System

Abstract

A system is provided.SOLUTION: A system comprising: virtual avatar means for interacting with an elderly person; recording means for recording an utterance of the elderly person obtained through the virtual avatar means; conversion means for converting the utterance recorded by the recording means into text data; summarization means for summarizing the text data; storage means for storing the summarized text data generated by the summarization means; and display means for allowing a user to access and check the stored summarized text data.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, an increasing number of elderly people are living alone, making it difficult for family members who live far away to keep track of their elderly parents' health. Furthermore, lack of direct communication can delay the detection of parents' well-being or emergencies. Furthermore, there is a lack of a way to easily obtain biometric data such as body temperature and pulse rate, and to immediately notify family members if an abnormality occurs. To address these issues, we aim to provide a system that easily monitors the health status of elderly people, allowing family members to check and respond to necessary information in a timely manner. [Means for solving the problem]

[0005] The present invention provides a system that includes a virtual avatar means for communicating with elderly people, a recording means for recording the speech, a conversion means for converting the recorded speech into text data, a summarization means for summarizing the text data, and a storage means for saving the summarized text data. The obtained information is accessible to the user through a display means, and if an abnormality is detected, the user is notified by a notification means. This allows the elderly person's health condition to be constantly monitored and allows for prompt response in the event of an abnormality. Furthermore, the virtual avatar means is realized using a smart device, allowing communication with the elderly person in a natural way in everyday life. This improves the well-being of the elderly person and allows family members living far away to keep an eye on them with peace of mind.

[0006] "Virtual avatar means" refers to means that use digital characters and voice interfaces to interact with elderly people.

[0007] "Recording means" refers to a means for recording sounds generated during interaction with a virtual avatar.

[0008] The "conversion means" is a means for converting the voice data recorded by the recording means into text data.

[0009] The "summarization means" is a means for shortening the text data obtained by the conversion means and extracting important information.

[0010] The "storage means" is a means for storing the summarized text data generated by the summarization means in a database or the like.

[0011] The "display means" is a means for providing an interface that allows a user to access and check the summary text data stored in the storage means.

[0012] The "notification means" is a means for reporting to the user when an abnormality occurs in the observed data.

[0013] "Smart devices" are devices that have Internet connectivity and can run a variety of applications, including mobile devices and wearable devices. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

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

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention provides a system for supporting the lives of elderly people and their families by using virtual avatars to interact with elderly people, summarizing and saving the information obtained, and making it easily accessible to families. The program processing of this system is explained below in natural language.

[0036] First, the device (such as a smart device or smartwatch) activates an AI avatar at a set time each day. For example, at 9 a.m., a virtual avatar appears on the elderly person's smartphone or smartwatch and greets them with a greeting such as "Good morning, how are you?" When the elderly person responds, the device records their voice and converts it into text data using a voice recognition engine.

[0037] The converted text data is then sent over the internet to a server, which runs the data through a generative AI model to create a summary of the conversation, which is then stored in a database.

[0038] Users (family members) can access the server via a dedicated app or web browser and check the saved summary text data. For example, when a user opens the app and selects a desired date from the list of conversation summaries, the detailed summary content is displayed.

[0039] The system also includes anomaly detection and notification functions. The device regularly monitors the elderly person's biological data, such as their body temperature and pulse, and if an abnormality is detected, it sends the data to the server. If the server detects an abnormality that exceeds a preset threshold, it notifies the user. For example, if an elderly person's body temperature exceeds 38 degrees, the server immediately sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check."

[0040] As a specific example, if a device launches a virtual avatar at 9:00 a.m. and asks an elderly person, "Did you sleep well last night?" and the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to a server. The server summarizes this information and saves it as, "I slept well, but I had a slight cough." The user can review this summary later and take action if necessary.

[0041] The above is an embodiment of the present invention. This system allows elderly people and their families to communicate smoothly over distance and to properly understand their health conditions.

[0042] The processing flow will be explained below.

[0043] Step 1:

[0044] The device is scheduled to launch the virtual avatar at a specific time each day (e.g., 9:00 a.m.). The device's internal clock and schedule function are used to launch the AI ​​avatar application at the specified time.

[0045] Step 2:

[0046] The device displays a virtual avatar on the screen and displays and plays a voice message to the elderly, such as "Good morning, did you sleep well last night?" The virtual avatar continues the conversation as appropriate until the elderly responds.

[0047] Step 3:

[0048] When the elderly person answers, the terminal records the voice. The voice of the elderly person is recorded using a recording means and passed to the next process.

[0049] Step 4:

[0050] The device converts the recorded voice data into text data using a voice recognition engine. Using voice recognition technology, the device converts the voice data into text information and generates text data.

[0051] Step 5:

[0052] The device sends the converted text data to the server via the Internet. The device sends an HTTP POST request to the server, and the text data is transferred to the server.

[0053] Step 6:

[0054] The server then passes the received text data to a generative AI model that analyzes the text data, extracts key information, and generates a summary of the conversation.

[0055] Step 7:

[0056] The server stores the generated summaries and the original text data in a database, and creates an index in the database to efficiently store the summaries and original data.

[0057] Step 8:

[0058] Users access the server using a dedicated app or a web browser and log in by entering their user authentication information.

[0059] Step 9:

[0060] The user can view a list of saved conversation summaries through a dedicated app or a web browser, send a request to the server to retrieve a list of conversation logs, and select any summary from there to view its details.

[0061] Step 10:

[0062] The device periodically measures the elderly person's body temperature and pulse rate and sends the data to a server. Biometric data is acquired using temperature and pulse sensors and sent to the server via the Internet.

[0063] Step 11:

[0064] The server analyzes the received biometric data and detects abnormalities if the data exceeds the threshold. An analysis module on the server checks the data and triggers a notification if an abnormality is detected.

[0065] Step 12:

[0066] The server immediately sends an abnormality notification to the user via email or smartphone push notification, such as "Your body temperature is high. Please check."

[0067] The above is the specific processing flow of this system. This detailed explanation will clarify what actions are required at each step.

[0068] Example 1

[0069] 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."

[0070] There is a need for a system that can efficiently collect information on the health status and daily life of elderly people and allow their families to easily access it. However, with existing technology, it is difficult to have a natural dialogue with the elderly, summarize the content of the dialogue, and provide it to their families. There is also a need for a system that can quickly notify their families if an abnormality is detected. To solve these issues, it is essential to have technology that can intelligently process the information obtained from dialogue with the elderly and provide it efficiently.

[0071] 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.

[0072] In this invention, the server includes a virtual assistant means for interacting with the elderly, a recording means for recording the elderly's speech obtained through the virtual assistant means, a conversion means for converting the speech recorded by the recording means into text data using a natural language processing engine, a summary generation means for summarizing the text data using a generative artificial intelligence model, a storage means for saving the summarized text data generated by the summary generation means in a database, a display means for allowing a user to access and check the saved summarized text data via dedicated software or a web application, and a monitoring means for periodically monitoring the elderly's biological information and transmitting the data to the server if an abnormality is detected. This allows information on the elderly's health condition and daily life to be efficiently collected, easily accessed and checked by family members, and quickly notified if an abnormality is detected.

[0073] A "virtual assistant" is an artificial intelligence interface used to interact with seniors.

[0074] The "recording means" is a device or function for recording the speech of the elderly person obtained through the virtual assistant means.

[0075] "Conversion means" refers to a device or function for converting recorded speech into text data using a natural language processing engine.

[0076] The "summary generation means" is a device or function for summarizing text data using a generative artificial intelligence model.

[0077] The "storage means" is a device or function for storing the summarized text data generated by the summary generation means in a database.

[0078] "Display means" refers to a device or function that allows a user to access and view the stored summary text data via dedicated software or a web application.

[0079] The "monitoring means" is a device or function that periodically monitors the elderly person's biological information and transmits the data to a server if an abnormality is detected.

[0080] The "abnormality notification means" is a device or function for notifying the user of an abnormality when an abnormality is detected in the display means.

[0081] "Electronic devices" refers to all devices with communication capabilities, such as smart devices, that are used to realize AI assistant functions.

[0082] A "generative artificial intelligence model" is an artificial intelligence algorithm that generates summaries and responses from input data through natural language processing, etc.

[0083] This invention is a system designed to support the lives of elderly people and their families, using a virtual assistant to interact with elderly people, summarize and store the information, and make it easily accessible to families. Below, the program processing of this system is explained in natural language.

[0084] First, the device is an electronic device with communication capabilities, such as a smartwatch or smartphone. The device activates the virtual assistant at a set time each day. The virtual assistant is a conversational interface using AI that periodically greets and asks questions to the elderly. For example, at 9 a.m., the smartphone activates the assistant and greets the elderly with, "Good morning, how are you?" When the elderly responds verbally, the device records the audio.

[0085] The recorded voice data is converted into text data using a natural language processing engine such as Google® Speech-to-Text API or IBM Watson® Speech to Text, and the converted text data is sent to a server via the Internet.

[0086] The server then runs the received text data through a generative AI model, such as OpenAI® GPT-4®, to generate a summary of the conversation. The system generates summaries using prompts, such as "Please summarize the following dialogue. Please indicate the elderly person's sleep status."

[0087] The generated summary text is stored in a database such as MySQL® or MongoDB. The saved summary text data can be accessed by the user (family member) via dedicated software or a web application. The user can access the server using an app or a web browser and check the saved summary text data. For example, if a user opens the app and selects the summary for "2023-10-05," the details "I slept well, but I had a slight cough" will be displayed.

[0088] Furthermore, the system includes anomaly detection and notification functions. The device periodically monitors the elderly person's vital signs, such as body temperature and pulse rate. If an anomaly is detected, the data is sent to the server. If the data exceeds a set threshold, the server notifies the user of the anomaly. For example, Firebase Cloud Messaging can be used to send a push notification to the user's smartphone saying, "Mom's temperature is high. Please check."

[0089] For example, if a virtual assistant asks "Did you sleep well last night?" at 9 a.m. and an elderly person replies, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to a server. The server summarizes this information and saves it as "I slept well, but I had a slight cough." The user can view this summary in a dedicated app and take action if necessary.

[0090] Examples of prompts are:

[0091] "Please summarize the following dialogue and indicate what the elderly person's sleep situation was like."

[0092] Such a system would enable efficient collection of information on the health status and daily life of elderly people, allowing family members to easily access and check the information and receive prompt notification if any abnormalities are detected.

[0093] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0094] Step 1: Launch the terminal

[0095] The device can be a smartwatch or smartphone, and at a set time each day, the device will activate the virtual assistant. For example, at 9:00 a.m., the device will sound an alarm and the virtual assistant will appear on the screen.

[0096] Input: Current time (9:00 AM)

[0097] Output: The virtual assistant appears on the screen and begins interacting with you.

[0098] What it does: The device software will wake up the virtual assistant at the set time and display a greeting such as "Good morning, how are you?"

[0099] Step 2: Talk to the elderly

[0100] The virtual assistant greets the elderly person and asks them questions, and the elderly person responds verbally. Recording begins.

[0101] Input: Virtual assistant greeting or question

[0102] Output: Elderly person's response voice data

[0103] Specific operation: For example, in response to the question, "Did you sleep well last night?", the elderly person answers, "Yes, I slept well." The device then records this.

[0104] Step 3: Speech to text

[0105] The device converts the elderly person's recorded voice data into text data using a natural language processing engine.

[0106] Input: Recorded audio data

[0107] Output: Text data

[0108] Specific operation: The device uses the Google Speech-to-Text API to convert the voice data into text data such as "Yes, I slept well."

[0109] Step 4: Sending data to the server

[0110] The converted text data is sent to a server via the Internet.

[0111] Input: Text data

[0112] Output: Text data is sent to the server

[0113] Specific operation: The device uses Wi-Fi or mobile network to send the converted text data to the server.

[0114] Step 5: Generate conversation summaries

[0115] The server runs the received text data through a generative AI model to create a summary of the conversation, using prompts to instruct the generation of the summary.

[0116] Input: Received text data

[0117] Output: Summary text data

[0118] Specific operation: The server passes the text "Did you sleep well last night?" and "Yes, I slept well" to the AI ​​model along with the prompt "Please summarize the following text," and generates the summary "I slept well."

[0119] Step 6: Saving to the Database

[0120] The generated summary text is stored in a database.

[0121] Input: Summary text data

[0122] Output: Summary text data stored in a database

[0123] What happens: The server saves the entry "2023-10-05: Sleep well" in the MySQL database.

[0124] Step 7: User access to data

[0125] Users can access the server via a dedicated app or web application to view the stored summary text data.

[0126] Input: User access request

[0127] Output: Summary text data displayed on the user's terminal

[0128] Specific operation: The user opens the dedicated app on their smartphone, selects the specified date "2023-10-05", and the summary "I slept well" is displayed.

[0129] Step 8: Anomaly detection and notification

[0130] The device periodically monitors the elderly person's body temperature and pulse, and if an abnormality is detected, it sends the data to the server, which then notifies the user.

[0131] Input: Biometric data

[0132] Output: Abnormality notification

[0133] Specific operation: The device measures the elderly person's temperature, and if it exceeds 38 degrees, it sends the data to the server. The server detects the abnormality and sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check."

[0134] (Application example 1)

[0135] 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."

[0136] It is often difficult to effectively monitor the safety and health of elderly people remotely, especially when sudden changes in their physical condition or minor everyday abnormalities are detected. Therefore, there is a need for a system that allows family members and caregivers to more reliably monitor the safety and health of elderly people and respond quickly when necessary.

[0137] 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.

[0138] In this invention, the server includes virtual character means for interacting with the elderly person, recording means for recording speech from the elderly person obtained through the virtual character means, conversion means for converting the speech recorded by the recording means into text data, summarizing means for summarizing the text data, storage means for storing the summarized text data generated by the summarizing means, display means for enabling a user to access and check the stored summarized text data, monitoring means for periodically measuring and recording biometric data of the elderly person, detection means for detecting abnormalities based on the biometric data, and notification means for sending a notification when an abnormality is detected by the detection means. This makes it possible to effectively remotely monitor the safety and health of the elderly person and to quickly respond to abnormalities when they occur.

[0139] The "virtual character means" is a character display function used to have a conversation with the elderly person.

[0140] The "recording means" is a function for recording the statements of the elderly person obtained through the virtual character means.

[0141] The "conversion means" is a function that converts the utterances recorded by the recording means into text data.

[0142] The "summarization means" is a function for summarizing the text data obtained by the conversion means.

[0143] The "storage means" is a function for storing the summarized text data generated by the summarization means.

[0144] The "display means" is a function that allows the user to access and check the saved summary text data.

[0145] "Monitoring means" refers to a function that periodically measures and records the elderly person's biometric data.

[0146] The "detection means" is a function that detects abnormalities based on the biological data obtained by the monitoring means.

[0147] The "notification means" is a function that sends a notification when an abnormality is detected by the detection means.

[0148] "Mobile information terminal" refers to a portable information processing device such as a smartphone or tablet.

[0149] The present invention is a system for effectively remotely monitoring the safety and health status of elderly people, and provides a concrete means for family members and caregivers to understand the elderly person's condition using a virtual character. The main components of this system include a virtual character means, a recording means, a conversion means, a summarization means, a storage means, a display means, a monitoring means, a detection means, and a notification means.

[0150] Program processing

[0151] Hardware and Software Use

[0152] This system uses the following hardware and software:

[0153] Smartphones: Used as everyday computing devices by seniors.

[0154] Smartwatch: Used as a device to collect biometric data such as body temperature, pulse, and blood pressure from the elderly and send it to a smartphone.

[0155] TENSORFLOW® / Generative AI Model: Used to summarize interaction data with virtual characters.

[0156] Firebase Cloud Messaging: Used as an external notification service to send push notifications.

[0157] The smartphone functions as an interface for conversation between the elderly person and the virtual character, displaying the virtual character at a set time each day and saying, "Good morning, how are you?" When the elderly person responds, the smartphone records the voice and converts it into text data using a voice recognition engine.

[0158] Data processing and calculation

[0159] The converted text data is sent to a server via the internet, where it is summarized using a generative AI model (e.g., TensorFlow). This summarized text data is stored in a database and can be accessed and viewed by users via a dedicated app or web browser.

[0160] Furthermore, the biometric data from the smartwatch is sent to a smartphone and monitored by a server. The server analyzes the periodically sent data, such as body temperature and pulse rate, and if an abnormality is detected, it sends a push notification to the user's smartphone using Firebase Cloud Messaging. For example, if an elderly person's body temperature exceeds 38 degrees, a message is immediately sent saying, "Your mother's temperature is high. Please check it."

[0161] Specific examples

[0162] As a concrete example, a virtual character might ask at 9 a.m., "Good morning, did you sleep well last night?" and the elderly person might respond, "Yes, I slept well, but I had a slight cough." This conversation is recorded, converted into text, and then sent to a server. The server summarizes the information as "I slept well, but I had a slight cough" and saves it. The user can later review this summary and take action if necessary.

[0163] Prompt Sentence Examples

[0164] Prompt for generative AI model:

[0165] "Please summarize the following conversation:

[0166] Virtual Character: Good morning, how are you?

[0167] Elderly person: Yes, I'm fine, but I have a slight cough.

[0168] Summary to generate: "I'm fine, but I have a cough."

[0169] The above is an embodiment of the present invention, which enables effective remote monitoring of the safety and health status of elderly people and rapid response in the event of an abnormality.

[0170] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0171] Step 1:

[0172] The terminal activates the virtual character means at a fixed time every day. The input is the current time, and the output is a virtual character that appears and speaks, "Good morning, how are you?" This starts a conversation with the elderly person.

[0173] Step 2:

[0174] The elderly person responds to the virtual character. The input is the elderly person's voice data, and the voice is recorded in a recording means as the output. This allows the content of the conversation to be saved.

[0175] Step 3:

[0176] The terminal converts the recorded voice data into text data using a conversion means. The input is voice data, and text data is generated as output. This converts voice information into text format.

[0177] Step 4:

[0178] The terminal sends the converted text data to a server via the Internet. The input is text data, and the data arrives at the server as output. This allows the data to be aggregated on a remote server.

[0179] Step 5:

[0180] The server summarizes the received text data through a generative AI model. The input is text data, and the output is summarized text data. This allows the content of the conversation to be summarized concisely.

[0181] Step 6:

[0182] The server saves the summarized text data in a database. The input is the summarized text data, and the saved data is added to the database as an output. This allows the summarized information to be managed.

[0183] Step 7:

[0184] The user accesses the server through a dedicated app or a web browser and checks the saved summary text data. The input is the user's request, and the summary text data is displayed as output. This allows family members to understand the condition of the elderly person.

[0185] Step 8:

[0186] The device receives the elderly person's biometric data from the smartwatch and sends it to the server. The input is biometric data such as body temperature and pulse rate, and the output data reaches the server. This allows real-time health status monitoring.

[0187] Step 9:

[0188] The server periodically analyzes biometric data and detects abnormalities. The input is biometric data, and the output is anomaly detection results. This allows abnormalities in health status to be confirmed.

[0189] Step 10:

[0190] When an abnormality is detected, the server sends a push notification to the user using a notification method. The input is the abnormality detection result, and the output is a notification message sent to the user's device. This enables emergency response.

[0191] 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.

[0192] The present invention provides a system that can interact with elderly people, summarize and store the information obtained, and provide easy access to the user. In addition to the virtual avatar means, the present invention also uses an emotion engine to recognize the emotions of the elderly and provide further information. The program processing of this system is explained below in natural language.

[0193] First, the device (such as a smart device or smartwatch) activates an AI avatar at a set time each day. For example, at 9 a.m., a virtual avatar appears on the elderly person's smartphone or smartwatch and greets them with a greeting such as "Good morning, how are you?" When the elderly person responds, the device records their voice, and the recorded data is converted into text using a voice recognition engine.

[0194] The converted text data is then sent over the internet to a server, which runs the data through a generative AI model to create a summary of the conversation, which is then stored in a database.

[0195] Furthermore, the terminal recognizes the emotions of the elderly person during the dialogue using an emotion engine. The emotion engine analyzes the elderly person's voice tone, facial expressions, and language patterns to recognize emotions such as joy, sadness, anger, etc. The recognized emotion data is included in the summarized text data generated by the summarization means.

[0196] Users (family members) can access the server via a dedicated app or web browser and check the saved summary text data and emotion data. For example, when a user opens the app and selects the desired date from the displayed list of conversation summaries, the detailed summary content and emotion data are displayed. This allows the user to understand the emotional state of the elderly person on that day.

[0197] The system also includes anomaly detection and notification functions. The device regularly monitors the elderly person's biological data, such as their body temperature and pulse, and if an abnormality is detected, it sends the data to the server. If the server detects an abnormality that exceeds a preset threshold, it notifies the user. For example, if an elderly person's body temperature exceeds 38 degrees, the server immediately sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check."

[0198] As a specific example, if a device launches a virtual avatar at 9:00 a.m. and asks an elderly person, "Did you sleep well last night?" and the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to the server. The server summarizes this information and saves it as "I slept well, but I had a slight cough." If the emotion engine recognizes "relief" in the elderly person's voice, this emotion data is also saved. The user can later review this summary and emotion data and take action as needed.

[0199] The above is an embodiment of the present invention. This system allows elderly people and their families to communicate smoothly over distances and to properly understand changes in their health conditions and emotions.

[0200] The processing flow will be explained below.

[0201] Step 1:

[0202] The device activates the virtual avatar at a fixed time each day (e.g., 9:00 a.m.), and the virtual avatar greets the elderly person by voice, such as "Good morning, did you sleep well last night?"

[0203] Step 2:

[0204] The terminal records the elderly person's response, and uses a recording means to record the elderly person's voice and passes it on to the next process.

[0205] Step 3:

[0206] The device runs the recorded voice data through a voice recognition engine and converts it into text data. Voice recognition technology is used to convert voice into text information, generating text data.

[0207] Step 4:

[0208] The device sends the generated text data to the server via the Internet using an HTTP POST request to send the text data to a specified endpoint on the server.

[0209] Step 5:

[0210] The server inputs the received text data into a generative AI model to generate a summary of the conversation. The generative AI model analyzes the text data, extracts important information, and creates a concise summary.

[0211] Step 6:

[0212] The server stores the generated summaries and the original text data in a database, and creates an index in the database to efficiently store the summaries and original data.

[0213] Step 7:

[0214] The device activates an emotion engine that recognizes the elderly person's emotions during the conversation. The emotion engine generates emotion data by analyzing the elderly person's voice tone, facial expressions, and language patterns.

[0215] Step 8:

[0216] The device sends the generated emotion data together with the text data to the server, where the emotion data and the text data are stored together.

[0217] Step 9:

[0218] The user (family member) accesses the server from a dedicated app or web browser and logs in. The user enters authentication information to gain access to the server.

[0219] Step 10:

[0220] Users can check the saved summaries and emotion data through a dedicated app or a web browser. After logging in, they send a request to the server to retrieve the saved conversation summaries and emotion data.

[0221] Step 11:

[0222] The device periodically measures the elderly person's body temperature and pulse rate and sends the data to a server. The device measures biometric data using sensors and sends the data to the server via the Internet.

[0223] Step 12:

[0224] The server analyzes the received biometric data and detects abnormalities if the data exceeds preset thresholds. An analysis module on the server checks the data and triggers a notification if an abnormality is detected.

[0225] Step 13:

[0226] If an abnormality is detected, the server will notify the user via email or push notification, sending an alert such as "Your temperature is high. Please check."

[0227] The above is the specific processing flow of this system. This detailed explanation will clarify what actions are required at each step.

[0228] Example 2

[0229] 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."

[0230] There is a need to provide a means to reduce the sense of loneliness felt by the elderly and to enable family members and caregivers to properly understand changes in their health status and emotions, but existing systems lack the means to provide multiple integrated functions such as summarizing conversation content, recognizing emotions, detecting abnormalities in biometric data, and notifying them. There is also a need to develop a system that can efficiently manage and notify data while smoothly communicating with the elderly.

[0231] 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.

[0232] In this invention, the server includes a virtual avatar means for interacting with the elderly person, a recording means for recording the elderly person's speech, a conversion means for converting the recorded speech into text data, a summarization means for summarizing the text data, a storage means for saving the summarized text data, a display means for making the saved summarized text data accessible, an emotion recognition means for recognizing the emotions of the elderly person, an additional storage means for saving the emotion data, a monitoring means for monitoring the elderly person's biometric data, and a notification means for notifying the user of detected abnormalities. This makes it possible to perform the summarization of the content of the conversation with the elderly person, the recording of changes in emotions, and the detection and notification of abnormalities in the biometric data in an integrated manner.

[0233] "Virtual avatar means" refers to a virtual character used to interact with the senior citizen.

[0234] "Recording means" refers to a device or function that records the speech of the elderly person in audio form.

[0235] "Conversion means" refers to a device or function that converts recorded voice data into text data.

[0236] The "summarization means" refers to a function of concisely summarizing the text data obtained by the conversion means.

[0237] The "storage means" refers to a device or function that records and stores the summarized text data generated by the summarization means.

[0238] "Display means" refers to a device or function that allows a user to visually confirm the saved summary text data.

[0239] "Emotion recognition means" refers to a device or function that analyzes and recognizes emotions from the voice and facial expressions of elderly people.

[0240] The "additional storage means" refers to a device or function that records and stores emotion data generated by the emotion recognition means.

[0241] "Monitoring means" refers to a device or function that continuously measures and monitors the elderly person's biometric data (such as body temperature and heart rate).

[0242] The "notification means" refers to a device or function that notifies the user of an abnormality detected by the monitoring means.

[0243] "Biometric data" refers to data that indicates an individual's physical condition, such as body temperature and heart rate.

[0244] The present invention provides a system that can engage in dialogue with elderly people, summarize information obtained from the dialogue, recognize emotions, and provide easy user access. Furthermore, the system also has the function of monitoring the elderly person's biometric data and notifying the user if an abnormality is detected. A specific embodiment of this system will be described below.

[0245] First, the device (e.g., a smartphone or smartwatch) activates the virtual avatar means at a fixed time each day. For example, at 9:00 a.m., the virtual avatar appears on the elderly person's device and greets them with "Good morning, how are you?" When the elderly person responds, the device records the voice and acquires the recorded data. This recorded data is converted into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). The generated text data is sent to a server via the Internet.

[0246] The server then applies a generative AI model (e.g., OpenAI GPT-3®) to the received text data to create a summary. This summarized text data is stored in a database. Furthermore, the device uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the elderly person's emotions during the conversation. The emotion engine analyzes the elderly person's voice tone, facial expressions, and language patterns to recognize emotions such as joy, sadness, and anger. The recognized emotion data is included in the summarized text data generated by the summarization means.

[0247] Users (family members or caregivers) can access the server via a dedicated app or web browser and check the saved summary text data and emotion data. For example, when a user opens the app and selects the desired date from the displayed list of conversation summaries, the detailed summary content and emotion data are displayed. This allows the user to understand the emotional state of the elderly person on that day.

[0248] Furthermore, the device regularly monitors the elderly person's biological data, such as their body temperature and pulse rate. If an abnormality is detected, the data is sent to the server. If the server exceeds a preset threshold, it notifies the user of the abnormality. For example, if an elderly person's body temperature exceeds 38 degrees, the server immediately sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check it."

[0249] As a specific example, if a device launches a virtual avatar at 9:00 a.m. and asks an elderly person, "Did you sleep well last night?" and the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to the server. The server summarizes this information and saves it as "I slept well, but I had a slight cough." If the emotion engine recognizes "relief" in the elderly person's voice, this emotion data is also saved. The user can later review this summary and emotion data and take action as needed.

[0250] Here are some example prompts for creating summaries using a generative AI model (e.g., GPT-3):

[0251] Input text: "Yes, I slept well, but I have a bit of a cough."

[0252] Prompt: "Summarize the following conversation."

[0253] Example of generated summary: "I slept well, but I had a cough."

[0254] This concludes the "Mode for Carrying Out the Invention" of the present invention. This system enables elderly people and their families to communicate smoothly over distances and to appropriately understand changes in their health status and emotions.

[0255] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0256] Step 1:

[0257] The device launches the virtual avatar.

[0258] How it works: When the device's internal clock hits 9:00 AM, a virtual avatar application will automatically launch. The virtual avatar will then say "Good morning, how are you?"

[0259] Input: Clock information in the device.

[0260] Output: Virtual avatar activation and voice utterance.

[0261] Step 2:

[0262] The elderly person responds by voice.

[0263] Specific operation: The elderly person responds to the virtual avatar's speech by saying, "Yes, I'm fine." The device's microphone records this voice.

[0264] Input: Senior citizen's voice.

[0265] Output: Recorded audio data.

[0266] Step 3:

[0267] Convert the recorded data into text data.

[0268] Specific operation: The device sends the recorded voice data to a speech recognition engine (e.g., Google Cloud Speech-to-Text API). The speech recognition engine converts the voice "Yes, I'm fine" into text and returns it to the device.

[0269] Input: Audio data.

[0270] Output: Text data.

[0271] Step 4:

[0272] Sends text data to the server.

[0273] Specific operation: The terminal sends the converted text data to the server via the Internet. At this time, the data is encrypted before being sent.

[0274] Input: Text data.

[0275] Output: The text data sent to the server.

[0276] Step 5:

[0277] The server summarizes the text data.

[0278] How it works: The server inputs the received text data into a generative AI model (e.g., OpenAI GPT-3). The model generates a summary based on a pre-set prompt. For example, a summary such as "I slept well, but I had a cough" is generated.

[0279] Input: text data, prompt statement.

[0280] Output: Summary text data.

[0281] Step 6:

[0282] Recognizing the emotions of the elderly using an emotion recognition engine.

[0283] Specific operation: During the conversation, the device sends the recorded voice to an emotion recognition engine (e.g., IBM Watson Tone Analyzer). The engine analyzes the voice tone and generates emotion data. For example, the emotion data for "relief."

[0284] Input: Audio data.

[0285] Output: Emotion data.

[0286] Step 7:

[0287] Stores sentiment data and summary data.

[0288] Specific operation: The server stores the generated summary text data and emotion data in a database, which can be accessed by users in the future.

[0289] Input: Summary text data, sentiment data.

[0290] Output: Data stored in the database.

[0291] Step 8:

[0292] The user accesses the data.

[0293] Specific operation: The user accesses the server using a dedicated app or a web browser and logs in. An interface is displayed where the saved summary data and emotion data can be viewed. The user can select the desired date to view the data.

[0294] Input: The user's access request.

[0295] Output: Display of summary data and sentiment data.

[0296] Step 9:

[0297] Provides biometric data monitoring and abnormality notification functions.

[0298] Specific operation: The device periodically measures the elderly person's biometric data (e.g., body temperature and heart rate) using sensors. If an abnormality is detected, the data is sent to the server. If the server detects a value that exceeds a set threshold, it sends an abnormality notification (e.g., "Mom's body temperature is high. Please check it.") to the user's smartphone.

[0299] Input: Biometric data.

[0300] Output: Abnormality notification.

[0301] (Application example 2)

[0302] 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."

[0303] There is a need for a system that allows family members and caregivers to accurately understand the elderly's condition by smoothly conducting dialogue with them and appropriately storing those records. However, existing systems have difficulty accurately detecting changes in the elderly's emotions and health status and responding promptly based on those changes. Furthermore, because summarization and emotion analysis of the elderly's speech are not automated, family members and caregivers must take the time and effort to check the speech. The present invention aims to solve these problems.

[0304] 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.

[0305] In this invention, the server includes a virtual avatar means, a recording means, a conversion means, a summarizing means, a storage means, a display means, an emotion engine means, and an emotion data storage means, which allows for smooth dialogue with the elderly, automates the summarization of the dialogue content and the analysis and storage of emotion data, and makes it possible to quickly grasp and respond to changes in the elderly's emotions and health condition.

[0306] "Virtual avatar means" refers to devices or software that simulate conversations with elderly people using audio and video and record the content of those conversations.

[0307] A "recording means" is a device or software that records the elderly person's speech as digital data.

[0308] The "conversion means" is software or an algorithm that converts the audio data obtained by the recording means into text data.

[0309] The "summarization means" is software or an algorithm that concisely summarizes the text data obtained by the conversion means.

[0310] The "storage means" is a device or software for storing the text data and emotion data generated by the summarization means in a database or storage device.

[0311] A "display means" is a device or software that allows a user to access and view data stored by a storage means.

[0312] The "emotion engine means" is software or algorithm that analyzes the elderly person's speech, facial expressions, and tone of voice to recognize their emotional state.

[0313] The "emotion data storage means" is a device or software that stores the emotion data recognized by the emotion engine means by including it in the summary text data.

[0314] The present invention provides a system that summarizes information obtained through dialogue with elderly people, analyzes and stores emotion data based on the information, and allows users to easily access the data. The following system is applied as an embodiment of the invention.

[0315] First, a smart device (such as a smartphone or tablet) is used as the terminal. A virtual avatar is installed on this terminal, and it periodically interacts with the elderly. The interaction is conducted via voice, and the content of the interaction is saved as digital data using a recording device.

[0316] The recorded voice data is converted into text data by a conversion means using a voice recognition engine, and the converted text data is then sent to a server.

[0317] The server summarizes the received text data using a summarization means. The summarization means uses natural language processing technology (e.g., a generative AI model). The summarized text data is stored in a database by a storage means.

[0318] A distinctive feature of this system is the emotion engine means, which analyzes voice tone, facial expressions, and language patterns to recognize the emotions of the elderly. This emotion data is stored in the emotion data storage means together with the text data generated by the summarization means.

[0319] Users can access and check the saved summary text data and emotion data using dedicated display means. For example, they can access the database via a dedicated application or a web browser. Users can easily check past conversation data and emotion data, and understand changes in the health status and emotions of elderly people.

[0320] Furthermore, the system is also equipped with anomaly detection and notification functions. The terminals and server regularly monitor the elderly person's biological data, such as their body temperature and pulse rate, and if an abnormality is detected, the user is notified via a notification means. In this case, push notifications can be used to quickly notify the user of the abnormality.

[0321] As a specific example, the device starts up a virtual avatar every day at 9:00 a.m. and asks the elderly person, "Did you sleep well last night?" If the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded and converted into text data. It is then sent to a server and saved as summarized text data, such as "I slept well, but I had a slight cough." The emotion engine means also recognizes "relief" from the elderly person's voice and saves it as emotion data. This data can be later checked by the user using a dedicated application. An example of a specific prompt sentence is, "Did you sleep well last night?"

[0322] The above is a specific embodiment for carrying out the present invention. This system is a great help to family members and caregivers because it can properly grasp the emotions and health status of elderly people and respond quickly.

[0323] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0324] Step 1:

[0325] The terminal (smart device) periodically (e.g., at 9 a.m.) wakes up the virtual avatar. The virtual avatar speaks a prompt to the elderly (e.g., "Good morning, how are you?") and receives a verbal response from the elderly. In this step, the input is the elderly's voice, and the output is the voice data.

[0326] Step 2:

[0327] The terminal uses a recording means to record the elderly person's response as digital voice data. The recorded voice data is temporarily stored in the device's memory. In this step, the input is the elderly person's response voice, and the output is digital voice data.

[0328] Step 3:

[0329] The device uses a conversion means to convert the recorded voice data into text data. A speech recognition engine (e.g., Google Speech-to-Text API) is used to recognize this voice data as text. In this step, the input is digital voice data and the output is text data.

[0330] Step 4:

[0331] The terminal sends the converted text data to the server via the Internet. The text data is encrypted and sent using a secure communication protocol (e.g., HTTPS). In this step, the input is the text data, and the output is the data sent to the server.

[0332] Step 5:

[0333] The server summarizes the received text data using a generative AI model. A natural language processing algorithm is used as a summarization method to remove redundant parts and extract important information. In this step, the input is text data, and the output is summarized text data.

[0334] Step 6:

[0335] The server stores the summarized text data in a database using a storage means. The stored data also includes a timestamp and identification information. In this step, the input is the summarized text data, and the output is the data stored in the database.

[0336] Step 7:

[0337] The server uses an emotion engine means to analyze the emotion of the elderly person from the received text data and voice tone. As a result of the analysis, emotion data is generated. In this step, the input is the text data and voice tone, and the output is the emotion data.

[0338] Step 8:

[0339] The server adds the emotion data to the summarized text data and stores it in a database using the emotion data storage means. In this step, the input is the emotion data and the summarized text data, and the output is stored data including the emotion data.

[0340] Step 9:

[0341] The user checks the saved summary text data and emotion data using a dedicated display means, for example, by accessing and displaying the data using a dedicated application or a web browser. In this step, the input is data from the database, and the output is the displayed information.

[0342] Step 10:

[0343] The server monitors biometric data (e.g., body temperature, pulse rate), and if an abnormality is detected, immediately sends a notification to the user using a notification means. This notification is sent as a push notification to a smartphone, etc. In this step, the input is biometric data, and the output is a notification to the user.

[0344] 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.

[0345] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0346] 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.

[0347] [Second embodiment]

[0348] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0349] 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.

[0350] 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).

[0351] 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.

[0352] 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.

[0353] 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).

[0354] 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.

[0355] 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.

[0356] 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.

[0357] 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.

[0358] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0359] 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."

[0360] The present invention provides a system for supporting the lives of elderly people and their families by using virtual avatars to interact with elderly people, summarizing and saving the information obtained, and making it easily accessible to families. The program processing of this system is explained below in natural language.

[0361] First, the device (such as a smart device or smartwatch) activates an AI avatar at a set time each day. For example, at 9 a.m., a virtual avatar appears on the elderly person's smartphone or smartwatch and greets them with a greeting such as "Good morning, how are you?" When the elderly person responds, the device records their voice and converts it into text data using a voice recognition engine.

[0362] The converted text data is then sent over the internet to a server, which runs the data through a generative AI model to create a summary of the conversation, which is then stored in a database.

[0363] Users (family members) can access the server via a dedicated app or web browser and check the saved summary text data. For example, when a user opens the app and selects a desired date from the list of conversation summaries, the detailed summary content is displayed.

[0364] The system also includes anomaly detection and notification functions. The device regularly monitors the elderly person's biological data, such as their body temperature and pulse, and if an abnormality is detected, it sends the data to the server. If the server detects an abnormality that exceeds a preset threshold, it notifies the user. For example, if an elderly person's body temperature exceeds 38 degrees, the server immediately sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check."

[0365] As a specific example, if a device launches a virtual avatar at 9:00 a.m. and asks an elderly person, "Did you sleep well last night?" and the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to a server. The server summarizes this information and saves it as, "I slept well, but I had a slight cough." The user can review this summary later and take action if necessary.

[0366] The above is an embodiment of the present invention. This system allows elderly people and their families to communicate smoothly over distance and to properly understand their health conditions.

[0367] The processing flow will be explained below.

[0368] Step 1:

[0369] The device is scheduled to launch the virtual avatar at a specific time each day (e.g., 9:00 a.m.). The device's internal clock and schedule function are used to launch the AI ​​avatar application at the specified time.

[0370] Step 2:

[0371] The device displays a virtual avatar on the screen and displays and plays a voice message to the elderly, such as "Good morning, did you sleep well last night?" The virtual avatar continues the conversation as appropriate until the elderly responds.

[0372] Step 3:

[0373] When the elderly person answers, the terminal records the voice. The voice of the elderly person is recorded using a recording means and passed to the next process.

[0374] Step 4:

[0375] The device converts the recorded voice data into text data using a voice recognition engine. Using voice recognition technology, the device converts the voice data into text information and generates text data.

[0376] Step 5:

[0377] The device sends the converted text data to the server via the Internet. The device sends an HTTP POST request to the server, and the text data is transferred to the server.

[0378] Step 6:

[0379] The server then passes the received text data to a generative AI model that analyzes the text data, extracts key information, and generates a summary of the conversation.

[0380] Step 7:

[0381] The server stores the generated summaries and the original text data in a database, and creates an index in the database to efficiently store the summaries and original data.

[0382] Step 8:

[0383] Users access the server using a dedicated app or a web browser and log in by entering their user authentication information.

[0384] Step 9:

[0385] The user can view a list of saved conversation summaries through a dedicated app or a web browser, send a request to the server to retrieve a list of conversation logs, and select any summary from there to view its details.

[0386] Step 10:

[0387] The device periodically measures the elderly person's body temperature and pulse rate and sends the data to a server. Biometric data is acquired using temperature and pulse sensors and sent to the server via the Internet.

[0388] Step 11:

[0389] The server analyzes the received biometric data and detects abnormalities if the data exceeds the threshold. An analysis module on the server checks the data and triggers a notification if an abnormality is detected.

[0390] Step 12:

[0391] The server immediately sends an abnormality notification to the user via email or smartphone push notification, such as "Your body temperature is high. Please check."

[0392] The above is the specific processing flow of this system. This detailed explanation will clarify what actions are required at each step.

[0393] Example 1

[0394] 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."

[0395] There is a need for a system that can efficiently collect information on the health status and daily life of elderly people and allow their families to easily access it. However, with existing technology, it is difficult to have a natural dialogue with the elderly, summarize the content of the dialogue, and provide it to their families. There is also a need for a system that can quickly notify their families if an abnormality is detected. To solve these issues, it is essential to have technology that can intelligently process the information obtained from dialogue with the elderly and provide it efficiently.

[0396] 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.

[0397] In this invention, the server includes a virtual assistant means for interacting with the elderly, a recording means for recording the elderly's speech obtained through the virtual assistant means, a conversion means for converting the speech recorded by the recording means into text data using a natural language processing engine, a summary generation means for summarizing the text data using a generative artificial intelligence model, a storage means for saving the summarized text data generated by the summary generation means in a database, a display means for allowing a user to access and check the saved summarized text data via dedicated software or a web application, and a monitoring means for periodically monitoring the elderly's biological information and transmitting the data to the server if an abnormality is detected. This allows information on the elderly's health condition and daily life to be efficiently collected, easily accessed and checked by family members, and quickly notified if an abnormality is detected.

[0398] A "virtual assistant" is an artificial intelligence interface used to interact with seniors.

[0399] The "recording means" is a device or function for recording the speech of the elderly person obtained through the virtual assistant means.

[0400] "Conversion means" refers to a device or function for converting recorded speech into text data using a natural language processing engine.

[0401] The "summary generation means" is a device or function for summarizing text data using a generative artificial intelligence model.

[0402] The "storage means" is a device or function for storing the summarized text data generated by the summary generation means in a database.

[0403] "Display means" refers to a device or function that allows a user to access and view the stored summary text data via dedicated software or a web application.

[0404] The "monitoring means" is a device or function that periodically monitors the elderly person's biological information and transmits the data to a server if an abnormality is detected.

[0405] The "abnormality notification means" is a device or function for notifying the user of an abnormality when an abnormality is detected in the display means.

[0406] "Electronic devices" refers to all devices with communication capabilities, such as smart devices, that are used to realize AI assistant functions.

[0407] A "generative artificial intelligence model" is an artificial intelligence algorithm that generates summaries and responses from input data through natural language processing, etc.

[0408] This invention is a system designed to support the lives of elderly people and their families, using a virtual assistant to interact with elderly people, summarize and store the information, and make it easily accessible to families. Below, the program processing of this system is explained in natural language.

[0409] First, the device is an electronic device with communication capabilities, such as a smartwatch or smartphone. The device activates the virtual assistant at a set time each day. The virtual assistant is a conversational interface using AI that periodically greets and asks questions to the elderly. For example, at 9 a.m., the smartphone activates the assistant and greets the elderly with, "Good morning, how are you?" When the elderly responds verbally, the device records the audio.

[0410] The recorded voice data is converted into text data using a natural language processing engine such as Google Speech-to-Text API or IBM Watson Speech to Text, and the converted text data is sent to a server via the Internet.

[0411] The server then runs the received text data through a generative AI model, such as OpenAI GPT-4, to create a summary of the conversation. Our system generates summaries using prompts, such as "Please summarize the following conversation. Please indicate the elderly person's sleeping conditions."

[0412] The generated summary text is stored in a database such as MySQL or MongoDB. The saved summary text data can be accessed by users (family members) via dedicated software or a web application. Users can access the server using an app or a web browser and check the saved summary text data. For example, if a user opens the app and selects the summary for "2023-10-05," the details "I slept well, but I had a slight cough" will be displayed.

[0413] Furthermore, the system includes anomaly detection and notification functions. The device periodically monitors the elderly person's vital signs, such as body temperature and pulse rate. If an anomaly is detected, the data is sent to the server. If the data exceeds a set threshold, the server notifies the user of the anomaly. For example, Firebase Cloud Messaging can be used to send a push notification to the user's smartphone saying, "Mom's temperature is high. Please check."

[0414] For example, if a virtual assistant asks "Did you sleep well last night?" at 9 a.m. and an elderly person replies, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to a server. The server summarizes this information and saves it as "I slept well, but I had a slight cough." The user can view this summary in a dedicated app and take action if necessary.

[0415] Examples of prompts are:

[0416] "Please summarize the following dialogue and indicate what the elderly person's sleep situation was like."

[0417] Such a system would enable efficient collection of information on the health status and daily life of elderly people, allowing family members to easily access and check the information and receive prompt notification if any abnormalities are detected.

[0418] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0419] Step 1: Launch the terminal

[0420] The device can be a smartwatch or smartphone, and at a set time each day, the device will activate the virtual assistant. For example, at 9:00 a.m., the device will sound an alarm and the virtual assistant will appear on the screen.

[0421] Input: Current time (9:00 AM)

[0422] Output: The virtual assistant appears on the screen and begins interacting with you.

[0423] What it does: The device software will wake up the virtual assistant at the set time and display a greeting such as "Good morning, how are you?"

[0424] Step 2: Talk to the elderly

[0425] The virtual assistant greets the elderly person and asks them questions, and the elderly person responds verbally. Recording begins.

[0426] Input: Virtual assistant greeting or question

[0427] Output: Elderly person's response voice data

[0428] Specific operation: For example, in response to the question, "Did you sleep well last night?", the elderly person answers, "Yes, I slept well." The device then records this.

[0429] Step 3: Speech to text

[0430] The device converts the elderly person's recorded voice data into text data using a natural language processing engine.

[0431] Input: Recorded audio data

[0432] Output: Text data

[0433] Specific operation: The device uses the Google Speech-to-Text API to convert the voice data into text data such as "Yes, I slept well."

[0434] Step 4: Sending data to the server

[0435] The converted text data is sent to a server via the Internet.

[0436] Input: Text data

[0437] Output: Text data is sent to the server

[0438] Specific operation: The device uses Wi-Fi or mobile network to send the converted text data to the server.

[0439] Step 5: Generate conversation summaries

[0440] The server runs the received text data through a generative AI model to create a summary of the conversation, using prompts to instruct the generation of the summary.

[0441] Input: Received text data

[0442] Output: Summary text data

[0443] Specific operation: The server passes the text "Did you sleep well last night?" and "Yes, I slept well" to the AI ​​model along with the prompt "Please summarize the following text," and generates the summary "I slept well."

[0444] Step 6: Saving to the Database

[0445] The generated summary text is stored in a database.

[0446] Input: Summary text data

[0447] Output: Summary text data stored in a database

[0448] What happens: The server saves the entry "2023-10-05: Sleep well" in the MySQL database.

[0449] Step 7: User access to data

[0450] Users can access the server via a dedicated app or web application to view the stored summary text data.

[0451] Input: User access request

[0452] Output: Summary text data displayed on the user's terminal

[0453] Specific operation: The user opens the dedicated app on their smartphone, selects the specified date "2023-10-05", and the summary "I slept well" is displayed.

[0454] Step 8: Anomaly detection and notification

[0455] The device periodically monitors the elderly person's body temperature and pulse, and if an abnormality is detected, it sends the data to the server, which then notifies the user.

[0456] Input: Biometric data

[0457] Output: Abnormality notification

[0458] Specific operation: The device measures the elderly person's temperature, and if it exceeds 38 degrees, it sends the data to the server. The server detects the abnormality and sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check."

[0459] (Application example 1)

[0460] 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."

[0461] It is often difficult to effectively monitor the safety and health of elderly people remotely, especially when sudden changes in their physical condition or minor everyday abnormalities are detected. Therefore, there is a need for a system that allows family members and caregivers to more reliably monitor the safety and health of elderly people and respond quickly when necessary.

[0462] 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.

[0463] In this invention, the server includes virtual character means for interacting with the elderly person, recording means for recording speech from the elderly person obtained through the virtual character means, conversion means for converting the speech recorded by the recording means into text data, summarizing means for summarizing the text data, storage means for storing the summarized text data generated by the summarizing means, display means for enabling a user to access and check the stored summarized text data, monitoring means for periodically measuring and recording biometric data of the elderly person, detection means for detecting abnormalities based on the biometric data, and notification means for sending a notification when an abnormality is detected by the detection means. This makes it possible to effectively remotely monitor the safety and health of the elderly person and to quickly respond to abnormalities when they occur.

[0464] The "virtual character means" is a character display function used to have a conversation with the elderly person.

[0465] The "recording means" is a function for recording the statements of the elderly person obtained through the virtual character means.

[0466] The "conversion means" is a function that converts the utterances recorded by the recording means into text data.

[0467] The "summarization means" is a function for summarizing the text data obtained by the conversion means.

[0468] The "storage means" is a function for storing the summarized text data generated by the summarization means.

[0469] The "display means" is a function that allows the user to access and check the saved summary text data.

[0470] "Monitoring means" refers to a function that periodically measures and records the elderly person's biometric data.

[0471] The "detection means" is a function that detects abnormalities based on the biological data obtained by the monitoring means.

[0472] The "notification means" is a function that sends a notification when an abnormality is detected by the detection means.

[0473] "Mobile information terminal" refers to a portable information processing device such as a smartphone or tablet.

[0474] The present invention is a system for effectively remotely monitoring the safety and health status of elderly people, and provides a concrete means for family members and caregivers to understand the elderly person's condition using a virtual character. The main components of this system include a virtual character means, a recording means, a conversion means, a summarization means, a storage means, a display means, a monitoring means, a detection means, and a notification means.

[0475] Program processing

[0476] Hardware and Software Use

[0477] This system uses the following hardware and software:

[0478] Smartphones: Used as everyday computing devices by seniors.

[0479] Smartwatch: Used as a device to collect biometric data such as body temperature, pulse, and blood pressure from the elderly and send it to a smartphone.

[0480] TensorFlow / generative AI model: Used to summarize interaction data with virtual characters.

[0481] Firebase Cloud Messaging: Used as an external notification service to send push notifications.

[0482] The smartphone functions as an interface for conversation between the elderly person and the virtual character, displaying the virtual character at a set time each day and saying, "Good morning, how are you?" When the elderly person responds, the smartphone records the voice and converts it into text data using a voice recognition engine.

[0483] Data processing and calculation

[0484] The converted text data is sent to a server via the internet, where it is summarized using a generative AI model (e.g., TensorFlow). This summarized text data is stored in a database and can be accessed and viewed by users via a dedicated app or web browser.

[0485] Furthermore, the biometric data from the smartwatch is sent to a smartphone and monitored by a server. The server analyzes the periodically sent data, such as body temperature and pulse rate, and if an abnormality is detected, it sends a push notification to the user's smartphone using Firebase Cloud Messaging. For example, if an elderly person's body temperature exceeds 38 degrees, a message is immediately sent saying, "Your mother's temperature is high. Please check it."

[0486] Specific examples

[0487] As a concrete example, a virtual character might ask at 9 a.m., "Good morning, did you sleep well last night?" and the elderly person might respond, "Yes, I slept well, but I had a slight cough." This conversation is recorded, converted into text, and then sent to a server. The server summarizes the information as "I slept well, but I had a slight cough" and saves it. The user can later review this summary and take action if necessary.

[0488] Prompt Sentence Examples

[0489] Prompt for generative AI model:

[0490] "Please summarize the following conversation:

[0491] Virtual Character: Good morning, how are you?

[0492] Elderly person: Yes, I'm fine, but I have a slight cough.

[0493] Summary to generate: "I'm fine, but I have a cough."

[0494] The above is an embodiment of the present invention, which enables effective remote monitoring of the safety and health status of elderly people and rapid response in the event of an abnormality.

[0495] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0496] Step 1:

[0497] The terminal activates the virtual character means at a fixed time every day. The input is the current time, and the output is a virtual character that appears and speaks, "Good morning, how are you?" This starts a conversation with the elderly person.

[0498] Step 2:

[0499] The elderly person responds to the virtual character. The input is the elderly person's voice data, and the voice is recorded in a recording means as the output. This allows the content of the conversation to be saved.

[0500] Step 3:

[0501] The terminal converts the recorded voice data into text data using a conversion means. The input is voice data, and text data is generated as output. This converts voice information into text format.

[0502] Step 4:

[0503] The terminal sends the converted text data to a server via the Internet. The input is text data, and the data arrives at the server as output. This allows the data to be aggregated on a remote server.

[0504] Step 5:

[0505] The server summarizes the received text data through a generative AI model. The input is text data, and the output is summarized text data. This allows the content of the conversation to be summarized concisely.

[0506] Step 6:

[0507] The server saves the summarized text data in a database. The input is the summarized text data, and the saved data is added to the database as an output. This allows the summarized information to be managed.

[0508] Step 7:

[0509] The user accesses the server through a dedicated app or a web browser and checks the saved summary text data. The input is the user's request, and the summary text data is displayed as output. This allows family members to understand the condition of the elderly person.

[0510] Step 8:

[0511] The device receives the elderly person's biometric data from the smartwatch and sends it to the server. The input is biometric data such as body temperature and pulse rate, and the output data reaches the server. This allows real-time health status monitoring.

[0512] Step 9:

[0513] The server periodically analyzes biometric data and detects abnormalities. The input is biometric data, and the output is anomaly detection results. This allows abnormalities in health status to be confirmed.

[0514] Step 10:

[0515] When an abnormality is detected, the server sends a push notification to the user using a notification method. The input is the abnormality detection result, and the output is a notification message sent to the user's device. This enables emergency response.

[0516] 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.

[0517] The present invention provides a system that can interact with elderly people, summarize and store the information obtained, and provide easy access to the user. In addition to the virtual avatar means, the present invention also uses an emotion engine to recognize the emotions of the elderly and provide further information. The program processing of this system is explained below in natural language.

[0518] First, the device (such as a smart device or smartwatch) activates an AI avatar at a set time each day. For example, at 9 a.m., a virtual avatar appears on the elderly person's smartphone or smartwatch and greets them with a greeting such as "Good morning, how are you?" When the elderly person responds, the device records their voice, and the recorded data is converted into text using a voice recognition engine.

[0519] The converted text data is then sent over the internet to a server, which runs the data through a generative AI model to create a summary of the conversation, which is then stored in a database.

[0520] Furthermore, the terminal recognizes the emotions of the elderly person during the dialogue using an emotion engine. The emotion engine analyzes the elderly person's voice tone, facial expressions, and language patterns to recognize emotions such as joy, sadness, anger, etc. The recognized emotion data is included in the summarized text data generated by the summarization means.

[0521] Users (family members) can access the server via a dedicated app or web browser and check the saved summary text data and emotion data. For example, when a user opens the app and selects the desired date from the displayed list of conversation summaries, the detailed summary content and emotion data are displayed. This allows the user to understand the emotional state of the elderly person on that day.

[0522] The system also includes anomaly detection and notification functions. The device regularly monitors the elderly person's biological data, such as their body temperature and pulse, and if an abnormality is detected, it sends the data to the server. If the server detects an abnormality that exceeds a preset threshold, it notifies the user. For example, if an elderly person's body temperature exceeds 38 degrees, the server immediately sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check."

[0523] As a specific example, if a device launches a virtual avatar at 9:00 a.m. and asks an elderly person, "Did you sleep well last night?" and the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to the server. The server summarizes this information and saves it as "I slept well, but I had a slight cough." If the emotion engine recognizes "relief" in the elderly person's voice, this emotion data is also saved. The user can later review this summary and emotion data and take action as needed.

[0524] The above is an embodiment of the present invention. This system allows elderly people and their families to communicate smoothly over distances and to properly understand changes in their health conditions and emotions.

[0525] The processing flow will be explained below.

[0526] Step 1:

[0527] The device activates the virtual avatar at a fixed time each day (e.g., 9:00 a.m.), and the virtual avatar greets the elderly person by voice, such as "Good morning, did you sleep well last night?"

[0528] Step 2:

[0529] The terminal records the elderly person's response, and uses a recording means to record the elderly person's voice and passes it on to the next process.

[0530] Step 3:

[0531] The device runs the recorded voice data through a voice recognition engine and converts it into text data. Voice recognition technology is used to convert voice into text information, generating text data.

[0532] Step 4:

[0533] The device sends the generated text data to the server via the Internet using an HTTP POST request to send the text data to a specified endpoint on the server.

[0534] Step 5:

[0535] The server inputs the received text data into a generative AI model to generate a summary of the conversation. The generative AI model analyzes the text data, extracts important information, and creates a concise summary.

[0536] Step 6:

[0537] The server stores the generated summaries and the original text data in a database, and creates an index in the database to efficiently store the summaries and original data.

[0538] Step 7:

[0539] The device activates an emotion engine that recognizes the elderly person's emotions during the conversation. The emotion engine generates emotion data by analyzing the elderly person's voice tone, facial expressions, and language patterns.

[0540] Step 8:

[0541] The device sends the generated emotion data together with the text data to the server, where the emotion data and the text data are stored together.

[0542] Step 9:

[0543] The user (family member) accesses the server from a dedicated app or web browser and logs in. The user enters authentication information to gain access to the server.

[0544] Step 10:

[0545] Users can check the saved summaries and emotion data through a dedicated app or a web browser. After logging in, they send a request to the server to retrieve the saved conversation summaries and emotion data.

[0546] Step 11:

[0547] The device periodically measures the elderly person's body temperature and pulse rate and sends the data to a server. The device measures biometric data using sensors and sends the data to the server via the Internet.

[0548] Step 12:

[0549] The server analyzes the received biometric data and detects abnormalities if the data exceeds preset thresholds. An analysis module on the server checks the data and triggers a notification if an abnormality is detected.

[0550] Step 13:

[0551] If an abnormality is detected, the server will notify the user via email or push notification, sending an alert such as "Your temperature is high. Please check."

[0552] The above is the specific processing flow of this system. This detailed explanation will clarify what actions are required at each step.

[0553] Example 2

[0554] 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."

[0555] There is a need to provide a means to reduce the sense of loneliness felt by the elderly and to enable family members and caregivers to properly understand changes in their health status and emotions, but existing systems lack the means to provide multiple integrated functions such as summarizing conversation content, recognizing emotions, detecting abnormalities in biometric data, and notifying them. There is also a need to develop a system that can efficiently manage and notify data while smoothly communicating with the elderly.

[0556] 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.

[0557] In this invention, the server includes a virtual avatar means for interacting with the elderly person, a recording means for recording the elderly person's speech, a conversion means for converting the recorded speech into text data, a summarization means for summarizing the text data, a storage means for saving the summarized text data, a display means for making the saved summarized text data accessible, an emotion recognition means for recognizing the emotions of the elderly person, an additional storage means for saving the emotion data, a monitoring means for monitoring the elderly person's biometric data, and a notification means for notifying the user of detected abnormalities. This makes it possible to perform the summarization of the content of the conversation with the elderly person, the recording of changes in emotions, and the detection and notification of abnormalities in the biometric data in an integrated manner.

[0558] "Virtual avatar means" refers to a virtual character used to interact with the senior citizen.

[0559] "Recording means" refers to a device or function that records the speech of the elderly person in audio form.

[0560] "Conversion means" refers to a device or function that converts recorded voice data into text data.

[0561] The "summarization means" refers to a function of concisely summarizing the text data obtained by the conversion means.

[0562] The "storage means" refers to a device or function that records and stores the summarized text data generated by the summarization means.

[0563] "Display means" refers to a device or function that allows a user to visually confirm the saved summary text data.

[0564] "Emotion recognition means" refers to a device or function that analyzes and recognizes emotions from the voice and facial expressions of elderly people.

[0565] The "additional storage means" refers to a device or function that records and stores emotion data generated by the emotion recognition means.

[0566] "Monitoring means" refers to a device or function that continuously measures and monitors the elderly person's biometric data (such as body temperature and heart rate).

[0567] The "notification means" refers to a device or function that notifies the user of an abnormality detected by the monitoring means.

[0568] "Biometric data" refers to data that indicates an individual's physical condition, such as body temperature and heart rate.

[0569] The present invention provides a system that can engage in dialogue with elderly people, summarize information obtained from the dialogue, recognize emotions, and provide easy user access. Furthermore, the system also has the function of monitoring the elderly person's biometric data and notifying the user if an abnormality is detected. A specific embodiment of this system will be described below.

[0570] First, the device (e.g., a smartphone or smartwatch) activates the virtual avatar means at a fixed time each day. For example, at 9:00 a.m., the virtual avatar appears on the elderly person's device and greets them with "Good morning, how are you?" When the elderly person responds, the device records the voice and acquires the recorded data. This recorded data is converted into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). The generated text data is sent to a server via the Internet.

[0571] The server then applies a generative AI model (e.g., OpenAI GPT-3) to the received text data to create a summary. This summarized text data is stored in a database. Furthermore, the device uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the elderly person's emotions during the conversation. The emotion engine analyzes the elderly person's voice tone, facial expressions, and language patterns to recognize emotions such as joy, sadness, and anger. The recognized emotion data is included in the summarized text data generated by the summarization means.

[0572] Users (family members or caregivers) can access the server via a dedicated app or web browser and check the saved summary text data and emotion data. For example, when a user opens the app and selects the desired date from the displayed list of conversation summaries, the detailed summary content and emotion data are displayed. This allows the user to understand the emotional state of the elderly person on that day.

[0573] Furthermore, the device regularly monitors the elderly person's biological data, such as their body temperature and pulse rate. If an abnormality is detected, the data is sent to the server. If the server exceeds a preset threshold, it notifies the user of the abnormality. For example, if an elderly person's body temperature exceeds 38 degrees, the server immediately sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check it."

[0574] As a specific example, if a device launches a virtual avatar at 9:00 a.m. and asks an elderly person, "Did you sleep well last night?" and the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to the server. The server summarizes this information and saves it as "I slept well, but I had a slight cough." If the emotion engine recognizes "relief" in the elderly person's voice, this emotion data is also saved. The user can later review this summary and emotion data and take action as needed.

[0575] Here are some example prompts for creating summaries using a generative AI model (e.g., GPT-3):

[0576] Input text: "Yes, I slept well, but I have a bit of a cough."

[0577] Prompt: "Summarize the following conversation."

[0578] Example of generated summary: "I slept well, but I had a cough."

[0579] This concludes the "Mode for Carrying Out the Invention" of the present invention. This system enables elderly people and their families to communicate smoothly over distances and to appropriately understand changes in their health status and emotions.

[0580] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0581] Step 1:

[0582] The device launches the virtual avatar.

[0583] How it works: When the device's internal clock hits 9:00 AM, a virtual avatar application will automatically launch. The virtual avatar will then say "Good morning, how are you?"

[0584] Input: Clock information in the device.

[0585] Output: Virtual avatar activation and voice utterance.

[0586] Step 2:

[0587] The elderly person responds by voice.

[0588] Specific operation: The elderly person responds to the virtual avatar's speech by saying, "Yes, I'm fine." The device's microphone records this voice.

[0589] Input: Senior citizen's voice.

[0590] Output: Recorded audio data.

[0591] Step 3:

[0592] Convert the recorded data into text data.

[0593] Specific operation: The device sends the recorded voice data to a speech recognition engine (e.g., Google Cloud Speech-to-Text API). The speech recognition engine converts the voice "Yes, I'm fine" into text and returns it to the device.

[0594] Input: Audio data.

[0595] Output: Text data.

[0596] Step 4:

[0597] Sends text data to the server.

[0598] Specific operation: The terminal sends the converted text data to the server via the Internet. At this time, the data is encrypted before being sent.

[0599] Input: Text data.

[0600] Output: The text data sent to the server.

[0601] Step 5:

[0602] The server summarizes the text data.

[0603] How it works: The server inputs the received text data into a generative AI model (e.g., OpenAI GPT-3). The model generates a summary based on a pre-set prompt. For example, a summary such as "I slept well, but I had a cough" is generated.

[0604] Input: text data, prompt statement.

[0605] Output: Summary text data.

[0606] Step 6:

[0607] Recognizing the emotions of the elderly using an emotion recognition engine.

[0608] Specific operation: During the conversation, the device sends the recorded voice to an emotion recognition engine (e.g., IBM Watson Tone Analyzer). The engine analyzes the voice tone and generates emotion data. For example, the emotion data for "relief."

[0609] Input: Audio data.

[0610] Output: Emotion data.

[0611] Step 7:

[0612] Stores sentiment data and summary data.

[0613] Specific operation: The server stores the generated summary text data and emotion data in a database, which can be accessed by users in the future.

[0614] Input: Summary text data, sentiment data.

[0615] Output: Data stored in the database.

[0616] Step 8:

[0617] The user accesses the data.

[0618] Specific operation: The user accesses the server using a dedicated app or a web browser and logs in. An interface is displayed where the saved summary data and emotion data can be viewed. The user can select the desired date to view the data.

[0619] Input: The user's access request.

[0620] Output: Display of summary data and sentiment data.

[0621] Step 9:

[0622] Provides biometric data monitoring and abnormality notification functions.

[0623] Specific operation: The device periodically measures the elderly person's biometric data (e.g., body temperature and heart rate) using sensors. If an abnormality is detected, the data is sent to the server. If the server detects a value that exceeds a set threshold, it sends an abnormality notification (e.g., "Mom's body temperature is high. Please check it.") to the user's smartphone.

[0624] Input: Biometric data.

[0625] Output: Abnormality notification.

[0626] (Application example 2)

[0627] 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."

[0628] There is a need for a system that allows family members and caregivers to accurately understand the elderly's condition by smoothly conducting dialogue with them and appropriately storing those records. However, existing systems have difficulty accurately detecting changes in the elderly's emotions and health status and responding promptly based on those changes. Furthermore, because summarization and emotion analysis of the elderly's speech are not automated, family members and caregivers must take the time and effort to check the speech. The present invention aims to solve these problems.

[0629] 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.

[0630] In this invention, the server includes a virtual avatar means, a recording means, a conversion means, a summarizing means, a storage means, a display means, an emotion engine means, and an emotion data storage means, which allows for smooth dialogue with the elderly, automates the summarization of the dialogue content and the analysis and storage of emotion data, and makes it possible to quickly grasp and respond to changes in the elderly's emotions and health condition.

[0631] "Virtual avatar means" refers to devices or software that simulate conversations with elderly people using audio and video and record the content of those conversations.

[0632] A "recording means" is a device or software that records the elderly person's speech as digital data.

[0633] The "conversion means" is software or an algorithm that converts the audio data obtained by the recording means into text data.

[0634] The "summarization means" is software or an algorithm that concisely summarizes the text data obtained by the conversion means.

[0635] The "storage means" is a device or software for storing the text data and emotion data generated by the summarization means in a database or storage device.

[0636] A "display means" is a device or software that allows a user to access and view data stored by a storage means.

[0637] The "emotion engine means" is software or algorithm that analyzes the elderly person's speech, facial expressions, and tone of voice to recognize their emotional state.

[0638] The "emotion data storage means" is a device or software that stores the emotion data recognized by the emotion engine means by including it in the summary text data.

[0639] The present invention provides a system that summarizes information obtained through dialogue with elderly people, analyzes and stores emotion data based on the information, and allows users to easily access the data. The following system is applied as an embodiment of the invention.

[0640] First, a smart device (such as a smartphone or tablet) is used as the terminal. A virtual avatar is installed on this terminal, and it periodically interacts with the elderly. The interaction is conducted via voice, and the content of the interaction is saved as digital data using a recording device.

[0641] The recorded voice data is converted into text data by a conversion means using a voice recognition engine, and the converted text data is then sent to a server.

[0642] The server summarizes the received text data using a summarization means. The summarization means uses natural language processing technology (e.g., a generative AI model). The summarized text data is stored in a database by a storage means.

[0643] A distinctive feature of this system is the emotion engine means, which analyzes voice tone, facial expressions, and language patterns to recognize the emotions of the elderly. This emotion data is stored in the emotion data storage means together with the text data generated by the summarization means.

[0644] Users can access and check the saved summary text data and emotion data using dedicated display means. For example, they can access the database via a dedicated application or a web browser. Users can easily check past conversation data and emotion data, and understand changes in the health status and emotions of elderly people.

[0645] Furthermore, the system is also equipped with anomaly detection and notification functions. The terminals and server regularly monitor the elderly person's biological data, such as their body temperature and pulse rate, and if an abnormality is detected, the user is notified via a notification means. In this case, push notifications can be used to quickly notify the user of the abnormality.

[0646] As a specific example, the device starts up a virtual avatar every day at 9:00 a.m. and asks the elderly person, "Did you sleep well last night?" If the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded and converted into text data. It is then sent to a server and saved as summarized text data, such as "I slept well, but I had a slight cough." The emotion engine means also recognizes "relief" from the elderly person's voice and saves it as emotion data. This data can be later checked by the user using a dedicated application. An example of a specific prompt sentence is, "Did you sleep well last night?"

[0647] The above is a specific embodiment for carrying out the present invention. This system is a great help to family members and caregivers because it can properly grasp the emotions and health status of elderly people and respond quickly.

[0648] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0649] Step 1:

[0650] The terminal (smart device) periodically (e.g., at 9 a.m.) wakes up the virtual avatar. The virtual avatar speaks a prompt to the elderly (e.g., "Good morning, how are you?") and receives a verbal response from the elderly. In this step, the input is the elderly's voice, and the output is the voice data.

[0651] Step 2:

[0652] The terminal uses a recording means to record the elderly person's response as digital voice data. The recorded voice data is temporarily stored in the device's memory. In this step, the input is the elderly person's response voice, and the output is digital voice data.

[0653] Step 3:

[0654] The device uses a conversion means to convert the recorded voice data into text data. A speech recognition engine (e.g., Google Speech-to-Text API) is used to recognize this voice data as text. In this step, the input is digital voice data and the output is text data.

[0655] Step 4:

[0656] The terminal sends the converted text data to the server via the Internet. The text data is encrypted and sent using a secure communication protocol (e.g., HTTPS). In this step, the input is the text data, and the output is the data sent to the server.

[0657] Step 5:

[0658] The server summarizes the received text data using a generative AI model. A natural language processing algorithm is used as a summarization method to remove redundant parts and extract important information. In this step, the input is text data, and the output is summarized text data.

[0659] Step 6:

[0660] The server stores the summarized text data in a database using a storage means. The stored data also includes a timestamp and identification information. In this step, the input is the summarized text data, and the output is the data stored in the database.

[0661] Step 7:

[0662] The server uses an emotion engine means to analyze the emotion of the elderly person from the received text data and voice tone. As a result of the analysis, emotion data is generated. In this step, the input is the text data and voice tone, and the output is the emotion data.

[0663] Step 8:

[0664] The server adds the emotion data to the summarized text data and stores it in a database using the emotion data storage means. In this step, the input is the emotion data and the summarized text data, and the output is stored data including the emotion data.

[0665] Step 9:

[0666] The user checks the saved summary text data and emotion data using a dedicated display means, for example, by accessing and displaying the data using a dedicated application or a web browser. In this step, the input is data from the database, and the output is the displayed information.

[0667] Step 10:

[0668] The server monitors biometric data (e.g., body temperature, pulse rate), and if an abnormality is detected, immediately sends a notification to the user using a notification means. This notification is sent as a push notification to a smartphone, etc. In this step, the input is biometric data, and the output is a notification to the user.

[0669] 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.

[0670] 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.

[0671] 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.

[0672] [Third embodiment]

[0673] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0674] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0675] 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).

[0676] 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.

[0677] 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.

[0678] 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).

[0679] 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.

[0680] 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.

[0681] 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.

[0682] 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.

[0683] 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.

[0684] 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."

[0685] The present invention provides a system for supporting the lives of elderly people and their families by using virtual avatars to interact with elderly people, summarizing and saving the information obtained, and making it easily accessible to families. The program processing of this system is explained below in natural language.

[0686] First, the device (such as a smart device or smartwatch) activates an AI avatar at a set time each day. For example, at 9 a.m., a virtual avatar appears on the elderly person's smartphone or smartwatch and greets them with a greeting such as "Good morning, how are you?" When the elderly person responds, the device records their voice and converts it into text data using a voice recognition engine.

[0687] The converted text data is then sent over the internet to a server, which runs the data through a generative AI model to create a summary of the conversation, which is then stored in a database.

[0688] Users (family members) can access the server via a dedicated app or web browser and check the saved summary text data. For example, when a user opens the app and selects a desired date from the list of conversation summaries, the detailed summary content is displayed.

[0689] The system also includes anomaly detection and notification functions. The device regularly monitors the elderly person's biological data, such as their body temperature and pulse, and if an abnormality is detected, it sends the data to the server. If the server detects an abnormality that exceeds a preset threshold, it notifies the user. For example, if an elderly person's body temperature exceeds 38 degrees, the server immediately sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check."

[0690] As a specific example, if a device launches a virtual avatar at 9:00 a.m. and asks an elderly person, "Did you sleep well last night?" and the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to a server. The server summarizes this information and saves it as, "I slept well, but I had a slight cough." The user can review this summary later and take action if necessary.

[0691] The above is an embodiment of the present invention. This system allows elderly people and their families to communicate smoothly over distance and to properly understand their health conditions.

[0692] The processing flow will be explained below.

[0693] Step 1:

[0694] The device is scheduled to launch the virtual avatar at a specific time each day (e.g., 9:00 a.m.). The device's internal clock and schedule function are used to launch the AI ​​avatar application at the specified time.

[0695] Step 2:

[0696] The device displays a virtual avatar on the screen and displays and plays a voice message to the elderly, such as "Good morning, did you sleep well last night?" The virtual avatar continues the conversation as appropriate until the elderly responds.

[0697] Step 3:

[0698] When the elderly person answers, the terminal records the voice. The voice of the elderly person is recorded using a recording means and passed to the next process.

[0699] Step 4:

[0700] The device converts the recorded voice data into text data using a voice recognition engine. Using voice recognition technology, the device converts the voice data into text information and generates text data.

[0701] Step 5:

[0702] The device sends the converted text data to the server via the Internet. The device sends an HTTP POST request to the server, and the text data is transferred to the server.

[0703] Step 6:

[0704] The server then passes the received text data to a generative AI model that analyzes the text data, extracts key information, and generates a summary of the conversation.

[0705] Step 7:

[0706] The server stores the generated summaries and the original text data in a database, and creates an index in the database to efficiently store the summaries and original data.

[0707] Step 8:

[0708] Users access the server using a dedicated app or a web browser and log in by entering their user authentication information.

[0709] Step 9:

[0710] The user can view a list of saved conversation summaries through a dedicated app or a web browser, send a request to the server to retrieve a list of conversation logs, and select any summary from there to view its details.

[0711] Step 10:

[0712] The device periodically measures the elderly person's body temperature and pulse rate and sends the data to a server. Biometric data is acquired using temperature and pulse sensors and sent to the server via the Internet.

[0713] Step 11:

[0714] The server analyzes the received biometric data and detects abnormalities if the data exceeds the threshold. An analysis module on the server checks the data and triggers a notification if an abnormality is detected.

[0715] Step 12:

[0716] The server immediately sends an abnormality notification to the user via email or smartphone push notification, such as "Your body temperature is high. Please check."

[0717] The above is the specific processing flow of this system. This detailed explanation will clarify what actions are required at each step.

[0718] Example 1

[0719] 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."

[0720] There is a need for a system that can efficiently collect information on the health status and daily life of elderly people and allow their families to easily access it. However, with existing technology, it is difficult to have a natural dialogue with the elderly, summarize the content of the dialogue, and provide it to their families. There is also a need for a system that can quickly notify their families if an abnormality is detected. To solve these issues, it is essential to have technology that can intelligently process the information obtained from dialogue with the elderly and provide it efficiently.

[0721] 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.

[0722] In this invention, the server includes a virtual assistant means for interacting with the elderly, a recording means for recording the elderly's speech obtained through the virtual assistant means, a conversion means for converting the speech recorded by the recording means into text data using a natural language processing engine, a summary generation means for summarizing the text data using a generative artificial intelligence model, a storage means for saving the summarized text data generated by the summary generation means in a database, a display means for allowing a user to access and check the saved summarized text data via dedicated software or a web application, and a monitoring means for periodically monitoring the elderly's biological information and transmitting the data to the server if an abnormality is detected. This allows information on the elderly's health condition and daily life to be efficiently collected, easily accessed and checked by family members, and quickly notified if an abnormality is detected.

[0723] A "virtual assistant" is an artificial intelligence interface used to interact with seniors.

[0724] The "recording means" is a device or function for recording the speech of the elderly person obtained through the virtual assistant means.

[0725] "Conversion means" refers to a device or function for converting recorded speech into text data using a natural language processing engine.

[0726] The "summary generation means" is a device or function for summarizing text data using a generative artificial intelligence model.

[0727] The "storage means" is a device or function for storing the summarized text data generated by the summary generation means in a database.

[0728] "Display means" refers to a device or function that allows a user to access and view the stored summary text data via dedicated software or a web application.

[0729] The "monitoring means" is a device or function that periodically monitors the elderly person's biological information and transmits the data to a server if an abnormality is detected.

[0730] The "abnormality notification means" is a device or function for notifying the user of an abnormality when an abnormality is detected in the display means.

[0731] "Electronic devices" refers to all devices with communication capabilities, such as smart devices, that are used to realize AI assistant functions.

[0732] A "generative artificial intelligence model" is an artificial intelligence algorithm that generates summaries and responses from input data through natural language processing, etc.

[0733] This invention is a system designed to support the lives of elderly people and their families, using a virtual assistant to interact with elderly people, summarize and store the information, and make it easily accessible to families. Below, the program processing of this system is explained in natural language.

[0734] First, the device is an electronic device with communication capabilities, such as a smartwatch or smartphone. The device activates the virtual assistant at a set time each day. The virtual assistant is a conversational interface using AI that periodically greets and asks questions to the elderly. For example, at 9 a.m., the smartphone activates the assistant and greets the elderly with, "Good morning, how are you?" When the elderly responds verbally, the device records the audio.

[0735] The recorded voice data is converted into text data using a natural language processing engine such as Google Speech-to-Text API or IBM Watson Speech to Text, and the converted text data is sent to a server via the Internet.

[0736] The server then runs the received text data through a generative AI model, such as OpenAI GPT-4, to create a summary of the conversation. Our system generates summaries using prompts, such as "Please summarize the following conversation. Please indicate the elderly person's sleeping conditions."

[0737] The generated summary text is stored in a database such as MySQL or MongoDB. The saved summary text data can be accessed by users (family members) via dedicated software or a web application. Users can access the server using an app or a web browser and check the saved summary text data. For example, if a user opens the app and selects the summary for "2023-10-05," the details "I slept well, but I had a slight cough" will be displayed.

[0738] Furthermore, the system includes anomaly detection and notification functions. The device periodically monitors the elderly person's vital signs, such as body temperature and pulse rate. If an anomaly is detected, the data is sent to the server. If the data exceeds a set threshold, the server notifies the user of the anomaly. For example, Firebase Cloud Messaging can be used to send a push notification to the user's smartphone saying, "Mom's temperature is high. Please check."

[0739] For example, if a virtual assistant asks "Did you sleep well last night?" at 9 a.m. and an elderly person replies, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to a server. The server summarizes this information and saves it as "I slept well, but I had a slight cough." The user can view this summary in a dedicated app and take action if necessary.

[0740] Examples of prompts are:

[0741] "Please summarize the following dialogue and indicate what the elderly person's sleep situation was like."

[0742] Such a system would enable efficient collection of information on the health status and daily life of elderly people, allowing family members to easily access and check the information and receive prompt notification if any abnormalities are detected.

[0743] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0744] Step 1: Launch the terminal

[0745] The device can be a smartwatch or smartphone, and at a set time each day, the device will activate the virtual assistant. For example, at 9:00 a.m., the device will sound an alarm and the virtual assistant will appear on the screen.

[0746] Input: Current time (9:00 AM)

[0747] Output: The virtual assistant appears on the screen and begins interacting with you.

[0748] What it does: The device software will wake up the virtual assistant at the set time and display a greeting such as "Good morning, how are you?"

[0749] Step 2: Talk to the elderly

[0750] The virtual assistant greets the elderly person and asks them questions, and the elderly person responds verbally. Recording begins.

[0751] Input: Virtual assistant greeting or question

[0752] Output: Elderly person's response voice data

[0753] Specific operation: For example, in response to the question, "Did you sleep well last night?", the elderly person answers, "Yes, I slept well." The device then records this.

[0754] Step 3: Speech to text

[0755] The device converts the elderly person's recorded voice data into text data using a natural language processing engine.

[0756] Input: Recorded audio data

[0757] Output: Text data

[0758] Specific operation: The device uses the Google Speech-to-Text API to convert the voice data into text data such as "Yes, I slept well."

[0759] Step 4: Sending data to the server

[0760] The converted text data is sent to a server via the Internet.

[0761] Input: Text data

[0762] Output: Text data is sent to the server

[0763] Specific operation: The device uses Wi-Fi or mobile network to send the converted text data to the server.

[0764] Step 5: Generate conversation summaries

[0765] The server runs the received text data through a generative AI model to create a summary of the conversation, using prompts to instruct the generation of the summary.

[0766] Input: Received text data

[0767] Output: Summary text data

[0768] Specific operation: The server passes the text "Did you sleep well last night?" and "Yes, I slept well" to the AI ​​model along with the prompt "Please summarize the following text," and generates the summary "I slept well."

[0769] Step 6: Saving to the Database

[0770] The generated summary text is stored in a database.

[0771] Input: Summary text data

[0772] Output: Summary text data stored in a database

[0773] What happens: The server saves the entry "2023-10-05: Sleep well" in the MySQL database.

[0774] Step 7: User access to data

[0775] Users can access the server via a dedicated app or web application to view the stored summary text data.

[0776] Input: User access request

[0777] Output: Summary text data displayed on the user's terminal

[0778] Specific operation: The user opens the dedicated app on their smartphone, selects the specified date "2023-10-05", and the summary "I slept well" is displayed.

[0779] Step 8: Anomaly detection and notification

[0780] The device periodically monitors the elderly person's body temperature and pulse, and if an abnormality is detected, it sends the data to the server, which then notifies the user.

[0781] Input: Biometric data

[0782] Output: Abnormality notification

[0783] Specific operation: The device measures the elderly person's temperature, and if it exceeds 38 degrees, it sends the data to the server. The server detects the abnormality and sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check."

[0784] (Application example 1)

[0785] 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."

[0786] It is often difficult to effectively monitor the safety and health of elderly people remotely, especially when sudden changes in their physical condition or minor everyday abnormalities are detected promptly. Therefore, there is a need for a system that allows family members and caregivers to more reliably monitor the safety and health of elderly people and respond quickly when necessary.

[0787] 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.

[0788] In this invention, the server includes virtual character means for interacting with the elderly person, recording means for recording speech from the elderly person obtained through the virtual character means, conversion means for converting the speech recorded by the recording means into text data, summarizing means for summarizing the text data, storage means for storing the summarized text data generated by the summarizing means, display means for enabling a user to access and check the stored summarized text data, monitoring means for periodically measuring and recording biometric data of the elderly person, detection means for detecting abnormalities based on the biometric data, and notification means for sending a notification when an abnormality is detected by the detection means. This makes it possible to effectively remotely monitor the safety and health of the elderly person and to quickly respond to abnormalities when they occur.

[0789] The "virtual character means" is a character display function used to have a conversation with the elderly person.

[0790] The "recording means" is a function for recording the statements of the elderly person obtained through the virtual character means.

[0791] The "conversion means" is a function that converts the utterances recorded by the recording means into text data.

[0792] The "summarization means" is a function for summarizing the text data obtained by the conversion means.

[0793] The "storage means" is a function for storing the summarized text data generated by the summarization means.

[0794] The "display means" is a function that allows the user to access and check the saved summary text data.

[0795] "Monitoring means" refers to a function that periodically measures and records the elderly person's biometric data.

[0796] The "detection means" is a function that detects abnormalities based on the biological data obtained by the monitoring means.

[0797] The "notification means" is a function that sends a notification when an abnormality is detected by the detection means.

[0798] "Mobile information terminal" refers to a portable information processing device such as a smartphone or tablet.

[0799] The present invention is a system for effectively remotely monitoring the safety and health status of elderly people, and provides a concrete means for family members and caregivers to understand the elderly person's condition using a virtual character. The main components of this system include a virtual character means, a recording means, a conversion means, a summarization means, a storage means, a display means, a monitoring means, a detection means, and a notification means.

[0800] Program processing

[0801] Hardware and Software Use

[0802] This system uses the following hardware and software:

[0803] Smartphones: Used as everyday computing devices by seniors.

[0804] Smartwatch: Used as a device to collect biometric data such as body temperature, pulse, and blood pressure from the elderly and send it to a smartphone.

[0805] TensorFlow / generative AI model: Used to summarize interaction data with virtual characters.

[0806] Firebase Cloud Messaging: Used as an external notification service to send push notifications.

[0807] The smartphone functions as an interface for conversation between the elderly person and the virtual character, displaying the virtual character at a set time each day and saying, "Good morning, how are you?" When the elderly person responds, the smartphone records the voice and converts it into text data using a voice recognition engine.

[0808] Data processing and calculation

[0809] The converted text data is sent to a server via the internet, where it is summarized using a generative AI model (e.g., TensorFlow). This summarized text data is stored in a database and can be accessed and viewed by users via a dedicated app or web browser.

[0810] Furthermore, the biometric data from the smartwatch is sent to a smartphone and monitored by a server. The server analyzes the periodically sent data, such as body temperature and pulse rate, and if an abnormality is detected, it sends a push notification to the user's smartphone using Firebase Cloud Messaging. For example, if an elderly person's body temperature exceeds 38 degrees, a message is immediately sent saying, "Your mother's temperature is high. Please check it."

[0811] Specific examples

[0812] As a concrete example, a virtual character might ask at 9 a.m., "Good morning, did you sleep well last night?" and the elderly person might respond, "Yes, I slept well, but I had a slight cough." This conversation is recorded, converted into text, and then sent to a server. The server summarizes the information as "I slept well, but I had a slight cough" and saves it. The user can later review this summary and take action if necessary.

[0813] Prompt Sentence Examples

[0814] Prompt for generative AI model:

[0815] "Please summarize the following conversation:

[0816] Virtual Character: Good morning, how are you?

[0817] Elderly person: Yes, I'm fine, but I have a slight cough.

[0818] Summary to generate: "I'm fine, but I have a cough."

[0819] The above is an embodiment of the present invention, which enables effective remote monitoring of the safety and health status of elderly people and rapid response in the event of an abnormality.

[0820] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0821] Step 1:

[0822] The terminal activates the virtual character means at a fixed time every day. The input is the current time, and the output is a virtual character that appears and speaks, "Good morning, how are you?" This starts a conversation with the elderly person.

[0823] Step 2:

[0824] The elderly person responds to the virtual character. The input is the elderly person's voice data, and the voice is recorded in a recording means as the output. This allows the content of the conversation to be saved.

[0825] Step 3:

[0826] The terminal converts the recorded voice data into text data using a conversion means. The input is voice data, and text data is generated as output. This converts voice information into text format.

[0827] Step 4:

[0828] The terminal sends the converted text data to a server via the Internet. The input is text data, and the data arrives at the server as output. This allows the data to be aggregated on a remote server.

[0829] Step 5:

[0830] The server summarizes the received text data through a generative AI model. The input is text data, and the output is summarized text data. This allows the content of the conversation to be summarized concisely.

[0831] Step 6:

[0832] The server saves the summarized text data in a database. The input is the summarized text data, and the saved data is added to the database as an output. This allows the summarized information to be managed.

[0833] Step 7:

[0834] The user accesses the server through a dedicated app or a web browser and checks the saved summary text data. The input is the user's request, and the summary text data is displayed as output. This allows family members to understand the condition of the elderly person.

[0835] Step 8:

[0836] The device receives the elderly person's biometric data from the smartwatch and sends it to the server. The input is biometric data such as body temperature and pulse rate, and the output data reaches the server. This allows real-time health status monitoring.

[0837] Step 9:

[0838] The server periodically analyzes biometric data and detects abnormalities. The input is biometric data, and the output is anomaly detection results. This allows abnormalities in health status to be confirmed.

[0839] Step 10:

[0840] When an abnormality is detected, the server sends a push notification to the user using a notification method. The input is the abnormality detection result, and the output is a notification message sent to the user's device. This enables emergency response.

[0841] 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.

[0842] The present invention provides a system that can interact with elderly people, summarize and store the information obtained, and provide easy access to the user. In addition to the virtual avatar means, the present invention also uses an emotion engine to recognize the emotions of the elderly and provide further information. The program processing of this system is explained below in natural language.

[0843] First, the device (such as a smart device or smartwatch) activates an AI avatar at a set time each day. For example, at 9 a.m., a virtual avatar appears on the elderly person's smartphone or smartwatch and greets them with a greeting such as "Good morning, how are you?" When the elderly person responds, the device records their voice, and the recorded data is converted into text using a voice recognition engine.

[0844] The converted text data is then sent over the internet to a server, which runs the data through a generative AI model to create a summary of the conversation, which is then stored in a database.

[0845] Furthermore, the terminal recognizes the emotions of the elderly person during the dialogue using an emotion engine. The emotion engine analyzes the elderly person's voice tone, facial expressions, and language patterns to recognize emotions such as joy, sadness, anger, etc. The recognized emotion data is included in the summarized text data generated by the summarization means.

[0846] Users (family members) can access the server via a dedicated app or web browser and check the saved summary text data and emotion data. For example, when a user opens the app and selects the desired date from the displayed list of conversation summaries, the detailed summary content and emotion data are displayed. This allows the user to understand the emotional state of the elderly person on that day.

[0847] The system also includes anomaly detection and notification functions. The device regularly monitors the elderly person's biological data, such as their body temperature and pulse, and if an abnormality is detected, it sends the data to the server. If the server detects an abnormality that exceeds a preset threshold, it notifies the user. For example, if an elderly person's body temperature exceeds 38 degrees, the server immediately sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check."

[0848] As a specific example, if a device launches a virtual avatar at 9:00 a.m. and asks an elderly person, "Did you sleep well last night?" and the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to the server. The server summarizes this information and saves it as "I slept well, but I had a slight cough." If the emotion engine recognizes "relief" in the elderly person's voice, this emotion data is also saved. The user can later review this summary and emotion data and take action as needed.

[0849] The above is an embodiment of the present invention. This system allows elderly people and their families to communicate smoothly over distances and to properly understand changes in their health conditions and emotions.

[0850] The processing flow will be explained below.

[0851] Step 1:

[0852] The device activates the virtual avatar at a fixed time each day (e.g., 9:00 a.m.), and the virtual avatar greets the elderly person by voice, such as "Good morning, did you sleep well last night?"

[0853] Step 2:

[0854] The terminal records the elderly person's response, and uses a recording means to record the elderly person's voice and passes it on to the next process.

[0855] Step 3:

[0856] The device runs the recorded voice data through a voice recognition engine and converts it into text data. Voice recognition technology is used to convert voice into text information, generating text data.

[0857] Step 4:

[0858] The device sends the generated text data to the server via the Internet using an HTTP POST request to send the text data to a specified endpoint on the server.

[0859] Step 5:

[0860] The server inputs the received text data into a generative AI model to generate a summary of the conversation. The generative AI model analyzes the text data, extracts important information, and creates a concise summary.

[0861] Step 6:

[0862] The server stores the generated summaries and the original text data in a database, and creates an index in the database to efficiently store the summaries and original data.

[0863] Step 7:

[0864] The device activates an emotion engine that recognizes the elderly person's emotions during the conversation. The emotion engine generates emotion data by analyzing the elderly person's voice tone, facial expressions, and language patterns.

[0865] Step 8:

[0866] The device sends the generated emotion data together with the text data to the server, where the emotion data and the text data are stored together.

[0867] Step 9:

[0868] The user (family member) accesses the server from a dedicated app or web browser and logs in. The user enters authentication information to gain access to the server.

[0869] Step 10:

[0870] Users can check the saved summaries and emotion data through a dedicated app or a web browser. After logging in, they send a request to the server to retrieve the saved conversation summaries and emotion data.

[0871] Step 11:

[0872] The device periodically measures the elderly person's body temperature and pulse rate and sends the data to a server. The device measures biometric data using sensors and sends the data to the server via the Internet.

[0873] Step 12:

[0874] The server analyzes the received biometric data and detects abnormalities if the data exceeds preset thresholds. An analysis module on the server checks the data and triggers a notification if an abnormality is detected.

[0875] Step 13:

[0876] If an abnormality is detected, the server will notify the user via email or push notification, sending an alert such as "Your temperature is high. Please check."

[0877] The above is the specific processing flow of this system. This detailed explanation will clarify what actions are required at each step.

[0878] Example 2

[0879] 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."

[0880] There is a need to provide a means to reduce the sense of loneliness felt by the elderly and to enable family members and caregivers to properly understand changes in their health status and emotions, but existing systems lack the means to provide multiple integrated functions such as summarizing conversation content, recognizing emotions, detecting abnormalities in biometric data, and notifying them. There is also a need to develop a system that can efficiently manage and notify data while smoothly communicating with the elderly.

[0881] 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.

[0882] In this invention, the server includes a virtual avatar means for interacting with the elderly person, a recording means for recording the elderly person's speech, a conversion means for converting the recorded speech into text data, a summarization means for summarizing the text data, a storage means for saving the summarized text data, a display means for making the saved summarized text data accessible, an emotion recognition means for recognizing the emotions of the elderly person, an additional storage means for saving the emotion data, a monitoring means for monitoring the elderly person's biometric data, and a notification means for notifying the user of detected abnormalities. This makes it possible to perform the summarization of the content of the conversation with the elderly person, the recording of changes in emotions, and the detection and notification of abnormalities in the biometric data in an integrated manner.

[0883] "Virtual avatar means" refers to a virtual character used to interact with the senior citizen.

[0884] "Recording means" refers to a device or function that records the speech of the elderly person in audio form.

[0885] "Conversion means" refers to a device or function that converts recorded voice data into text data.

[0886] The "summarization means" refers to a function of concisely summarizing the text data obtained by the conversion means.

[0887] The "storage means" refers to a device or function that records and stores the summarized text data generated by the summarization means.

[0888] "Display means" refers to a device or function that allows a user to visually confirm the saved summary text data.

[0889] "Emotion recognition means" refers to a device or function that analyzes and recognizes emotions from the voice and facial expressions of elderly people.

[0890] The "additional storage means" refers to a device or function that records and stores emotion data generated by the emotion recognition means.

[0891] "Monitoring means" refers to a device or function that continuously measures and monitors the elderly person's biometric data (such as body temperature and heart rate).

[0892] The "notification means" refers to a device or function that notifies the user of an abnormality detected by the monitoring means.

[0893] "Biometric data" refers to data that indicates an individual's physical condition, such as body temperature and heart rate.

[0894] The present invention provides a system that can engage in dialogue with elderly people, summarize information obtained from the dialogue, recognize emotions, and provide easy user access. Furthermore, the system also has the function of monitoring the elderly person's biometric data and notifying the user if an abnormality is detected. A specific embodiment of this system will be described below.

[0895] First, the device (e.g., a smartphone or smartwatch) activates the virtual avatar means at a fixed time each day. For example, at 9:00 a.m., the virtual avatar appears on the elderly person's device and greets them with "Good morning, how are you?" When the elderly person responds, the device records the voice and acquires the recorded data. This recorded data is converted into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). The generated text data is sent to a server via the Internet.

[0896] The server then applies a generative AI model (e.g., OpenAI GPT-3) to the received text data to create a summary. This summarized text data is stored in a database. Furthermore, the device uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the elderly person's emotions during the conversation. The emotion engine analyzes the elderly person's voice tone, facial expressions, and language patterns to recognize emotions such as joy, sadness, and anger. The recognized emotion data is included in the summarized text data generated by the summarization means.

[0897] Users (family members or caregivers) can access the server via a dedicated app or web browser and check the saved summary text data and emotion data. For example, when a user opens the app and selects the desired date from the displayed list of conversation summaries, the detailed summary content and emotion data are displayed. This allows the user to understand the emotional state of the elderly person on that day.

[0898] Furthermore, the device regularly monitors the elderly person's biological data, such as their body temperature and pulse rate. If an abnormality is detected, the data is sent to the server. If the server exceeds a preset threshold, it notifies the user of the abnormality. For example, if an elderly person's body temperature exceeds 38 degrees, the server immediately sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check it."

[0899] As a specific example, if a device launches a virtual avatar at 9:00 a.m. and asks an elderly person, "Did you sleep well last night?" and the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to the server. The server summarizes this information and saves it as "I slept well, but I had a slight cough." If the emotion engine recognizes "relief" in the elderly person's voice, this emotion data is also saved. The user can later review this summary and emotion data and take action as needed.

[0900] Here are some example prompts for creating summaries using a generative AI model (e.g., GPT-3):

[0901] Input text: "Yes, I slept well, but I have a bit of a cough."

[0902] Prompt: "Summarize the following conversation."

[0903] Example of generated summary: "I slept well, but I had a cough."

[0904] This concludes the "Mode for Carrying Out the Invention" of the present invention. This system enables elderly people and their families to communicate smoothly over distances and to appropriately understand changes in their health status and emotions.

[0905] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0906] Step 1:

[0907] The device launches the virtual avatar.

[0908] How it works: When the device's internal clock hits 9:00 AM, a virtual avatar application will automatically launch. The virtual avatar will then say "Good morning, how are you?"

[0909] Input: Clock information in the device.

[0910] Output: Virtual avatar activation and voice utterance.

[0911] Step 2:

[0912] The elderly person responds by voice.

[0913] Specific operation: The elderly person responds to the virtual avatar's speech by saying, "Yes, I'm fine." The device's microphone records this voice.

[0914] Input: Senior citizen's voice.

[0915] Output: Recorded audio data.

[0916] Step 3:

[0917] Convert the recorded data into text data.

[0918] Specific operation: The device sends the recorded voice data to a speech recognition engine (e.g., Google Cloud Speech-to-Text API). The speech recognition engine converts the voice "Yes, I'm fine" into text and returns it to the device.

[0919] Input: Audio data.

[0920] Output: Text data.

[0921] Step 4:

[0922] Sends text data to the server.

[0923] Specific operation: The terminal sends the converted text data to the server via the Internet. At this time, the data is encrypted before being sent.

[0924] Input: Text data.

[0925] Output: The text data sent to the server.

[0926] Step 5:

[0927] The server summarizes the text data.

[0928] How it works: The server inputs the received text data into a generative AI model (e.g., OpenAI GPT-3). The model generates a summary based on a pre-set prompt. For example, a summary such as "I slept well, but I had a cough" is generated.

[0929] Input: text data, prompt statement.

[0930] Output: Summary text data.

[0931] Step 6:

[0932] Recognizing the emotions of the elderly using an emotion recognition engine.

[0933] Specific operation: During the conversation, the device sends the recorded voice to an emotion recognition engine (e.g., IBM Watson Tone Analyzer). The engine analyzes the voice tone and generates emotion data. For example, the emotion data for "relief."

[0934] Input: Audio data.

[0935] Output: Emotion data.

[0936] Step 7:

[0937] Stores sentiment data and summary data.

[0938] Specific operation: The server stores the generated summary text data and emotion data in a database, which can be accessed by users in the future.

[0939] Input: Summary text data, sentiment data.

[0940] Output: Data stored in the database.

[0941] Step 8:

[0942] The user accesses the data.

[0943] Specific operation: The user accesses the server using a dedicated app or a web browser and logs in. An interface is displayed where the saved summary data and emotion data can be viewed. The user can select the desired date to view the data.

[0944] Input: The user's access request.

[0945] Output: Display of summary data and sentiment data.

[0946] Step 9:

[0947] Provides biometric data monitoring and abnormality notification functions.

[0948] Specific operation: The device periodically measures the elderly person's biometric data (e.g., body temperature and heart rate) using sensors. If an abnormality is detected, the data is sent to the server. If the server detects a value that exceeds a set threshold, it sends an abnormality notification (e.g., "Mom's body temperature is high. Please check it.") to the user's smartphone.

[0949] Input: Biometric data.

[0950] Output: Abnormality notification.

[0951] (Application example 2)

[0952] 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."

[0953] There is a need for a system that allows family members and caregivers to accurately understand the elderly's condition by smoothly conducting dialogue with them and appropriately storing those records. However, existing systems have difficulty accurately detecting changes in the elderly's emotions and health status and responding promptly based on those changes. Furthermore, because summarization and emotion analysis of the elderly's speech are not automated, family members and caregivers must take the time and effort to check the speech. The present invention aims to solve these problems.

[0954] 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.

[0955] In this invention, the server includes a virtual avatar means, a recording means, a conversion means, a summarizing means, a storage means, a display means, an emotion engine means, and an emotion data storage means, which allows for smooth dialogue with the elderly, automates the summarization of the dialogue content and the analysis and storage of emotion data, and makes it possible to quickly grasp and respond to changes in the elderly's emotions and health condition.

[0956] "Virtual avatar means" refers to devices or software that simulate conversations with elderly people using audio and video and record the content of those conversations.

[0957] A "recording means" is a device or software that records the elderly person's speech as digital data.

[0958] The "conversion means" is software or an algorithm that converts the audio data obtained by the recording means into text data.

[0959] The "summarization means" is software or an algorithm that concisely summarizes the text data obtained by the conversion means.

[0960] The "storage means" is a device or software for storing the text data and emotion data generated by the summarization means in a database or storage device.

[0961] A "display means" is a device or software that allows a user to access and view data stored by a storage means.

[0962] The "emotion engine means" is software or algorithm that analyzes the elderly person's speech, facial expressions, and tone of voice to recognize their emotional state.

[0963] The "emotion data storage means" is a device or software that stores the emotion data recognized by the emotion engine means by including it in the summary text data.

[0964] The present invention provides a system that summarizes information obtained through dialogue with elderly people, analyzes and stores emotion data based on the information, and allows users to easily access the data. The following system is applied as an embodiment of the invention.

[0965] First, a smart device (such as a smartphone or tablet) is used as the terminal. A virtual avatar is installed on this terminal, and it periodically interacts with the elderly. The interaction is conducted via voice, and the content of the interaction is saved as digital data using a recording device.

[0966] The recorded voice data is converted into text data by a conversion means using a voice recognition engine, and the converted text data is then sent to a server.

[0967] The server summarizes the received text data using a summarization means. The summarization means uses natural language processing technology (e.g., a generative AI model). The summarized text data is stored in a database by a storage means.

[0968] A distinctive feature of this system is the emotion engine means, which analyzes voice tone, facial expressions, and language patterns to recognize the emotions of the elderly. This emotion data is stored in the emotion data storage means together with the text data generated by the summarization means.

[0969] Users can access and check the saved summary text data and emotion data using dedicated display means. For example, they can access the database via a dedicated application or a web browser. Users can easily check past conversation data and emotion data, and understand changes in the health status and emotions of elderly people.

[0970] Furthermore, the system is also equipped with anomaly detection and notification functions. The terminals and server regularly monitor the elderly person's biological data, such as their body temperature and pulse rate, and if an abnormality is detected, the user is notified via a notification means. In this case, push notifications can be used to quickly notify the user of the abnormality.

[0971] As a specific example, the device starts up a virtual avatar every day at 9:00 a.m. and asks the elderly person, "Did you sleep well last night?" If the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded and converted into text data. It is then sent to a server and saved as summarized text data, such as "I slept well, but I had a slight cough." The emotion engine means also recognizes "relief" from the elderly person's voice and saves it as emotion data. This data can be later checked by the user using a dedicated application. An example of a specific prompt sentence is, "Did you sleep well last night?"

[0972] The above is a specific embodiment for carrying out the present invention. This system is a great help to family members and caregivers because it can properly grasp the emotions and health status of elderly people and respond quickly.

[0973] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0974] Step 1:

[0975] The terminal (smart device) periodically (e.g., at 9 a.m.) wakes up the virtual avatar. The virtual avatar speaks a prompt to the elderly (e.g., "Good morning, how are you?") and receives a verbal response from the elderly. In this step, the input is the elderly's voice, and the output is the voice data.

[0976] Step 2:

[0977] The terminal uses a recording means to record the elderly person's response as digital voice data. The recorded voice data is temporarily stored in the device's memory. In this step, the input is the elderly person's response voice, and the output is digital voice data.

[0978] Step 3:

[0979] The device uses a conversion means to convert the recorded voice data into text data. A speech recognition engine (e.g., Google Speech-to-Text API) is used to recognize this voice data as text. In this step, the input is digital voice data and the output is text data.

[0980] Step 4:

[0981] The terminal sends the converted text data to the server via the Internet. The text data is encrypted and sent using a secure communication protocol (e.g., HTTPS). In this step, the input is the text data, and the output is the data sent to the server.

[0982] Step 5:

[0983] The server summarizes the received text data using a generative AI model. A natural language processing algorithm is used as a summarization method to remove redundant parts and extract important information. In this step, the input is text data, and the output is summarized text data.

[0984] Step 6:

[0985] The server stores the summarized text data in a database using a storage means. The stored data also includes a timestamp and identification information. In this step, the input is the summarized text data, and the output is the data stored in the database.

[0986] Step 7:

[0987] The server uses an emotion engine means to analyze the emotion of the elderly person from the received text data and voice tone. As a result of the analysis, emotion data is generated. In this step, the input is the text data and voice tone, and the output is the emotion data.

[0988] Step 8:

[0989] The server adds the emotion data to the summarized text data and stores it in a database using the emotion data storage means. In this step, the input is the emotion data and the summarized text data, and the output is stored data including the emotion data.

[0990] Step 9:

[0991] The user checks the saved summary text data and emotion data using a dedicated display means, for example, by accessing and displaying the data using a dedicated application or a web browser. In this step, the input is data from the database, and the output is the displayed information.

[0992] Step 10:

[0993] The server monitors biometric data (e.g., body temperature, pulse rate), and if an abnormality is detected, immediately sends a notification to the user using a notification means. This notification is sent as a push notification to a smartphone, etc. In this step, the input is biometric data, and the output is a notification to the user.

[0994] 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.

[0995] 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.

[0996] 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.

[0997] [Fourth embodiment]

[0998] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0999] 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.

[1000] 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).

[1001] 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.

[1002] 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.

[1003] 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).

[1004] 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.

[1005] 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.

[1006] 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.

[1007] 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.

[1008] 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.

[1009] 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.

[1010] 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."

[1011] The present invention provides a system for supporting the lives of elderly people and their families by using virtual avatars to interact with elderly people, summarizing and saving the information obtained, and making it easily accessible to families. The program processing of this system is explained below in natural language.

[1012] First, the device (such as a smart device or smartwatch) activates an AI avatar at a set time each day. For example, at 9 a.m., a virtual avatar appears on the elderly person's smartphone or smartwatch and greets them with a greeting such as "Good morning, how are you?" When the elderly person responds, the device records their voice and converts it into text data using a voice recognition engine.

[1013] The converted text data is then sent over the internet to a server, which runs the data through a generative AI model to create a summary of the conversation, which is then stored in a database.

[1014] Users (family members) can access the server via a dedicated app or web browser and check the saved summary text data. For example, when a user opens the app and selects a desired date from the list of conversation summaries, the detailed summary content is displayed.

[1015] The system also includes anomaly detection and notification functions. The device regularly monitors the elderly person's biological data, such as their body temperature and pulse, and if an abnormality is detected, it sends the data to the server. If the server detects an abnormality that exceeds a preset threshold, it notifies the user. For example, if an elderly person's body temperature exceeds 38 degrees, the server immediately sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check."

[1016] As a specific example, if a device launches a virtual avatar at 9:00 a.m. and asks an elderly person, "Did you sleep well last night?" and the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to a server. The server summarizes this information and saves it as, "I slept well, but I had a slight cough." The user can review this summary later and take action if necessary.

[1017] The above is an embodiment of the present invention. This system allows elderly people and their families to communicate smoothly over distance and to properly understand their health conditions.

[1018] The processing flow will be explained below.

[1019] Step 1:

[1020] The device is scheduled to launch the virtual avatar at a specific time each day (e.g., 9:00 a.m.). The device's internal clock and schedule function are used to launch the AI ​​avatar application at the specified time.

[1021] Step 2:

[1022] The device displays a virtual avatar on the screen and displays and plays a voice message to the elderly, such as "Good morning, did you sleep well last night?" The virtual avatar continues the conversation as appropriate until the elderly responds.

[1023] Step 3:

[1024] When the elderly person answers, the terminal records the voice. The voice of the elderly person is recorded using a recording means and passed to the next process.

[1025] Step 4:

[1026] The device converts the recorded voice data into text data using a voice recognition engine. Using voice recognition technology, the device converts the voice data into text information and generates text data.

[1027] Step 5:

[1028] The device sends the converted text data to the server via the Internet. The device sends an HTTP POST request to the server, and the text data is transferred to the server.

[1029] Step 6:

[1030] The server then passes the received text data to a generative AI model that analyzes the text data, extracts key information, and generates a summary of the conversation.

[1031] Step 7:

[1032] The server stores the generated summaries and the original text data in a database, and creates an index in the database to efficiently store the summaries and original data.

[1033] Step 8:

[1034] Users access the server using a dedicated app or a web browser and log in by entering their user authentication information.

[1035] Step 9:

[1036] The user can view a list of saved conversation summaries through a dedicated app or a web browser, send a request to the server to retrieve a list of conversation logs, and select any summary from there to view its details.

[1037] Step 10:

[1038] The device periodically measures the elderly person's body temperature and pulse rate and sends the data to a server. Biometric data is acquired using temperature and pulse sensors and sent to the server via the Internet.

[1039] Step 11:

[1040] The server analyzes the received biometric data and detects abnormalities if the data exceeds the threshold. An analysis module on the server checks the data and triggers a notification if an abnormality is detected.

[1041] Step 12:

[1042] The server immediately sends an abnormality notification to the user via email or smartphone push notification, such as "Your body temperature is high. Please check."

[1043] The above is the specific processing flow of this system. This detailed explanation will clarify what actions are required at each step.

[1044] Example 1

[1045] 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."

[1046] There is a need for a system that can efficiently collect information on the health status and daily life of elderly people and allow their families to easily access it. However, with existing technology, it is difficult to have a natural dialogue with the elderly, summarize the content of the dialogue, and provide it to their families. There is also a need for a system that can quickly notify their families if an abnormality is detected. To solve these issues, it is essential to have technology that can intelligently process the information obtained from dialogue with the elderly and provide it efficiently.

[1047] 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.

[1048] In this invention, the server includes a virtual assistant means for interacting with the elderly, a recording means for recording the elderly's speech obtained through the virtual assistant means, a conversion means for converting the speech recorded by the recording means into text data using a natural language processing engine, a summary generation means for summarizing the text data using a generative artificial intelligence model, a storage means for saving the summarized text data generated by the summary generation means in a database, a display means for allowing a user to access and check the saved summarized text data via dedicated software or a web application, and a monitoring means for periodically monitoring the elderly's biological information and transmitting the data to the server if an abnormality is detected. This allows information on the elderly's health condition and daily life to be efficiently collected, easily accessed and checked by family members, and quickly notified if an abnormality is detected.

[1049] A "virtual assistant" is an artificial intelligence interface used to interact with seniors.

[1050] The "recording means" is a device or function for recording the speech of the elderly person obtained through the virtual assistant means.

[1051] "Conversion means" refers to a device or function for converting recorded speech into text data using a natural language processing engine.

[1052] The "summary generation means" is a device or function for summarizing text data using a generative artificial intelligence model.

[1053] The "storage means" is a device or function for storing the summarized text data generated by the summary generation means in a database.

[1054] "Display means" refers to a device or function that allows a user to access and view the stored summary text data via dedicated software or a web application.

[1055] The "monitoring means" is a device or function that periodically monitors the elderly person's biological information and transmits the data to a server if an abnormality is detected.

[1056] The "abnormality notification means" is a device or function for notifying the user of an abnormality when an abnormality is detected in the display means.

[1057] "Electronic devices" refers to all devices with communication capabilities, such as smart devices, that are used to realize AI assistant functions.

[1058] A "generative artificial intelligence model" is an artificial intelligence algorithm that generates summaries and responses from input data through natural language processing, etc.

[1059] This invention is a system designed to support the lives of elderly people and their families, using a virtual assistant to interact with elderly people, summarize and store the information, and make it easily accessible to families. Below, the program processing of this system is explained in natural language.

[1060] First, the device is an electronic device with communication capabilities, such as a smartwatch or smartphone. The device activates the virtual assistant at a set time each day. The virtual assistant is a conversational interface using AI that periodically greets and asks questions to the elderly. For example, at 9 a.m., the smartphone activates the assistant and greets the elderly with, "Good morning, how are you?" When the elderly responds verbally, the device records the audio.

[1061] The recorded voice data is converted into text data using a natural language processing engine such as Google Speech-to-Text API or IBM Watson Speech to Text, and the converted text data is sent to a server via the Internet.

[1062] The server then runs the received text data through a generative AI model, such as OpenAI GPT-4, to create a summary of the conversation. Our system generates summaries using prompts, such as "Please summarize the following conversation. Please indicate the elderly person's sleeping conditions."

[1063] The generated summary text is stored in a database such as MySQL or MongoDB. The saved summary text data can be accessed by users (family members) via dedicated software or a web application. Users can access the server using an app or a web browser and check the saved summary text data. For example, if a user opens the app and selects the summary for "2023-10-05," the details "I slept well, but I had a slight cough" will be displayed.

[1064] Furthermore, the system includes anomaly detection and notification functions. The device periodically monitors the elderly person's vital signs, such as body temperature and pulse rate. If an anomaly is detected, the data is sent to the server. If the data exceeds a set threshold, the server notifies the user of the anomaly. For example, Firebase Cloud Messaging can be used to send a push notification to the user's smartphone saying, "Mom's temperature is high. Please check."

[1065] For example, if a virtual assistant asks "Did you sleep well last night?" at 9 a.m. and an elderly person replies, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to a server. The server summarizes this information and saves it as "I slept well, but I had a slight cough." The user can view this summary in a dedicated app and take action if necessary.

[1066] Examples of prompts are:

[1067] "Please summarize the following dialogue and indicate what the elderly person's sleep situation was like."

[1068] Such a system would enable efficient collection of information on the health status and daily life of elderly people, allowing family members to easily access and check the information and receive prompt notification if any abnormalities are detected.

[1069] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1070] Step 1: Launch the terminal

[1071] The device can be a smartwatch or smartphone, and at a set time each day, the device will activate the virtual assistant. For example, at 9:00 a.m., the device will sound an alarm and the virtual assistant will appear on the screen.

[1072] Input: Current time (9:00 AM)

[1073] Output: The virtual assistant appears on the screen and begins interacting with you.

[1074] What it does: The device software will wake up the virtual assistant at the set time and display a greeting such as "Good morning, how are you?"

[1075] Step 2: Talk to the elderly

[1076] The virtual assistant greets the elderly person and asks them questions, and the elderly person responds verbally. Recording begins.

[1077] Input: Virtual assistant greeting or question

[1078] Output: Elderly person's response voice data

[1079] Specific operation: For example, in response to the question, "Did you sleep well last night?", the elderly person answers, "Yes, I slept well." The device then records this.

[1080] Step 3: Speech to text

[1081] The device converts the elderly person's recorded voice data into text data using a natural language processing engine.

[1082] Input: Recorded audio data

[1083] Output: Text data

[1084] Specific operation: The device uses the Google Speech-to-Text API to convert the voice data into text data such as "Yes, I slept well."

[1085] Step 4: Sending data to the server

[1086] The converted text data is sent to a server via the Internet.

[1087] Input: Text data

[1088] Output: Text data is sent to the server

[1089] Specific operation: The device uses Wi-Fi or mobile network to send the converted text data to the server.

[1090] Step 5: Generate conversation summaries

[1091] The server runs the received text data through a generative AI model to create a summary of the conversation, using prompts to instruct the generation of the summary.

[1092] Input: Received text data

[1093] Output: Summary text data

[1094] Specific operation: The server passes the text "Did you sleep well last night?" and "Yes, I slept well" to the AI ​​model along with the prompt "Please summarize the following text," and generates the summary "I slept well."

[1095] Step 6: Saving to the Database

[1096] The generated summary text is stored in a database.

[1097] Input: Summary text data

[1098] Output: Summary text data stored in a database

[1099] What happens: The server saves the entry "2023-10-05: Sleep well" in the MySQL database.

[1100] Step 7: User access to data

[1101] Users can access the server via a dedicated app or web application to view the stored summary text data.

[1102] Input: User access request

[1103] Output: Summary text data displayed on the user's terminal

[1104] Specific operation: The user opens the dedicated app on their smartphone, selects the specified date "2023-10-05", and the summary "I slept well" is displayed.

[1105] Step 8: Anomaly detection and notification

[1106] The device periodically monitors the elderly person's body temperature and pulse, and if an abnormality is detected, it sends the data to the server, which then notifies the user.

[1107] Input: Biometric data

[1108] Output: Abnormality notification

[1109] Specific operation: The device measures the elderly person's temperature, and if it exceeds 38 degrees, it sends the data to the server. The server detects the abnormality and sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check."

[1110] (Application example 1)

[1111] 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."

[1112] It is often difficult to effectively monitor the safety and health of elderly people remotely, especially when sudden changes in their physical condition or minor everyday abnormalities are detected. Therefore, there is a need for a system that allows family members and caregivers to more reliably monitor the safety and health of elderly people and respond quickly when necessary.

[1113] 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.

[1114] In this invention, the server includes virtual character means for interacting with the elderly person, recording means for recording speech from the elderly person obtained through the virtual character means, conversion means for converting the speech recorded by the recording means into text data, summarizing means for summarizing the text data, storage means for storing the summarized text data generated by the summarizing means, display means for enabling a user to access and check the stored summarized text data, monitoring means for periodically measuring and recording biometric data of the elderly person, detection means for detecting abnormalities based on the biometric data, and notification means for sending a notification when an abnormality is detected by the detection means. This makes it possible to effectively remotely monitor the safety and health of the elderly person and to quickly respond to abnormalities when they occur.

[1115] The "virtual character means" is a character display function used to have a conversation with the elderly person.

[1116] The "recording means" is a function for recording the statements of the elderly person obtained through the virtual character means.

[1117] The "conversion means" is a function that converts the utterances recorded by the recording means into text data.

[1118] The "summarization means" is a function for summarizing the text data obtained by the conversion means.

[1119] The "storage means" is a function for storing the summarized text data generated by the summarization means.

[1120] The "display means" is a function that allows the user to access and check the saved summary text data.

[1121] "Monitoring means" refers to a function that periodically measures and records the elderly person's biometric data.

[1122] The "detection means" is a function that detects abnormalities based on the biological data obtained by the monitoring means.

[1123] The "notification means" is a function that sends a notification when an abnormality is detected by the detection means.

[1124] "Mobile information terminal" refers to a portable information processing device such as a smartphone or tablet.

[1125] The present invention is a system for effectively remotely monitoring the safety and health status of elderly people, and provides a concrete means for family members and caregivers to understand the elderly person's condition using a virtual character. The main components of this system include a virtual character means, a recording means, a conversion means, a summarization means, a storage means, a display means, a monitoring means, a detection means, and a notification means.

[1126] Program processing

[1127] Hardware and Software Use

[1128] This system uses the following hardware and software:

[1129] Smartphones: Used as everyday computing devices by seniors.

[1130] Smartwatch: Used as a device to collect biometric data such as body temperature, pulse, and blood pressure from the elderly and send it to a smartphone.

[1131] TensorFlow / generative AI model: Used to summarize interaction data with virtual characters.

[1132] Firebase Cloud Messaging: Used as an external notification service to send push notifications.

[1133] The smartphone functions as an interface for conversation between the elderly person and the virtual character, displaying the virtual character at a set time each day and saying, "Good morning, how are you?" When the elderly person responds, the smartphone records the voice and converts it into text data using a voice recognition engine.

[1134] Data processing and calculation

[1135] The converted text data is sent to a server via the internet, where it is summarized using a generative AI model (e.g., TensorFlow). This summarized text data is stored in a database and can be accessed and viewed by users via a dedicated app or web browser.

[1136] Furthermore, the biometric data from the smartwatch is sent to a smartphone and monitored by a server. The server analyzes the periodically sent data, such as body temperature and pulse rate, and if an abnormality is detected, it sends a push notification to the user's smartphone using Firebase Cloud Messaging. For example, if an elderly person's body temperature exceeds 38 degrees, a message is immediately sent saying, "Your mother's temperature is high. Please check it."

[1137] Specific examples

[1138] As a concrete example, a virtual character might ask at 9 a.m., "Good morning, did you sleep well last night?" and the elderly person might respond, "Yes, I slept well, but I had a slight cough." This conversation is recorded, converted into text, and then sent to a server. The server summarizes the information as "I slept well, but I had a slight cough" and saves it. The user can later review this summary and take action if necessary.

[1139] Prompt Sentence Examples

[1140] Prompt for generative AI model:

[1141] "Please summarize the following conversation:

[1142] Virtual Character: Good morning, how are you?

[1143] Elderly person: Yes, I'm fine, but I have a slight cough.

[1144] Summary to generate: "I'm fine, but I have a cough."

[1145] The above is an embodiment of the present invention, which enables effective remote monitoring of the safety and health status of elderly people and rapid response in the event of an abnormality.

[1146] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1147] Step 1:

[1148] The terminal activates the virtual character means at a fixed time every day. The input is the current time, and the output is a virtual character that appears and speaks, "Good morning, how are you?" This starts a conversation with the elderly person.

[1149] Step 2:

[1150] The elderly person responds to the virtual character. The input is the elderly person's voice data, and the voice is recorded in a recording means as the output. This allows the content of the conversation to be saved.

[1151] Step 3:

[1152] The terminal converts the recorded voice data into text data using a conversion means. The input is voice data, and text data is generated as output. This converts voice information into text format.

[1153] Step 4:

[1154] The terminal sends the converted text data to a server via the Internet. The input is text data, and the data arrives at the server as output. This allows the data to be aggregated on a remote server.

[1155] Step 5:

[1156] The server summarizes the received text data through a generative AI model. The input is text data, and the output is summarized text data. This allows the content of the conversation to be summarized concisely.

[1157] Step 6:

[1158] The server saves the summarized text data in a database. The input is the summarized text data, and the saved data is added to the database as an output. This allows the summarized information to be managed.

[1159] Step 7:

[1160] The user accesses the server through a dedicated app or a web browser and checks the saved summary text data. The input is the user's request, and the summary text data is displayed as output. This allows family members to understand the condition of the elderly person.

[1161] Step 8:

[1162] The device receives the elderly person's biometric data from the smartwatch and sends it to the server. The input is biometric data such as body temperature and pulse rate, and the output data reaches the server. This allows real-time health status monitoring.

[1163] Step 9:

[1164] The server periodically analyzes biometric data and detects abnormalities. The input is biometric data, and the output is anomaly detection results. This allows abnormalities in health status to be confirmed.

[1165] Step 10:

[1166] When an abnormality is detected, the server sends a push notification to the user using a notification method. The input is the abnormality detection result, and the output is a notification message sent to the user's device. This enables emergency response.

[1167] 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.

[1168] The present invention provides a system that can interact with elderly people, summarize and store the information obtained, and provide easy access to the user. In addition to the virtual avatar means, the present invention also uses an emotion engine to recognize the emotions of the elderly and provide further information. The program processing of this system is explained below in natural language.

[1169] First, the device (such as a smart device or smartwatch) activates an AI avatar at a set time each day. For example, at 9 a.m., a virtual avatar appears on the elderly person's smartphone or smartwatch and greets them with a greeting such as "Good morning, how are you?" When the elderly person responds, the device records their voice, and the recorded data is converted into text using a voice recognition engine.

[1170] The converted text data is then sent over the internet to a server, which runs the data through a generative AI model to create a summary of the conversation, which is then stored in a database.

[1171] Furthermore, the terminal recognizes the emotions of the elderly person during the dialogue using an emotion engine. The emotion engine analyzes the elderly person's voice tone, facial expressions, and language patterns to recognize emotions such as joy, sadness, anger, etc. The recognized emotion data is included in the summarized text data generated by the summarization means.

[1172] Users (family members) can access the server via a dedicated app or web browser and check the saved summary text data and emotion data. For example, when a user opens the app and selects the desired date from the displayed list of conversation summaries, the detailed summary content and emotion data are displayed. This allows the user to understand the emotional state of the elderly person on that day.

[1173] The system also includes anomaly detection and notification functions. The device regularly monitors the elderly person's biological data, such as their body temperature and pulse, and if an abnormality is detected, it sends the data to the server. If the server detects an abnormality that exceeds a preset threshold, it notifies the user. For example, if an elderly person's body temperature exceeds 38 degrees, the server immediately sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check."

[1174] As a specific example, if a device launches a virtual avatar at 9:00 a.m. and asks an elderly person, "Did you sleep well last night?" and the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to the server. The server summarizes this information and saves it as "I slept well, but I had a slight cough." If the emotion engine recognizes "relief" in the elderly person's voice, this emotion data is also saved. The user can later review this summary and emotion data and take action as needed.

[1175] The above is an embodiment of the present invention. This system allows elderly people and their families to communicate smoothly over distances and to properly understand changes in their health conditions and emotions.

[1176] The processing flow will be explained below.

[1177] Step 1:

[1178] The device activates the virtual avatar at a fixed time each day (e.g., 9:00 a.m.), and the virtual avatar greets the elderly person by voice, such as "Good morning, did you sleep well last night?"

[1179] Step 2:

[1180] The terminal records the elderly person's response, and uses a recording means to record the elderly person's voice and passes it on to the next process.

[1181] Step 3:

[1182] The device runs the recorded voice data through a voice recognition engine and converts it into text data. Voice recognition technology is used to convert voice into text information, generating text data.

[1183] Step 4:

[1184] The device sends the generated text data to the server via the Internet using an HTTP POST request to send the text data to a specified endpoint on the server.

[1185] Step 5:

[1186] The server inputs the received text data into a generative AI model to generate a summary of the conversation. The generative AI model analyzes the text data, extracts important information, and creates a concise summary.

[1187] Step 6:

[1188] The server stores the generated summaries and the original text data in a database, and creates an index in the database to efficiently store the summaries and original data.

[1189] Step 7:

[1190] The device activates an emotion engine that recognizes the elderly person's emotions during the conversation. The emotion engine generates emotion data by analyzing the elderly person's voice tone, facial expressions, and language patterns.

[1191] Step 8:

[1192] The device sends the generated emotion data together with the text data to the server, where the emotion data and the text data are stored together.

[1193] Step 9:

[1194] The user (family member) accesses the server from a dedicated app or web browser and logs in. The user enters authentication information to gain access to the server.

[1195] Step 10:

[1196] Users can check the saved summaries and emotion data through a dedicated app or a web browser. After logging in, they send a request to the server to retrieve the saved conversation summaries and emotion data.

[1197] Step 11:

[1198] The device periodically measures the elderly person's body temperature and pulse rate and sends the data to a server. The device measures biometric data using sensors and sends the data to the server via the Internet.

[1199] Step 12:

[1200] The server analyzes the received biometric data and detects abnormalities if the data exceeds preset thresholds. An analysis module on the server checks the data and triggers a notification if an abnormality is detected.

[1201] Step 13:

[1202] If an abnormality is detected, the server will notify the user via email or push notification, sending an alert such as "Your temperature is high. Please check."

[1203] The above is the specific processing flow of this system. This detailed explanation will clarify what actions are required at each step.

[1204] Example 2

[1205] 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."

[1206] There is a need to provide a means to reduce the sense of loneliness felt by the elderly and to enable family members and caregivers to properly understand changes in their health status and emotions, but existing systems lack the means to provide multiple integrated functions such as summarizing conversation content, recognizing emotions, detecting abnormalities in biometric data, and notifying them. There is also a need to develop a system that can efficiently manage and notify data while smoothly communicating with the elderly.

[1207] 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.

[1208] In this invention, the server includes a virtual avatar means for interacting with the elderly person, a recording means for recording the elderly person's speech, a conversion means for converting the recorded speech into text data, a summarization means for summarizing the text data, a storage means for saving the summarized text data, a display means for making the saved summarized text data accessible, an emotion recognition means for recognizing the emotions of the elderly person, an additional storage means for saving the emotion data, a monitoring means for monitoring the elderly person's biometric data, and a notification means for notifying the user of detected abnormalities. This makes it possible to perform the summarization of the content of the conversation with the elderly person, the recording of changes in emotions, and the detection and notification of abnormalities in the biometric data in an integrated manner.

[1209] "Virtual avatar means" refers to a virtual character used to interact with the senior citizen.

[1210] "Recording means" refers to a device or function that records the speech of the elderly person in audio form.

[1211] "Conversion means" refers to a device or function that converts recorded voice data into text data.

[1212] The "summarization means" refers to a function of concisely summarizing the text data obtained by the conversion means.

[1213] The "storage means" refers to a device or function that records and stores the summarized text data generated by the summarization means.

[1214] "Display means" refers to a device or function that allows a user to visually confirm the saved summary text data.

[1215] "Emotion recognition means" refers to a device or function that analyzes and recognizes emotions from the voice and facial expressions of elderly people.

[1216] The "additional storage means" refers to a device or function that records and stores emotion data generated by the emotion recognition means.

[1217] "Monitoring means" refers to a device or function that continuously measures and monitors the elderly person's biometric data (such as body temperature and heart rate).

[1218] The "notification means" refers to a device or function that notifies the user of an abnormality detected by the monitoring means.

[1219] "Biometric data" refers to data that indicates an individual's physical condition, such as body temperature and heart rate.

[1220] The present invention provides a system that can engage in dialogue with elderly people, summarize information obtained from the dialogue, recognize emotions, and provide easy user access. Furthermore, the system also has the function of monitoring the elderly person's biometric data and notifying the user if an abnormality is detected. A specific embodiment of this system will be described below.

[1221] First, the device (e.g., a smartphone or smartwatch) activates the virtual avatar means at a fixed time each day. For example, at 9:00 a.m., the virtual avatar appears on the elderly person's device and greets them with "Good morning, how are you?" When the elderly person responds, the device records the voice and acquires the recorded data. This recorded data is converted into text data using a speech recognition engine (e.g., Google Cloud Speech-to-Text API). The generated text data is sent to a server via the Internet.

[1222] The server then applies a generative AI model (e.g., OpenAI GPT-3) to the received text data to create a summary. This summarized text data is stored in a database. Furthermore, the device uses an emotion engine (e.g., IBM Watson Tone Analyzer) to recognize the elderly person's emotions during the conversation. The emotion engine analyzes the elderly person's voice tone, facial expressions, and language patterns to recognize emotions such as joy, sadness, and anger. The recognized emotion data is included in the summarized text data generated by the summarization means.

[1223] Users (family members or caregivers) can access the server via a dedicated app or web browser and check the saved summary text data and emotion data. For example, when a user opens the app and selects the desired date from the displayed list of conversation summaries, the detailed summary content and emotion data are displayed. This allows the user to understand the emotional state of the elderly person on that day.

[1224] Furthermore, the device regularly monitors the elderly person's biological data, such as their body temperature and pulse rate. If an abnormality is detected, the data is sent to the server. If the server exceeds a preset threshold, it notifies the user of the abnormality. For example, if an elderly person's body temperature exceeds 38 degrees, the server immediately sends a push notification to the user's smartphone saying, "Your mother's temperature is high. Please check it."

[1225] As a specific example, if a device launches a virtual avatar at 9:00 a.m. and asks an elderly person, "Did you sleep well last night?" and the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded, converted into text, and sent to the server. The server summarizes this information and saves it as "I slept well, but I had a slight cough." If the emotion engine recognizes "relief" in the elderly person's voice, this emotion data is also saved. The user can later review this summary and emotion data and take action as needed.

[1226] Here are some example prompts for creating summaries using a generative AI model (e.g., GPT-3):

[1227] Input text: "Yes, I slept well, but I have a bit of a cough."

[1228] Prompt: "Summarize the following conversation."

[1229] Example of generated summary: "I slept well, but I had a cough."

[1230] This concludes the "Mode for Carrying Out the Invention" of the present invention. This system enables elderly people and their families to communicate smoothly over distances and to appropriately understand changes in their health status and emotions.

[1231] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1232] Step 1:

[1233] The device launches the virtual avatar.

[1234] How it works: When the device's internal clock hits 9:00 AM, a virtual avatar application will automatically launch. The virtual avatar will then say "Good morning, how are you?"

[1235] Input: Clock information in the device.

[1236] Output: Virtual avatar activation and voice utterance.

[1237] Step 2:

[1238] The elderly person responds by voice.

[1239] Specific operation: The elderly person responds to the virtual avatar's speech by saying, "Yes, I'm fine." The device's microphone records this voice.

[1240] Input: Senior citizen's voice.

[1241] Output: Recorded audio data.

[1242] Step 3:

[1243] Convert the recorded data into text data.

[1244] Specific operation: The device sends the recorded voice data to a speech recognition engine (e.g., Google Cloud Speech-to-Text API). The speech recognition engine converts the voice "Yes, I'm fine" into text and returns it to the device.

[1245] Input: Audio data.

[1246] Output: Text data.

[1247] Step 4:

[1248] Sends text data to the server.

[1249] Specific operation: The terminal sends the converted text data to the server via the Internet. At this time, the data is encrypted before being sent.

[1250] Input: Text data.

[1251] Output: The text data sent to the server.

[1252] Step 5:

[1253] The server summarizes the text data.

[1254] How it works: The server inputs the received text data into a generative AI model (e.g., OpenAI GPT-3). The model generates a summary based on a pre-set prompt. For example, a summary such as "I slept well, but I had a cough" is generated.

[1255] Input: text data, prompt statement.

[1256] Output: Summary text data.

[1257] Step 6:

[1258] Recognizing the emotions of the elderly using an emotion recognition engine.

[1259] Specific operation: During the conversation, the device sends the recorded voice to an emotion recognition engine (e.g., IBM Watson Tone Analyzer). The engine analyzes the voice tone and generates emotion data. For example, the emotion data for "relief."

[1260] Input: Audio data.

[1261] Output: Emotion data.

[1262] Step 7:

[1263] Stores sentiment data and summary data.

[1264] Specific operation: The server stores the generated summary text data and emotion data in a database, which can be accessed by users in the future.

[1265] Input: Summary text data, sentiment data.

[1266] Output: Data stored in the database.

[1267] Step 8:

[1268] The user accesses the data.

[1269] Specific operation: The user accesses the server using a dedicated app or a web browser and logs in. An interface is displayed where the saved summary data and emotion data can be viewed. The user can select the desired date to view the data.

[1270] Input: The user's access request.

[1271] Output: Display of summary data and sentiment data.

[1272] Step 9:

[1273] Provides biometric data monitoring and abnormality notification functions.

[1274] Specific operation: The device periodically measures the elderly person's biometric data (e.g., body temperature and heart rate) using sensors. If an abnormality is detected, the data is sent to the server. If the server detects a value that exceeds a set threshold, it sends an abnormality notification to the user's smartphone (e.g., "Mom's body temperature is high. Please check it.").

[1275] Input: Biometric data.

[1276] Output: Abnormality notification.

[1277] (Application example 2)

[1278] 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."

[1279] There is a need for a system that allows family members and caregivers to accurately understand the elderly's condition by smoothly conducting dialogue with them and appropriately storing those records. However, existing systems have difficulty accurately detecting changes in the elderly's emotions and health status and responding promptly based on those changes. Furthermore, because summarization and emotion analysis of the elderly's speech are not automated, family members and caregivers must take the time and effort to check the speech. The present invention aims to solve these problems.

[1280] 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.

[1281] In this invention, the server includes a virtual avatar means, a recording means, a conversion means, a summarizing means, a storage means, a display means, an emotion engine means, and an emotion data storage means, which allows for smooth dialogue with the elderly, automates the summarization of the dialogue content and the analysis and storage of emotion data, and makes it possible to quickly grasp and respond to changes in the elderly's emotions and health condition.

[1282] "Virtual avatar means" refers to devices or software that simulate conversations with elderly people using audio and video and record the content of those conversations.

[1283] A "recording means" is a device or software that records the elderly person's speech as digital data.

[1284] The "conversion means" is software or an algorithm that converts the audio data obtained by the recording means into text data.

[1285] The "summarization means" is software or an algorithm that concisely summarizes the text data obtained by the conversion means.

[1286] The "storage means" is a device or software for storing the text data and emotion data generated by the summarization means in a database or storage device.

[1287] A "display means" is a device or software that allows a user to access and view data stored by a storage means.

[1288] The "emotion engine means" is software or algorithm that analyzes the elderly person's speech, facial expressions, and tone of voice to recognize their emotional state.

[1289] The "emotion data storage means" is a device or software that stores the emotion data recognized by the emotion engine means by including it in the summary text data.

[1290] The present invention provides a system that summarizes information obtained through dialogue with elderly people, analyzes and stores emotion data based on the information, and allows users to easily access the data. The following system is applied as an embodiment of the invention.

[1291] First, a smart device (such as a smartphone or tablet) is used as the terminal. A virtual avatar is installed on this terminal, and it periodically interacts with the elderly. The interaction is conducted via voice, and the content of the interaction is saved as digital data using a recording device.

[1292] The recorded voice data is converted into text data by a conversion means using a voice recognition engine, and the converted text data is then sent to a server.

[1293] The server summarizes the received text data using a summarization means. The summarization means uses natural language processing technology (e.g., a generative AI model). The summarized text data is stored in a database by a storage means.

[1294] A distinctive feature of this system is the emotion engine means, which analyzes voice tone, facial expressions, and language patterns to recognize the emotions of the elderly. This emotion data is stored in the emotion data storage means together with the text data generated by the summarization means.

[1295] Users can access and check the saved summary text data and emotion data using dedicated display means. For example, they can access the database via a dedicated application or a web browser. Users can easily check past conversation data and emotion data, and understand changes in the health status and emotions of elderly people.

[1296] Furthermore, the system is also equipped with anomaly detection and notification functions. The terminals and server regularly monitor the elderly person's biological data, such as their body temperature and pulse rate, and if an abnormality is detected, the user is notified via a notification means. In this case, push notifications can be used to quickly notify the user of the abnormality.

[1297] As a specific example, the device starts up a virtual avatar every day at 9:00 a.m. and asks the elderly person, "Did you sleep well last night?" If the elderly person responds, "Yes, I slept well, but I had a slight cough," this conversation is recorded and converted into text data. It is then sent to a server and saved as summarized text data, such as "I slept well, but I had a slight cough." The emotion engine means also recognizes "relief" from the elderly person's voice and saves it as emotion data. This data can be later checked by the user using a dedicated application. An example of a specific prompt sentence is, "Did you sleep well last night?"

[1298] The above is a specific embodiment for carrying out the present invention. This system is a great help to family members and caregivers because it can properly grasp the emotions and health status of elderly people and respond quickly.

[1299] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1300] Step 1:

[1301] The terminal (smart device) periodically (e.g., at 9 a.m.) wakes up the virtual avatar. The virtual avatar speaks a prompt to the elderly (e.g., "Good morning, how are you?") and receives a verbal response from the elderly. In this step, the input is the elderly's voice, and the output is the voice data.

[1302] Step 2:

[1303] The terminal uses a recording means to record the elderly person's response as digital voice data. The recorded voice data is temporarily stored in the device's memory. In this step, the input is the elderly person's response voice, and the output is digital voice data.

[1304] Step 3:

[1305] The device uses a conversion means to convert the recorded voice data into text data. A speech recognition engine (e.g., Google Speech-to-Text API) is used to recognize this voice data as text. In this step, the input is digital voice data and the output is text data.

[1306] Step 4:

[1307] The terminal sends the converted text data to the server via the Internet. The text data is encrypted and sent using a secure communication protocol (e.g., HTTPS). In this step, the input is the text data, and the output is the data sent to the server.

[1308] Step 5:

[1309] The server summarizes the received text data using a generative AI model. A natural language processing algorithm is used as a summarization method to remove redundant parts and extract important information. In this step, the input is text data, and the output is summarized text data.

[1310] Step 6:

[1311] The server stores the summarized text data in a database using a storage means. The stored data also includes a timestamp and identification information. In this step, the input is the summarized text data, and the output is the data stored in the database.

[1312] Step 7:

[1313] The server uses an emotion engine means to analyze the emotion of the elderly person from the received text data and voice tone. As a result of the analysis, emotion data is generated. In this step, the input is the text data and voice tone, and the output is the emotion data.

[1314] Step 8:

[1315] The server adds the emotion data to the summarized text data and stores it in a database using the emotion data storage means. In this step, the input is the emotion data and the summarized text data, and the output is stored data including the emotion data.

[1316] Step 9:

[1317] The user checks the saved summary text data and emotion data using a dedicated display means, for example, by accessing and displaying the data using a dedicated application or a web browser. In this step, the input is data from the database, and the output is the displayed information.

[1318] Step 10:

[1319] The server monitors biometric data (e.g., body temperature, pulse rate), and if an abnormality is detected, immediately sends a notification to the user using a notification means. This notification is sent as a push notification to a smartphone, etc. In this step, the input is biometric data, and the output is a notification to the user.

[1320] 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.

[1321] 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.

[1322] 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 robot 414.

[1323] 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.

[1324] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1325] 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.

[1326] 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).

[1327] 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.

[1328] 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."

[1329] 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.

[1330] 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).

[1331] 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.

[1332] 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.

[1333] 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.

[1334] 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.

[1335] 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.

[1336] 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.

[1337] 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.

[1338] 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.

[1339] 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.

[1340] 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.

[1341] The following is further disclosed regarding the above embodiment.

[1342] (Claim 1)

[1343] a virtual avatar means for interacting with the elderly;

[1344] a recording means for recording the speech of the elderly person obtained through the virtual avatar means;

[1345] a conversion means for converting the speech recorded by the recording means into text data;

[1346] summarizing means for summarizing the text data;

[1347] a storage means for storing the summarized text data generated by the summarizing means;

[1348] display means for allowing a user to access and review the stored summary text data;

[1349] A system including:

[1350] (Claim 2)

[1351] 2. The system according to claim 1, further comprising a notification means for notifying a user when an abnormality is detected in said display means.

[1352] (Claim 3)

[1353] 10. The system of claim 1, wherein the virtual avatar means is implemented by a smart device.

[1354] "Example 1"

[1355] (Claim 1)

[1356] a virtual assistant means for interacting with the elderly;

[1357] A recording means for recording the speech of the elderly person obtained through the virtual assistant means;

[1358] a conversion means for converting the speech recorded by the recording means into text data using a natural language processing engine;

[1359] a summary generation means for summarizing the text data using a generative artificial intelligence model;

[1360] a storage means for storing the summarized text data generated by the summary generating means in a database;

[1361] a display means for allowing a user to access and view the stored summary text data via dedicated software or a web application;

[1362] a monitoring means for periodically monitoring the biological information of the elderly person and transmitting the data to a server when an abnormality is detected;

[1363] A system including:

[1364] (Claim 2)

[1365] 2. The system according to claim 1, further comprising a warning unit that notifies a user of an abnormality when an abnormality is detected in said display unit.

[1366] (Claim 3)

[1367] The system according to claim 1, wherein the virtual assistant means is realized by an electronic device having a communication function.

[1368] "Application Example 1"

[1369] (Claim 1)

[1370] a virtual character means for interacting with the elderly;

[1371] a recording means for recording the speech of the elderly person obtained through the virtual character means;

[1372] a conversion means for converting the utterances recorded by the recording means into text data;

[1373] summarizing means for summarizing the text data;

[1374] a storage means for storing the summarized text data generated by the summarizing means;

[1375] display means for enabling a user to access and review said stored summary text data;

[1376] a monitoring means for periodically measuring and recording the elderly person's vital signs;

[1377] a detection means for detecting an abnormality based on the biological data;

[1378] a notification means for transmitting a notification when an abnormality is detected by the detection means;

[1379] A system including:

[1380] (Claim 2)

[1381] 2. The system according to claim 1, wherein a user is notified when an abnormality is detected by said notification means.

[1382] (Claim 3)

[1383] 10. The system of claim 1, wherein the virtual character means is implemented by a personal digital assistant.

[1384] "Example 2: Combining Emotion Engines"

[1385] (Claim 1)

[1386] a virtual avatar means for interacting with the elderly;

[1387] a recording means for recording the speech of the elderly person obtained through the virtual avatar means;

[1388] a conversion means for converting the speech recorded by the recording means into text data;

[1389] summarizing means for summarizing the text data;

[1390] a storage means for storing the summarized text data generated by the summarizing means;

[1391] display means for providing access to the stored summary text data;

[1392] emotion recognition means for recognizing the emotion of the elderly person;

[1393] additional storage means for storing emotion data recognized by the emotion recognition means;

[1394] a monitoring means for monitoring the biometric data of the elderly person;

[1395] a notification means for notifying a user of an abnormality detected by the monitoring means;

[1396] A system including:

[1397] (Claim 2)

[1398] 2. The system according to claim 1, wherein the saved summary text data and emotion data are presented to the user on the display means.

[1399] (Claim 3)

[1400] 2. The system according to claim 1, wherein the virtual avatar means is realized by a mobile information terminal.

[1401] "Application example 2 when combining emotion engines"

[1402] (Claim 1)

[1403] a virtual avatar means for interacting with the elderly;

[1404] a recording means for recording the speech of the elderly person obtained through the virtual avatar means;

[1405] a conversion means for converting the speech recorded by the recording means into text data;

[1406] summarizing means for summarizing the text data;

[1407] a storage means for storing the summarized text data generated by the summarizing means;

[1408] display means for allowing a user to access and review the stored summary text data;

[1409] emotion engine means for analyzing the emotions of the elderly person;

[1410] means for including emotion data generated by said emotion engine means in said summarized text data;

[1411] A system including:

[1412] (Claim 2)

[1413] 2. The system according to claim 1, further comprising a notification means for notifying a user when an abnormality is detected in said display means.

[1414] (Claim 3)

[1415] 10. The system of claim 1, wherein the virtual avatar means is implemented by a smart device. [Explanation of symbols]

[1416] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a virtual avatar means for interacting with the elderly; a recording means for recording the speech of the elderly person obtained through the virtual avatar means; a conversion means for converting the speech recorded by the recording means into text data; summarizing means for summarizing the text data; a storage means for storing the summarized text data generated by the summarizing means; display means for allowing a user to access and review the stored summary text data; A system including:

2. 2. The system according to claim 1, further comprising a notification means for notifying a user when an abnormality is detected in said display means.

3. The system of claim 1 , wherein the virtual avatar means is implemented by a smart device.

Images