hobby gatherings. The server sends this information to the device to recommend appropriate events based on the user's hobbies and interests. The device displays the event information, and the user selects the event they wish to attend and clicks the application button. The device then sends the application information for the event to the server, which contacts the organizer to confirm the user's participation. This allows the user to participate in local events and build social connections.
[0048] Specific examples
[0049] Mr. Tanaka, 75, had been living alone for a long time and was concerned about his physical and mental health. He installed the "Soba de Mimamoru" app and entered his name, health condition (e.g., back pain), and hobby (e.g., gardening). Based on Mr. Tanaka's information, the server generated a virtual character modeled after his late wife and displayed it on his device. Every morning, Mr. Tanaka entered his body temperature and blood pressure into the app, and received advice based on that information from the virtual character. The app also displayed information about local gardening classes, allowing Mr. Tanaka to make new friends by participating in these events.
[0050] In this way, this invention not only enables elderly people living alone and unmarried people to manage their physical and mental health, but also enables them to have social connections, thereby improving their quality of life (QOL).
[0051] The processing flow will be explained below.
[0052] ---
[0053] User registration and initial settings
[0054] Step 1:
[0055] The user installs and launches the "Sobade Mimamoru" app.
[0056] Step 2:
[0057] The device displays a user information input form (name, age, health status, preferences, etc.) on the screen.
[0058] Step 3:
[0059] The user enters the required information and clicks the submit button.
[0060] Step 4:
[0061] The terminal transmits the input information to the server.
[0062] Step 5:
[0063] Based on the user's information, the server uses artificial intelligence to generate a virtual character modeled after a close friend or family member.
[0064] Step 6:
[0065] The server transmits the generated virtual character to the terminal.
[0066] Step 7:
[0067] The terminal displays the transmitted virtual character on the screen, allowing the user to start a conversation with the virtual character.
[0068] Daily health management
[0069] Step 1:
[0070] The device displays a daily health check form on the screen (e.g., temperature, blood pressure, heart rate, mood, etc.).
[0071] Step 2:
[0072] The user inputs their daily health status and clicks the submit button.
[0073] Step 3:
[0074] The terminal transmits the input health information to the server.
[0075] Step 4:
[0076] The server uses AI to analyze health data and generate advice.
[0077] Step 5:
[0078] The server transmits the generated advice to the terminal.
[0079] Step 6:
[0080] The device will then give advice to the user through a virtual character UI, for example, displaying a message such as "Your blood pressure is a little high, so try to limit your salt intake."
[0081] Supporting social connections
[0082] Step 1:
[0083] The server collects information about local and social events (for example, walking events and hobby gatherings held in the neighborhood).
[0084] Step 2:
[0085] The server selects events that the user can participate in based on the user's hobbies and interests.
[0086] Step 3:
[0087] The server transmits the selected event information to the terminal.
[0088] Step 4:
[0089] The event information received by the terminal is displayed on the screen.
[0090] Step 5:
[0091] The user checks the event information and selects the event they want to attend.
[0092] Step 6:
[0093] The user clicks the sign up button.
[0094] Step 7:
[0095] The terminal transmits the application information to the server.
[0096] Step 8:
[0097] The server contacts the event organizer to confirm the user's participation.
[0098] Step 9:
[0099] The server sends participation confirmation information to the terminal.
[0100] Step 10:
[0101] The terminal notifies the user of the participation confirmation information.
[0102] ---
[0103] This concludes the processing flow of the "Soba de Mimamoru" system. At each step, the system effectively manages the user's information, supports their physical and mental health, and provides social connections.
[0104] Example 1
[0105] 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."
[0106] In modern society, elderly people living alone and unmarried people face challenges in managing their physical and mental health and maintaining social connections. This problem, particularly for the elderly, increases feelings of loneliness and health risks, leading to a decline in quality of life (QOL). Furthermore, low participation in local events and social activities also contributes to social isolation. Therefore, there is a need for a system that allows these people to easily manage their health information, receive appropriate advice, and form social connections.
[0107] 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.
[0108] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using generative intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status, means for analyzing health data and generating advice, means for collecting local event information and recommending it to users, means for supporting event participation, means for providing daily health data analysis results using AI technology, and means for conveying advice to users through the generated virtual character, thereby enabling users to manage their physical and mental health and build social connections.
[0109] An "information input form" is an online form where a user enters personal information such as name, age, health status, hobbies, etc.
[0110] "User information" refers to personal data such as name, age, health status, and hobbies entered by the user in the information input form.
[0111] "Generative intelligence" refers to artificial intelligence technology that uses a generative AI model (e.g., GPT-4) to automatically generate virtual characters based on user input data.
[0112] A "virtual character" is a 3D or 2D digital character created to resemble a close friend or family member based on the user's personal information and past experiences.
[0113] "User interface" refers to the application screen or digital interface through which a user interacts with a virtual character.
[0114] "Health Status" refers to the user's daily health data, such as temperature, blood pressure, heart rate, and mood.
[0115] "Health data" refers to information entered by the user, such as body temperature, blood pressure, heart rate, and mood.
[0116] "Advice" refers to specific health management instructions or suggestions provided to the user based on the results of analyzing the health data.
[0117] "Local event information" refers to event information such as local walking clubs and hobby gatherings that is automatically collected by the server.
[0118] "Means for using generative intelligence" means the ability to automatically generate virtual characters using a generative AI model.
[0119] "Means to support event participation" refers to a function that supports users in applying to participate in local events.
[0120] The present invention is a system that provides an "AI life supporter" that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. The details are explained below.
[0121] Configuration and Hardware / Software
[0122] The system operates using a user device (such as a smartphone), a server, and a generative AI model.
[0123] Device: User device such as a smartphone or tablet. Install and use the Android or iOS app "Soba de Mimamoru."
[0124] Server: A high-performance cloud server that runs generative AI models (e.g., OpenAI's GPT-4) and AI libraries for health data analysis (e.g., Python's TensorFlow and Scikit-learn).
[0125] Generative AI model: Used to generate a virtual character based on user information. It receives prompt text as input data and generates a virtual character.
[0126] Program processing and data manipulation
[0127] 1. User registration and initial settings
[0128] The user installs and launches the "Soba de Mimamoru" app. After launching the app, an information input form is displayed, and the user enters the necessary information, such as name, age, health status, and hobbies. This information is then sent from the device to the server.
[0129] 2. Virtual Character Generation
[0130] The server uses a generative AI model to generate a virtual character based on the received user information. This virtual character is modeled after a person close to the user or their family, and is designed to feel familiar to the user. The generated character is sent from the server to the device and displayed within the app.
[0131] 3. Daily health management
[0132] The device displays a health check form every day. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and clicks the submit button. The device then sends the entered health information to the server. The server uses AI to analyze the health data and generates and sends advice to the device. The advice is then conveyed to the user through a virtual character.
[0133] 4. Supporting social connections
[0134] The server collects information about local and social events and recommends appropriate events based on the user's interests. This information is sent to the device, and the user can choose to participate. When a user registers to participate in an event, the device sends the information to the server, and the server provides the participation information to the event organizer.
[0135] Specific examples
[0136] Suppose a 75-year-old user has been living alone for a long time and is concerned about his health. He installs the "Soba de Mimamoru" app and inputs his name, health condition (e.g., he has back pain), and hobby (e.g., reading). Based on this information, the server generates a virtual character modeled after his late wife and displays it on the device.
[0137] Every morning, he enters his temperature, blood pressure, and other information into the app, and receives advice based on that information from a virtual character. The app also displays information about events such as book clubs held in the area, allowing him to make new friends by participating in these events.
[0138] Prompt Sentence Examples
[0139] Below are some example prompts to input to a generative AI model:
[0140] User Information:
[0141] Name: Username
[0142] Age: 75
[0143] Health condition: Back pain
[0144] Hobbies: Reading
[0145] Virtual characters to be generated:
[0146] A character modeled after the user's late wife
[0147] Based on this prompt, the generative AI model generates the most suitable virtual character based on the user's personal information and provides a wide range of support.
[0148] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0149] Step 1:
[0150] The user installs and launches the "Sobade Mimamoru" app.
[0151] Step 2:
[0152] The device displays a form for entering information.
[0153] The user enters the required information such as name, age, health status, hobbies, etc. and clicks the submit button.
[0154] Input: User-entered information about name, age, health, and hobbies.
[0155] Output: The entered user information is sent from the terminal to the server.
[0156] Step 3:
[0157] The server receives and stores the user information.
[0158] Input: User information sent from the device.
[0159] Output: User information stored in the database.
[0160] Step 4:
[0161] The server executes a generative AI model based on the received user information to generate a virtual character.
[0162] Input: Stored user information.
[0163] Data processing: User information is input into the generative AI model as a prompt sentence.
[0164] Output: The generative AI model generates a virtual character and returns the character data to the server.
[0165] Specific operation: The server processes the data (e.g., 3D model and text information) of the generated virtual character.
[0166] Step 5:
[0167] The server transmits the data of the generated virtual character to the terminal.
[0168] Input: Data of the generated virtual character.
[0169] Output: The virtual character data is sent to the device.
[0170] Step 6:
[0171] The terminal displays the virtual character on a user interface.
[0172] Input: Virtual character data sent from the server.
[0173] Output: A virtual character is displayed in the app.
[0174] Specific behavior: In some cases, animation and audio functions are also included.
[0175] Step 7:
[0176] The device displays a health check form every day.
[0177] The user enters their health status, such as temperature, blood pressure, heart rate, and mood, and clicks the submit button.
[0178] Input: User-entered health data.
[0179] Output: Health status data is sent from the device to the server.
[0180] Step 8:
[0181] The server receives the health data and analyzes it using AI.
[0182] Input: Health status data sent from the device.
[0183] Data Computing: Analyzing health data using AI models (such as TensorFlow and Scikit-learn).
[0184] Output: Health advice is generated based on the analysis results.
[0185] What it does: The AI model detects outliers and compares them with historical data to identify trends.
[0186] Step 9:
[0187] The server sends the generated health advice to the terminal.
[0188] Input: AI-generated health advice.
[0189] Output: Health advice is sent to the device.
[0190] Step 10:
[0191] The device displays health advice to the user through a virtual character.
[0192] Input: Health advice sent from the server.
[0193] Output: Health advice is displayed to the user through the virtual character UI.
[0194] Example: A virtual character gives advice such as, "Your blood pressure is a little high, so try to limit your salt intake."
[0195] Step 11:
[0196] The server collects local event information and filters it based on the user's interests.
[0197] Input: Local event information collected from the internet.
[0198] Data processing: Filtering event information based on user hobbies and interests.
[0199] Output: Recommended event information is generated.
[0200] Step 12:
[0201] The server transmits the filtered event information to the terminal.
[0202] Input: Recommended event information.
[0203] Output: Event information is sent to the terminal.
[0204] Step 13:
[0205] The terminal displays the event information to the user and accepts participation applications.
[0206] Input: Event information sent from the server.
[0207] Output: The event information is displayed in the app and the user clicks to register.
[0208] Step 14:
[0209] The terminal sends the user's participation application to the server.
[0210] Input: User's event registration information.
[0211] Output: The registration information is sent to the server.
[0212] Step 15:
[0213] The server provides the participation information to the event organizer and confirms the participation.
[0214] Input: Application information.
[0215] Output: Notify the user that their participation is confirmed.
[0216] Example: An in-app notification says, "You've been accepted into a local gardening class."
[0217] (Application example 1)
[0218] 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."
[0219] Elderly people living alone and unmarried people face challenges in managing their physical and mental health and in maintaining social connections. Welfare facilities and community centers, in particular, lack the means for users to understand their own health status and receive appropriate advice. There is also a lack of systems for providing appropriate information about local events and encouraging participation. This raises concerns that users may become increasingly socially isolated and experience a decline in their quality of life.
[0220] 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.
[0221] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using artificial intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status information, means for analyzing health data and generating advice, means for collecting local event information and recommending it to the user, means for supporting event participation, means for providing an application to be installed on a smartphone, means for automatically notifying emergency contacts, and means for supporting community activities within a facility. This enables elderly people living alone and unmarried people to maintain their daily health management and social connections and improve their quality of life.
[0222] An "information input form" is a screen or interface that allows a user to enter their own information (such as name, age, health status, hobbies, etc.).
[0223] "User information" refers to data about the user (such as name, age, health status, hobbies, etc.) and is information used by the system to provide individualized support.
[0224] "Generative AI" is an AI technology that generates appropriate virtual characters and advice based on input data.
[0225] A "virtual character" is a virtual person or character generated using artificial intelligence, which interacts with and assists the user.
[0226] A "user interface" is the screen or means of interaction that a user uses to interact with an application.
[0227] "Health data" refers to information about the user's daily health condition, such as body temperature, blood pressure, heart rate, and mood.
[0228] "Advice" is advice and suggestions regarding daily health management and lifestyle improvements generated by artificial intelligence based on health data.
[0229] "Local event information" is information about various events and activities held in the area where the user lives.
[0230] "Means to support event participation" refers to support functions for users to participate in local events (provision of event information, application procedures, etc.).
[0231] The "application installed on the smartphone" is software that runs on the smartphone and provides the functions of the present invention.
[0232] The "means for automatically notifying emergency contacts" is a function that automatically sends a notification to a pre-registered emergency contact if there is an abnormality in the user's health condition.
[0233] "Means to support community activities within the facility" refers to functions for managing activities that take place within welfare facilities and community centers and promoting user participation.
[0234] This invention is a system that supports single-person elderly people and unmarried people in managing their health and maintaining social connections on a daily basis. The configuration and operation of this system will be described below.
[0235] User registration and initial settings
[0236] First, the user launches the application installed on their smartphone and enters information such as their name, age, health condition, and hobbies into an information input form. This information is sent from the device to a server and stored. Using generative artificial intelligence, a virtual character is generated based on the input information, and the character is displayed on the user interface. The virtual character is modeled after a familiar person or family member, helping the user to feel a sense of familiarity.
[0237] Daily health management
[0238] Every day, users enter their health status (body temperature, blood pressure, heart rate, mood, etc.) into the device and send it. This health data is sent to a server and analyzed by AI. Based on the analysis results, advice for health management is generated. For example, specific advice such as "Your blood pressure is high, so try to limit your salt intake" is provided.
[0239] Supporting social connections
[0240] The server collects information about local events and recommends appropriate events based on the user's hobbies and interests. This event information is displayed on the device, allowing the user to select and register for the events they wish to attend. Furthermore, in preparation for unforeseen circumstances, the system has an emergency contact function that automatically sends a notification to registered emergency contacts if any abnormalities are detected in the user's health condition.
[0241] Specific examples
[0242] Mr. Suzuki, 70 years old, lives alone. He installed the application on his smartphone and completed the registration process. Every morning, Mr. Suzuki enters his health status into the app and receives advice based on it. He can also easily register for local walking groups and hobby classes, which has enabled him to make new friends. One day, when his health worsened, the emergency contact function was activated, and his family who live nearby were contacted, allowing for a quick response.
[0243] Prompt Sentence Examples
[0244] "On a day when 70-year-old Suzuki has a body temperature of 36.8°C, blood pressure of 135 / 80, a heart rate of 72 beats per minute, and feels normal, what should he be careful of in his daily life?"
[0245] This system will make it easier for single-person elderly people and unmarried people to manage their health and maintain social connections, which is expected to improve their quality of life.
[0246] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0247] Program processing flow
[0248] Step 1:
[0249] A user installs an application on their smartphone and opens an information input form. This form has fields for entering information such as name, age, health status, and hobbies. When the user enters all the information and clicks the "Submit" button, the input data is sent to the server via the device. Input: User information. Output: User information saved on the server.
[0250] Step 2:
[0251] The server uses artificial intelligence to generate a virtual character based on the received user information. This virtual character is modeled after the user's preferences and familiar faces. The generated character is sent from the server to the terminal and displayed on the user interface. Input: User information. Output: Displayed virtual character.
[0252] Step 3:
[0253] Every day, users enter their health status (body temperature, blood pressure, heart rate, mood, etc.) into the health check form within the application. Once the entry is complete, they click the "Submit" button and the data is sent from the device to the server. Input: Health data. Output: Health data sent to the server.
[0254] Step 4:
[0255] The server uses AI to analyze the received health data. Data such as body temperature, blood pressure, heart rate, and mood are used for the analysis. The AI evaluates the user's health condition based on past data and a medical knowledge base, and generates appropriate advice. This advice is sent from the server to the device and conveyed to the user through a virtual character. Input: Health data. Output: Advice.
[0256] Step 5:
[0257] The server collects local event information and recommends appropriate events based on the user's hobbies and interests. Event information is sent from the server to the terminal and displayed on the user interface. When the user selects the event they want to attend and clicks the "Apply" button, participation information is sent to the server and contacted with the event organizer. Input: User's hobbies and interests. Output: Recommended event information, application to attend.
[0258] Step 6:
[0259] If an abnormality is detected based on the health data, the emergency contact function will be activated. The server will automatically send a notification to pre-registered emergency contacts. This notification will inform the user that there is an abnormality in their health condition. Input: Abnormal health data. Output: Emergency contact notification.
[0260] Step 7:
[0261] Designed for use in welfare facilities and community centers, the system provides a means to support community activities within the facility, including event management and participant health monitoring. Input: Facility event information, participant health data. Output: Event information management, participant health report.
[0262] In this way, elderly people living alone and unmarried people can improve their quality of life by managing their daily health and participating in community events.
[0263] 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.
[0264] ---
[0265] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. The system supports daily health management and participation in local events through a virtual character generated based on the user's input information. The system also incorporates an emotion engine that recognizes the user's emotions and responds accordingly.
[0266] 1. User registration and initial settings
[0267] The process begins when the user installs and launches the "Soba de Mimamoru" app. After launching the app, the device displays a form for entering user information. The user enters the necessary information, such as name, age, health condition, and hobbies, and clicks the submit button. The device then sends the entered information to the server, completing user registration. Based on the user information, the server uses generative artificial intelligence to generate a virtual character modeled after a close friend or family member, and sends the virtual character to the device for display. In addition, an emotion engine begins to operate, recognizing emotions from the user's voice and facial expressions.
[0268] 2. Daily health management
[0269] The device displays a health check form every day. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and clicks the submit button. The device then sends the entered health information to the server. The server uses AI to analyze the health data and generates advice based on it. The generated advice is sent to the device and communicated to the user through a virtual character UI. For example, the advice might be, "Your blood pressure is a little high, so try to limit your salt intake." Furthermore, an emotion engine recognizes the user's emotions and provides emotion-based advice, such as, "You seem to be feeling stressed lately. Why not try a relaxing aroma?"
[0270] 3. Supporting social connections
[0271] The server collects information about local and social events, such as walking clubs and hobby gatherings held in the neighborhood. The server sends this information to the device to recommend appropriate events based on the user's hobbies and interests. The device displays the event information, the user selects the event they wish to attend, and clicks the application button. The device sends the event participation application information to the server, and the server contacts the organizer to confirm the user's participation. This allows the user to participate in local events and build social connections. When participating in an event, the emotion engine checks whether the user is feeling anxious or nervous, and sends words of encouragement through a virtual character if necessary.
[0272] Specific examples
[0273] Mr. Tanaka, 75, had been living alone for a long time and was concerned about his physical and mental health. He installed the "Soba de Mimamoru" app and entered his name, health condition (e.g., back pain), and hobby (e.g., gardening). Based on Mr. Tanaka's information, the server generated a virtual character modeled after his late wife and displayed it on his device. Every morning, Mr. Tanaka entered his temperature and blood pressure into the app and received advice from the virtual character based on that information. The app also displayed information about local gardening classes, and by participating in these events, he was able to make new friends. Furthermore, the emotion engine recognized that Mr. Tanaka had been feeling stressed recently, and the virtual character encouraged him to "take time to relax and not push yourself too hard," helping him live a more secure life.
[0274] In this way, this invention not only enables elderly people living alone and unmarried people to manage their physical and mental health, but also enables them to form social connections, improving their quality of life (QOL). The addition of an emotion engine enables more personalized support tailored to the user's psychological state, contributing to easing feelings of loneliness and reducing stress.
[0275] ---
[0276] The processing flow will be explained below.
[0277] ---
[0278] User registration and initial settings
[0279] Step 1:
[0280] The user installs and launches the "Sobade Mimamoru" app.
[0281] Step 2:
[0282] The device displays a user information input form (name, age, health status, preferences, etc.) on the screen.
[0283] Step 3:
[0284] The user enters the required information and clicks the submit button.
[0285] Step 4:
[0286] The terminal transmits the input information to the server.
[0287] Step 5:
[0288] Based on the user's information, the server uses artificial intelligence to generate a virtual character modeled after a close friend or family member.
[0289] Step 6:
[0290] The server transmits the generated virtual character to the terminal.
[0291] Step 7:
[0292] The device displays the virtual character on the screen, and the emotion engine starts up, preparing to recognize emotions from the user's voice and facial expressions.
[0293] Daily health management
[0294] Step 1:
[0295] The device displays a daily health check form (temperature, blood pressure, heart rate, mood, etc.) on the screen.
[0296] Step 2:
[0297] The user inputs their daily health status and clicks the submit button.
[0298] Step 3:
[0299] The terminal transmits the input health information to the server.
[0300] Step 4:
[0301] The server uses AI to analyze health data and generate advice.
[0302] Step 5:
[0303] The server transmits the generated advice to the terminal.
[0304] Step 6:
[0305] The device will then give advice to the user through a virtual character UI, for example, displaying a message such as "Your blood pressure is a little high, so try to limit your salt intake."
[0306] Step 7:
[0307] The device analyzes the user's voice and facial expressions and recognizes emotions using an emotion engine.
[0308] Step 8:
[0309] The server receives data from the emotion engine, analyzes the user's emotion data, and generates emotion-based advice, such as "You seem to be stressed out lately. Why don't you try a relaxing aroma?"
[0310] Step 9:
[0311] The server transmits the generated emotion-based advice to the terminal.
[0312] Step 10:
[0313] The device conveys emotion-based advice to the user through a virtual character UI.
[0314] Supporting social connections
[0315] Step 1:
[0316] The server collects information about local and social events (for example, walking events and hobby gatherings held in the neighborhood).
[0317] Step 2:
[0318] The server selects events that the user can participate in based on the user's hobbies and interests.
[0319] Step 3:
[0320] The server transmits the selected event information to the terminal.
[0321] Step 4:
[0322] The event information received by the terminal is displayed on the screen.
[0323] Step 5:
[0324] The user checks the event information and selects the event they want to attend.
[0325] Step 6:
[0326] The user clicks the sign up button.
[0327] Step 7:
[0328] The terminal transmits the application information to the server.
[0329] Step 8:
[0330] The server contacts the event organizer to confirm the user's participation.
[0331] Step 9:
[0332] The server sends participation confirmation information to the terminal.
[0333] Step 10:
[0334] The device will notify the user of the confirmation of participation. Furthermore, if the emotion engine detects the user's anxiety or tension, it will provide an encouraging message through the virtual character.
[0335] ---
[0336] The above is the processing flow of the "Soba de Mimamoru" system, which combines an emotion engine. At each step, the system effectively manages the user's information, supports their physical and mental health, and provides social connections. In addition, the emotion engine enables personalized support based on the user's psychological state.
[0337] Example 2
[0338] 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."
[0339] It is difficult for elderly people living alone or unmarried people to properly manage their physical and mental health and maintain social connections. Furthermore, they are prone to feeling lonely and stressed in their daily lives, which often threatens their mental health. In such situations, a system that can provide appropriate support is needed.
[0340] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[0341] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using a generation artificial intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status, means for analyzing health data and generating advice, means for collecting local event information and recommending events to the user, means for supporting event participation, means for recognizing the user's emotions from voice and facial expressions and generating a response based thereon, and means for providing additional advice and encouraging messages based on the user's emotional state, thereby enabling consistent management of the user's physical and mental health, maintaining social connections, and improving quality of life.
[0342] The "means for providing an information input form" is a mechanism that provides an interface for a user to input information such as his / her name, age, health condition, hobbies, etc.
[0343] The "means for transmitting and storing user information" is a mechanism that has the function of transmitting information entered by the user to a server and safely storing that information.
[0344] "Means for generating a virtual character using artificial intelligence" refers to a mechanism that uses artificial intelligence technology to create a virtual character based on user information.
[0345] The "means for displaying the generated virtual character on the user interface" is a mechanism for displaying the generated virtual character on the screen of a digital device.
[0346] The "means for inputting and transmitting health status" is a mechanism that allows a user to input their daily health status, such as body temperature, blood pressure, and heart rate, and transmit that information to a server.
[0347] The "means for analyzing health data and generating advice" refers to a mechanism in which the server analyzes the health data received using an AI algorithm and generates health management advice based on that data.
[0348] The "means for collecting local event information and recommending it to the user" is a mechanism by which the server collects local event information, filters it based on the user's hobbies and interests, and recommends it to the user.
[0349] The "means for supporting event participation" is a mechanism that handles the participation procedures for the event selected by the user and communicates with the organizer.
[0350] "Means for recognizing the user's emotions from their voice and facial expressions and generating a response based on that" refers to a mechanism that uses an emotion engine to analyze the user's voice and facial expressions and generates appropriate responses and advice based on the results.
[0351] The "means for providing additional advice or encouraging messages based on the user's emotional state" is a mechanism for providing additional specific advice or encouraging messages based on the user's emotional state recognized by the emotion engine.
[0352] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. This system includes the following components:
[0353] 1. The user installs and launches the application on a device such as a smartphone or tablet. After launching, the device displays a user information input form, and the user enters the required information, such as name, age, health status, and hobbies, and submits it. The device then sends the entered information to the server, completing user registration.
[0354] 2. The server uses artificial intelligence to generate a virtual character based on user information. The generated virtual character is designed based on the user's preferences and past information, and is displayed on the smartphone or tablet. It also incorporates an emotion engine that recognizes emotions from the user's voice and facial expressions, and generates responses based on the user's emotional state.
[0355] 3. As part of daily health management, the device displays a health check form, and the user enters and submits their health status information, such as body temperature, blood pressure, heart rate, and mood, each day. The device then sends the entered health information to a server. The server uses AI to analyze the health data and generates advice based on it. The generated advice is then sent to the device and communicated to the user through a virtual character. For example, advice such as "Your blood pressure is a little high, so try to limit your salt intake" is displayed. Furthermore, an emotion engine recognizes the user's emotions and provides emotion-based advice, such as "You seem to be feeling stressed lately. Why not try a relaxing aroma?"
[0356] 4. To support social connections, the server collects information about local and community events, such as walking clubs and hobby gatherings held in the neighborhood. The server then sends this information to the device to recommend appropriate events based on the user's hobbies and interests. The device displays the event information, and the user selects the event they wish to attend and clicks the application button. The device then sends the event application information to the server, which then contacts the organizer to confirm the user's participation. This allows the user to participate in local events and build social connections. When participating in an event, the emotion engine checks whether the user is feeling anxious or nervous, and sends encouraging words through a virtual character if necessary.
[0357] Specific examples
[0358] For example, consider a user named Tanaka, 75 years old. Tanaka lives alone and was concerned about his physical and mental health. He installed the AI Life Supporter and entered his name, health condition (e.g., back pain), and hobby (e.g., gardening). Based on Tanaka's information, the server generated a virtual character modeled after his late wife and displayed it on his device. Every morning, Tanaka enters his temperature and blood pressure into the app and receives advice from the virtual character based on that information. The app then displays information about local gardening classes, and Tanaka is able to make new friends by participating in the event. The emotion engine also recognizes that Tanaka has been feeling stressed recently, and the virtual character encourages him to "take time to relax and not push yourself too hard," helping him live a more secure life.
[0359] Below are some examples of prompts to input to the generative AI model.
[0360] Mr. Tanaka, 75, lives alone and is concerned about his health. He installed the "AI Life Supporter" app. After entering his information into the app, a virtual character modeled after his late wife was generated and displayed on his device. Every morning, Mr. Tanaka enters his temperature and blood pressure and receives generated advice. He also participates in a local gardening class and makes new friends. The emotion engine recognizes when Mr. Tanaka is feeling stressed, and the virtual character sends him advice on how to relax, allowing him to live a life with peace of mind.
[0361] In this way, this invention not only enables elderly people living alone and unmarried people to manage their physical and mental health, but also enables them to form social connections, improving their quality of life. The addition of an emotion engine enables more personalized support tailored to the user's psychological state, contributing to alleviating feelings of loneliness and reducing stress.
[0362] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0363] Program processing flow and specific explanation
[0364] Step 1:
[0365] The user installs the app and launches it for the first time. By launching the app, the initial setup screen is displayed. Specifically, the user downloads the app from the app store and clicks the install button. The user then taps the app icon to launch it.
[0366] Step 2:
[0367] The device displays a user information input form. The user enters information such as name, age, health condition, hobbies, etc. and submits it. Specifically, the device displays the input form on the screen and accepts input from the user. The entered information is temporarily stored within the device.
[0368] Input: Information entered by the user, such as name, age, health status, hobbies, etc.
[0369] Output: The entered user information is sent to the server in JSON format.
[0370] Step 3:
[0371] The server accumulates the received user information and generates a virtual character using generative AI. Specifically, the server stores the received user information in a database. Then, it generates a virtual character using a generative AI model, converts the data, and sends it to the device.
[0372] Input: User information (name, age, health status, hobbies, etc.)
[0373] Output: Send the generated virtual character data to the terminal
[0374] Step 4:
[0375] The terminal displays the generated virtual character on the user interface. Specifically, the terminal displays the virtual character on the screen based on the received virtual character data.
[0376] Input: Data of the generated virtual character
[0377] Output: A virtual character displayed on the user interface.
[0378] Step 5:
[0379] The device starts the emotion engine and prepares to recognize emotions from the user's voice and facial expressions. Specifically, the device uses a microphone and camera to collect voice and facial expression data and inputs it into the emotion engine in real time. The emotion engine analyzes this data and determines the user's emotions.
[0380] Input: User voice and facial expression data
[0381] Output: Recognized user emotion data
[0382] Step 6:
[0383] The device presents a health check form to the user every day. The user inputs their health status, such as body temperature, blood pressure, heart rate, and mood, and submits it. Specifically, the device displays the health check form at a specific time every day and waits for input from the user. The user inputs the data and clicks the submit button.
[0384] Input: User-entered health data such as temperature, blood pressure, heart rate, and mood
[0385] Output: Send the input health data to the server in JSON format
[0386] Step 7:
[0387] The server uses AI to analyze the health data it receives and generate appropriate advice. Specifically, the server stores the received health data in a database and analyzes the data using an AI algorithm. Based on the analysis results, it generates advice and sends the data to the device.
[0388] Input: User health data (temperature, blood pressure, heart rate, mood, etc.)
[0389] Output: Sends generated advice data to the terminal
[0390] Step 8:
[0391] The device communicates advice to the user through the virtual character. Specifically, the device displays the received advice data in an easy-to-understand manner to the user through the virtual character's UI.
[0392] Input: Data for generated advice
[0393] Output: Advice displayed through a virtual character
[0394] Step 9:
[0395] The emotion engine checks the user's emotions and generates additional advice or encouraging messages based on the emotions. Specifically, the emotion engine re-analyzes the user's voice and facial expression data to detect signs of stress or anxiety. Based on the results, it generates additional advice or encouraging messages and sends them to the device.
[0396] Input: Emotion data analyzed from voice and facial expressions
[0397] Output: Any additional advice or encouragement messages generated are sent to the terminal.
[0398] Step 10:
[0399] The server collects local event information. Specifically, the server uses APIs from local governments and community centers to collect event information and stores it in a database. The collected information is then filtered based on the user's hobbies and interests.
[0400] Input: Local event information
[0401] Output: Sends filtered event information to the terminal
[0402] Step 11:
[0403] The terminal displays the event information and the user selects an event to participate in. Specifically, the terminal displays the filtered event information on a user interface and allows the user to select the event they want to participate in. The user clicks the participate button.
[0404] Input: Filtered event information
[0405] Output: Sends the user's selected event participation information to the server
[0406] Step 12:
[0407] The server sends the application information for event participation to the organizer and confirms the participation. Specifically, the server notifies the organizer of the received user's participation request and waits for confirmation from the organizer. Once confirmation is received, the server notifies the user of the participation information.
[0408] Input: Event participation information selected by the user
[0409] Output: Send user participation confirmation data to the terminal
[0410] Step 13:
[0411] The emotion engine checks the user's emotions before participating in the event, and if they feel anxious or nervous, it sends encouraging words. Specifically, the emotion engine re-analyzes the user's voice and facial expressions just before participating in the event, and if stress or anxiety is detected, it generates an encouraging message and sends it to the device.
[0412] Input: Emotion data analyzed from voice and facial expressions
[0413] Output: Generated encouraging message sent to terminal
[0414] (Application example 2)
[0415] 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."
[0416] Elderly people and single-person households face challenges in managing their physical and mental health and maintaining social connections, and it is also challenging for them to receive appropriate information and support while in physical stores. In particular, there is a lack of appropriate responses and support tailored to the user's emotional state, which can lead to feelings of loneliness and increased stress. The challenge is to solve these problems and enable elderly people and single-person households to lead fulfilling lives.
[0417] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.
[0418] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using a generation artificial intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status, means for analyzing health data and generating advice, means for collecting local event information and recommending it to the user, means for supporting event participation, means for providing in-store navigation information through the smart glasses, and means for recognizing emotions using an emotion engine and generating responses. This allows users to receive comprehensive support during activities in physical stores while maintaining their health management and social connections.
[0419] "Information input form" refers to an interface for users to input their own information.
[0420] "User Information" refers to data about a user, such as the user's name, age, health status, hobbies, etc.
[0421] "Generative AI" refers to AI technology for generating virtual characters based on user information.
[0422] "Virtual character" refers to a fictitious character generated based on user information.
[0423] "User interface" refers to the interface through which a user interacts with a system.
[0424] "Health status" refers to health-related data such as a user's temperature, blood pressure, heart rate, and mood.
[0425] "Health data" refers to information about a user's health condition entered by the user.
[0426] "Advice" refers to advice generated based on the analyzed health data.
[0427] "Local event information" refers to information about events held in the user's local area.
[0428] "Event participation" refers to the process of helping users participate in local events.
[0429] "Smart glasses" refers to wearable devices used to display information.
[0430] "In-store navigation information" refers to information necessary for a user to navigate within a physical store.
[0431] "Emotion engine" refers to technology that recognizes a user's emotions and generates a response accordingly.
[0432] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. The system aims to enrich users' lives in brick-and-mortar stores by using smart glasses and other wearable devices.
[0433] 1. User registration and initial settings
[0434] The process begins when the user puts on the smart glasses and launches the application. After launching the application, the smart glasses display a form for entering user information. The user enters the necessary information, such as name, age, health status, and hobbies, and submits it. This sends the user information to the server and stores it.
[0435] Using generative artificial intelligence, the server generates a virtual character based on the user's information. This virtual character is modeled after a loved one or family member, and the generated character is displayed on the smart glasses' display. Furthermore, an emotion engine is activated to recognize emotions from the user's voice and facial expressions.
[0436] 2. Daily health management
[0437] The smart glasses display a health check form every morning. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and sends it to the server. The server uses AI to analyze the collected health data and generates advice based on it. The advice is then sent to the smart glasses, where a virtual character delivers it to the user via voice.
[0438] 3. In-store support
[0439] When a user visits a physical store, the smart glasses provide navigation information within the store. When the user specifies the location they want to go to, the server calculates the route and displays it on the smart glasses' display. A virtual character then gives voice instructions, such as "Turn left at the next corner."
[0440] 4. Supporting social connections
[0441] The server collects local event information and recommends events based on the user's hobbies and interests. Users can check the event information through the smart glasses, select the events they want to attend, and sign up. The server then contacts the organizers to confirm the user's participation. In addition, the emotion engine checks whether the user is feeling anxious or nervous, and sends encouraging words through the virtual character as needed.
[0442] Hardware and Software Use
[0443] Smart glasses (wearable devices): Used for user interface and data entry / display.
[0444] Server: Performs back-end processing such as accumulating user information, generating virtual characters, analyzing health data, calculating route information, and operating the emotion engine.
[0445] Emotion engine: Software that recognizes emotions from the user's voice and facial expressions and generates a response.
[0446] Specific examples
[0447] Consider a scenario in which a 75-year-old user wears smart glasses and goes to a supermarket. First, the user enters the store and instructs the smart glasses to "go to the vegetable section." The server calculates the route within the store and sends that information to the smart glasses. Navigation information is displayed on the smart glasses' display, and a virtual character provides voice guidance such as "Turn left at the next corner." While the virtual character is displayed, the emotion engine analyzes the user's facial expressions, and if it detects fatigue, it will say, "Let's take a short break."
[0448] Prompt Sentence Examples
[0449] Entered data:
[0450] Name: User
[0451] Age: 75
[0452] Health condition: High blood pressure
[0453] Hobbies: Gardening
[0454] Tasks to be performed:
[0455] 1. Health data collection and analysis
[0456] 2. In-store navigation
[0457] 3. Providing event information
[0458] 4. Emotion-based response generation
[0459] Please provide the following navigation steps:
[0460] "Turn right at the next door."
[0461] This concludes the description of the embodiment of the present invention, which allows elderly people and single-person households to receive comprehensive support while they are active in a physical store, while managing their health and maintaining social connections.
[0462] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0463] Step 1:
[0464] The user puts on the smart glasses and starts the application. The smart glasses display a user information input form, and the user enters the necessary information, such as name, age, health status, and hobbies. The input data is sent to the server and stored.
[0465] Input: User information (name, age, health status, hobbies)
[0466] Output: User information stored on the server
[0467] Step 2:
[0468] The server uses artificial intelligence to generate a virtual character based on the input user information. The generated virtual character is modeled after a close friend or family member, and the data of this virtual character is sent to the smart glasses and displayed to the user.
[0469] Input: User information
[0470] Output: Virtual character data
[0471] Step 3:
[0472] The emotion engine is activated and recognizes emotions from the user's voice and facial expressions. The emotion engine uses the smart glasses' camera and microphone to capture the user's real-time facial expressions and voice, and analyzes emotions based on them.
[0473] Input: User's voice and facial expression data
[0474] Output: Parsed emotion results
[0475] Step 4:
[0476] The smart glasses display a health check form every morning. Users enter their health status, such as body temperature, blood pressure, heart rate, and mood, and send it to a server. The server then uses AI to analyze the collected health data and generate advice based on it.
[0477] Input: User's health status (temperature, blood pressure, heart rate, mood)
[0478] Output: Analysis results and advice
[0479] Step 5:
[0480] The generated advice is sent to the smart glasses, where a virtual character will give it to the user via voice. For example, specific advice such as "Your blood pressure is high, so try to limit your salt intake" is displayed.
[0481] Input: Analysis results and advice
[0482] Output: Voice advice from a virtual character
[0483] Step 6:
[0484] When a user visits a physical store, the smart glasses provide navigation information within the store. When the user specifies the location they want to go to, the server calculates the route and displays it on the smart glasses' display. A virtual character then gives voice instructions, such as "Turn left at the next corner."
[0485] Input: Specify destination
[0486] Output: Navigation information
[0487] Step 7:
[0488] The server collects local event information and recommends events based on the user's hobbies and interests. Users can check the event information through the smart glasses, select the event they want to attend, and register. The server then contacts the organizer to confirm the user's participation.
[0489] Input: Hobbies and interests, local event information
[0490] Output: Recommended event information and participation confirmation
[0491] Step 8:
[0492] The emotion engine checks whether the user is feeling anxious or nervous. If necessary, the virtual character will offer words of encouragement. For example, it will provide advice based on the user's emotions, such as, "You seem to be feeling stressed lately. Why don't you try a relaxing aroma?"
[0493] Input: User emotion data
[0494] Output: Emotion-based response
[0495] The above are the specific processing steps of the system that realizes the application example.
[0496] 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.
[0497] 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.
[0498] 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.
[0499] [Second embodiment]
[0500] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.
[0501] 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.
[0502] 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).
[0503] 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.
[0504] 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.
[0505] 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).
[0506] 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.
[0507] 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.
[0508] 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.
[0509] 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.
[0510] In the smart glasses 214, 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.
[0511] 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."
[0512] ---
[0513] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. In this system, users enter their own information into an information input form, and the system supports daily health management and participation in local events through a virtual character generated based on that information.
[0514] 1. User registration and initial settings
[0515] The process begins when the user installs and launches the "Soba de Mimamoru" app. After launching the app, the device displays a form for entering user information. The user enters the necessary information, such as name, age, health condition, and hobbies, and clicks the submit button. The device then sends the entered information to the server, completing user registration. Based on the user information, the server uses generative artificial intelligence to generate a virtual character modeled after a close friend or family member, and sends the virtual character to the device for display.
[0516] 2. Daily health management
[0517] The device displays a health check form every day. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and clicks the submit button. The device then sends the entered health information to the server. The server uses AI to analyze the health data and generates advice based on it. The advice generated is sent to the device and communicated to the user through the virtual character's UI. For example, the advice might be, "Your blood pressure is a little high, so try to limit your salt intake."
[0518] 3. Supporting social connections
[0519] The server collects information about local and social events, such as nearby walking clubs and hobby gatherings. The server sends this information to the device to recommend appropriate events based on the user's hobbies and interests. The device displays the event information, and the user selects the event they wish to attend and clicks the application button. The device then sends the application information for the event to the server, which contacts the organizer to confirm the user's participation. This allows the user to participate in local events and build social connections.
[0520] Specific examples
[0521] Mr. Tanaka, 75, had been living alone for a long time and was concerned about his physical and mental health. He installed the "Soba de Mimamoru" app and entered his name, health condition (e.g., back pain), and hobby (e.g., gardening). Based on Mr. Tanaka's information, the server generated a virtual character modeled after his late wife and displayed it on his device. Every morning, Mr. Tanaka entered his body temperature and blood pressure into the app, and received advice based on that information from the virtual character. The app also displayed information about local gardening classes, allowing Mr. Tanaka to make new friends by participating in these events.
[0522] In this way, this invention not only enables elderly people living alone and unmarried people to manage their physical and mental health, but also enables them to have social connections, thereby improving their quality of life (QOL).
[0523] The processing flow will be explained below.
[0524] ---
[0525] User registration and initial settings
[0526] Step 1:
[0527] The user installs and launches the "Sobade Mimamoru" app.
[0528] Step 2:
[0529] The device displays a user information input form (name, age, health status, preferences, etc.) on the screen.
[0530] Step 3:
[0531] The user enters the required information and clicks the submit button.
[0532] Step 4:
[0533] The terminal transmits the input information to the server.
[0534] Step 5:
[0535] Based on the user's information, the server uses artificial intelligence to generate a virtual character modeled after a close friend or family member.
[0536] Step 6:
[0537] The server transmits the generated virtual character to the terminal.
[0538] Step 7:
[0539] The terminal displays the transmitted virtual character on the screen, allowing the user to start a conversation with the virtual character.
[0540] Daily health management
[0541] Step 1:
[0542] The device displays a daily health check form on the screen (e.g., temperature, blood pressure, heart rate, mood, etc.).
[0543] Step 2:
[0544] The user inputs their daily health status and clicks the submit button.
[0545] Step 3:
[0546] The terminal transmits the input health information to the server.
[0547] Step 4:
[0548] The server uses AI to analyze health data and generate advice.
[0549] Step 5:
[0550] The server transmits the generated advice to the terminal.
[0551] Step 6:
[0552] The device will then give advice to the user through a virtual character UI, for example, displaying a message such as "Your blood pressure is a little high, so try to limit your salt intake."
[0553] Supporting social connections
[0554] Step 1:
[0555] The server collects information about local and social events (for example, walking events and hobby gatherings held in the neighborhood).
[0556] Step 2:
[0557] The server selects events that the user can participate in based on the user's hobbies and interests.
[0558] Step 3:
[0559] The server transmits the selected event information to the terminal.
[0560] Step 4:
[0561] The event information received by the terminal is displayed on the screen.
[0562] Step 5:
[0563] The user checks the event information and selects the event they want to attend.
[0564] Step 6:
[0565] The user clicks the sign up button.
[0566] Step 7:
[0567] The terminal transmits the application information to the server.
[0568] Step 8:
[0569] The server contacts the event organizer to confirm the user's participation.
[0570] Step 9:
[0571] The server sends participation confirmation information to the terminal.
[0572] Step 10:
[0573] The terminal notifies the user of the participation confirmation information.
[0574] ---
[0575] This concludes the processing flow of the "Soba de Mimamoru" system. At each step, the system effectively manages the user's information, supports their physical and mental health, and provides social connections.
[0576] Example 1
[0577] 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."
[0578] In modern society, elderly people living alone and unmarried people face challenges in managing their physical and mental health and maintaining social connections. This problem, particularly for the elderly, increases feelings of loneliness and health risks, leading to a decline in quality of life (QOL). Furthermore, low participation in local events and social activities also contributes to social isolation. Therefore, there is a need for a system that allows these people to easily manage their health information, receive appropriate advice, and form social connections.
[0579] 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.
[0580] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using generative intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status, means for analyzing health data and generating advice, means for collecting local event information and recommending it to users, means for supporting event participation, means for providing daily health data analysis results using AI technology, and means for conveying advice to users through the generated virtual character, thereby enabling users to manage their physical and mental health and build social connections.
[0581] An "information input form" is an online form where a user enters personal information such as name, age, health status, hobbies, etc.
[0582] "User information" refers to personal data such as name, age, health status, and hobbies entered by the user in the information input form.
[0583] "Generative intelligence" refers to artificial intelligence technology that uses a generative AI model (e.g., GPT-4) to automatically generate virtual characters based on user input data.
[0584] A "virtual character" is a 3D or 2D digital character created to resemble a close friend or family member based on the user's personal information and past experiences.
[0585] "User interface" refers to the application screen or digital interface through which a user interacts with a virtual character.
[0586] "Health Status" refers to the user's daily health data, such as temperature, blood pressure, heart rate, and mood.
[0587] "Health data" refers to information entered by the user, such as body temperature, blood pressure, heart rate, and mood.
[0588] "Advice" refers to specific health management instructions or suggestions provided to the user based on the results of analyzing the health data.
[0589] "Local event information" refers to event information such as local walking clubs and hobby gatherings that is automatically collected by the server.
[0590] "Means for using generative intelligence" means the ability to automatically generate virtual characters using a generative AI model.
[0591] "Means to support event participation" refers to a function that supports users in applying to participate in local events.
[0592] The present invention is a system that provides an "AI life supporter" that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. The details are explained below.
[0593] Configuration and Hardware / Software
[0594] The system operates using a user device (such as a smartphone), a server, and a generative AI model.
[0595] Device: User device such as a smartphone or tablet. Install and use the Android or iOS app "Soba de Mimamoru."
[0596] Server: A high-performance cloud server that runs generative AI models (e.g., OpenAI's GPT-4) and AI libraries for health data analysis (e.g., Python's TensorFlow and Scikit-learn).
[0597] Generative AI model: Used to generate a virtual character based on user information. It receives a prompt as input and generates a virtual character.
[0598] Program processing and data manipulation
[0599] 1. User registration and initial settings
[0600] The user installs and launches the "Soba de Mimamoru" app. After launching the app, an information input form is displayed, and the user enters the necessary information, such as name, age, health status, and hobbies. This information is then sent from the device to the server.
[0601] 2. Virtual Character Generation
[0602] The server uses a generative AI model to generate a virtual character based on the received user information. This virtual character is modeled after a person close to the user or their family, and is designed to feel familiar to the user. The generated character is sent from the server to the device and displayed within the app.
[0603] 3. Daily health management
[0604] The device displays a health check form every day. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and clicks the submit button. The device then sends the entered health information to the server. The server uses AI to analyze the health data and generates and sends advice to the device. The advice is then conveyed to the user through a virtual character.
[0605] 4. Supporting social connections
[0606] The server collects information about local and social events and recommends appropriate events based on the user's interests. This information is sent to the device, and the user can choose to participate. When a user registers to participate in an event, the device sends the information to the server, and the server provides the participation information to the event organizer.
[0607] Specific examples
[0608] Suppose a 75-year-old user has been living alone for a long time and is concerned about his health. He installs the "Soba de Mimamoru" app and inputs his name, health condition (e.g., he has back pain), and hobby (e.g., reading). Based on this information, the server generates a virtual character modeled after his late wife and displays it on the device.
[0609] Every morning, he enters his temperature, blood pressure, and other information into the app, and receives advice based on that information from a virtual character. The app also displays information about events such as book clubs held in the area, allowing him to make new friends by participating in these events.
[0610] Prompt Sentence Examples
[0611] Below are some example prompts to input to a generative AI model:
[0612] User Information:
[0613] Name: Username
[0614] Age: 75
[0615] Health condition: Back pain
[0616] Hobbies: Reading
[0617] Virtual characters to be generated:
[0618] A character modeled after the user's late wife
[0619] Based on this prompt, the generative AI model generates the most suitable virtual character based on the user's personal information and provides a wide range of support.
[0620] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0621] Step 1:
[0622] The user installs and launches the "Sobade Mimamoru" app.
[0623] Step 2:
[0624] The device displays a form for entering information.
[0625] The user enters the required information such as name, age, health status, hobbies, etc. and clicks the submit button.
[0626] Input: User-entered information about name, age, health, and hobbies.
[0627] Output: The entered user information is sent from the terminal to the server.
[0628] Step 3:
[0629] The server receives and stores the user information.
[0630] Input: User information sent from the device.
[0631] Output: User information stored in the database.
[0632] Step 4:
[0633] The server executes a generative AI model based on the received user information to generate a virtual character.
[0634] Input: Stored user information.
[0635] Data processing: User information is input into the generative AI model as a prompt sentence.
[0636] Output: The generative AI model generates a virtual character and returns the character data to the server.
[0637] Specific operation: The server processes the data (e.g., 3D model and text information) of the generated virtual character.
[0638] Step 5:
[0639] The server transmits the data of the generated virtual character to the terminal.
[0640] Input: Data of the generated virtual character.
[0641] Output: The virtual character data is sent to the device.
[0642] Step 6:
[0643] The terminal displays the virtual character on a user interface.
[0644] Input: Virtual character data sent from the server.
[0645] Output: A virtual character is displayed in the app.
[0646] Specific behavior: In some cases, animation and audio functions are also included.
[0647] Step 7:
[0648] The device displays a health check form every day.
[0649] The user enters their health status, such as temperature, blood pressure, heart rate, and mood, and clicks the submit button.
[0650] Input: User-entered health data.
[0651] Output: Health status data is sent from the device to the server.
[0652] Step 8:
[0653] The server receives the health data and analyzes it using AI.
[0654] Input: Health status data sent from the device.
[0655] Data Computing: Analyzing health data using AI models (such as TensorFlow and Scikit-learn).
[0656] Output: Health advice is generated based on the analysis results.
[0657] What it does: The AI model detects outliers and compares them with historical data to identify trends.
[0658] Step 9:
[0659] The server sends the generated health advice to the terminal.
[0660] Input: AI-generated health advice.
[0661] Output: Health advice is sent to the device.
[0662] Step 10:
[0663] The device displays health advice to the user through a virtual character.
[0664] Input: Health advice sent from the server.
[0665] Output: Health advice is displayed to the user through the virtual character UI.
[0666] Example: A virtual character gives advice such as, "Your blood pressure is a little high, so try to limit your salt intake."
[0667] Step 11:
[0668] The server collects local event information and filters it based on the user's interests.
[0669] Input: Local event information collected from the internet.
[0670] Data processing: Filtering event information based on user hobbies and interests.
[0671] Output: Recommended event information is generated.
[0672] Step 12:
[0673] The server transmits the filtered event information to the terminal.
[0674] Input: Recommended event information.
[0675] Output: Event information is sent to the terminal.
[0676] Step 13:
[0677] The terminal displays the event information to the user and accepts participation applications.
[0678] Input: Event information sent from the server.
[0679] Output: The event information is displayed in the app and the user clicks to register.
[0680] Step 14:
[0681] The terminal sends the user's participation application to the server.
[0682] Input: User's event registration information.
[0683] Output: The registration information is sent to the server.
[0684] Step 15:
[0685] The server provides the participation information to the event organizer and confirms the participation.
[0686] Input: Application information.
[0687] Output: Notify the user that their participation is confirmed.
[0688] Example: An in-app notification says, "You've been accepted into a local gardening class."
[0689] (Application example 1)
[0690] 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."
[0691] Elderly people living alone and unmarried people face challenges in managing their physical and mental health and in maintaining social connections. Welfare facilities and community centers, in particular, lack the means for users to understand their own health status and receive appropriate advice. There is also a lack of systems for providing appropriate information about local events and encouraging participation. This raises concerns that users may become increasingly socially isolated and experience a decline in their quality of life.
[0692] 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.
[0693] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using artificial intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status information, means for analyzing health data and generating advice, means for collecting local event information and recommending it to the user, means for supporting event participation, means for providing an application to be installed on a smartphone, means for automatically notifying emergency contacts, and means for supporting community activities within a facility. This enables elderly people living alone and unmarried people to maintain their daily health management and social connections and improve their quality of life.
[0694] An "information input form" is a screen or interface that allows a user to enter their own information (such as name, age, health status, hobbies, etc.).
[0695] "User information" refers to data about the user (such as name, age, health status, hobbies, etc.) and is information used by the system to provide individualized support.
[0696] "Generative AI" is an AI technology that generates appropriate virtual characters and advice based on input data.
[0697] A "virtual character" is a virtual person or character generated using artificial intelligence, which interacts with and assists the user.
[0698] A "user interface" is the screen or means of interaction that a user uses to interact with an application.
[0699] "Health data" refers to information about the user's daily health condition, such as body temperature, blood pressure, heart rate, and mood.
[0700] "Advice" is advice and suggestions regarding daily health management and lifestyle improvements generated by artificial intelligence based on health data.
[0701] "Local event information" is information about various events and activities held in the area where the user lives.
[0702] "Means to support event participation" refers to support functions for users to participate in local events (provision of event information, application procedures, etc.).
[0703] The "application installed on the smartphone" is software that runs on the smartphone and provides the functions of the present invention.
[0704] The "means for automatically notifying emergency contacts" is a function that automatically sends a notification to a pre-registered emergency contact if there is an abnormality in the user's health condition.
[0705] "Means to support community activities within the facility" refers to functions for managing activities that take place within welfare facilities and community centers and promoting user participation.
[0706] This invention is a system that supports single-person elderly people and unmarried people in managing their health and maintaining social connections on a daily basis. The configuration and operation of this system will be described below.
[0707] User registration and initial settings
[0708] First, the user launches the application installed on their smartphone and enters information such as their name, age, health condition, and hobbies into an information input form. This information is sent from the device to a server and stored. Using generative artificial intelligence, a virtual character is generated based on the input information, and the character is displayed on the user interface. The virtual character is modeled after a familiar person or family member, helping the user to feel a sense of familiarity.
[0709] Daily health management
[0710] Every day, users enter their health status (body temperature, blood pressure, heart rate, mood, etc.) into the device and send it. This health data is sent to a server and analyzed by AI. Based on the analysis results, advice for health management is generated. For example, specific advice such as "Your blood pressure is high, so try to limit your salt intake" is provided.
[0711] Supporting social connections
[0712] The server collects information about local events and recommends appropriate events based on the user's hobbies and interests. This event information is displayed on the device, allowing the user to select and register for the events they wish to attend. Furthermore, in preparation for unforeseen circumstances, the system has an emergency contact function that automatically sends a notification to registered emergency contacts if any abnormalities are detected in the user's health condition.
[0713] Specific examples
[0714] Mr. Suzuki, 70 years old, lives alone. He installed the application on his smartphone and completed the registration process. Every morning, Mr. Suzuki enters his health status into the app and receives advice based on it. He can also easily register for local walking groups and hobby classes, which has enabled him to make new friends. One day, when his health worsened, the emergency contact function was activated, and his family who live nearby were contacted, allowing for a quick response.
[0715] Prompt Sentence Examples
[0716] "On a day when 70-year-old Suzuki has a body temperature of 36.8°C, blood pressure of 135 / 80, a heart rate of 72 beats per minute, and feels normal, what should he be careful of in his daily life?"
[0717] This system will make it easier for single-person elderly people and unmarried people to manage their health and maintain social connections, which is expected to improve their quality of life.
[0718] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0719] Program processing flow
[0720] Step 1:
[0721] A user installs an application on their smartphone and opens an information input form. This form has fields for entering information such as name, age, health status, and hobbies. When the user enters all the information and clicks the "Submit" button, the input data is sent to the server via the device. Input: User information. Output: User information saved on the server.
[0722] Step 2:
[0723] The server uses artificial intelligence to generate a virtual character based on the received user information. This virtual character is modeled after the user's preferences and familiar faces. The generated character is sent from the server to the terminal and displayed on the user interface. Input: User information. Output: Displayed virtual character.
[0724] Step 3:
[0725] Every day, users enter their health status (body temperature, blood pressure, heart rate, mood, etc.) into the health check form within the application. Once they have completed the entry, they click the "Submit" button and the data is sent from the device to the server. Input: Health data. Output: Health data sent to the server.
[0726] Step 4:
[0727] The server uses AI to analyze the received health data. Data such as body temperature, blood pressure, heart rate, and mood are used for the analysis. The AI evaluates the user's health condition based on past data and a medical knowledge base, and generates appropriate advice. This advice is sent from the server to the device and conveyed to the user through a virtual character. Input: Health data. Output: Advice.
[0728] Step 5:
[0729] The server collects local event information and recommends appropriate events based on the user's hobbies and interests. Event information is sent from the server to the terminal and displayed on the user interface. When the user selects the event they want to attend and clicks the "Apply" button, participation information is sent to the server and contacted with the event organizer. Input: User's hobbies and interests. Output: Recommended event information, application to attend.
[0730] Step 6:
[0731] If an abnormality is detected based on the health data, the emergency contact function will be activated. The server will automatically send a notification to pre-registered emergency contacts. This notification will inform the user that there is an abnormality in their health condition. Input: Abnormal health data. Output: Emergency contact notification.
[0732] Step 7:
[0733] Designed for use in welfare facilities and community centers, the system provides a means to support community activities within the facility, including event management and participant health monitoring. Input: Facility event information, participant health data. Output: Event information management, participant health report.
[0734] In this way, elderly people living alone and unmarried people can improve their quality of life by managing their daily health and participating in community events.
[0735] 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.
[0736] ---
[0737] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. The system supports daily health management and participation in local events through a virtual character generated based on the user's input information. The system also incorporates an emotion engine that recognizes the user's emotions and responds accordingly.
[0738] 1. User registration and initial settings
[0739] The process begins when the user installs and launches the "Soba de Mimamoru" app. After launching the app, the device displays a form for entering user information. The user enters the necessary information, such as name, age, health condition, and hobbies, and clicks the submit button. The device then sends the entered information to the server, completing user registration. Based on the user information, the server uses generative artificial intelligence to generate a virtual character modeled after a close friend or family member, and sends the virtual character to the device for display. In addition, an emotion engine begins to operate, recognizing emotions from the user's voice and facial expressions.
[0740] 2. Daily health management
[0741] The device displays a health check form every day. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and clicks the submit button. The device then sends the entered health information to the server. The server uses AI to analyze the health data and generates advice based on it. The generated advice is sent to the device and communicated to the user through a virtual character UI. For example, the advice might be, "Your blood pressure is a little high, so try to limit your salt intake." Furthermore, an emotion engine recognizes the user's emotions and provides emotion-based advice, such as, "You seem to be feeling stressed lately. Why not try a relaxing aroma?"
[0742] 3. Supporting social connections
[0743] The server collects information about local and social events, such as walking clubs and hobby gatherings held in the neighborhood. The server sends this information to the device to recommend appropriate events based on the user's hobbies and interests. The device displays the event information, the user selects the event they wish to attend, and clicks the application button. The device sends the event participation application information to the server, and the server contacts the organizer to confirm the user's participation. This allows the user to participate in local events and build social connections. When participating in an event, the emotion engine checks whether the user is feeling anxious or nervous, and sends words of encouragement through a virtual character if necessary.
[0744] Specific examples
[0745] Mr. Tanaka, 75, had been living alone for a long time and was concerned about his physical and mental health. He installed the "Soba de Mimamoru" app and entered his name, health condition (e.g., back pain), and hobby (e.g., gardening). Based on Mr. Tanaka's information, the server generated a virtual character modeled after his late wife and displayed it on his device. Every morning, Mr. Tanaka entered his temperature and blood pressure into the app and received advice from the virtual character based on that information. The app also displayed information about local gardening classes, and by participating in these events, he was able to make new friends. Furthermore, the emotion engine recognized that Mr. Tanaka had been feeling stressed recently, and the virtual character encouraged him to "take time to relax and not push yourself too hard," helping him live a more secure life.
[0746] In this way, this invention not only enables elderly people living alone and unmarried people to manage their physical and mental health, but also enables them to form social connections, improving their quality of life (QOL). The addition of an emotion engine enables more personalized support tailored to the user's psychological state, contributing to easing feelings of loneliness and reducing stress.
[0747] ---
[0748] The processing flow will be explained below.
[0749] ---
[0750] User registration and initial settings
[0751] Step 1:
[0752] The user installs and launches the "Sobade Mimamoru" app.
[0753] Step 2:
[0754] The device displays a user information input form (name, age, health status, preferences, etc.) on the screen.
[0755] Step 3:
[0756] The user enters the required information and clicks the submit button.
[0757] Step 4:
[0758] The terminal transmits the input information to the server.
[0759] Step 5:
[0760] Based on the user's information, the server uses artificial intelligence to generate a virtual character modeled after a close friend or family member.
[0761] Step 6:
[0762] The server transmits the generated virtual character to the terminal.
[0763] Step 7:
[0764] The device displays the virtual character on the screen, and the emotion engine starts up, preparing to recognize emotions from the user's voice and facial expressions.
[0765] Daily health management
[0766] Step 1:
[0767] The device displays a daily health check form (temperature, blood pressure, heart rate, mood, etc.) on the screen.
[0768] Step 2:
[0769] The user inputs their daily health status and clicks the submit button.
[0770] Step 3:
[0771] The terminal transmits the input health information to the server.
[0772] Step 4:
[0773] The server uses AI to analyze health data and generate advice.
[0774] Step 5:
[0775] The server transmits the generated advice to the terminal.
[0776] Step 6:
[0777] The device will then give advice to the user through a virtual character UI, for example, displaying a message such as "Your blood pressure is a little high, so try to limit your salt intake."
[0778] Step 7:
[0779] The device analyzes the user's voice and facial expressions and recognizes emotions using an emotion engine.
[0780] Step 8:
[0781] The server receives data from the emotion engine, analyzes the user's emotion data, and generates emotion-based advice, such as "You seem to be stressed out lately. Why don't you try a relaxing aroma?"
[0782] Step 9:
[0783] The server transmits the generated emotion-based advice to the terminal.
[0784] Step 10:
[0785] The device conveys emotion-based advice to the user through a virtual character UI.
[0786] Supporting social connections
[0787] Step 1:
[0788] The server collects information about local and social events (for example, walking events and hobby gatherings held in the neighborhood).
[0789] Step 2:
[0790] The server selects events that the user can participate in based on the user's hobbies and interests.
[0791] Step 3:
[0792] The server transmits the selected event information to the terminal.
[0793] Step 4:
[0794] The event information received by the terminal is displayed on the screen.
[0795] Step 5:
[0796] The user checks the event information and selects the event they want to attend.
[0797] Step 6:
[0798] The user clicks the sign up button.
[0799] Step 7:
[0800] The terminal transmits the application information to the server.
[0801] Step 8:
[0802] The server contacts the event organizer to confirm the user's participation.
[0803] Step 9:
[0804] The server sends participation confirmation information to the terminal.
[0805] Step 10:
[0806] The device will notify the user of the confirmation of participation. Furthermore, if the emotion engine detects the user's anxiety or tension, it will provide an encouraging message through the virtual character.
[0807] ---
[0808] The above is the processing flow of the "Soba de Mimamoru" system, which combines an emotion engine. At each step, the system effectively manages the user's information, supports their physical and mental health, and provides social connections. The emotion engine also enables personalized support based on the user's psychological state.
[0809] Example 2
[0810] 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."
[0811] It is difficult for elderly people living alone or unmarried people to properly manage their physical and mental health and maintain social connections. Furthermore, they are prone to feeling lonely and stressed in their daily lives, which often threatens their mental health. In such situations, a system that can provide appropriate support is needed.
[0812] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[0813] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using a generation artificial intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status, means for analyzing health data and generating advice, means for collecting local event information and recommending events to the user, means for supporting event participation, means for recognizing the user's emotions from voice and facial expressions and generating a response based thereon, and means for providing additional advice and encouraging messages based on the user's emotional state, thereby enabling consistent management of the user's physical and mental health, maintaining social connections, and improving quality of life.
[0814] The "means for providing an information input form" is a mechanism that provides an interface for a user to input information such as his / her name, age, health condition, hobbies, etc.
[0815] The "means for transmitting and storing user information" is a mechanism that has the function of transmitting information entered by the user to a server and safely storing that information.
[0816] "Means for generating a virtual character using artificial intelligence" refers to a mechanism that uses artificial intelligence technology to create a virtual character based on user information.
[0817] The "means for displaying the generated virtual character on the user interface" is a mechanism for displaying the generated virtual character on the screen of a digital device.
[0818] The "means for inputting and transmitting health status" is a mechanism that allows a user to input their daily health status, such as body temperature, blood pressure, and heart rate, and transmit that information to a server.
[0819] The "means for analyzing health data and generating advice" refers to a mechanism in which the server analyzes the health data received using an AI algorithm and generates health management advice based on that data.
[0820] The "means for collecting local event information and recommending it to the user" is a mechanism by which the server collects local event information, filters it based on the user's hobbies and interests, and recommends it to the user.
[0821] The "means for supporting event participation" is a mechanism that handles the participation procedures for the event selected by the user and communicates with the organizer.
[0822] "Means for recognizing the user's emotions from their voice and facial expressions and generating a response based on that" refers to a mechanism that uses an emotion engine to analyze the user's voice and facial expressions and generates appropriate responses and advice based on the results.
[0823] The "means for providing additional advice or encouraging messages based on the user's emotional state" is a mechanism for providing additional specific advice or encouraging messages based on the user's emotional state recognized by the emotion engine.
[0824] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. This system includes the following components:
[0825] 1. The user installs and launches the application on a device such as a smartphone or tablet. After launching, the device displays a user information input form, and the user enters the required information, such as name, age, health status, and hobbies, and submits it. The device then sends the entered information to the server, completing user registration.
[0826] 2. The server uses artificial intelligence to generate a virtual character based on user information. The generated virtual character is designed based on the user's preferences and past information, and is displayed on the smartphone or tablet. It also incorporates an emotion engine that recognizes emotions from the user's voice and facial expressions, and generates responses based on the user's emotional state.
[0827] 3. As part of daily health management, the device displays a health check form, and the user enters and submits their health status information, such as body temperature, blood pressure, heart rate, and mood, each day. The device then sends the entered health information to a server. The server uses AI to analyze the health data and generates advice based on it. The generated advice is then sent to the device and communicated to the user through a virtual character. For example, advice such as "Your blood pressure is a little high, so try to limit your salt intake" is displayed. Furthermore, an emotion engine recognizes the user's emotions and provides emotion-based advice, such as "You seem to be feeling stressed lately. Why not try a relaxing aroma?"
[0828] 4. To support social connections, the server collects information about local and community events, such as walking clubs and hobby gatherings held in the neighborhood. The server then sends this information to the device to recommend appropriate events based on the user's hobbies and interests. The device displays the event information, and the user selects the event they wish to attend and clicks the application button. The device then sends the event application information to the server, which then contacts the organizer to confirm the user's participation. This allows the user to participate in local events and build social connections. When participating in an event, the emotion engine checks whether the user is feeling anxious or nervous, and sends encouraging words through a virtual character if necessary.
[0829] Specific examples
[0830] For example, consider a user named Tanaka, 75 years old. Tanaka lives alone and was concerned about his physical and mental health. He installed the AI Life Supporter and entered his name, health condition (e.g., back pain), and hobby (e.g., gardening). Based on Tanaka's information, the server generated a virtual character modeled after his late wife and displayed it on his device. Every morning, Tanaka enters his temperature and blood pressure into the app and receives advice from the virtual character based on that information. The app then displays information about local gardening classes, and Tanaka is able to make new friends by participating in the event. The emotion engine also recognizes that Tanaka has been feeling stressed recently, and the virtual character encourages him to "take time to relax and not push yourself too hard," helping him live a more secure life.
[0831] Below are some examples of prompts to input to the generative AI model.
[0832] Mr. Tanaka, 75, lives alone and is concerned about his health. He installed the "AI Life Supporter" app. After entering his information into the app, a virtual character modeled after his late wife was generated and displayed on his device. Every morning, Mr. Tanaka enters his temperature and blood pressure and receives generated advice. He also participates in a local gardening class and makes new friends. The emotion engine recognizes when Mr. Tanaka is feeling stressed, and the virtual character sends him advice on how to relax, allowing him to live a life with peace of mind.
[0833] In this way, this invention not only enables elderly people living alone and unmarried people to manage their physical and mental health, but also enables them to form social connections, improving their quality of life. The addition of an emotion engine enables more personalized support tailored to the user's psychological state, contributing to alleviating feelings of loneliness and reducing stress.
[0834] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0835] Program processing flow and specific explanation
[0836] Step 1:
[0837] The user installs the app and launches it for the first time. By launching the app, the initial setup screen is displayed. Specifically, the user downloads the app from the app store and clicks the install button. The user then taps the app icon to launch it.
[0838] Step 2:
[0839] The device displays a user information input form. The user enters information such as name, age, health condition, hobbies, etc. and submits it. Specifically, the device displays the input form on the screen and accepts input from the user. The entered information is temporarily stored within the device.
[0840] Input: Information entered by the user, such as name, age, health status, hobbies, etc.
[0841] Output: The entered user information is sent to the server in JSON format.
[0842] Step 3:
[0843] The server accumulates the received user information and generates a virtual character using generative AI. Specifically, the server stores the received user information in a database. Then, it generates a virtual character using a generative AI model, converts the data, and sends it to the device.
[0844] Input: User information (name, age, health status, hobbies, etc.)
[0845] Output: Send the generated virtual character data to the terminal
[0846] Step 4:
[0847] The terminal displays the generated virtual character on the user interface. Specifically, the terminal displays the virtual character on the screen based on the received virtual character data.
[0848] Input: Data of the generated virtual character
[0849] Output: A virtual character displayed on the user interface.
[0850] Step 5:
[0851] The device starts the emotion engine and prepares to recognize emotions from the user's voice and facial expressions. Specifically, the device uses a microphone and camera to collect voice and facial expression data and inputs it into the emotion engine in real time. The emotion engine analyzes this data and determines the user's emotions.
[0852] Input: User voice and facial expression data
[0853] Output: Recognized user emotion data
[0854] Step 6:
[0855] The device presents a health check form to the user every day. The user inputs their health status, such as body temperature, blood pressure, heart rate, and mood, and submits it. Specifically, the device displays the health check form at a specific time every day and waits for input from the user. The user inputs the data and clicks the submit button.
[0856] Input: User-entered health data such as temperature, blood pressure, heart rate, and mood
[0857] Output: Send the input health data to the server in JSON format
[0858] Step 7:
[0859] The server uses AI to analyze the health data it receives and generate appropriate advice. Specifically, the server stores the received health data in a database and analyzes the data using an AI algorithm. It generates advice based on the analysis results and sends the data to the device.
[0860] Input: User health data (temperature, blood pressure, heart rate, mood, etc.)
[0861] Output: Sends generated advice data to the terminal
[0862] Step 8:
[0863] The device communicates advice to the user through the virtual character. Specifically, the device displays the received advice data in an easy-to-understand manner for the user through the virtual character's UI.
[0864] Input: Data for generated advice
[0865] Output: Advice displayed through a virtual character
[0866] Step 9:
[0867] The emotion engine checks the user's emotions and generates additional advice or encouraging messages based on the emotions. Specifically, the emotion engine re-analyzes the user's voice and facial expression data to detect signs of stress or anxiety. Based on the results, it generates additional advice or encouraging messages and sends them to the device.
[0868] Input: Emotion data analyzed from voice and facial expressions
[0869] Output: Any additional advice or encouragement messages generated are sent to the terminal.
[0870] Step 10:
[0871] The server collects local event information. Specifically, the server uses APIs from local governments and community centers to collect event information and stores it in a database. The collected information is then filtered based on the user's hobbies and interests.
[0872] Input: Local event information
[0873] Output: Sends filtered event information to the terminal
[0874] Step 11:
[0875] The terminal displays the event information and the user selects an event to participate in. Specifically, the terminal displays the filtered event information on a user interface and allows the user to select the event they want to participate in. The user clicks the participate button.
[0876] Input: Filtered event information
[0877] Output: Sends the user's selected event participation information to the server
[0878] Step 12:
[0879] The server sends the application information for event participation to the organizer and confirms the participation. Specifically, the server notifies the organizer of the received user's participation request and waits for confirmation from the organizer. Once confirmation is received, the server notifies the user of the participation information.
[0880] Input: Event participation information selected by the user
[0881] Output: Send user participation confirmation data to the terminal
[0882] Step 13:
[0883] The emotion engine checks the user's emotions before participating in the event, and if they feel anxious or nervous, it sends encouraging words. Specifically, the emotion engine re-analyzes the user's voice and facial expressions just before participating in the event, and if stress or anxiety is detected, it generates an encouraging message and sends it to the device.
[0884] Input: Emotion data analyzed from voice and facial expressions
[0885] Output: Generated encouraging message sent to terminal
[0886] (Application example 2)
[0887] 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."
[0888] Elderly people and single-person households face challenges in managing their physical and mental health and maintaining social connections, and it is also challenging for them to receive appropriate information and support while in physical stores. In particular, there is a lack of appropriate responses and support tailored to the user's emotional state, which can lead to feelings of loneliness and increased stress. The challenge is to solve these problems and enable elderly people and single-person households to lead fulfilling lives.
[0889] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.
[0890] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using a generation artificial intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status, means for analyzing health data and generating advice, means for collecting local event information and recommending it to the user, means for supporting event participation, means for providing in-store navigation information through the smart glasses, and means for recognizing emotions using an emotion engine and generating responses. This allows users to receive comprehensive support during activities in physical stores while maintaining their health management and social connections.
[0891] "Information input form" refers to an interface for users to input their own information.
[0892] "User Information" refers to data about a user, such as the user's name, age, health status, hobbies, etc.
[0893] "Generative AI" refers to AI technology for generating virtual characters based on user information.
[0894] "Virtual character" refers to a fictitious character generated based on user information.
[0895] "User interface" refers to the interface through which a user interacts with a system.
[0896] "Health status" refers to health-related data such as a user's temperature, blood pressure, heart rate, and mood.
[0897] "Health data" refers to information about a user's health condition entered by the user.
[0898] "Advice" refers to advice generated based on the analyzed health data.
[0899] "Local event information" refers to information about events held in the user's local area.
[0900] "Event participation" refers to the process of helping users participate in local events.
[0901] "Smart glasses" refers to wearable devices used to display information.
[0902] "In-store navigation information" refers to information necessary for a user to navigate within a physical store.
[0903] "Emotion engine" refers to technology that recognizes a user's emotions and generates a response accordingly.
[0904] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. The system aims to enrich users' lives in brick-and-mortar stores by using smart glasses and other wearable devices.
[0905] 1. User registration and initial settings
[0906] The process begins when the user puts on the smart glasses and launches the application. After launching the application, the smart glasses display a form for entering user information. The user enters the necessary information, such as name, age, health status, and hobbies, and submits it. This sends the user information to the server and stores it.
[0907] Using generative artificial intelligence, the server generates a virtual character based on the user's information. This virtual character is modeled after a loved one or family member, and the generated character is displayed on the smart glasses' display. Furthermore, an emotion engine is activated to recognize emotions from the user's voice and facial expressions.
[0908] 2. Daily health management
[0909] The smart glasses display a health check form every morning. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and sends it to the server. The server uses AI to analyze the collected health data and generates advice based on it. The advice is then sent to the smart glasses, where a virtual character delivers it to the user via voice.
[0910] 3. In-store support
[0911] When a user visits a physical store, the smart glasses provide navigation information within the store. When the user specifies the location they want to go to, the server calculates the route and displays it on the smart glasses' display. A virtual character then gives voice instructions, such as "Turn left at the next corner."
[0912] 4. Supporting social connections
[0913] The server collects local event information and recommends events based on the user's hobbies and interests. Users can check the event information through the smart glasses, select the events they want to attend, and sign up. The server then contacts the organizers to confirm the user's participation. In addition, the emotion engine checks whether the user is feeling anxious or nervous, and sends encouraging words through the virtual character as needed.
[0914] Hardware and Software Use
[0915] Smart glasses (wearable devices): Used for user interface and data entry / display.
[0916] Server: Performs back-end processing such as accumulating user information, generating virtual characters, analyzing health data, calculating route information, and operating the emotion engine.
[0917] Emotion engine: Software that recognizes emotions from the user's voice and facial expressions and generates a response.
[0918] Specific examples
[0919] Consider a scenario in which a 75-year-old user wears smart glasses and goes to a supermarket. First, the user enters the store and instructs the smart glasses to "go to the vegetable section." The server calculates the route within the store and sends that information to the smart glasses. Navigation information is displayed on the smart glasses' display, and a virtual character provides voice guidance such as "Turn left at the next corner." While the virtual character is displayed, the emotion engine analyzes the user's facial expressions, and if it detects fatigue, it will say, "Let's take a short break."
[0920] Prompt Sentence Examples
[0921] Entered data:
[0922] Name: User
[0923] Age: 75
[0924] Health condition: High blood pressure
[0925] Hobbies: Gardening
[0926] Tasks to be performed:
[0927] 1. Health data collection and analysis
[0928] 2. In-store navigation
[0929] 3. Providing event information
[0930] 4. Emotion-based response generation
[0931] Please provide the following navigation steps:
[0932] "Turn right at the next door."
[0933] This concludes the description of the embodiment of the present invention, which allows elderly people and single-person households to receive comprehensive support while they are active in a physical store, while managing their health and maintaining social connections.
[0934] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0935] Step 1:
[0936] The user puts on the smart glasses and starts the application. The smart glasses display a user information input form, and the user enters the necessary information, such as name, age, health status, and hobbies. The input data is sent to the server and stored.
[0937] Input: User information (name, age, health status, hobbies)
[0938] Output: User information stored on the server
[0939] Step 2:
[0940] The server uses artificial intelligence to generate a virtual character based on the input user information. The generated virtual character is modeled after a close friend or family member, and the data of this virtual character is sent to the smart glasses and displayed to the user.
[0941] Input: User information
[0942] Output: Virtual character data
[0943] Step 3:
[0944] The emotion engine is activated and recognizes emotions from the user's voice and facial expressions. The emotion engine uses the smart glasses' camera and microphone to capture the user's real-time facial expressions and voice, and analyzes emotions based on them.
[0945] Input: User's voice and facial expression data
[0946] Output: Parsed emotion results
[0947] Step 4:
[0948] The smart glasses display a health check form every morning. Users enter their health status, such as body temperature, blood pressure, heart rate, and mood, and send it to a server. The server then uses AI to analyze the collected health data and generate advice based on it.
[0949] Input: User's health status (temperature, blood pressure, heart rate, mood)
[0950] Output: Analysis results and advice
[0951] Step 5:
[0952] The generated advice is sent to the smart glasses, where a virtual character will give it to the user via voice. For example, specific advice such as "Your blood pressure is high, so try to limit your salt intake" is displayed.
[0953] Input: Analysis results and advice
[0954] Output: Voice advice from a virtual character
[0955] Step 6:
[0956] When a user visits a physical store, the smart glasses provide navigation information within the store. When the user specifies the location they want to go to, the server calculates the route and displays it on the smart glasses' display. A virtual character then gives voice instructions, such as "Turn left at the next corner."
[0957] Input: Specify destination
[0958] Output: Navigation information
[0959] Step 7:
[0960] The server collects local event information and recommends events based on the user's hobbies and interests. Users can check the event information through the smart glasses, select the event they want to attend, and register. The server then contacts the organizer to confirm the user's participation.
[0961] Input: Hobbies and interests, local event information
[0962] Output: Recommended event information and participation confirmation
[0963] Step 8:
[0964] The emotion engine checks whether the user is feeling anxious or nervous. If necessary, the virtual character will offer words of encouragement. For example, it will provide advice based on the user's emotions, such as, "You seem to be feeling stressed lately. Why don't you try a relaxing aroma?"
[0965] Input: User emotion data
[0966] Output: Emotion-based response
[0967] The above are the specific processing steps of the system that realizes the application example.
[0968] 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.
[0969] 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.
[0970] 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.
[0971] [Third embodiment]
[0972] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.
[0973] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.
[0974] 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).
[0975] 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.
[0976] 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.
[0977] 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).
[0978] 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.
[0979] 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.
[0980] 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.
[0981] 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.
[0982] 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.
[0983] 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."
[0984] ---
[0985] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. In this system, users enter their own information into an information input form, and the system supports daily health management and participation in local events through a virtual character generated based on that information.
[0986] 1. User registration and initial settings
[0987] The process begins when the user installs and launches the "Soba de Mimamoru" app. After launching the app, the device displays a form for entering user information. The user enters the necessary information, such as name, age, health condition, and hobbies, and clicks the submit button. The device then sends the entered information to the server, completing user registration. Based on the user information, the server uses generative artificial intelligence to generate a virtual character modeled after a close friend or family member, and sends the virtual character to the device for display.
[0988] 2. Daily health management
[0989] The device displays a health check form every day. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and clicks the submit button. The device then sends the entered health information to the server. The server uses AI to analyze the health data and generates advice based on it. The advice generated is sent to the device and communicated to the user through the virtual character's UI. For example, the advice might be, "Your blood pressure is a little high, so try to limit your salt intake."
[0990] 3. Supporting social connections
[0991] The server collects information about local and social events, such as nearby walking clubs and hobby gatherings. The server sends this information to the device to recommend appropriate events based on the user's hobbies and interests. The device displays the event information, and the user selects the event they wish to attend and clicks the application button. The device then sends the application information for the event to the server, which contacts the organizer to confirm the user's participation. This allows the user to participate in local events and build social connections.
[0992] Specific examples
[0993] Mr. Tanaka, 75, had been living alone for a long time and was concerned about his physical and mental health. He installed the "Soba de Mimamoru" app and entered his name, health condition (e.g., back pain), and hobby (e.g., gardening). Based on Mr. Tanaka's information, the server generated a virtual character modeled after his late wife and displayed it on his device. Every morning, Mr. Tanaka entered his body temperature and blood pressure into the app, and received advice based on that information from the virtual character. The app also displayed information about local gardening classes, allowing Mr. Tanaka to make new friends by participating in these events.
[0994] In this way, this invention not only enables elderly people living alone and unmarried people to manage their physical and mental health, but also enables them to have social connections, thereby improving their quality of life (QOL).
[0995] The processing flow will be explained below.
[0996] ---
[0997] User registration and initial settings
[0998] Step 1:
[0999] The user installs and launches the "Sobade Mimamoru" app.
[1000] Step 2:
[1001] The device displays a user information input form (name, age, health status, preferences, etc.) on the screen.
[1002] Step 3:
[1003] The user enters the required information and clicks the submit button.
[1004] Step 4:
[1005] The terminal transmits the input information to the server.
[1006] Step 5:
[1007] Based on the user's information, the server uses artificial intelligence to generate a virtual character modeled after a close friend or family member.
[1008] Step 6:
[1009] The server transmits the generated virtual character to the terminal.
[1010] Step 7:
[1011] The terminal displays the transmitted virtual character on the screen, allowing the user to start a conversation with the virtual character.
[1012] Daily health management
[1013] Step 1:
[1014] The device displays a daily health check form on the screen (e.g., temperature, blood pressure, heart rate, mood, etc.).
[1015] Step 2:
[1016] The user inputs their daily health status and clicks the submit button.
[1017] Step 3:
[1018] The terminal transmits the input health information to the server.
[1019] Step 4:
[1020] The server uses AI to analyze health data and generate advice.
[1021] Step 5:
[1022] The server transmits the generated advice to the terminal.
[1023] Step 6:
[1024] The device will then give advice to the user through a virtual character UI, for example, displaying a message such as "Your blood pressure is a little high, so try to limit your salt intake."
[1025] Supporting social connections
[1026] Step 1:
[1027] The server collects information about local and social events (for example, walking events and hobby gatherings held in the neighborhood).
[1028] Step 2:
[1029] The server selects events that the user can participate in based on the user's hobbies and interests.
[1030] Step 3:
[1031] The server transmits the selected event information to the terminal.
[1032] Step 4:
[1033] The event information received by the terminal is displayed on the screen.
[1034] Step 5:
[1035] The user checks the event information and selects the event they want to attend.
[1036] Step 6:
[1037] The user clicks the sign up button.
[1038] Step 7:
[1039] The terminal transmits the application information to the server.
[1040] Step 8:
[1041] The server contacts the event organizer to confirm the user's participation.
[1042] Step 9:
[1043] The server sends participation confirmation information to the terminal.
[1044] Step 10:
[1045] The terminal notifies the user of the participation confirmation information.
[1046] ---
[1047] This concludes the processing flow of the "Soba de Mimamoru" system. At each step, the system effectively manages the user's information, supports their physical and mental health, and provides social connections.
[1048] Example 1
[1049] 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."
[1050] In modern society, elderly people living alone and unmarried people face challenges in managing their physical and mental health and maintaining social connections. This problem, particularly for the elderly, increases feelings of loneliness and health risks, leading to a decline in quality of life (QOL). Furthermore, low participation in local events and social activities also contributes to social isolation. Therefore, there is a need for a system that allows these people to easily manage their health information, receive appropriate advice, and form social connections.
[1051] 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.
[1052] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using generative intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status, means for analyzing health data and generating advice, means for collecting local event information and recommending it to users, means for supporting event participation, means for providing daily health data analysis results using AI technology, and means for conveying advice to users through the generated virtual character, thereby enabling users to manage their physical and mental health and build social connections.
[1053] An "information input form" is an online form where a user enters personal information such as name, age, health status, hobbies, etc.
[1054] "User information" refers to personal data such as name, age, health status, and hobbies entered by the user in the information input form.
[1055] "Generative intelligence" refers to artificial intelligence technology that uses a generative AI model (e.g., GPT-4) to automatically generate virtual characters based on user input data.
[1056] A "virtual character" is a 3D or 2D digital character created to resemble a close friend or family member based on the user's personal information and past experiences.
[1057] "User interface" refers to the application screen or digital interface through which a user interacts with a virtual character.
[1058] "Health Status" refers to the user's daily health data, such as temperature, blood pressure, heart rate, and mood.
[1059] "Health data" refers to information entered by the user, such as body temperature, blood pressure, heart rate, and mood.
[1060] "Advice" refers to specific health management instructions or suggestions provided to the user based on the results of analyzing the health data.
[1061] "Local event information" refers to event information such as local walking clubs and hobby gatherings that is automatically collected by the server.
[1062] "Means for using generative intelligence" means the ability to automatically generate virtual characters using a generative AI model.
[1063] "Means to support event participation" refers to a function that supports users in applying to participate in local events.
[1064] The present invention is a system that provides an "AI life supporter" that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. The details are explained below.
[1065] Configuration and Hardware / Software
[1066] The system operates using a user device (such as a smartphone), a server, and a generative AI model.
[1067] Device: User device such as a smartphone or tablet. Install and use the Android or iOS app "Soba de Mimamoru."
[1068] Server: A high-performance cloud server that runs generative AI models (e.g., OpenAI's GPT-4) and AI libraries for health data analysis (e.g., Python's TensorFlow and Scikit-learn).
[1069] Generative AI model: Used to generate a virtual character based on user information. It receives a prompt as input and generates a virtual character.
[1070] Program processing and data manipulation
[1071] 1. User registration and initial settings
[1072] The user installs and launches the "Soba de Mimamoru" app. After launching the app, an information input form is displayed, and the user enters the necessary information, such as name, age, health status, and hobbies. This information is then sent from the device to the server.
[1073] 2. Virtual Character Generation
[1074] The server uses a generative AI model to generate a virtual character based on the received user information. This virtual character is modeled after a person close to the user or their family, and is designed to feel familiar to the user. The generated character is sent from the server to the device and displayed within the app.
[1075] 3. Daily health management
[1076] The device displays a health check form every day. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and clicks the submit button. The device then sends the entered health information to the server. The server uses AI to analyze the health data and generates and sends advice to the device. The advice is then conveyed to the user through a virtual character.
[1077] 4. Supporting social connections
[1078] The server collects information about local and social events and recommends appropriate events based on the user's interests. This information is sent to the device, and the user can choose to participate. When a user registers to participate in an event, the device sends the information to the server, and the server provides the participation information to the event organizer.
[1079] Specific examples
[1080] Suppose a 75-year-old user has been living alone for a long time and is concerned about his health. He installs the "Soba de Mimamoru" app and inputs his name, health condition (e.g., he has back pain), and hobby (e.g., reading). Based on this information, the server generates a virtual character modeled after his late wife and displays it on the device.
[1081] Every morning, he enters his temperature, blood pressure, and other information into the app, and receives advice based on that information from a virtual character. The app also displays information about events such as book clubs held in the area, allowing him to make new friends by participating in these events.
[1082] Prompt Sentence Examples
[1083] Below are some example prompts to input to a generative AI model:
[1084] User Information:
[1085] Name: Username
[1086] Age: 75
[1087] Health condition: Back pain
[1088] Hobbies: Reading
[1089] Virtual characters to be generated:
[1090] A character modeled after the user's late wife
[1091] Based on this prompt, the generative AI model generates the most suitable virtual character based on the user's personal information and provides a wide range of support.
[1092] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1093] Step 1:
[1094] The user installs and launches the "Sobade Mimamoru" app.
[1095] Step 2:
[1096] The device displays a form for entering information.
[1097] The user enters the required information such as name, age, health status, hobbies, etc. and clicks the submit button.
[1098] Input: User-entered information about name, age, health, and hobbies.
[1099] Output: The entered user information is sent from the terminal to the server.
[1100] Step 3:
[1101] The server receives and stores the user information.
[1102] Input: User information sent from the device.
[1103] Output: User information stored in the database.
[1104] Step 4:
[1105] The server executes a generative AI model based on the received user information to generate a virtual character.
[1106] Input: Stored user information.
[1107] Data processing: User information is input into the generative AI model as a prompt sentence.
[1108] Output: The generative AI model generates a virtual character and returns the character data to the server.
[1109] Specific operation: The server processes the data (e.g., 3D model and text information) of the generated virtual character.
[1110] Step 5:
[1111] The server transmits the data of the generated virtual character to the terminal.
[1112] Input: Data of the generated virtual character.
[1113] Output: The virtual character data is sent to the device.
[1114] Step 6:
[1115] The terminal displays the virtual character on a user interface.
[1116] Input: Virtual character data sent from the server.
[1117] Output: A virtual character is displayed in the app.
[1118] Specific behavior: In some cases, animation and audio functions are also included.
[1119] Step 7:
[1120] The device displays a health check form every day.
[1121] The user enters their health status, such as temperature, blood pressure, heart rate, and mood, and clicks the submit button.
[1122] Input: User-entered health data.
[1123] Output: Health status data is sent from the device to the server.
[1124] Step 8:
[1125] The server receives the health data and analyzes it using AI.
[1126] Input: Health status data sent from the device.
[1127] Data Computing: Analyzing health data using AI models (such as TensorFlow and Scikit-learn).
[1128] Output: Health advice is generated based on the analysis results.
[1129] What it does: The AI model detects outliers and compares them with historical data to identify trends.
[1130] Step 9:
[1131] The server sends the generated health advice to the terminal.
[1132] Input: AI-generated health advice.
[1133] Output: Health advice is sent to the device.
[1134] Step 10:
[1135] The device displays health advice to the user through a virtual character.
[1136] Input: Health advice sent from the server.
[1137] Output: Health advice is displayed to the user through the virtual character UI.
[1138] Example: A virtual character gives advice such as, "Your blood pressure is a little high, so try to limit your salt intake."
[1139] Step 11:
[1140] The server collects local event information and filters it based on the user's interests.
[1141] Input: Local event information collected from the internet.
[1142] Data processing: Filtering event information based on user hobbies and interests.
[1143] Output: Recommended event information is generated.
[1144] Step 12:
[1145] The server transmits the filtered event information to the terminal.
[1146] Input: Recommended event information.
[1147] Output: Event information is sent to the terminal.
[1148] Step 13:
[1149] The terminal displays the event information to the user and accepts participation applications.
[1150] Input: Event information sent from the server.
[1151] Output: The event information is displayed in the app and the user clicks to register.
[1152] Step 14:
[1153] The terminal sends the user's participation application to the server.
[1154] Input: User's event registration information.
[1155] Output: The registration information is sent to the server.
[1156] Step 15:
[1157] The server provides the participation information to the event organizer and confirms the participation.
[1158] Input: Application information.
[1159] Output: Notify the user that their participation is confirmed.
[1160] Example: An in-app notification says, "You've been accepted into a local gardening class."
[1161] (Application example 1)
[1162] 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."
[1163] Elderly people living alone and unmarried people face challenges in managing their physical and mental health and in maintaining social connections. Welfare facilities and community centers, in particular, lack the means for users to understand their own health status and receive appropriate advice. There is also a lack of systems for providing appropriate information about local events and encouraging participation. This raises concerns that users may become increasingly socially isolated and experience a decline in their quality of life.
[1164] 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.
[1165] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using artificial intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status information, means for analyzing health data and generating advice, means for collecting local event information and recommending it to the user, means for supporting event participation, means for providing an application to be installed on a smartphone, means for automatically notifying emergency contacts, and means for supporting community activities within a facility. This enables elderly people living alone and unmarried people to maintain their daily health management and social connections and improve their quality of life.
[1166] An "information input form" is a screen or interface that allows a user to enter their own information (such as name, age, health status, hobbies, etc.).
[1167] "User information" refers to data about the user (such as name, age, health status, hobbies, etc.) and is information used by the system to provide individualized support.
[1168] "Generative AI" is an AI technology that generates appropriate virtual characters and advice based on input data.
[1169] A "virtual character" is a virtual person or character generated using artificial intelligence, which interacts with and assists the user.
[1170] A "user interface" is the screen or means of interaction that a user uses to interact with an application.
[1171] "Health data" refers to information about the user's daily health condition, such as body temperature, blood pressure, heart rate, and mood.
[1172] "Advice" is advice and suggestions regarding daily health management and lifestyle improvements generated by artificial intelligence based on health data.
[1173] "Local event information" is information about various events and activities held in the area where the user lives.
[1174] "Means to support event participation" refers to support functions for users to participate in local events (provision of event information, application procedures, etc.).
[1175] The "application installed on the smartphone" is software that runs on the smartphone and provides the functions of the present invention.
[1176] The "means for automatically notifying emergency contacts" is a function that automatically sends a notification to a pre-registered emergency contact if there is an abnormality in the user's health condition.
[1177] "Means to support community activities within the facility" refers to functions for managing activities that take place within welfare facilities and community centers and promoting user participation.
[1178] This invention is a system that supports single-person elderly people and unmarried people in managing their health and maintaining social connections on a daily basis. The configuration and operation of this system will be described below.
[1179] User registration and initial settings
[1180] First, the user launches the application installed on their smartphone and enters information such as their name, age, health condition, and hobbies into an information input form. This information is sent from the device to a server and stored. Using generative artificial intelligence, a virtual character is generated based on the input information, and the character is displayed on the user interface. The virtual character is modeled after a familiar person or family member, helping the user to feel a sense of familiarity.
[1181] Daily health management
[1182] Every day, users enter their health status (body temperature, blood pressure, heart rate, mood, etc.) into the device and send it. This health data is sent to a server and analyzed by AI. Based on the analysis results, advice for health management is generated. For example, specific advice such as "Your blood pressure is high, so try to limit your salt intake" is provided.
[1183] Supporting social connections
[1184] The server collects information about local events and recommends appropriate events based on the user's hobbies and interests. This event information is displayed on the device, allowing the user to select and register for the events they wish to attend. Furthermore, in preparation for unforeseen circumstances, the system has an emergency contact function that automatically sends a notification to registered emergency contacts if any abnormalities are detected in the user's health condition.
[1185] Specific examples
[1186] Mr. Suzuki, 70 years old, lives alone. He installed the application on his smartphone and completed the registration process. Every morning, Mr. Suzuki enters his health status into the app and receives advice based on it. He can also easily register for local walking groups and hobby classes, which has enabled him to make new friends. One day, when his health worsened, the emergency contact function was activated, and his family who live nearby were contacted, allowing for a quick response.
[1187] Prompt Sentence Examples
[1188] "On a day when 70-year-old Suzuki has a body temperature of 36.8°C, blood pressure of 135 / 80, a heart rate of 72 beats per minute, and feels normal, what should he be careful of in his daily life?"
[1189] This system will make it easier for single-person elderly people and unmarried people to manage their health and maintain social connections, which is expected to improve their quality of life.
[1190] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1191] Program processing flow
[1192] Step 1:
[1193] A user installs an application on their smartphone and opens an information input form. This form has fields for entering information such as name, age, health status, and hobbies. When the user enters all the information and clicks the "Submit" button, the input data is sent to the server via the device. Input: User information. Output: User information saved on the server.
[1194] Step 2:
[1195] The server uses artificial intelligence to generate a virtual character based on the received user information. This virtual character is modeled after the user's preferences and familiar faces. The generated character is sent from the server to the terminal and displayed on the user interface. Input: User information. Output: Displayed virtual character.
[1196] Step 3:
[1197] Every day, users enter their health status (body temperature, blood pressure, heart rate, mood, etc.) into the health check form within the application. Once they have completed the entry, they click the "Submit" button and the data is sent from the device to the server. Input: Health data. Output: Health data sent to the server.
[1198] Step 4:
[1199] The server uses AI to analyze the received health data. Data such as body temperature, blood pressure, heart rate, and mood are used for the analysis. The AI evaluates the user's health condition based on past data and a medical knowledge base, and generates appropriate advice. This advice is sent from the server to the device and conveyed to the user through a virtual character. Input: Health data. Output: Advice.
[1200] Step 5:
[1201] The server collects local event information and recommends appropriate events based on the user's hobbies and interests. Event information is sent from the server to the terminal and displayed on the user interface. When the user selects the event they want to attend and clicks the "Apply" button, participation information is sent to the server and contacted with the event organizer. Input: User's hobbies and interests. Output: Recommended event information, application to attend.
[1202] Step 6:
[1203] If an abnormality is detected based on the health data, the emergency contact function will be activated. The server will automatically send a notification to pre-registered emergency contacts. This notification will inform the user that there is an abnormality in their health condition. Input: Abnormal health data. Output: Emergency contact notification.
[1204] Step 7:
[1205] Designed for use in welfare facilities and community centers, the system provides a means to support community activities within the facility, including event management and participant health monitoring. Input: Facility event information, participant health data. Output: Event information management, participant health report.
[1206] In this way, elderly people living alone and unmarried people can improve their quality of life by managing their daily health and participating in community events.
[1207] 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.
[1208] ---
[1209] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. The system supports daily health management and participation in local events through a virtual character generated based on the user's input information. The system also incorporates an emotion engine that recognizes the user's emotions and responds accordingly.
[1210] 1. User registration and initial settings
[1211] The process begins when the user installs and launches the "Soba de Mimamoru" app. After launching the app, the device displays a form for entering user information. The user enters the necessary information, such as name, age, health condition, and hobbies, and clicks the submit button. The device then sends the entered information to the server, completing user registration. Based on the user information, the server uses generative artificial intelligence to generate a virtual character modeled after a close friend or family member, and sends the virtual character to the device for display. In addition, an emotion engine begins to operate, recognizing emotions from the user's voice and facial expressions.
[1212] 2. Daily health management
[1213] The device displays a health check form every day. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and clicks the submit button. The device then sends the entered health information to the server. The server uses AI to analyze the health data and generates advice based on it. The generated advice is sent to the device and communicated to the user through a virtual character UI. For example, the advice might be, "Your blood pressure is a little high, so try to limit your salt intake." Furthermore, an emotion engine recognizes the user's emotions and provides emotion-based advice, such as, "You seem to be feeling stressed lately. Why not try a relaxing aroma?"
[1214] 3. Supporting social connections
[1215] The server collects information about local and social events, such as walking clubs and hobby gatherings held in the neighborhood. The server sends this information to the device to recommend appropriate events based on the user's hobbies and interests. The device displays the event information, the user selects the event they wish to attend, and clicks the application button. The device sends the event participation application information to the server, and the server contacts the organizer to confirm the user's participation. This allows the user to participate in local events and build social connections. When participating in an event, the emotion engine checks whether the user is feeling anxious or nervous, and sends words of encouragement through a virtual character if necessary.
[1216] Specific examples
[1217] Mr. Tanaka, 75, had been living alone for a long time and was concerned about his physical and mental health. He installed the "Soba de Mimamoru" app and entered his name, health condition (e.g., back pain), and hobby (e.g., gardening). Based on Mr. Tanaka's information, the server generated a virtual character modeled after his late wife and displayed it on his device. Every morning, Mr. Tanaka entered his temperature and blood pressure into the app and received advice from the virtual character based on that information. The app also displayed information about local gardening classes, and by participating in these events, he was able to make new friends. Furthermore, the emotion engine recognized that Mr. Tanaka had been feeling stressed recently, and the virtual character encouraged him to "take time to relax and not push yourself too hard," helping him live a more secure life.
[1218] In this way, this invention not only enables elderly people living alone and unmarried people to manage their physical and mental health, but also enables them to form social connections, improving their quality of life (QOL). The addition of an emotion engine enables more personalized support tailored to the user's psychological state, contributing to easing feelings of loneliness and reducing stress.
[1219] ---
[1220] The processing flow will be explained below.
[1221] ---
[1222] User registration and initial settings
[1223] Step 1:
[1224] The user installs and launches the "Sobade Mimamoru" app.
[1225] Step 2:
[1226] The device displays a user information input form (name, age, health status, preferences, etc.) on the screen.
[1227] Step 3:
[1228] The user enters the required information and clicks the submit button.
[1229] Step 4:
[1230] The terminal transmits the input information to the server.
[1231] Step 5:
[1232] Based on the user's information, the server uses artificial intelligence to generate a virtual character modeled after a close friend or family member.
[1233] Step 6:
[1234] The server transmits the generated virtual character to the terminal.
[1235] Step 7:
[1236] The device displays the virtual character on the screen, and the emotion engine starts up, preparing to recognize emotions from the user's voice and facial expressions.
[1237] Daily health management
[1238] Step 1:
[1239] The device displays a daily health check form (temperature, blood pressure, heart rate, mood, etc.) on the screen.
[1240] Step 2:
[1241] The user inputs their daily health status and clicks the submit button.
[1242] Step 3:
[1243] The terminal transmits the input health information to the server.
[1244] Step 4:
[1245] The server uses AI to analyze health data and generate advice.
[1246] Step 5:
[1247] The server transmits the generated advice to the terminal.
[1248] Step 6:
[1249] The device will then give advice to the user through a virtual character UI, for example, displaying a message such as "Your blood pressure is a little high, so try to limit your salt intake."
[1250] Step 7:
[1251] The device analyzes the user's voice and facial expressions and recognizes emotions using an emotion engine.
[1252] Step 8:
[1253] The server receives data from the emotion engine, analyzes the user's emotion data, and generates emotion-based advice, such as "You seem to be stressed out lately. Why don't you try a relaxing aroma?"
[1254] Step 9:
[1255] The server transmits the generated emotion-based advice to the terminal.
[1256] Step 10:
[1257] The device conveys emotion-based advice to the user through a virtual character UI.
[1258] Supporting social connections
[1259] Step 1:
[1260] The server collects information about local and social events (for example, walking events and hobby gatherings held in the neighborhood).
[1261] Step 2:
[1262] The server selects events that the user can participate in based on the user's hobbies and interests.
[1263] Step 3:
[1264] The server transmits the selected event information to the terminal.
[1265] Step 4:
[1266] The event information received by the terminal is displayed on the screen.
[1267] Step 5:
[1268] The user checks the event information and selects the event they want to attend.
[1269] Step 6:
[1270] The user clicks the sign up button.
[1271] Step 7:
[1272] The terminal transmits the application information to the server.
[1273] Step 8:
[1274] The server contacts the event organizer to confirm the user's participation.
[1275] Step 9:
[1276] The server sends participation confirmation information to the terminal.
[1277] Step 10:
[1278] The device will notify the user of the confirmation of participation. Furthermore, if the emotion engine detects the user's anxiety or tension, it will provide an encouraging message through the virtual character.
[1279] ---
[1280] The above is the processing flow of the "Soba de Mimamoru" system, which combines an emotion engine. At each step, the system effectively manages the user's information, supports their physical and mental health, and provides social connections. The emotion engine also enables personalized support based on the user's psychological state.
[1281] Example 2
[1282] 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."
[1283] It is difficult for elderly people living alone or unmarried people to properly manage their physical and mental health and maintain social connections. Furthermore, they are prone to feeling lonely and stressed in their daily lives, which often threatens their mental health. In such situations, a system that can provide appropriate support is needed.
[1284] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[1285] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using a generation artificial intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status, means for analyzing health data and generating advice, means for collecting local event information and recommending events to the user, means for supporting event participation, means for recognizing the user's emotions from voice and facial expressions and generating a response based thereon, and means for providing additional advice and encouraging messages based on the user's emotional state, thereby enabling consistent management of the user's physical and mental health, maintaining social connections, and improving quality of life.
[1286] The "means for providing an information input form" is a mechanism that provides an interface for a user to input information such as his / her name, age, health condition, hobbies, etc.
[1287] The "means for transmitting and storing user information" is a mechanism that has the function of transmitting information entered by the user to a server and safely storing that information.
[1288] "Means for generating a virtual character using artificial intelligence" refers to a mechanism that uses artificial intelligence technology to create a virtual character based on user information.
[1289] The "means for displaying the generated virtual character on the user interface" is a mechanism for displaying the generated virtual character on the screen of a digital device.
[1290] The "means for inputting and transmitting health status" is a mechanism that allows a user to input their daily health status, such as body temperature, blood pressure, and heart rate, and transmit that information to a server.
[1291] The "means for analyzing health data and generating advice" refers to a mechanism in which the server analyzes the health data received using an AI algorithm and generates health management advice based on that data.
[1292] The "means for collecting local event information and recommending it to the user" is a mechanism by which the server collects local event information, filters it based on the user's hobbies and interests, and recommends it to the user.
[1293] The "means for supporting event participation" is a mechanism that handles the participation procedures for the event selected by the user and communicates with the organizer.
[1294] "Means for recognizing the user's emotions from their voice and facial expressions and generating a response based on that" refers to a mechanism that uses an emotion engine to analyze the user's voice and facial expressions and generates appropriate responses and advice based on the results.
[1295] The "means for providing additional advice or encouraging messages based on the user's emotional state" is a mechanism for providing additional specific advice or encouraging messages based on the user's emotional state recognized by the emotion engine.
[1296] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. This system includes the following components:
[1297] 1. The user installs and launches the application on a device such as a smartphone or tablet. After launching, the device displays a user information input form, and the user enters the required information, such as name, age, health status, and hobbies, and submits it. The device then sends the entered information to the server, completing user registration.
[1298] 2. The server uses artificial intelligence to generate a virtual character based on user information. The generated virtual character is designed based on the user's preferences and past information, and is displayed on the smartphone or tablet. It also incorporates an emotion engine that recognizes emotions from the user's voice and facial expressions, and generates responses based on the user's emotional state.
[1299] 3. As part of daily health management, the device displays a health check form, and the user enters and submits their health status information, such as body temperature, blood pressure, heart rate, and mood, each day. The device then sends the entered health information to a server. The server uses AI to analyze the health data and generates advice based on it. The generated advice is then sent to the device and communicated to the user through a virtual character. For example, advice such as "Your blood pressure is a little high, so try to limit your salt intake" is displayed. Furthermore, an emotion engine recognizes the user's emotions and provides emotion-based advice, such as "You seem to be feeling stressed lately. Why not try a relaxing aroma?"
[1300] 4. To support social connections, the server collects information about local and community events, such as walking clubs and hobby gatherings held in the neighborhood. The server then sends this information to the device to recommend appropriate events based on the user's hobbies and interests. The device displays the event information, and the user selects the event they wish to attend and clicks the application button. The device then sends the event application information to the server, which then contacts the organizer to confirm the user's participation. This allows the user to participate in local events and build social connections. When participating in an event, the emotion engine checks whether the user is feeling anxious or nervous, and sends encouraging words through a virtual character if necessary.
[1301] Specific examples
[1302] For example, consider a user named Tanaka, 75 years old. Tanaka lives alone and was concerned about his physical and mental health. He installed the AI Life Supporter and entered his name, health condition (e.g., back pain), and hobby (e.g., gardening). Based on Tanaka's information, the server generated a virtual character modeled after his late wife and displayed it on his device. Every morning, Tanaka enters his temperature and blood pressure into the app and receives advice from the virtual character based on that information. The app then displays information about local gardening classes, and Tanaka is able to make new friends by participating in the event. The emotion engine also recognizes that Tanaka has been feeling stressed recently, and the virtual character encourages him to "take time to relax and not push yourself too hard," helping him live a more secure life.
[1303] Below are some examples of prompts to input to the generative AI model.
[1304] Mr. Tanaka, 75, lives alone and is concerned about his health. He installed the "AI Life Supporter" app. After entering his information into the app, a virtual character modeled after his late wife was generated and displayed on his device. Every morning, Mr. Tanaka enters his temperature and blood pressure and receives generated advice. He also participates in a local gardening class and makes new friends. The emotion engine recognizes when Mr. Tanaka is feeling stressed, and the virtual character sends him advice on how to relax, allowing him to live a life with peace of mind.
[1305] In this way, this invention not only enables elderly people living alone and unmarried people to manage their physical and mental health, but also enables them to form social connections, improving their quality of life. The addition of an emotion engine enables more personalized support tailored to the user's psychological state, contributing to alleviating feelings of loneliness and reducing stress.
[1306] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1307] Program processing flow and specific explanation
[1308] Step 1:
[1309] The user installs the app and launches it for the first time. By launching the app, the initial setup screen is displayed. Specifically, the user downloads the app from the app store and clicks the install button. The user then taps the app icon to launch it.
[1310] Step 2:
[1311] The device displays a user information input form. The user enters information such as name, age, health condition, hobbies, etc. and submits it. Specifically, the device displays the input form on the screen and accepts input from the user. The entered information is temporarily stored within the device.
[1312] Input: Information entered by the user, such as name, age, health status, hobbies, etc.
[1313] Output: The entered user information is sent to the server in JSON format.
[1314] Step 3:
[1315] The server accumulates the received user information and generates a virtual character using generative AI. Specifically, the server stores the received user information in a database. Then, it generates a virtual character using a generative AI model, converts the data, and sends it to the device.
[1316] Input: User information (name, age, health status, hobbies, etc.)
[1317] Output: Send the generated virtual character data to the terminal
[1318] Step 4:
[1319] The terminal displays the generated virtual character on the user interface. Specifically, the terminal displays the virtual character on the screen based on the received virtual character data.
[1320] Input: Data of the generated virtual character
[1321] Output: A virtual character displayed on the user interface.
[1322] Step 5:
[1323] The device starts the emotion engine and prepares to recognize emotions from the user's voice and facial expressions. Specifically, the device uses a microphone and camera to collect voice and facial expression data and inputs it into the emotion engine in real time. The emotion engine analyzes this data and determines the user's emotions.
[1324] Input: User voice and facial expression data
[1325] Output: Recognized user emotion data
[1326] Step 6:
[1327] The device presents a health check form to the user every day. The user inputs their health status, such as body temperature, blood pressure, heart rate, and mood, and submits it. Specifically, the device displays the health check form at a specific time every day and waits for input from the user. The user inputs the data and clicks the submit button.
[1328] Input: User-entered health data such as temperature, blood pressure, heart rate, and mood
[1329] Output: Send the input health data to the server in JSON format
[1330] Step 7:
[1331] The server uses AI to analyze the health data it receives and generate appropriate advice. Specifically, the server stores the received health data in a database and analyzes the data using an AI algorithm. It generates advice based on the analysis results and sends the data to the device.
[1332] Input: User health data (temperature, blood pressure, heart rate, mood, etc.)
[1333] Output: Sends generated advice data to the terminal
[1334] Step 8:
[1335] The device communicates advice to the user through the virtual character. Specifically, the device displays the received advice data in an easy-to-understand manner for the user through the virtual character's UI.
[1336] Input: Data for generated advice
[1337] Output: Advice displayed through a virtual character
[1338] Step 9:
[1339] The emotion engine checks the user's emotions and generates additional advice or encouraging messages based on the emotions. Specifically, the emotion engine re-analyzes the user's voice and facial expression data to detect signs of stress or anxiety. Based on the results, it generates additional advice or encouraging messages and sends them to the device.
[1340] Input: Emotion data analyzed from voice and facial expressions
[1341] Output: Any additional advice or encouragement messages generated are sent to the terminal.
[1342] Step 10:
[1343] The server collects local event information. Specifically, the server uses APIs from local governments and community centers to collect event information and stores it in a database. The collected information is then filtered based on the user's hobbies and interests.
[1344] Input: Local event information
[1345] Output: Sends filtered event information to the terminal
[1346] Step 11:
[1347] The terminal displays the event information and the user selects an event to participate in. Specifically, the terminal displays the filtered event information on a user interface and allows the user to select the event they want to participate in. The user clicks the participate button.
[1348] Input: Filtered event information
[1349] Output: Sends the user's selected event participation information to the server
[1350] Step 12:
[1351] The server sends the application information for event participation to the organizer and confirms the participation. Specifically, the server notifies the organizer of the received user's participation request and waits for confirmation from the organizer. Once confirmation is received, the server notifies the user of the participation information.
[1352] Input: Event participation information selected by the user
[1353] Output: Send user participation confirmation data to the terminal
[1354] Step 13:
[1355] The emotion engine checks the user's emotions before participating in the event, and if they feel anxious or nervous, it sends encouraging words. Specifically, the emotion engine re-analyzes the user's voice and facial expressions just before participating in the event, and if stress or anxiety is detected, it generates an encouraging message and sends it to the device.
[1356] Input: Emotion data analyzed from voice and facial expressions
[1357] Output: Generated encouraging message sent to terminal
[1358] (Application example 2)
[1359] 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."
[1360] Elderly people and single-person households face challenges in managing their physical and mental health and maintaining social connections, and it is also challenging for them to receive appropriate information and support while in physical stores. In particular, there is a lack of appropriate responses and support tailored to the user's emotional state, which can lead to feelings of loneliness and increased stress. The challenge is to solve these problems and enable elderly people and single-person households to lead fulfilling lives.
[1361] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.
[1362] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using a generation artificial intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status, means for analyzing health data and generating advice, means for collecting local event information and recommending it to the user, means for supporting event participation, means for providing in-store navigation information through the smart glasses, and means for recognizing emotions using an emotion engine and generating responses. This allows users to receive comprehensive support during activities in physical stores while maintaining their health management and social connections.
[1363] "Information input form" refers to an interface for users to input their own information.
[1364] "User Information" refers to data about a user, such as the user's name, age, health status, hobbies, etc.
[1365] "Generative AI" refers to AI technology for generating virtual characters based on user information.
[1366] "Virtual character" refers to a fictitious character generated based on user information.
[1367] "User interface" refers to the interface through which a user interacts with a system.
[1368] "Health status" refers to health-related data such as a user's temperature, blood pressure, heart rate, and mood.
[1369] "Health data" refers to information about a user's health condition entered by the user.
[1370] "Advice" refers to advice generated based on the analyzed health data.
[1371] "Local event information" refers to information about events held in the user's local area.
[1372] "Event participation" refers to the process of helping users participate in local events.
[1373] "Smart glasses" refers to wearable devices used to display information.
[1374] "In-store navigation information" refers to information necessary for a user to navigate within a physical store.
[1375] "Emotion engine" refers to technology that recognizes a user's emotions and generates a response accordingly.
[1376] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. The system aims to enrich users' lives in brick-and-mortar stores by using smart glasses and other wearable devices.
[1377] 1. User registration and initial settings
[1378] The process begins when the user puts on the smart glasses and launches the application. After launching the application, the smart glasses display a form for entering user information. The user enters the necessary information, such as name, age, health status, and hobbies, and submits it. This sends the user information to the server and stores it.
[1379] Using generative artificial intelligence, the server generates a virtual character based on the user's information. This virtual character is modeled after a loved one or family member, and the generated character is displayed on the smart glasses' display. Furthermore, an emotion engine is activated to recognize emotions from the user's voice and facial expressions.
[1380] 2. Daily health management
[1381] The smart glasses display a health check form every morning. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and sends it to the server. The server uses AI to analyze the collected health data and generates advice based on it. The advice is then sent to the smart glasses, where a virtual character delivers it to the user via voice.
[1382] 3. In-store support
[1383] When a user visits a physical store, the smart glasses provide navigation information within the store. When the user specifies the location they want to go to, the server calculates the route and displays it on the smart glasses' display. A virtual character then gives voice instructions, such as "Turn left at the next corner."
[1384] 4. Supporting social connections
[1385] The server collects local event information and recommends events based on the user's hobbies and interests. Users can check the event information through the smart glasses, select the events they want to attend, and sign up. The server then contacts the organizers to confirm the user's participation. In addition, the emotion engine checks whether the user is feeling anxious or nervous, and sends encouraging words through the virtual character as needed.
[1386] Hardware and Software Use
[1387] Smart glasses (wearable devices): Used for user interface and data entry / display.
[1388] Server: Performs back-end processing such as accumulating user information, generating virtual characters, analyzing health data, calculating route information, and operating the emotion engine.
[1389] Emotion engine: Software that recognizes emotions from the user's voice and facial expressions and generates a response.
[1390] Specific examples
[1391] Consider a scenario in which a 75-year-old user wears smart glasses and goes to a supermarket. First, the user enters the store and instructs the smart glasses to "go to the vegetable section." The server calculates the route within the store and sends that information to the smart glasses. Navigation information is displayed on the smart glasses' display, and a virtual character provides voice guidance such as "Turn left at the next corner." While the virtual character is displayed, the emotion engine analyzes the user's facial expressions, and if it detects fatigue, it will say, "Let's take a short break."
[1392] Prompt Sentence Examples
[1393] Entered data:
[1394] Name: User
[1395] Age: 75
[1396] Health condition: High blood pressure
[1397] Hobbies: Gardening
[1398] Tasks to be performed:
[1399] 1. Health data collection and analysis
[1400] 2. In-store navigation
[1401] 3. Providing event information
[1402] 4. Emotion-based response generation
[1403] Please provide the following navigation steps:
[1404] "Turn right at the next door."
[1405] This concludes the description of the embodiment of the present invention, which allows elderly people and single-person households to receive comprehensive support while engaging in activities at physical stores, while also managing their health and maintaining social connections.
[1406] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1407] Step 1:
[1408] The user puts on the smart glasses and starts the application. The smart glasses display a user information input form, and the user enters the necessary information, such as name, age, health status, and hobbies. The input data is sent to the server and stored.
[1409] Input: User information (name, age, health status, hobbies)
[1410] Output: User information stored on the server
[1411] Step 2:
[1412] The server uses artificial intelligence to generate a virtual character based on the input user information. The generated virtual character is modeled after a close friend or family member, and the data of this virtual character is sent to the smart glasses and displayed to the user.
[1413] Input: User information
[1414] Output: Virtual character data
[1415] Step 3:
[1416] The emotion engine is activated and recognizes emotions from the user's voice and facial expressions. The emotion engine uses the smart glasses' camera and microphone to capture the user's real-time facial expressions and voice, and analyzes emotions based on them.
[1417] Input: User's voice and facial expression data
[1418] Output: Parsed emotion results
[1419] Step 4:
[1420] The smart glasses display a health check form every morning. Users enter their health status, such as body temperature, blood pressure, heart rate, and mood, and send it to a server. The server then uses AI to analyze the collected health data and generate advice based on it.
[1421] Input: User's health status (temperature, blood pressure, heart rate, mood)
[1422] Output: Analysis results and advice
[1423] Step 5:
[1424] The generated advice is sent to the smart glasses, where a virtual character will give it to the user via voice. For example, specific advice such as "Your blood pressure is high, so try to limit your salt intake" is displayed.
[1425] Input: Analysis results and advice
[1426] Output: Voice advice from a virtual character
[1427] Step 6:
[1428] When a user visits a physical store, the smart glasses provide navigation information within the store. When the user specifies the location they want to go to, the server calculates the route and displays it on the smart glasses' display. A virtual character then gives voice instructions, such as "Turn left at the next corner."
[1429] Input: Specify destination
[1430] Output: Navigation information
[1431] Step 7:
[1432] The server collects local event information and recommends events based on the user's hobbies and interests. Users can check the event information through the smart glasses, select the event they want to attend, and register. The server then contacts the organizer to confirm the user's participation.
[1433] Input: Hobbies and interests, local event information
[1434] Output: Recommended event information and participation confirmation
[1435] Step 8:
[1436] The emotion engine checks whether the user is feeling anxious or nervous. If necessary, the virtual character will offer words of encouragement. For example, it will provide advice based on the user's emotions, such as, "You seem to be feeling stressed lately. Why don't you try a relaxing aroma?"
[1437] Input: User emotion data
[1438] Output: Emotion-based response
[1439] The above are the specific processing steps of the system that realizes the application example.
[1440] 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.
[1441] 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.
[1442] 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.
[1443] [Fourth embodiment]
[1444] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.
[1445] 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.
[1446] 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).
[1447] 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.
[1448] 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.
[1449] 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).
[1450] 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. 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.
[1451] 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.
[1452] 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.
[1453] 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.
[1454] 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.
[1455] 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.
[1456] 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."
[1457] ---
[1458] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. In this system, users enter their own information into an information input form, and the system supports daily health management and participation in local events through a virtual character generated based on that information.
[1459] 1. User registration and initial settings
[1460] The process begins when the user installs and launches the "Soba de Mimamoru" app. After launching the app, the device displays a form for entering user information. The user enters the necessary information, such as name, age, health condition, and hobbies, and clicks the submit button. The device then sends the entered information to the server, completing user registration. Based on the user information, the server uses generative artificial intelligence to generate a virtual character modeled after a close friend or family member, and sends the virtual character to the device for display.
[1461] 2. Daily health management
[1462] The device displays a health check form every day. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and clicks the submit button. The device then sends the entered health information to the server. The server uses AI to analyze the health data and generates advice based on it. The advice generated is sent to the device and communicated to the user through the virtual character's UI. For example, the advice might be, "Your blood pressure is a little high, so try to limit your salt intake."
[1463] 3. Supporting social connections
[1464] The server collects information about local and social events, such as nearby walking clubs and hobby gatherings. The server sends this information to the device to recommend appropriate events based on the user's hobbies and interests. The device displays the event information, and the user selects the event they wish to attend and clicks the application button. The device then sends the application information for the event to the server, which contacts the organizer to confirm the user's participation. This allows the user to participate in local events and build social connections.
[1465] Specific examples
[1466] Mr. Tanaka, 75, had been living alone for a long time and was concerned about his physical and mental health. He installed the "Soba de Mimamoru" app and entered his name, health condition (e.g., back pain), and hobby (e.g., gardening). Based on Mr. Tanaka's information, the server generated a virtual character modeled after his late wife and displayed it on his device. Every morning, Mr. Tanaka entered his body temperature and blood pressure into the app, and received advice based on that information from the virtual character. The app also displayed information about local gardening classes, allowing Mr. Tanaka to make new friends by participating in these events.
[1467] In this way, this invention not only enables elderly people living alone and unmarried people to manage their physical and mental health, but also enables them to have social connections, thereby improving their quality of life (QOL).
[1468] The processing flow will be explained below.
[1469] ---
[1470] User registration and initial settings
[1471] Step 1:
[1472] The user installs and launches the "Sobade Mimamoru" app.
[1473] Step 2:
[1474] The device displays a user information input form (name, age, health status, preferences, etc.) on the screen.
[1475] Step 3:
[1476] The user enters the required information and clicks the submit button.
[1477] Step 4:
[1478] The terminal transmits the input information to the server.
[1479] Step 5:
[1480] Based on the user's information, the server uses artificial intelligence to generate a virtual character modeled after a close friend or family member.
[1481] Step 6:
[1482] The server transmits the generated virtual character to the terminal.
[1483] Step 7:
[1484] The terminal displays the transmitted virtual character on the screen, allowing the user to start a conversation with the virtual character.
[1485] Daily health management
[1486] Step 1:
[1487] The device displays a daily health check form on the screen (e.g., temperature, blood pressure, heart rate, mood, etc.).
[1488] Step 2:
[1489] The user inputs their daily health status and clicks the submit button.
[1490] Step 3:
[1491] The terminal transmits the input health information to the server.
[1492] Step 4:
[1493] The server uses AI to analyze health data and generate advice.
[1494] Step 5:
[1495] The server transmits the generated advice to the terminal.
[1496] Step 6:
[1497] The device will then give advice to the user through a virtual character UI, for example, displaying a message such as "Your blood pressure is a little high, so try to limit your salt intake."
[1498] Supporting social connections
[1499] Step 1:
[1500] The server collects information about local and social events (for example, walking events and hobby gatherings held in the neighborhood).
[1501] Step 2:
[1502] The server selects events that the user can participate in based on the user's hobbies and interests.
[1503] Step 3:
[1504] The server transmits the selected event information to the terminal.
[1505] Step 4:
[1506] The event information received by the terminal is displayed on the screen.
[1507] Step 5:
[1508] The user checks the event information and selects the event they want to attend.
[1509] Step 6:
[1510] The user clicks the sign up button.
[1511] Step 7:
[1512] The terminal transmits the application information to the server.
[1513] Step 8:
[1514] The server contacts the event organizer to confirm the user's participation.
[1515] Step 9:
[1516] The server sends participation confirmation information to the terminal.
[1517] Step 10:
[1518] The terminal notifies the user of the participation confirmation information.
[1519] ---
[1520] This concludes the processing flow of the "Soba de Mimamoru" system. At each step, the system effectively manages the user's information, supports their physical and mental health, and provides social connections.
[1521] Example 1
[1522] 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."
[1523] In modern society, elderly people living alone and unmarried people face challenges in managing their physical and mental health and maintaining social connections. This problem, particularly for the elderly, increases feelings of loneliness and health risks, leading to a decline in quality of life (QOL). Furthermore, low participation in local events and social activities also contributes to social isolation. Therefore, there is a need for a system that allows these people to easily manage their health information, receive appropriate advice, and form social connections.
[1524] 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.
[1525] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using generative intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status, means for analyzing health data and generating advice, means for collecting local event information and recommending it to users, means for supporting event participation, means for providing daily health data analysis results using AI technology, and means for conveying advice to users through the generated virtual character, thereby enabling users to manage their physical and mental health and build social connections.
[1526] An "information input form" is an online form where a user enters personal information such as name, age, health status, hobbies, etc.
[1527] "User information" refers to personal data such as name, age, health status, and hobbies entered by the user in the information input form.
[1528] "Generative intelligence" refers to artificial intelligence technology that uses a generative AI model (e.g., GPT-4) to automatically generate virtual characters based on user input data.
[1529] A "virtual character" is a 3D or 2D digital character created to resemble a close friend or family member based on the user's personal information and past experiences.
[1530] "User interface" refers to the application screen or digital interface through which a user interacts with a virtual character.
[1531] "Health Status" refers to the user's daily health data, such as temperature, blood pressure, heart rate, and mood.
[1532] "Health data" refers to information entered by the user, such as body temperature, blood pressure, heart rate, and mood.
[1533] "Advice" refers to specific health management instructions or suggestions provided to the user based on the results of analyzing the health data.
[1534] "Local event information" refers to event information such as local walking clubs and hobby gatherings that is automatically collected by the server.
[1535] "Means for using generative intelligence" means the ability to automatically generate virtual characters using a generative AI model.
[1536] "Means to support event participation" refers to a function that supports users in applying to participate in local events.
[1537] The present invention is a system that provides an "AI life supporter" that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. The details are explained below.
[1538] Configuration and Hardware / Software
[1539] The system operates using a user device (such as a smartphone), a server, and a generative AI model.
[1540] Device: User device such as a smartphone or tablet. Install and use the Android or iOS app "Soba de Mimamoru."
[1541] Server: A high-performance cloud server that runs generative AI models (e.g., OpenAI's GPT-4) and AI libraries for health data analysis (e.g., Python's TensorFlow and Scikit-learn).
[1542] Generative AI model: Used to generate a virtual character based on user information. It receives a prompt as input and generates a virtual character.
[1543] Program processing and data manipulation
[1544] 1. User registration and initial settings
[1545] The user installs and launches the "Soba de Mimamoru" app. After launching the app, an information input form is displayed, and the user enters the necessary information, such as name, age, health status, and hobbies. This information is then sent from the device to the server.
[1546] 2. Virtual Character Generation
[1547] The server uses a generative AI model to generate a virtual character based on the received user information. This virtual character is modeled after a person close to the user or their family, and is designed to feel familiar to the user. The generated character is sent from the server to the device and displayed within the app.
[1548] 3. Daily health management
[1549] The device displays a health check form every day. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and clicks the submit button. The device then sends the entered health information to the server. The server uses AI to analyze the health data and generates and sends advice to the device. The advice is then conveyed to the user through a virtual character.
[1550] 4. Supporting social connections
[1551] The server collects information about local and social events and recommends appropriate events based on the user's interests. This information is sent to the device, and the user can choose to participate. When a user registers to participate in an event, the device sends the information to the server, and the server provides the participation information to the event organizer.
[1552] Specific examples
[1553] Suppose a 75-year-old user has been living alone for a long time and is concerned about his health. He installs the "Soba de Mimamoru" app and inputs his name, health condition (e.g., he has back pain), and hobby (e.g., reading). Based on this information, the server generates a virtual character modeled after his late wife and displays it on the device.
[1554] Every morning, he enters his temperature, blood pressure, and other information into the app, and receives advice based on that information from a virtual character. The app also displays information about events such as book clubs held in the area, and he can make new friends by participating in these events.
[1555] Prompt Sentence Examples
[1556] Below are some example prompts to input to a generative AI model:
[1557] User Information:
[1558] Name: Username
[1559] Age: 75
[1560] Health condition: Back pain
[1561] Hobbies: Reading
[1562] Virtual characters to be generated:
[1563] A character modeled after the user's late wife
[1564] Based on this prompt, the generative AI model generates the most suitable virtual character based on the user's personal information and provides a wide range of support.
[1565] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1566] Step 1:
[1567] The user installs and launches the "Sobade Mimamoru" app.
[1568] Step 2:
[1569] The device displays a form for entering information.
[1570] The user enters the required information such as name, age, health status, hobbies, etc. and clicks the submit button.
[1571] Input: User-entered information about name, age, health, and hobbies.
[1572] Output: The entered user information is sent from the terminal to the server.
[1573] Step 3:
[1574] The server receives and stores the user information.
[1575] Input: User information sent from the device.
[1576] Output: User information stored in the database.
[1577] Step 4:
[1578] The server executes a generative AI model based on the received user information to generate a virtual character.
[1579] Input: Stored user information.
[1580] Data processing: User information is input into the generative AI model as a prompt sentence.
[1581] Output: The generative AI model generates a virtual character and returns the character data to the server.
[1582] Specific operation: The server processes the data (e.g., 3D model and text information) of the generated virtual character.
[1583] Step 5:
[1584] The server transmits the data of the generated virtual character to the terminal.
[1585] Input: Data of the generated virtual character.
[1586] Output: The virtual character data is sent to the device.
[1587] Step 6:
[1588] The terminal displays the virtual character on a user interface.
[1589] Input: Virtual character data sent from the server.
[1590] Output: A virtual character is displayed in the app.
[1591] Specific behavior: In some cases, animation and audio functions are also included.
[1592] Step 7:
[1593] The device displays a health check form every day.
[1594] The user enters their health status, such as temperature, blood pressure, heart rate, and mood, and clicks the submit button.
[1595] Input: User-entered health data.
[1596] Output: Health status data is sent from the device to the server.
[1597] Step 8:
[1598] The server receives the health data and analyzes it using AI.
[1599] Input: Health status data sent from the device.
[1600] Data Computing: Analyzing health data using AI models (such as TensorFlow and Scikit-learn).
[1601] Output: Health advice is generated based on the analysis results.
[1602] What it does: The AI model detects outliers and compares them with historical data to identify trends.
[1603] Step 9:
[1604] The server sends the generated health advice to the terminal.
[1605] Input: AI-generated health advice.
[1606] Output: Health advice is sent to the device.
[1607] Step 10:
[1608] The device displays health advice to the user through a virtual character.
[1609] Input: Health advice sent from the server.
[1610] Output: Health advice is displayed to the user through the virtual character UI.
[1611] Example: A virtual character gives advice such as, "Your blood pressure is a little high, so try to limit your salt intake."
[1612] Step 11:
[1613] The server collects local event information and filters it based on the user's interests.
[1614] Input: Local event information collected from the internet.
[1615] Data processing: Filtering event information based on user hobbies and interests.
[1616] Output: Recommended event information is generated.
[1617] Step 12:
[1618] The server transmits the filtered event information to the terminal.
[1619] Input: Recommended event information.
[1620] Output: Event information is sent to the terminal.
[1621] Step 13:
[1622] The terminal displays the event information to the user and accepts participation applications.
[1623] Input: Event information sent from the server.
[1624] Output: The event information is displayed in the app and the user clicks to register.
[1625] Step 14:
[1626] The terminal sends the user's participation application to the server.
[1627] Input: User's event registration information.
[1628] Output: The registration information is sent to the server.
[1629] Step 15:
[1630] The server provides the participation information to the event organizer and confirms the participation.
[1631] Input: Application information.
[1632] Output: Notify the user that their participation is confirmed.
[1633] Example: An in-app notification says, "You've been accepted into a local gardening class."
[1634] (Application example 1)
[1635] 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."
[1636] Elderly people living alone and unmarried people face challenges in managing their physical and mental health and in maintaining social connections. Welfare facilities and community centers, in particular, lack the means for users to understand their own health status and receive appropriate advice. There is also a lack of systems for providing appropriate information about local events and encouraging participation. This raises concerns that users may become increasingly socially isolated and experience a decline in their quality of life.
[1637] 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.
[1638] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using artificial intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status information, means for analyzing health data and generating advice, means for collecting local event information and recommending it to the user, means for supporting event participation, means for providing an application to be installed on a smartphone, means for automatically notifying emergency contacts, and means for supporting community activities within a facility. This enables elderly people living alone and unmarried people to maintain their daily health management and social connections and improve their quality of life.
[1639] An "information input form" is a screen or interface that allows a user to enter their own information (such as name, age, health status, hobbies, etc.).
[1640] "User information" refers to data about the user (such as name, age, health status, hobbies, etc.) and is information used by the system to provide individualized support.
[1641] "Generative AI" is an AI technology that generates appropriate virtual characters and advice based on input data.
[1642] A "virtual character" is a virtual person or character generated using artificial intelligence, which interacts with and assists the user.
[1643] A "user interface" is the screen or means of interaction that a user uses to interact with an application.
[1644] "Health data" refers to information about the user's daily health condition, such as body temperature, blood pressure, heart rate, and mood.
[1645] "Advice" is advice and suggestions regarding daily health management and lifestyle improvements generated by artificial intelligence based on health data.
[1646] "Local event information" is information about various events and activities held in the area where the user lives.
[1647] "Means to support event participation" refers to support functions for users to participate in local events (provision of event information, application procedures, etc.).
[1648] The "application installed on the smartphone" is software that runs on the smartphone and provides the functions of the present invention.
[1649] The "means for automatically notifying emergency contacts" is a function that automatically sends a notification to a pre-registered emergency contact if there is an abnormality in the user's health condition.
[1650] "Means to support community activities within the facility" refers to functions for managing activities that take place within welfare facilities and community centers and promoting user participation.
[1651] This invention is a system that supports single-person elderly people and unmarried people in managing their health and maintaining social connections on a daily basis. The configuration and operation of this system will be described below.
[1652] User registration and initial settings
[1653] First, the user launches the application installed on their smartphone and enters information such as their name, age, health condition, and hobbies into an information input form. This information is sent from the device to a server and stored. Using generative artificial intelligence, a virtual character is generated based on the input information, and the character is displayed on the user interface. The virtual character is modeled after a familiar person or family member, helping the user to feel a sense of familiarity.
[1654] Daily health management
[1655] Every day, users enter their health status (body temperature, blood pressure, heart rate, mood, etc.) into the device and send it. This health data is sent to a server and analyzed by AI. Based on the analysis results, advice for health management is generated. For example, specific advice such as "Your blood pressure is high, so try to limit your salt intake" is provided.
[1656] Supporting social connections
[1657] The server collects information about local events and recommends appropriate events based on the user's hobbies and interests. This event information is displayed on the device, allowing the user to select and register for the events they wish to attend. Furthermore, in preparation for unforeseen circumstances, the system has an emergency contact function that automatically sends a notification to registered emergency contacts if any abnormalities are detected in the user's health condition.
[1658] Specific examples
[1659] Mr. Suzuki, 70 years old, lives alone. He installed the application on his smartphone and completed the registration process. Every morning, Mr. Suzuki enters his health status into the app and receives advice based on it. He can also easily register for local walking groups and hobby classes, which has enabled him to make new friends. One day, when his health worsened, the emergency contact function was activated, and his family who live nearby were contacted, allowing for a quick response.
[1660] Prompt Sentence Examples
[1661] "On a day when 70-year-old Suzuki has a body temperature of 36.8°C, blood pressure of 135 / 80, a heart rate of 72 beats per minute, and feels normal, what should he be careful of in his daily life?"
[1662] This system will make it easier for single-person elderly people and unmarried people to manage their health and maintain social connections, which is expected to improve their quality of life.
[1663] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1664] Program processing flow
[1665] Step 1:
[1666] A user installs an application on their smartphone and opens an information input form. This form has fields for entering information such as name, age, health status, and hobbies. When the user enters all the information and clicks the "Submit" button, the input data is sent to the server via the device. Input: User information. Output: User information saved on the server.
[1667] Step 2:
[1668] The server uses artificial intelligence to generate a virtual character based on the received user information. This virtual character is modeled after the user's preferences and familiar faces. The generated character is sent from the server to the terminal and displayed on the user interface. Input: User information. Output: Displayed virtual character.
[1669] Step 3:
[1670] Every day, users enter their health status (body temperature, blood pressure, heart rate, mood, etc.) into the health check form within the application. Once the entry is complete, they click the "Submit" button and the data is sent from the device to the server. Input: Health data. Output: Health data sent to the server.
[1671] Step 4:
[1672] The server uses AI to analyze the received health data. Data such as body temperature, blood pressure, heart rate, and mood are used for the analysis. The AI evaluates the user's health condition based on past data and a medical knowledge base, and generates appropriate advice. This advice is sent from the server to the device and conveyed to the user through a virtual character. Input: Health data. Output: Advice.
[1673] Step 5:
[1674] The server collects local event information and recommends appropriate events based on the user's hobbies and interests. Event information is sent from the server to the terminal and displayed on the user interface. When the user selects the event they want to attend and clicks the "Apply" button, participation information is sent to the server and contacted with the event organizer. Input: User's hobbies and interests. Output: Recommended event information, application to attend.
[1675] Step 6:
[1676] If an abnormality is detected based on the health data, the emergency contact function will be activated. The server will automatically send a notification to pre-registered emergency contacts. This notification will inform the user that there is an abnormality in their health condition. Input: Abnormal health data. Output: Emergency contact notification.
[1677] Step 7:
[1678] Designed for use in welfare facilities and community centers, the system provides a means to support community activities within the facility, including event management and participant health monitoring. Input: Facility event information, participant health data. Output: Event information management, participant health report.
[1679] In this way, elderly people living alone and unmarried people can improve their quality of life by managing their daily health and participating in community events.
[1680] 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.
[1681] ---
[1682] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. The system supports daily health management and participation in local events through a virtual character generated based on the user's input information. The system also incorporates an emotion engine that recognizes the user's emotions and responds accordingly.
[1683] 1. User registration and initial settings
[1684] The process begins when the user installs and launches the "Soba de Mimamoru" app. After launching the app, the device displays a form for entering user information. The user enters the necessary information, such as name, age, health condition, and hobbies, and clicks the submit button. The device then sends the entered information to the server, completing user registration. Based on the user information, the server uses generative artificial intelligence to generate a virtual character modeled after a close friend or family member, and sends the virtual character to the device for display. In addition, an emotion engine begins to operate, recognizing emotions from the user's voice and facial expressions.
[1685] 2. Daily health management
[1686] The device displays a health check form every day. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and clicks the submit button. The device then sends the entered health information to the server. The server uses AI to analyze the health data and generates advice based on it. The generated advice is sent to the device and communicated to the user through a virtual character UI. For example, the advice might be, "Your blood pressure is a little high, so try to limit your salt intake." Furthermore, an emotion engine recognizes the user's emotions and provides emotion-based advice, such as, "You seem to be feeling stressed lately. Why not try a relaxing aroma?"
[1687] 3. Supporting social connections
[1688] The server collects information about local and social events, such as walking clubs and hobby gatherings held in the neighborhood. The server sends this information to the device to recommend appropriate events based on the user's hobbies and interests. The device displays the event information, the user selects the event they wish to attend, and clicks the application button. The device sends the event participation application information to the server, and the server contacts the organizer to confirm the user's participation. This allows the user to participate in local events and build social connections. When participating in an event, the emotion engine checks whether the user is feeling anxious or nervous, and sends words of encouragement through a virtual character if necessary.
[1689] Specific examples
[1690] Mr. Tanaka, 75, had been living alone for a long time and was concerned about his physical and mental health. He installed the "Soba de Mimamoru" app and entered his name, health condition (e.g., back pain), and hobby (e.g., gardening). Based on Mr. Tanaka's information, the server generated a virtual character modeled after his late wife and displayed it on his device. Every morning, Mr. Tanaka entered his temperature and blood pressure into the app and received advice from the virtual character based on that information. The app also displayed information about local gardening classes, and by participating in these events, he was able to make new friends. Furthermore, the emotion engine recognized that Mr. Tanaka had been feeling stressed recently, and the virtual character encouraged him to "take time to relax and not push yourself too hard," helping him live a more secure life.
[1691] In this way, this invention not only enables elderly people living alone and unmarried people to manage their physical and mental health, but also enables them to form social connections, improving their quality of life (QOL). The addition of an emotion engine enables more personalized support tailored to the user's psychological state, contributing to easing feelings of loneliness and reducing stress.
[1692] ---
[1693] The processing flow will be explained below.
[1694] ---
[1695] User registration and initial settings
[1696] Step 1:
[1697] The user installs and launches the "Sobade Mimamoru" app.
[1698] Step 2:
[1699] The device displays a user information input form (name, age, health status, preferences, etc.) on the screen.
[1700] Step 3:
[1701] The user enters the required information and clicks the submit button.
[1702] Step 4:
[1703] The terminal transmits the input information to the server.
[1704] Step 5:
[1705] Based on the user's information, the server uses artificial intelligence to generate a virtual character modeled after a close friend or family member.
[1706] Step 6:
[1707] The server transmits the generated virtual character to the terminal.
[1708] Step 7:
[1709] The device displays the virtual character on the screen, and the emotion engine starts up, preparing to recognize emotions from the user's voice and facial expressions.
[1710] Daily health management
[1711] Step 1:
[1712] The device displays a daily health check form (temperature, blood pressure, heart rate, mood, etc.) on the screen.
[1713] Step 2:
[1714] The user inputs their daily health status and clicks the submit button.
[1715] Step 3:
[1716] The terminal transmits the input health information to the server.
[1717] Step 4:
[1718] The server uses AI to analyze health data and generate advice.
[1719] Step 5:
[1720] The server transmits the generated advice to the terminal.
[1721] Step 6:
[1722] The device will then give advice to the user through a virtual character UI, for example, displaying a message such as "Your blood pressure is a little high, so try to limit your salt intake."
[1723] Step 7:
[1724] The device analyzes the user's voice and facial expressions and recognizes emotions using an emotion engine.
[1725] Step 8:
[1726] The server receives data from the emotion engine, analyzes the user's emotion data, and generates emotion-based advice, such as "You seem to be stressed out lately. Why don't you try a relaxing aroma?"
[1727] Step 9:
[1728] The server transmits the generated emotion-based advice to the terminal.
[1729] Step 10:
[1730] The device conveys emotion-based advice to the user through a virtual character UI.
[1731] Supporting social connections
[1732] Step 1:
[1733] The server collects information about local and social events (for example, walking events and hobby gatherings held in the neighborhood).
[1734] Step 2:
[1735] The server selects events that the user can participate in based on the user's hobbies and interests.
[1736] Step 3:
[1737] The server transmits the selected event information to the terminal.
[1738] Step 4:
[1739] The event information received by the terminal is displayed on the screen.
[1740] Step 5:
[1741] The user checks the event information and selects the event they want to attend.
[1742] Step 6:
[1743] The user clicks the sign up button.
[1744] Step 7:
[1745] The terminal transmits the application information to the server.
[1746] Step 8:
[1747] The server contacts the event organizer to confirm the user's participation.
[1748] Step 9:
[1749] The server sends participation confirmation information to the terminal.
[1750] Step 10:
[1751] The device will notify the user of the confirmation of participation. Furthermore, if the emotion engine detects the user's anxiety or tension, it will provide an encouraging message through the virtual character.
[1752] ---
[1753] The above is the processing flow of the "Soba de Mimamoru" system, which combines an emotion engine. At each step, the system effectively manages the user's information, supports their physical and mental health, and provides social connections. In addition, the emotion engine enables personalized support based on the user's psychological state.
[1754] Example 2
[1755] 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."
[1756] It is difficult for elderly people living alone or unmarried people to properly manage their physical and mental health and maintain social connections. Furthermore, they are prone to feeling lonely and stressed in their daily lives, which often threatens their mental health. In such situations, a system that can provide appropriate support is needed.
[1757] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[1758] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using a generation artificial intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status, means for analyzing health data and generating advice, means for collecting local event information and recommending events to the user, means for supporting event participation, means for recognizing the user's emotions from voice and facial expressions and generating a response based thereon, and means for providing additional advice and encouraging messages based on the user's emotional state, thereby enabling consistent management of the user's physical and mental health, maintaining social connections, and improving quality of life.
[1759] The "means for providing an information input form" is a mechanism that provides an interface for a user to input information such as his / her name, age, health condition, hobbies, etc.
[1760] The "means for transmitting and storing user information" is a mechanism that has the function of transmitting information entered by the user to a server and safely storing that information.
[1761] "Means for generating a virtual character using artificial intelligence" refers to a mechanism that uses artificial intelligence technology to create a virtual character based on user information.
[1762] The "means for displaying the generated virtual character on the user interface" is a mechanism for displaying the generated virtual character on the screen of a digital device.
[1763] The "means for inputting and transmitting health status" is a mechanism that allows a user to input their daily health status, such as body temperature, blood pressure, and heart rate, and transmit that information to a server.
[1764] The "means for analyzing health data and generating advice" refers to a mechanism in which the server analyzes the health data received using an AI algorithm and generates health management advice based on that data.
[1765] The "means for collecting local event information and recommending it to the user" is a mechanism by which the server collects local event information, filters it based on the user's hobbies and interests, and recommends it to the user.
[1766] The "means for supporting event participation" is a mechanism that handles the participation procedures for the event selected by the user and communicates with the organizer.
[1767] "Means for recognizing the user's emotions from their voice and facial expressions and generating a response based on that" refers to a mechanism that uses an emotion engine to analyze the user's voice and facial expressions and generates appropriate responses and advice based on the results.
[1768] The "means for providing additional advice or encouraging messages based on the user's emotional state" is a mechanism for providing additional specific advice or encouraging messages based on the user's emotional state recognized by the emotion engine.
[1769] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. This system includes the following components:
[1770] 1. The user installs and launches the application on a device such as a smartphone or tablet. After launching, the device displays a user information input form, and the user enters the required information, such as name, age, health status, and hobbies, and submits it. The device then sends the entered information to the server, completing user registration.
[1771] 2. The server uses artificial intelligence to generate a virtual character based on user information. The generated virtual character is designed based on the user's preferences and past information, and is displayed on the smartphone or tablet. It also incorporates an emotion engine that recognizes emotions from the user's voice and facial expressions, and generates responses based on the user's emotional state.
[1772] 3. As part of daily health management, the device displays a health check form, and the user enters and submits their health status information, such as body temperature, blood pressure, heart rate, and mood, each day. The device then sends the entered health information to a server. The server uses AI to analyze the health data and generates advice based on it. The generated advice is then sent to the device and communicated to the user through a virtual character. For example, advice such as "Your blood pressure is a little high, so try to limit your salt intake" is displayed. Furthermore, an emotion engine recognizes the user's emotions and provides emotion-based advice, such as "You seem to be feeling stressed lately. Why not try a relaxing aroma?"
[1773] 4. To support social connections, the server collects information about local and community events, such as walking clubs and hobby gatherings held in the neighborhood. The server then sends this information to the device to recommend appropriate events based on the user's hobbies and interests. The device displays the event information, and the user selects the event they wish to attend and clicks the application button. The device then sends the event application information to the server, which then contacts the organizer to confirm the user's participation. This allows the user to participate in local events and build social connections. When participating in an event, the emotion engine checks whether the user is feeling anxious or nervous, and sends encouraging words through a virtual character if necessary.
[1774] Specific examples
[1775] For example, consider a user named Tanaka, 75 years old. Tanaka lives alone and was concerned about his physical and mental health. He installed the AI Life Supporter and entered his name, health condition (e.g., back pain), and hobby (e.g., gardening). Based on Tanaka's information, the server generated a virtual character modeled after his late wife and displayed it on his device. Every morning, Tanaka enters his temperature and blood pressure into the app and receives advice from the virtual character based on that information. The app then displays information about local gardening classes, and Tanaka is able to make new friends by participating in the event. The emotion engine also recognizes that Tanaka has been feeling stressed recently, and the virtual character encourages him to "take time to relax and not push yourself too hard," helping him live a more secure life.
[1776] Below are some examples of prompts to input to the generative AI model.
[1777] Mr. Tanaka, 75, lives alone and is concerned about his health. He installed the "AI Life Supporter" app. After entering his information into the app, a virtual character modeled after his late wife was generated and displayed on his device. Every morning, Mr. Tanaka enters his temperature and blood pressure and receives generated advice. He also participates in a local gardening class and makes new friends. The emotion engine recognizes when Mr. Tanaka is feeling stressed, and the virtual character sends him advice on how to relax, allowing him to live a life with peace of mind.
[1778] In this way, this invention not only enables elderly people living alone and unmarried people to manage their physical and mental health, but also enables them to form social connections, improving their quality of life. The addition of an emotion engine enables more personalized support tailored to the user's psychological state, contributing to alleviating feelings of loneliness and reducing stress.
[1779] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1780] Program processing flow and specific explanation
[1781] Step 1:
[1782] The user installs the app and launches it for the first time. By launching the app, the initial setup screen is displayed. Specifically, the user downloads the app from the app store and clicks the install button. The user then taps the app icon to launch it.
[1783] Step 2:
[1784] The device displays a user information input form. The user enters information such as name, age, health condition, hobbies, etc. and submits it. Specifically, the device displays the input form on the screen and accepts input from the user. The entered information is temporarily stored within the device.
[1785] Input: Information entered by the user, such as name, age, health status, hobbies, etc.
[1786] Output: The entered user information is sent to the server in JSON format.
[1787] Step 3:
[1788] The server accumulates the received user information and generates a virtual character using generative AI. Specifically, the server stores the received user information in a database. Then, it generates a virtual character using a generative AI model, converts the data, and sends it to the device.
[1789] Input: User information (name, age, health status, hobbies, etc.)
[1790] Output: Send the generated virtual character data to the terminal
[1791] Step 4:
[1792] The terminal displays the generated virtual character on the user interface. Specifically, the terminal displays the virtual character on the screen based on the received virtual character data.
[1793] Input: Data of the generated virtual character
[1794] Output: A virtual character displayed on the user interface.
[1795] Step 5:
[1796] The device starts the emotion engine and prepares to recognize emotions from the user's voice and facial expressions. Specifically, the device uses a microphone and camera to collect voice and facial expression data and inputs it into the emotion engine in real time. The emotion engine analyzes this data and determines the user's emotions.
[1797] Input: User voice and facial expression data
[1798] Output: Recognized user emotion data
[1799] Step 6:
[1800] The device presents a health check form to the user every day. The user inputs their health status, such as body temperature, blood pressure, heart rate, and mood, and submits it. Specifically, the device displays the health check form at a specific time every day and waits for input from the user. The user inputs the data and clicks the submit button.
[1801] Input: User-entered health data such as temperature, blood pressure, heart rate, and mood
[1802] Output: Send the input health data to the server in JSON format
[1803] Step 7:
[1804] The server uses AI to analyze the health data it receives and generate appropriate advice. Specifically, the server stores the received health data in a database and analyzes the data using an AI algorithm. It generates advice based on the analysis results and sends the data to the device.
[1805] Input: User health data (temperature, blood pressure, heart rate, mood, etc.)
[1806] Output: Sends generated advice data to the terminal
[1807] Step 8:
[1808] The device communicates advice to the user through the virtual character. Specifically, the device displays the received advice data in an easy-to-understand manner for the user through the virtual character's UI.
[1809] Input: Data for generated advice
[1810] Output: Advice displayed through a virtual character
[1811] Step 9:
[1812] The emotion engine checks the user's emotions and generates additional advice or encouraging messages based on the emotions. Specifically, the emotion engine re-analyzes the user's voice and facial expression data to detect signs of stress or anxiety. Based on the results, it generates additional advice or encouraging messages and sends them to the device.
[1813] Input: Emotion data analyzed from voice and facial expressions
[1814] Output: Any additional advice or encouragement messages generated are sent to the terminal.
[1815] Step 10:
[1816] The server collects local event information. Specifically, the server uses APIs from local governments and community centers to collect event information and stores it in a database. The collected information is then filtered based on the user's hobbies and interests.
[1817] Input: Local event information
[1818] Output: Sends filtered event information to the terminal
[1819] Step 11:
[1820] The terminal displays the event information and the user selects an event to participate in. Specifically, the terminal displays the filtered event information on a user interface and allows the user to select the event they want to participate in. The user clicks the participate button.
[1821] Input: Filtered event information
[1822] Output: Sends the user's selected event participation information to the server
[1823] Step 12:
[1824] The server sends the application information for event participation to the organizer and confirms the participation. Specifically, the server notifies the organizer of the received user's participation request and waits for confirmation from the organizer. Once confirmation is received, the server notifies the user of the participation information.
[1825] Input: Event participation information selected by the user
[1826] Output: Send user participation confirmation data to the terminal
[1827] Step 13:
[1828] The emotion engine checks the user's emotions before participating in the event, and if they feel anxious or nervous, it sends encouraging words. Specifically, the emotion engine re-analyzes the user's voice and facial expressions just before participating in the event, and if stress or anxiety is detected, it generates an encouraging message and sends it to the device.
[1829] Input: Emotion data analyzed from voice and facial expressions
[1830] Output: Generated encouraging message sent to terminal
[1831] (Application example 2)
[1832] 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."
[1833] Elderly people and single-person households face challenges in managing their physical and mental health and maintaining social connections, and it is also challenging for them to receive appropriate information and support while in physical stores. In particular, there is a lack of appropriate responses and support tailored to the user's emotional state, which can lead to feelings of loneliness and increased stress. The challenge is to solve these problems and enable elderly people and single-person households to lead fulfilling lives.
[1834] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.
[1835] In this invention, the server includes means for providing an information input form, means for transmitting and storing user information, means for generating a virtual character using a generation artificial intelligence, means for displaying the generated virtual character on a user interface, means for inputting and transmitting health status, means for analyzing health data and generating advice, means for collecting local event information and recommending it to the user, means for supporting event participation, means for providing in-store navigation information through the smart glasses, and means for recognizing emotions using an emotion engine and generating responses. This allows users to receive comprehensive support during activities in physical stores while maintaining their health management and social connections.
[1836] "Information input form" refers to an interface for users to input their own information.
[1837] "User Information" refers to data about a user, such as the user's name, age, health status, hobbies, etc.
[1838] "Generative AI" refers to AI technology for generating virtual characters based on user information.
[1839] "Virtual character" refers to a fictitious character generated based on user information.
[1840] "User interface" refers to the interface through which a user interacts with a system.
[1841] "Health status" refers to health-related data such as a user's temperature, blood pressure, heart rate, and mood.
[1842] "Health data" refers to information about a user's health condition entered by the user.
[1843] "Advice" refers to advice generated based on the analyzed health data.
[1844] "Local event information" refers to information about events held in the user's local area.
[1845] "Event participation" refers to the process of helping users participate in local events.
[1846] "Smart glasses" refers to wearable devices used to display information.
[1847] "In-store navigation information" refers to information necessary for a user to navigate within a physical store.
[1848] "Emotion engine" refers to technology that recognizes a user's emotions and generates a response accordingly.
[1849] This invention provides an "AI Life Supporter" system that helps elderly people living alone and unmarried people manage their physical and mental health and build social connections. The system aims to enrich users' lives in brick-and-mortar stores by using smart glasses and other wearable devices.
[1850] 1. User registration and initial settings
[1851] The process begins when the user puts on the smart glasses and launches the application. After launching the application, the smart glasses display a form for entering user information. The user enters the necessary information, such as name, age, health status, and hobbies, and submits it. This sends the user information to the server and stores it.
[1852] Using generative artificial intelligence, the server generates a virtual character based on the user's information. This virtual character is modeled after a loved one or family member, and the generated character is displayed on the smart glasses' display. Furthermore, an emotion engine is activated to recognize emotions from the user's voice and facial expressions.
[1853] 2. Daily health management
[1854] The smart glasses display a health check form every morning. The user enters their health status, such as body temperature, blood pressure, heart rate, and mood, and sends it to the server. The server uses AI to analyze the collected health data and generates advice based on it. The advice is then sent to the smart glasses, where a virtual character delivers it to the user via voice.
[1855] 3. In-store support
[1856] When a user visits a physical store, the smart glasses provide navigation information within the store. When the user specifies the location they want to go to, the server calculates the route and displays it on the smart glasses' display. A virtual character then gives voice instructions, such as "Turn left at the next corner."
[1857] 4. Supporting social connections
[1858] The server collects local event information and recommends events based on the user's hobbies and interests. Users can check the event information through the smart glasses, select the events they want to attend, and sign up. The server then contacts the organizers to confirm the user's participation. In addition, the emotion engine checks whether the user is feeling anxious or nervous, and sends encouraging words through the virtual character as needed.
[1859] Hardware and Software Use
[1860] Smart glasses (wearable devices): Used for user interface and data entry / display.
[1861] Server: Performs back-end processing such as accumulating user information, generating virtual characters, analyzing health data, calculating route information, and operating the emotion engine.
[1862] Emotion engine: Software that recognizes emotions from the user's voice and facial expressions and generates a response.
[1863] Specific examples
[1864] Consider a scenario in which a 75-year-old user wears smart glasses and goes to a supermarket. First, the user enters the store and instructs the smart glasses to "go to the vegetable section." The server calculates the route within the store and sends that information to the smart glasses. Navigation information is displayed on the smart glasses' display, and a virtual character provides voice guidance such as "Turn left at the next corner." While the virtual character is displayed, the emotion engine analyzes the user's facial expressions, and if it detects fatigue, it will say, "Let's take a short break."
[1865] Prompt Sentence Examples
[1866] Entered data:
[1867] Name: User
[1868] Age: 75
[1869] Health condition: High blood pressure
[1870] Hobbies: Gardening
[1871] Tasks to be performed:
[1872] 1. Health data collection and analysis
[1873] 2. In-store navigation
[1874] 3. Providing event information
[1875] 4. Emotion-based response generation
[1876] Please provide the following navigation steps:
[1877] "Turn right at the next door."
[1878] This concludes the description of the embodiment of the present invention, which allows elderly people and single-person households to receive comprehensive support while engaging in activities at physical stores, while also managing their health and maintaining social connections.
[1879] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1880] Step 1:
[1881] The user puts on the smart glasses and starts the application. The smart glasses display a user information input form, and the user enters the necessary information, such as name, age, health status, and hobbies. The input data is sent to the server and stored.
[1882] Input: User information (name, age, health status, hobbies)
[1883] Output: User information stored on the server
[1884] Step 2:
[1885] The server uses artificial intelligence to generate a virtual character based on the input user information. The generated virtual character is modeled after a close friend or family member, and the data of this virtual character is sent to the smart glasses and displayed to the user.
[1886] Input: User information
[1887] Output: Virtual character data
[1888] Step 3:
[1889] The emotion engine is activated and recognizes emotions from the user's voice and facial expressions. The emotion engine uses the smart glasses' camera and microphone to capture the user's real-time facial expressions and voice, and analyzes emotions based on them.
[1890] Input: User's voice and facial expression data
[1891] Output: Parsed emotion results
[1892] Step 4:
[1893] The smart glasses display a health check form every morning. Users enter their health status, such as body temperature, blood pressure, heart rate, and mood, and send it to a server. The server then uses AI to analyze the collected health data and generate advice based on it.
[1894] Input: User's health status (temperature, blood pressure, heart rate, mood)
[1895] Output: Analysis results and advice
[1896] Step 5:
[1897] The generated advice is sent to the smart glasses, where a virtual character will give it to the user via voice. For example, specific advice such as "Your blood pressure is high, so try to limit your salt intake" is displayed.
[1898] Input: Analysis results and advice
[1899] Output: Voice advice from a virtual character
[1900] Step 6:
[1901] When a user visits a physical store, the smart glasses provide navigation information within the store. When the user specifies the location they want to go to, the server calculates the route and displays it on the smart glasses' display. A virtual character then gives voice instructions, such as "Turn left at the next corner."
[1902] Input: Specify destination
[1903] Output: Navigation information
[1904] Step 7:
[1905] The server collects local event information and recommends events based on the user's hobbies and interests. Users can check the event information through the smart glasses, select the event they want to attend, and register. The server then contacts the organizer to confirm the user's participation.
[1906] Input: Hobbies and interests, local event information
[1907] Output: Recommended event information and participation confirmation
[1908] Step 8:
[1909] The emotion engine checks whether the user is feeling anxious or nervous. If necessary, the virtual character will offer words of encouragement. For example, it will provide advice based on the user's emotions, such as, "You seem to be feeling stressed lately. Why don't you try a relaxing aroma?"
[1910] Input: User emotion data
[1911] Output: Emotion-based response
[1912] The above are the specific processing steps of the system that realizes the application example.
[1913] 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.
[1914] 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.
[1915] 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.
[1916] 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.
[1917] 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.
[1918] 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.
[1919] 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).
[1920] 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.
[1921] 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."
[1922] 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.
[1923] 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).
[1924] 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.
[1925] 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.
[1926] 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.
[1927] 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.
[1928] 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.
[1929] 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.
[1930] 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.
[1931] 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.
[1932] 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.
[1933] 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.
[1934] The following is further disclosed regarding the above embodiment. ...
Claims
1. a means for providing an information entry form; means for transmitting and storing user information; means for generating a virtual character using a generative artificial intelligence; means for displaying the generated virtual character on a user interface; A means for inputting and transmitting health status; a means for analyzing health data and generating advice; A means of collecting local event information and recommending it to users; A system including a means for supporting event participation.
2. The system according to claim 1, wherein a virtual character is generated that resembles a close friend or family member.
3. The system of claim 1 , which provides personalized, optimized advice based on the user's health data.
Citation Information
Patent Citations
Persona chatbot control method and system
JP2022180282A