System

Abstract

A system is provided.SOLUTION: A system comprising: sensor means for collecting motion data of a user; collection means for collecting image data and audio data of daily activities of the user; analysis means for analyzing the collected motion data, image data, and audio data to identify a behavior pattern and health condition of the user; provision means for providing the user with a personalized care plan generated based on the analysis results; and interaction means for interacting with the user to collect and analyze information from the user.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 today's elderly care field, the shortage of caregivers and improving the quality of life of the elderly are major challenges. In particular, current care systems are unable to adequately grasp the behavior and health status of elderly people in real time, making it difficult to provide personalized care that meets individual needs. Furthermore, innovative solutions are needed to improve the quality of life of the elderly while reducing the workload of caregivers. The objective of this invention is to provide technology that can effectively solve these challenges. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following configuration. First, a sensor means is provided for collecting user motion data, specifically including a bed sensor and a movement line sensor. Second, a collection means is provided for collecting image data and audio data of the user's daily activities, specifically including a camera and a microphone. Third, an analysis means is provided for analyzing the collected motion data, image data, and audio data to identify the user's behavioral patterns and health status, using a machine learning model and a generative AI model. Fourth, a provision means is provided for providing a personalized care plan based on the analysis results. Finally, an interaction means is provided for interacting with the user, collecting and analyzing information from the user, using a generative AI model. This makes it possible to understand the behavior and health status of elderly people in real time and provide personalized services tailored to their individual needs, thereby improving the quality of life of elderly people while reducing the workload of caregivers.

[0006] "Sensor means" is a general term for devices and mechanisms used to collect user motion data.

[0007] "Collection means" is a general term for devices and mechanisms used to collect image data and audio data of a user's daily activities.

[0008] "Analysis means" is a general term for devices and mechanisms that analyze collected motion data, image data, and voice data to identify the user's behavioral patterns and health condition.

[0009] "Provision means" is a general term for devices and mechanisms for providing users with personalized care plans generated based on the analysis results.

[0010] "Dialogue means" is a general term for devices and mechanisms for interacting with users and collecting and analyzing information from users.

[0011] A "bed sensor" is a sensor for detecting the state of a user lying in bed and the time of waking up.

[0012] A "traffic flow sensor" is a sensor that detects the movements and positions of users as they move around the room.

[0013] A "camera" is a device for videotaping a user's daily activities and detecting specific actions.

[0014] A "microphone" is a device that records the voice spoken by the user and detects specific keywords.

[0015] A "machine learning model" is an algorithm that analyzes a user's behavioral patterns and health status based on collected data.

[0016] A "generative AI model" is an artificial intelligence model that generates optimal responses and advice based on collected data and dialogue content. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system designed to improve the quality of care for the elderly, by collecting and analyzing a wide variety of data and providing personalized care services according to individual needs. Below, we will explain in detail how the program of this system is implemented.

[0039] System configuration

[0040] 1. Sensor means

[0041] Terminal

[0042] Various sensors, such as bed sensors and movement sensors, are used to collect user behavior data. For example, the bed sensors record the user's bedtime and wake-up time, and the movement sensors track the user's movement patterns within the room.

[0043] Specific examples

[0044] The device records the user's sleep patterns each night through sensors installed in the user's bed and understands the user's activity level.

[0045] 2. Collection Method

[0046] Terminal

[0047] Using a camera and microphone, it collects image and audio data of the user's daily activities, which can detect specific actions (e.g., falling) and specific keywords (e.g., "help me").

[0048] Specific examples

[0049] The device uses a camera installed in the living room to record video of the user watching TV or eating, and picks up conversations and audio through a microphone.

[0050] 3. Analysis method

[0051] server

[0052] Analyze collected motion, image, and audio data and use machine learning and generative AI models to identify user behavior patterns, health conditions, and abnormalities (e.g., falls).

[0053] Specific examples

[0054] The server analyzes a month's worth of sleep pattern data to detect sleep deprivation trends, and recognizes the word "help" from voice data to generate an emergency alert.

[0055] 4. Means of provision

[0056] server

[0057] Based on the analysis, users are provided with a personalized care plan that includes a daily schedule, health management advice, and specific care techniques.

[0058] Specific examples

[0059] The server generates a weekly exercise program for the user to exercise regularly and transmits the contents of the program to the user via the terminal.

[0060] 5. Means of interaction

[0061] User

[0062] Users input information by speaking to the chatbot, which uses generative AI models to generate responses and assess the user's health and psychological state.

[0063] Specific examples

[0064] A user can tell the chatbot, "I'm not feeling well today," and the chatbot will compare the user's past health data and provide advice on getting adequate rest.

[0065] Operational Overview

[0066] Terminal

[0067] It collects motion data, image data, and audio data in real time, converts them into appropriate formats, and transmits them to a server.

[0068] server

[0069] The received data is analyzed to identify behavioral patterns, health conditions, and abnormalities, and a personalized care plan is generated and notified to the user.

[0070] User

[0071] Users enter information about their health and daily life through the chatbot, which then analyzes the information and provides appropriate responses.

[0072] Specific program operation example

[0073] Collecting operational data

[0074] Based on the data obtained from the bed sensor, the device records the user's bedtime and wake-up time and sends the data to the server.

[0075] Image and audio data collection

[0076] The device uses a camera and microphone to collect image and audio data of the user's daily activities (e.g., eating, watching TV) and transmits them to a server.

[0077] Data analysis

[0078] The server analyzes the received data and uses machine learning and generative AI models to identify the user's behavioral patterns and health status, for example, detecting trends of sleep deprivation based on weekly sleep patterns.

[0079] Providing analysis results

[0080] Based on the analysis results, the server generates a personalized care plan (e.g., exercise program, dietary advice) and provides it to the user via the terminal.

[0081] Chatbot conversation

[0082] Users talk to the chatbot and input information about their health and psychological state. The chatbot analyzes the information and provides appropriate responses and advice. For example, if a user inputs "I'm feeling unwell today," the chatbot will respond, "I suggest you reflect on your recent activities and take a short break."

[0083] In this way, this system can significantly improve the quality of life of users by monitoring the daily lives of elderly people from various angles and providing personalized care services.

[0084] The processing flow will be explained below.

[0085] Step 1:

[0086] The device activates the bed sensor and movement line sensor to collect user behavior data. Each sensor detects the user's bedtime, wake-up time, and movement patterns within the room in real time and records them as data.

[0087] Step 2:

[0088] The device uses a camera and microphone to collect image and audio data about the user's daily activities. For example, the camera records video of the user cooking in the kitchen, and the microphone records the user's voice and conversations.

[0089] Step 3:

[0090] The device then packetizes the collected motion data, image data, and audio data and transmits them in the appropriate format to a server over a local network or the Internet.

[0091] Step 4:

[0092] The server receives the data packets sent by the devices and reconstructs the data stream, making all the collected data available for analysis.

[0093] Step 5:

[0094] The server then uses machine learning and generative AI models to analyze the reconstructed data. Specifically, it analyzes the user's behavioral patterns from the motion data, detects specific actions (e.g., falls) from the image data, and recognizes specific keywords (e.g., "help me") from the voice data.

[0095] Step 6:

[0096] The server generates insights into the user's health status and behavioral patterns based on the analysis results. These insights are stored in a database and used for future data analysis and updating of care plans.

[0097] Step 7:

[0098] Based on the generated insights, the server creates a personalized care plan that includes a daily schedule, health management advice, and specific care techniques.

[0099] Step 8:

[0100] The server provides the created care plan to the user via the terminal, which displays or provides audio guidance of the contents of the care plan in a format that is easy for the user to understand.

[0101] Step 9:

[0102] The user speaks to the chatbot installed in the system, which uses a generative AI model to analyze the user's voice and text and understand their intent.

[0103] Step 10:

[0104] The chatbot generates and provides appropriate responses based on the user's past data and current health status. For example, if the user says, "I'm not feeling well today," the chatbot will respond, "I recommend you limit your recent activities and get some rest."

[0105] Step 11:

[0106] The server analyzes the chatbot's dialogue and updates the care plan as needed. It also sends notifications to caregivers and family members if an emergency or abnormality is detected.

[0107] Step 12:

[0108] The server periodically retrains the generated AI and machine learning models with new data to improve the accuracy of the service, thereby continuously improving overall system performance and user satisfaction.

[0109] Example 1

[0110] 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."

[0111] Improving the quality of nursing care services for users, such as the elderly, is a socially important issue. In particular, collecting and analyzing diverse data is essential to provide personalized nursing care plans tailored to the needs of each user. However, conventional technologies have not fully established methods for integrating and analyzing motion data, image data, and voice data to identify users' behavioral patterns and health conditions. Furthermore, there is a lack of mechanisms for collecting information in real time through dialogue with users and providing appropriate care. Against this background, this invention aims to build a comprehensive system that enables the provision of more effective nursing care services.

[0112] 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.

[0113] In this invention, the server includes an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health condition, a provision means for providing the user with a personalized care plan created based on the analysis results, and a transmission means for converting the collected data into an appropriate format and transmitting it to the server. This makes it possible to comprehensively analyze a variety of data and provide appropriate care in real time.

[0114] The term "sensor means" refers to a device for collecting user movement data, and includes, for example, a bed sensor and a movement line sensor.

[0115] "Collection means" refers to a device for collecting image data and audio data of a user's daily activities, and includes, for example, a camera and a microphone.

[0116] "Analysis Means" means means, including machine learning models and generative AI models, for analyzing collected motion data, image data, and audio data to identify user behavior patterns and health conditions.

[0117] "Provision means" refers to a means for providing a personalized care plan generated based on the analysis results to a user.

[0118] "Interactive means" refers to means for interacting with users and collecting and analyzing information from users, including chatbots.

[0119] "Transmission means" refers to means for converting collected data into an appropriate format and transmitting it to the server.

[0120] This invention is a system designed to improve the quality of care for users such as the elderly. This system collects and analyzes a wide variety of data to provide personalized care services tailored to individual needs.

[0121] System configuration

[0122] Sensor Means

[0123] Terminal

[0124] The device is equipped with a bed sensor and a movement line sensor, which are used to collect user behavior data. Specifically, the bed sensor records the time of going to bed and waking up, and the movement line sensor tracks the movement patterns within the room.

[0125] Collection Method

[0126] Terminal

[0127] The device is equipped with a camera and microphone, which are used to collect image and audio data of the user's daily activities. The camera is installed in the living room and records the user's activities. The microphone picks up conversations and voices and detects specific abnormal sounds and words.

[0128] Analysis means

[0129] server

[0130] The server analyzes the collected motion data, image data, and voice data. It uses machine learning and generative AI models to identify the user's behavioral patterns, health status, and abnormalities. For example, the server analyzes a week's worth of sleep data to detect trends of sleep deprivation. It also recognizes the word "help" in voice data and generates an emergency alert.

[0131] Providing means

[0132] server

[0133] Based on the analysis results, the server generates a personalized care plan, which includes a daily schedule, health management advice, and specific care techniques. For example, the server uses the user's sleep analysis results to generate a weekly sleep improvement program with the goal of "ensuring at least seven hours of sleep per day," and notifies the user of the program via their device.

[0134] Interaction methods

[0135] User

[0136] Users input information by speaking to the chatbot, which then uses generative AI models to assess the user's health and psychological state. For example, if a user says to the chatbot, "I'm feeling unwell today," the chatbot will compare that with past health data and provide advice on getting adequate rest.

[0137] Operational Overview

[0138] Terminal

[0139] The terminal collects motion data, image data, and voice data in real time, converts them into appropriate formats, and transmits them to the server.

[0140] server

[0141] The server analyzes the received data to identify behavioral patterns, health conditions, and abnormalities, and generates a personalized care plan and notifies the user.

[0142] User

[0143] Users input information about their health and daily life through the chatbot, which then analyzes the information and provides appropriate responses.

[0144] Specific examples

[0145] Collecting operational data

[0146] Based on the data obtained from the bed sensor, the device records the user's bedtime and wake-up time and sends the data to the server.

[0147] Image and audio data collection

[0148] The device uses a camera and microphone to collect image and audio data of the user's daily activities and transmits them to a server.

[0149] Data analysis

[0150] The server analyzes the received data and uses machine learning and generative AI models to identify the user's behavioral patterns and health status, for example, detecting trends of sleep deprivation based on weekly sleep patterns.

[0151] Providing analysis results

[0152] Based on the analysis results, the server generates a personalized care plan (e.g., exercise program, dietary advice) and provides it to the user via the terminal.

[0153] Chatbot conversation

[0154] Users talk to the chatbot and input information about their health and psychological state. The chatbot analyzes the information and provides appropriate responses and advice. For example, if a user inputs "I'm feeling unwell today," the chatbot will respond, "I suggest you reflect on your recent activities and take a short break."

[0155] Example prompts for generative AI models

[0156] "Show how to analyze the user's health status using the behavioral data collected by the device."

[0157] "Explain the steps a chatbot can take to provide health advice based on user input."

[0158] In this way, this system can significantly improve the quality of life of users by monitoring the daily lives of elderly people from various angles and providing personalized care services.

[0159] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0160] Step 1: Collecting behavioral data

[0161] input

[0162] The device obtains real-time movement data from bed sensors and movement line sensors.

[0163] process

[0164] The device uses a bed sensor to record the user's bedtime and wake-up time, and a movement sensor to track the user's movement patterns within the room. The collected data is then converted into an appropriate format.

[0165] output

[0166] The converted motion data is generated and ready for transmission in the next step.

[0167] Specific operation example

[0168] The device records your sleep patterns each night and also tracks your movement patterns during the night, accumulating data.

[0169] Step 2: Collect image and audio data

[0170] input

[0171] Image and audio data acquired by the device from the camera and microphone.

[0172] process

[0173] The device uses image data to record the user's daily activities and audio data to capture conversations and sounds, then processes the data in real time to detect specific abnormal sounds or keywords.

[0174] output

[0175] The collected image and audio data is converted into an appropriate format and stored.

[0176] Specific operation example

[0177] The device uses a camera installed in the living room to record activity between 9am and 9pm, and a microphone to pick up conversations.

[0178] Step 3: Sending data

[0179] input

[0180] Motion data, image data, and voice data collected and converted by the device.

[0181] process

[0182] The device encrypts this data to ensure security and sends it to the server.

[0183] output

[0184] The encrypted data package is sent to the server.

[0185] Specific operation example

[0186] The device encrypts all data for the day at midnight and sends it to the server. Once the transmission is complete, the device waits for a confirmation response from the server.

[0187] Step 4: Analyze the data

[0188] input

[0189] The motion data, image data, and audio data received by the server.

[0190] process

[0191] The server analyzes this data using machine learning and generative AI models to identify user behavioral patterns and health conditions, and generates emergency alerts if anomalies are detected.

[0192] output

[0193] Analysis results and insights are generated and saved as the basis for generating care plans in the next step.

[0194] Specific operation example

[0195] The server analyzes a week's worth of sleep data to detect trends of sleep deprivation, and recognizes occurrences of the word "help" in the voice data, generating emergency alerts if necessary.

[0196] Step 5: Generate a care plan

[0197] input

[0198] The result data analyzed by the server.

[0199] process

[0200] The server generates a personalized care plan based on the analysis results, which includes a daily schedule, health management advice, and specific care techniques.

[0201] output

[0202] The generated care plan is sent to the terminal and notified to the user.

[0203] Specific operation example

[0204] Based on the results of the user's sleep analysis, the server generates a weekly sleep improvement program with the goal of ensuring "at least seven hours of sleep per day."

[0205] Step 6: Chatbot interaction

[0206] input

[0207] Information about health and daily life entered by users into the chatbot.

[0208] process

[0209] The chatbot uses generative AI models to analyze the input information and generate appropriate responses and advice.

[0210] output

[0211] Appropriate advice or responses are generated to be provided to the user.

[0212] Specific operation example

[0213] A user tells the chatbot, "I'm not feeling well today," and the chatbot compares this with past health data and offers advice such as, "I recommend you take a short break."

[0214] Through the above steps, this system can monitor the daily lives of elderly people from various angles and significantly improve the quality of life of users.

[0215] (Application example 1)

[0216] 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."

[0217] Conventional nursing care systems have struggled to comprehensively and in real time monitor the daily lives and health status of elderly people and provide personalized nursing care services tailored to their individual needs. Furthermore, in work environments such as factories, there was a lack of mechanisms to monitor the health status of employees and provide appropriate health management and work support. As a result, it was difficult to detect overwork and abnormal work patterns early on, increasing the risk of reduced labor productivity and safety.

[0218] 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.

[0219] In this invention, the server includes a sensor means for collecting user motion data, a collection means for collecting image data and voice data of the user's daily activities, an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health condition, a provision means for providing the user with a personalized care plan created based on the analysis results, a dialogue means for interacting with the user and collecting and analyzing information from the user, and a health monitoring means for detecting abnormalities and providing appropriate health management advice and work plans based on the analysis results using a machine learning model. This makes it possible to monitor the health condition of employees in real time and detect abnormalities early, thereby preventing overwork and improving work efficiency.

[0220] "Sensor means" refers to a set of devices for collecting user motion data.

[0221] The "collection means" is a device for collecting image data and audio data relating to the user's daily activities.

[0222] "Analysis means" means a computer-based system for analyzing collected motion data, image data, and audio data to identify user behavior patterns and health conditions.

[0223] The "provision means" is a mechanism for providing a personalized care plan generated based on the analysis results to the user.

[0224] An "interaction means" is an interface or system for collecting and analyzing information through interaction with a user.

[0225] The "health monitoring tool" is a system that detects abnormalities and provides appropriate health management advice and work plans based on the analysis results using machine learning models.

[0226] A "machine learning model" is a set of algorithms for analyzing large amounts of data and identifying patterns.

[0227] A "generative AI model" is a type of artificial intelligence algorithm that generates new data and answers based on specific tasks.

[0228] The system for implementing the present invention collects and analyzes motion data, image data, and voice data of a user, and provides a personalized care plan. This system is composed of the following means.

[0229] Sensor Means

[0230] The sensor means is a device for collecting user movement data. For example, a bed sensor or a movement line sensor is used to monitor the user's bedtime, wake-up time, and movement patterns within the room.

[0231] Collection Method

[0232] The collection means is a device that uses a camera and a microphone to collect image and audio data of the user's daily activities, allowing the user to record their meals, television viewing, conversations, and so on.

[0233] Analysis means

[0234] The analysis method is a system that analyzes the collected data using machine learning models and generative AI models on a server. This analysis identifies the user's behavioral patterns, health status, and abnormalities (e.g., falls). For example, it can detect trends of sleep deprivation from past data and generate emergency alerts.

[0235] Providing means

[0236] The provision method is a system that provides users with a personalized care plan created based on the analysis results, which includes a daily schedule, health management advice, exercise programs, etc.

[0237] Interaction methods

[0238] The dialogue means is an interface that interacts with the user and collects and analyzes information from the user. For example, a chatbot can be used to collect information such as "I'm feeling unwell today," and provide advice by comparing it with past data.

[0239] health monitoring measures

[0240] Health monitoring tools are systems that detect abnormalities and provide appropriate health management advice and work plans based on the results of analysis using machine learning models. For example, they can monitor the heart rates and movement patterns of employees working in a factory, and encourage them to take breaks if an abnormality is detected.

[0241] Hardware and software used

[0242] The system is implemented using the following hardware and software:

[0243] Sensor devices: bed sensors, movement sensors

[0244] Collection devices: camera, microphone

[0245] Analysis server: TensorFlow for machine learning, OpenCV for image processing

[0246] Devices provided: Smartphone, robot display

[0247] Conversational Interface: Chatbots

[0248] Specific examples

[0249] For example, if a user says "I'm feeling tired today" into their smartphone, the voice data is collected and compared with past health data by the server's generative AI model. As a result of the analysis, advice such as "I recommend you take a 15-minute break" is generated based on heart rate and movement patterns. This advice is then displayed on the smartphone screen.

[0250] Prompt Sentence Examples

[0251] "Please analyze my recent heart rate data and let me know what advice I need."

[0252] "What steps do you take when you detect abnormal employee behavior patterns?"

[0253] In this way, the system based on the present invention can comprehensively monitor the health status of elderly people and employees, detect abnormalities early, and provide care and health management that meets individual needs.

[0254] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0255] Step 1: Collecting Sensor Data

[0256] The server collects user behavior data through sensor means (bed sensors, movement line sensors). The input data obtained from the sensor means includes bedtime, wake-up time, and indoor movement patterns, and records these in real time. The output is a record of the user's activity.

[0257] Step 2: Collect image and audio data

[0258] The device uses collection means (camera, microphone) to collect image data and audio data related to the user's daily activities. The input includes the user's mealtimes and conversations, which are recorded as video clips and audio files. The output is the user's daily activity data.

[0259] Step 3: Sending data

[0260] The device sends the collected motion data, image data, and audio data to the server. The input is all sensor data and image / audio data stored in the device, which is converted into an appropriate format (e.g., JSON) and sent. The received data is saved on the server as output.

[0261] Step 4: Data analysis

[0262] The server analyzes the received data using a machine learning model (TensorFlow) and a generative AI model. The input data consists of motion data, image data, and audio data, which are analyzed to detect anomalies and identify behavioral patterns. Specifically, the server analyzes trends in sleep deprivation and the frequency of the keyword "help." The output generates analysis results related to the user's health condition and behavioral patterns.

[0263] Step 5: Generate analysis results

[0264] The server generates a personalized care plan based on the analysis results. The input is the analysis results obtained in the previous step, and based on this, it designs a daily schedule, health management advice, exercise programs, etc. The output is an individually tailored care plan.

[0265] Step 6: Notification by Delivery Method

[0266] The terminal notifies the user of the generated personalized care plan. The input data is the content of the care plan, which is displayed on the smartphone or robot's display. Specific actions include displaying a weekly exercise program and dietary advice. The output is a care plan in a format that the user can understand.

[0267] Step 7: Gather information through conversation

[0268] The user inputs information through an interactive means, which the device collects and analyzes. The input is voice input from the user (e.g., "I'm feeling unwell today"), which is analyzed to generate an appropriate response or advice. Using a generative AI model and comparing it with past data, appropriate advice such as advice on resting can be generated. Specific advice is provided to the user as an output.

[0269] Step 8: Health monitoring

[0270] The server detects anomalies and provides health management advice and work plans based on the analysis results using a machine learning model. Real-time sensor data and past analysis results are used as input, and based on this, it detects elevated heart rates and signs of overwork. Specifically, if the heart rate is abnormally high, the system outputs advice to "take a break," and the instruction is displayed on the device.

[0271] 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.

[0272] This invention is a system for improving the quality of care for the elderly. It collects and analyzes user motion data, image data of daily activities, and voice data to provide personalized care services tailored to individual needs. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it also supports emotional care. Below, we will explain in detail how the program of this system is implemented.

[0273] System configuration

[0274] 1. Sensor means

[0275] Terminal

[0276] To collect user behavior data, we use bed sensors and movement sensors. The bed sensors record the user's bedtime and wake-up time, and the movement sensors track the user's movement patterns within the room.

[0277] Specific examples

[0278] The device records the user's sleep patterns each night through sensors placed on the user's bed and understands the user's activity level.

[0279] 2. Collection Method

[0280] Terminal

[0281] Cameras and microphones are used to collect image and audio data of users' daily activities. For example, the camera records video of users cooking in the kitchen, and the microphone records their voices and conversations.

[0282] Specific examples

[0283] The device uses a camera installed in the living room to record video of the user watching TV or eating, and picks up conversations and audio through a microphone.

[0284] 3. Analysis method

[0285] server

[0286] The collected motion data, image data, and voice data are analyzed using machine learning and generative AI models. Specifically, the system analyzes the user's behavioral patterns from the motion data, detects specific motions (e.g., falls) from the image data, and recognizes specific keywords (e.g., "help me") from the voice data.

[0287] Specific examples

[0288] The server analyzes a month's worth of sleep pattern data to detect sleep deprivation trends, and recognizes the word "help" from voice data to generate an emergency alert.

[0289] 4. Means of provision

[0290] server

[0291] Based on the analysis results, a personalized care plan is generated and provided to the user, which includes a daily schedule, health management advice, and specific care techniques.

[0292] Specific examples

[0293] The server generates a weekly exercise program for the user to exercise regularly and transmits it to the user via the terminal.

[0294] 5. Means of interaction

[0295] User

[0296] Users input information by speaking to the chatbot installed in the system, which uses generative AI models to generate responses and assess the user's health and psychological state.

[0297] Specific examples

[0298] A user can tell the chatbot, "I'm not feeling well today," and the chatbot will compare the user's past health data and provide advice on getting adequate rest.

[0299] 6. Emotion Engine

[0300] server

[0301] The system is equipped with an emotion engine that recognizes emotions based on the user's image and voice data. The emotion engine analyzes the user's facial expressions and tone of voice to identify their emotional state.

[0302] Specific examples

[0303] The server analyzes the user's facial expressions captured by the camera to recognize signs of smiles or sadness, and analyzes the tone of voice from audio data to determine stress or relaxation.

[0304] Operational Overview

[0305] Terminal

[0306] It collects motion data, image data, and audio data in real time, converts them into appropriate formats, and transmits them to a server.

[0307] server

[0308] The received data is analyzed to identify behavioral patterns, health conditions, and emotional states, and a personalized care plan is generated and communicated to the user via delivery methods.

[0309] User

[0310] Users enter information about their health and daily life through the chatbot, which then analyzes the information and provides appropriate responses.

[0311] Specific program operation example

[0312] Collecting operational data

[0313] Based on the data obtained from the bed sensor, the device records the user's bedtime and wake-up time and sends the data to the server.

[0314] Image and audio data collection

[0315] The device uses a camera and microphone to collect image and audio data of the user's daily activities (e.g., eating, watching TV) and transmits them to a server.

[0316] Data analysis

[0317] The server analyzes the received data and uses machine learning and generative AI models to identify the user's behavioral patterns and health status. The emotion engine recognizes the user's emotional state based on image and audio data.

[0318] Providing analysis results

[0319] Based on the analysis results, the server generates a personalized care plan (e.g., exercise program, dietary advice) and provides it to the user via the device. Based on the results of the emotion engine, emotional care is also included.

[0320] Chatbot conversation

[0321] Users talk to the chatbot and input information about their health and psychological state. The chatbot analyzes the information and provides appropriate responses and advice. For example, if a user inputs "I'm feeling unwell today," the chatbot will respond, "I recommend you reduce your recent activities and take some rest."

[0322] In this way, this system utilizes multifaceted data to understand the user's behavior, health, and emotional state in real time, and provides personalized care services, thereby significantly improving the user's quality of life.

[0323] The processing flow will be explained below.

[0324] Step 1:

[0325] The device activates the bed sensor and the movement sensor to collect user behavior data. The bed sensor records the user's bedtime and wake-up time, and the movement sensor tracks the user's movement patterns within the room.

[0326] Step 2:

[0327] The device uses a camera and microphone to collect image and audio data of the user's daily activities. The camera records video of the user cooking in the kitchen, and the microphone records audio.

[0328] Step 3:

[0329] The terminal divides the collected motion data, image data, and voice data into packets, converts them into an appropriate format, and transmits them to the server.

[0330] Step 4:

[0331] The server receives the data packets sent by the devices and reconstructs the data stream, making the collected data in a form that can be analyzed.

[0332] Step 5:

[0333] The server then uses machine learning and generative AI models to analyze the reconstructed data. Specifically, it analyzes the user's behavioral patterns from the motion data, detects specific actions (e.g., falls) from the image data, and recognizes specific keywords (e.g., "help me") from the voice data.

[0334] Step 6:

[0335] The server uses an emotion engine to analyze the user's emotions from image and audio data, specifically analyzing facial expressions and tone of voice to identify their emotional state.

[0336] Step 7:

[0337] Based on the analysis results, the server generates insights into the user's health, behavioral patterns, and emotional state. These insights are stored in a database and used for future data analysis and updating of care plans.

[0338] Step 8:

[0339] Based on the generated insights, the server creates a personalized care plan for the user, which includes daily schedules, health management advice, specific care techniques, emotional care, and more.

[0340] Step 9:

[0341] The server provides the created care plan to the user via the terminal, which displays or provides audio guidance of the contents of the care plan in a format that is easy for the user to understand.

[0342] Step 10:

[0343] The user speaks to the chatbot installed in the system, which uses a generative AI model and an emotion engine to analyze the user's voice and text and understand their intentions and emotions.

[0344] Step 11:

[0345] The chatbot generates and provides appropriate responses based on the user's past data and current health and emotional state. For example, if the user says, "I'm not feeling well today," the chatbot will respond, "I suggest you review your recent activities and take a short break. Is there anything you're worried about?"

[0346] Step 12:

[0347] The server analyzes the chatbot's dialogue and the results of the emotion engine analysis, updates the care plan as needed, and sends notifications to caregivers and family members if an emergency or abnormality is detected.

[0348] Step 13:

[0349] The server periodically retrains the generated AI and machine learning models with new data to improve the accuracy of the service, thereby continuously improving overall system performance and user satisfaction.

[0350] Example 2

[0351] 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."

[0352] The challenge is to improve the quality of care for the elderly and provide personalized care according to their individual needs, especially by recognizing their emotional state and emergency situations in real time and providing appropriate responses.

[0353] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a detection means for collecting motion data, an acquisition means for collecting image data and voice data of daily activities, an analysis means for analyzing the collected motion data, image data, and voice data to identify behavioral patterns and health conditions, a supply means for providing an individual care plan generated based on the analysis results, a dialogue means for dialogue with the user and collecting and analyzing information from the user, and an emotion recognition means for identifying an emotional state from facial expressions and voice. This makes it possible to grasp the motion and emotional state of the user in real time and to respond quickly to emergencies.

[0354] "Motion data" is data that collects information about the user's body movements and position.

[0355] "Sensing means" refers to a device or sensor system for collecting operational data.

[0356] "Image data of daily activities" is video data that captures the user's daily life.

[0357] "Voice data" refers to data that records the user's speech and surrounding sounds.

[0358] "Capture means" refers to a device or system for collecting image and audio data of daily activities.

[0359] "Analysis means" refers to devices or algorithms that analyze collected motion data, image data, and audio data to identify a user's behavioral patterns and health status.

[0360] "Supply means" refers to a system for providing users with individual care plans generated based on the analysis results.

[0361] "Interaction means" refers to means for interacting with users and collecting and analyzing information from users.

[0362] "Emotion recognition means" refers to systems or algorithms that identify a user's emotional state from facial expressions and voice.

[0363] A "machine learning model" is a statistical model that recognizes patterns based on collected data and makes predictions and classifications.

[0364] A "generative AI model" is an artificial intelligence model for performing natural language processing and generation tasks.

[0365] "Anomaly detection" refers to the process of detecting deviations from normal behavior or data patterns.

[0366] "Insight generation" is the process of deriving important findings and insights gained through data analysis.

[0367] This invention is a system for improving the quality of care for the elderly. It collects and analyzes user motion data, image data of daily activities, and voice data to provide personalized care services according to individual needs. In addition, by combining it with an emotion engine, it also supports emotional care.

[0368] System Configuration

[0369] Detection Method

[0370] To collect motion data, the device uses bed sensors and movement sensors. These sensors are typically home IoT devices (e.g., Withings Sleep) that record the user's bedtime, wake-up time, and movement patterns within the room.

[0371] Specific examples

[0372] The device records the user's sleep patterns each night through a sensor placed on the user's bed, and determines the user's activity level. For example, the device collects data that the user went to bed at 10 p.m. and woke up at 7 a.m.

[0373] Acquisition means

[0374] The device uses a camera and a microphone to collect image and audio data of daily activities. For example, a network camera (e.g., Nest Cam Indoor) and a microphone installed in the living room are used to record the user's daily activities.

[0375] Specific examples

[0376] The device uses a camera installed in the living room to record video of the user watching TV or eating, and a microphone to pick up conversations and voices, such as "I'm going to make curry today."

[0377] analytical means

[0378] The server analyzes the collected motion, image, and audio data, using Google Cloud's machine learning services and OpenAI's generative AI models (e.g., GPT-4) to analyze behavioral patterns and health conditions.

[0379] Specific examples

[0380] The server analyzes one month's worth of sleep pattern data to detect whether the user is experiencing sleep deprivation. The server also automatically detects the word "help" from the voice data and determines this as an abnormality.

[0381] supply means

[0382] Based on the analysis results, the server generates an individually customized care plan and provides it to the user via their device, including health management advice and a daily schedule.

[0383] Specific examples

[0384] The server generates a weekly exercise program to encourage regular exercise and notifies the user via the device. For example, it recommends "stretching for 10 minutes every morning."

[0385] Interaction methods

[0386] Users input information by speaking to the chatbot installed on their device, which uses OpenAI GPT-4 to generate appropriate responses and assess the user's health and psychological state.

[0387] Specific examples

[0388] If a user tells the chatbot, "I'm not feeling well today," the chatbot will respond, "I recommend you limit your recent activities and take some rest."

[0389] emotion recognition means

[0390] The server runs an emotion engine based on the user's image and voice data to recognize their emotional state, which includes common recognition algorithms for analyzing facial expressions and tone of voice.

[0391] Specific examples

[0392] The server analyzes the user's facial expressions captured by the camera to recognize signs of smiles or sadness, and also uses voice data to determine stress or relaxation levels based on the tone of the voice.

[0393] In this way, the system of the present invention utilizes multifaceted data to grasp the user's behavior, health condition, and emotional state in real time, and provides personalized care services, thereby significantly improving the quality of life of the elderly.

[0394] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0395] Step 1:

[0396] Collecting operational data

[0397] The device collects the user's movement data. Using the bed sensor and movement line sensor, the device records the user's bedtime, wake-up time, and movement patterns within the room. As input, the device receives real-time data from the bed sensor and movement line sensor, and as output, it sends the collected movement data to a cloud server. This data includes precise time information and the type of movement (e.g., going to sleep, waking up, moving).

[0398] Specific examples

[0399] The device collects data that the user went to bed at 10 p.m. and woke up at 7 a.m. This data is sent to a cloud server.

[0400] Step 2:

[0401] Image and audio data collection

[0402] The device uses a camera and a microphone to collect image and audio data of the user's daily activities. As input, it receives video data from the camera and audio data from the microphone, and as output, it transmits these data to a cloud server.

[0403] Specific examples

[0404] The device uses a camera installed in the living room to record video of users watching TV or eating, and a microphone to pick up conversations and voices, and sends the collected data to a cloud server.

[0405] Step 3:

[0406] Data Preprocessing

[0407] The server receives the data sent from the device and converts it into an analyzable format. It receives raw motion, image, and audio data as input, and produces pre-processed data as output, including noise filtering and cropping. This includes noise filtering for audio data and adjusting the resolution of video data.

[0408] Specific examples

[0409] The server removes noise from the image data and crops only the necessary parts, and filters background noise from the audio data and extracts the main dialogue.

[0410] Step 4:

[0411] Data analysis

[0412] The server performs analysis using the preprocessed data. It receives the preprocessed data as input and generates a report of movement patterns, health status, and emotional state as output. This analysis uses machine learning models from Google Cloud Machine Learning Engine and OpenAI GPT-4.

[0413] Specific examples

[0414] The server analyzes one month's worth of sleep pattern data to detect whether the user is experiencing sleep deprivation. It also detects the keyword "help" from the voice data and recognizes it as an abnormality.

[0415] Step 5:

[0416] Generate analysis results

[0417] The server then generates a report based on the user's behavioral patterns and health status based on the analysis results. It receives the analysis data as input and generates a detailed report and recommended actions as output, including an assessment of the user's emotional state.

[0418] Specific examples

[0419] The server creates a report recommending that the user "get some rest early" based on their recent lack of sleep.

[0420] Step 6:

[0421] Providing personalized care plans

[0422] Based on the report generated by the server, an individually customized care plan is designed and provided to the user via the terminal.The report is received as input, and a care plan tailored to the user is generated as output.

[0423] Specific examples

[0424] The server creates a weekly exercise program to encourage regular exercise and communicates it to the user via the device. For example, it recommends "stretching for 10 minutes every morning."

[0425] Step 7:

[0426] Interacting with a chatbot

[0427] Users input information into the system by speaking to a chatbot installed on their device. The system receives the user's speech data as input, and generates an appropriate response as output using a generative AI model (e.g., OpenAI GPT-4).

[0428] Specific examples

[0429] If a user tells the chatbot, "I'm not feeling well today," the chatbot will respond, "I recommend you limit your recent activities and take some rest."

[0430] Step 8:

[0431] Emotion Recognition in Action

[0432] The server performs emotion recognition based on the user's image and audio data. It receives preprocessed image and audio data as input and generates data identifying the user's emotional state as output.

[0433] Specific examples

[0434] The server analyzes the user's facial expressions captured by the camera to recognize signs of smiles or sadness, and analyzes the tone of voice from audio data to determine stress or relaxation.

[0435] Step 9:

[0436] Emergency alert generation

[0437] If the server detects an abnormality, it generates an emergency alert and takes appropriate action. It receives anomaly detection data as input and generates an emergency alert notification as output.

[0438] Specific examples

[0439] The server detects the voice data saying "help," generates an emergency alert, and notifies the designated contacts. For example, it performs a process such as "the emergency button was pressed, so contact the care staff."

[0440] In this way, through the input, data processing, and output of each processing step, the user's movements, health condition, and emotional state can be grasped in real time, and appropriate nursing care services can be provided.

[0441] (Application example 2)

[0442] 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."

[0443] Current elderly care systems simply collect and analyze users' motion data and image and audio data of their daily activities, and provide personalized care plans based on the results. However, it is difficult to grasp the users' emotional state and provide appropriate emotional care. Furthermore, especially in brick-and-mortar stores, there is a need for a system that recognizes users' real-time emotional state and provides emotional care based on that. To solve this problem, it is necessary to build a system that includes an emotion recognition method.

[0444] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a sensor means for collecting user motion data, a collection means for collecting image data and voice data of the user's daily activities, an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health condition, a provision means for providing the user with a personalized care plan generated based on the analysis results, a dialogue means for dialogue with the user and collecting and analyzing information from the user, and an emotion recognition means for recognizing the user's emotional state and providing emotional care based on the emotional state. This makes it possible to comprehensively understand the user's behavior, health condition, and emotional state and provide a personalized care plan.

[0445] "Sensor means" refers to a plurality of sensor devices used to collect user motion data.

[0446] The "collection means" refers to a camera and microphone installed to record image data and audio data relating to the user's daily activities.

[0447] The "analysis means" is a system that analyzes collected motion data, image data, and audio data using machine learning models and generative AI models to identify the user's behavioral patterns and health status.

[0448] The "provision means" is a means for notifying the user of a personalized care plan generated based on the analysis results.

[0449] The "interactive means" is a system for interacting with users and collecting and analyzing information from users.

[0450] The "emotion recognition means" is a mechanism for recognizing the user's emotional state based on image data and voice data and providing emotional care.

[0451] A "personalized care plan" is a care service plan that is customized according to the specific needs and conditions of the user.

[0452] "Motion data" refers to data relating to the user's body movements and position.

[0453] "Image data" refers to data that records images of the user's daily activities.

[0454] "Audio data" refers to data that records the user's everyday conversations and environmental sounds.

[0455] A "machine learning model" is a model based on algorithms used for pattern recognition and data analysis.

[0456] A "generative AI model" is an artificial intelligence model used for natural language processing and response generation.

[0457] A "physical store" is a place that provides care services for the elderly in a physical location.

[0458] A "chatbot" is a program that interacts with users through text and voice.

[0459] The system for implementing this invention collects and analyzes motion data, image data, and voice data of a user, and provides a personalized care plan that also includes emotional state. The specific configuration and operation of this system are described in detail below.

[0460] System configuration

[0461] Hardware

[0462] 1. Sensor means: Includes bed sensors and movement line sensors for collecting user movement data. These are often installed in physical stores to detect user presence information and behavioral patterns.

[0463] 2. Collection methods: These include cameras and microphones to record users' daily activities, and are expected to be installed especially in physical stores.

[0464] 3. Emotion recognition means: These include cameras and microphones to analyze the user's facial expressions and tone of voice. These are also typically installed in physical stores.

[0465] 4. User terminal: A device carried by the user, such as a smartphone or smart glasses, used to display the collected and analyzed results.

[0466] software

[0467] 1. Machine learning models: These include algorithm-based models that analyze motion and image data to identify user behavior patterns and health conditions.

[0468] 2. Generative AI models: These include artificial intelligence models used for natural language processing and response generation. They are used to generate responses for chatbots as a means of dialogue.

[0469] 3. Emotion Engine: Includes software for recognizing the user's emotional state from image and audio data.

[0470] 4. Cloud servers: Includes cloud computing platforms for data analysis and storage, such as AWS and GCP.

[0471] System Operation

[0472] Data collection

[0473] The terminal uses the sensor means, the collection means, and the emotion recognition means to collect the user's motion data, image data, and voice data in real time, and transmits this data to a cloud server via the Internet.

[0474] Data analysis

[0475] The server analyzes the received data, specifically using machine learning and generative AI models to analyze motion, image, and audio data to identify the user's behavioral patterns, health, and emotional state.

[0476] Providing results

[0477] Based on the analysis results, personalized care plans and activity suggestions are generated and notified to the user via their device. Emotional care is also provided based on the results of the emotion engine.

[0478] Interactive features

[0479] When users input information about their health and daily life through the chatbot, the generative AI model uses that information to generate an appropriate response. For example, if a user inputs "I'm not feeling well today," the model will respond with "I recommend you limit your recent activities and take some time to rest."

[0480] Specific examples

[0481] Example prompt:

[0482] 1. "I've been analyzing your sleep patterns lately and have found that you're waking up frequently during the night. Should I try making some changes to my exercise program?"

[0483] 2. "According to your facial expression analysis, you seem to be stressed. Try taking a deep breath."

[0484] The system provides a comprehensive understanding of the user's behavior, health and emotional state, enabling it to provide personalized care plans.

[0485] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0486] Step 1:

[0487] The device uses sensor means, collection means, and emotion recognition means to collect the user's behavioral data (e.g., bedtime, wake-up time, movement patterns), image data (e.g., footage of cooking), and audio data (e.g., conversation content) in real time. The input is data from numerous sensors and devices, and the output is data converted into a format for sending to a cloud server. In terms of specific operations, the bed sensor records the time the user goes to bed and wakes up, the movement line sensor traces movement patterns within the room, and the camera and microphone record daily activities.

[0488] Step 2:

[0489] The data collected by the device is sent to the cloud server via the Internet. The input is the data collected in step 1, and the output is the data stored on the cloud server. Specifically, the data is sent to the server using an appropriate protocol (e.g., HTTP, MQTT) and stored in a database.

[0490] Step 3:

[0491] The server uses machine learning models and generative AI models to analyze the motion data, image data, and voice data stored on the cloud server. The input is the data stored on the server, and the output is the analysis results that identify the user's behavioral patterns, health status, and emotional state. Specific actions include extracting behavioral patterns from motion data, detecting specific actions (e.g., falling) from image data, and recognizing specific keywords (e.g., "help me") from voice data.

[0492] Step 4:

[0493] The server creates a personalized care plan based on the analysis results and provides it to the user via the terminal. The input is the analysis results obtained in step 3, and the output is a personalized care plan. Specifically, it generates an exercise program and dietary advice based on the user's health condition and behavioral patterns, and notifies them via the user's terminal.

[0494] Step 5:

[0495] Users input information about their health and daily life through the chatbot, and the generative AI model generates an appropriate response based on that information. The input is the user's voice and text information, and the output is the generated response. For example, if a user says, "I'm not feeling well today," the chatbot will respond, "I recommend you reduce your recent activities and take some rest."

[0496] Step 6:

[0497] The server uses an emotion recognition engine to identify the emotional state from image and audio data and provide emotional care based on that. The input is image and audio data, and the output is the identified emotional state and care suggestions based on that. Specific operations include recognizing signs of smiles and sadness from facial expression analysis, and displaying advice on the user's device to relieve stress as needed.

[0498] 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.

[0499] 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.

[0500] 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.

[0501] [Second embodiment]

[0502] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0503] 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.

[0504] 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).

[0505] 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.

[0506] 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.

[0507] 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).

[0508] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0509] 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.

[0510] 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.

[0511] 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.

[0512] 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.

[0513] 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."

[0514] This invention is a system designed to improve the quality of care for the elderly, by collecting and analyzing a wide variety of data and providing personalized care services according to individual needs. Below, we will explain in detail how the program of this system is implemented.

[0515] System configuration

[0516] 1. Sensor means

[0517] Terminal

[0518] Various sensors, such as bed sensors and movement sensors, are used to collect user behavior data. For example, the bed sensors record the user's bedtime and wake-up time, and the movement sensors track the user's movement patterns within the room.

[0519] Specific examples

[0520] The device records the user's sleep patterns each night through sensors installed in the user's bed and understands the user's activity level.

[0521] 2. Collection Method

[0522] Terminal

[0523] Using a camera and microphone, it collects image and audio data of the user's daily activities, which can detect specific actions (e.g., falling) and specific keywords (e.g., "help me").

[0524] Specific examples

[0525] The device uses a camera installed in the living room to record video of the user watching TV or eating, and picks up conversations and audio through a microphone.

[0526] 3. Analysis method

[0527] server

[0528] Analyze collected motion, image, and audio data and use machine learning and generative AI models to identify user behavior patterns, health conditions, and abnormalities (e.g., falls).

[0529] Specific examples

[0530] The server analyzes a month's worth of sleep pattern data to detect sleep deprivation trends, and recognizes the word "help" from voice data to generate an emergency alert.

[0531] 4. Means of provision

[0532] server

[0533] Based on the analysis, users are provided with a personalized care plan that includes a daily schedule, health management advice, and specific care techniques.

[0534] Specific examples

[0535] The server generates a weekly exercise program for the user to exercise regularly and transmits the contents of the program to the user via the terminal.

[0536] 5. Means of interaction

[0537] User

[0538] Users input information by speaking to the chatbot, which uses generative AI models to generate responses and assess the user's health and psychological state.

[0539] Specific examples

[0540] A user can tell the chatbot, "I'm not feeling well today," and the chatbot will compare the user's past health data and provide advice on getting adequate rest.

[0541] Operational Overview

[0542] Terminal

[0543] It collects motion data, image data, and audio data in real time, converts them into appropriate formats, and transmits them to a server.

[0544] server

[0545] The received data is analyzed to identify behavioral patterns, health conditions, and abnormalities, and a personalized care plan is generated and notified to the user.

[0546] User

[0547] Users enter information about their health and daily life through the chatbot, which then analyzes the information and provides appropriate responses.

[0548] Specific program operation example

[0549] Collecting operational data

[0550] Based on the data obtained from the bed sensor, the device records the user's bedtime and wake-up time and sends the data to the server.

[0551] Image and audio data collection

[0552] The device uses a camera and microphone to collect image and audio data of the user's daily activities (e.g., eating, watching TV) and transmits them to a server.

[0553] Data analysis

[0554] The server analyzes the received data and uses machine learning and generative AI models to identify the user's behavioral patterns and health status, for example, detecting trends of sleep deprivation based on weekly sleep patterns.

[0555] Providing analysis results

[0556] Based on the analysis results, the server generates a personalized care plan (e.g., exercise program, dietary advice) and provides it to the user via the terminal.

[0557] Chatbot conversation

[0558] Users talk to the chatbot and input information about their health and psychological state. The chatbot analyzes the information and provides appropriate responses and advice. For example, if a user inputs "I'm feeling unwell today," the chatbot will respond, "I suggest you reflect on your recent activities and take a short break."

[0559] In this way, this system can significantly improve the quality of life of users by monitoring the daily lives of elderly people from various angles and providing personalized care services.

[0560] The processing flow will be explained below.

[0561] Step 1:

[0562] The device activates the bed sensor and movement line sensor to collect user behavior data. Each sensor detects the user's bedtime, wake-up time, and movement patterns within the room in real time and records them as data.

[0563] Step 2:

[0564] The device uses a camera and microphone to collect image and audio data about the user's daily activities. For example, the camera records video of the user cooking in the kitchen, and the microphone records the user's voice and conversations.

[0565] Step 3:

[0566] The device then packetizes the collected motion data, image data, and audio data and transmits them in the appropriate format to a server over a local network or the Internet.

[0567] Step 4:

[0568] The server receives the data packets sent by the devices and reconstructs the data stream, making all the collected data available for analysis.

[0569] Step 5:

[0570] The server then uses machine learning and generative AI models to analyze the reconstructed data. Specifically, it analyzes the user's behavioral patterns from the motion data, detects specific actions (e.g., falls) from the image data, and recognizes specific keywords (e.g., "help me") from the voice data.

[0571] Step 6:

[0572] The server generates insights into the user's health status and behavioral patterns based on the analysis results. These insights are stored in a database and used for future data analysis and updating of care plans.

[0573] Step 7:

[0574] Based on the generated insights, the server creates a personalized care plan that includes a daily schedule, health management advice, and specific care techniques.

[0575] Step 8:

[0576] The server provides the created care plan to the user via the terminal, which displays or provides audio guidance of the contents of the care plan in a format that is easy for the user to understand.

[0577] Step 9:

[0578] The user speaks to the chatbot installed in the system, which uses a generative AI model to analyze the user's voice and text and understand their intent.

[0579] Step 10:

[0580] The chatbot generates and provides appropriate responses based on the user's past data and current health status. For example, if the user says, "I'm not feeling well today," the chatbot will respond, "I recommend you limit your recent activities and get some rest."

[0581] Step 11:

[0582] The server analyzes the chatbot's dialogue and updates the care plan as needed. It also sends notifications to caregivers and family members if an emergency or abnormality is detected.

[0583] Step 12:

[0584] The server periodically retrains the generated AI and machine learning models with new data to improve the accuracy of the service, thereby continuously improving overall system performance and user satisfaction.

[0585] Example 1

[0586] 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."

[0587] Improving the quality of nursing care services for users, such as the elderly, is a socially important issue. In particular, collecting and analyzing diverse data is essential to provide personalized nursing care plans tailored to the needs of each user. However, conventional technologies have not fully established methods for integrating and analyzing motion data, image data, and voice data to identify users' behavioral patterns and health conditions. Furthermore, there is a lack of mechanisms for collecting information in real time through dialogue with users and providing appropriate care. Against this background, this invention aims to build a comprehensive system that enables the provision of more effective nursing care services.

[0588] 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.

[0589] In this invention, the server includes an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health condition, a provision means for providing the user with a personalized care plan created based on the analysis results, and a transmission means for converting the collected data into an appropriate format and transmitting it to the server. This makes it possible to comprehensively analyze a variety of data and provide appropriate care in real time.

[0590] The term "sensor means" refers to a device for collecting user movement data, and includes, for example, a bed sensor and a movement line sensor.

[0591] "Collection means" refers to a device for collecting image data and audio data of a user's daily activities, and includes, for example, a camera and a microphone.

[0592] "Analysis Means" means means, including machine learning models and generative AI models, for analyzing collected motion data, image data, and audio data to identify user behavior patterns and health conditions.

[0593] "Provision means" refers to a means for providing a personalized care plan generated based on the analysis results to a user.

[0594] "Interactive means" refers to means for interacting with users and collecting and analyzing information from users, including chatbots.

[0595] "Transmission means" refers to means for converting collected data into an appropriate format and transmitting it to the server.

[0596] This invention is a system designed to improve the quality of care for users such as the elderly. This system collects and analyzes a wide variety of data to provide personalized care services tailored to individual needs.

[0597] System configuration

[0598] Sensor Means

[0599] Terminal

[0600] The device is equipped with a bed sensor and a movement line sensor, which are used to collect user behavior data. Specifically, the bed sensor records the time of going to bed and waking up, and the movement line sensor tracks the movement patterns within the room.

[0601] Collection Method

[0602] Terminal

[0603] The device is equipped with a camera and microphone, which are used to collect image and audio data of the user's daily activities. The camera is installed in the living room and records the user's activities. The microphone picks up conversations and voices and detects specific abnormal sounds and words.

[0604] Analysis means

[0605] server

[0606] The server analyzes the collected motion data, image data, and voice data. It uses machine learning and generative AI models to identify the user's behavioral patterns, health status, and abnormalities. For example, the server analyzes a week's worth of sleep data to detect trends of sleep deprivation. It also recognizes the word "help" in voice data and generates an emergency alert.

[0607] Providing means

[0608] server

[0609] Based on the analysis results, the server generates a personalized care plan, which includes a daily schedule, health management advice, and specific care techniques. For example, the server uses the user's sleep analysis results to generate a weekly sleep improvement program with the goal of "ensuring at least seven hours of sleep per day," and notifies the user of the program via their device.

[0610] Interaction methods

[0611] User

[0612] Users input information by speaking to the chatbot, which then uses generative AI models to assess the user's health and psychological state. For example, if a user says to the chatbot, "I'm feeling unwell today," the chatbot will compare that with past health data and provide advice on getting adequate rest.

[0613] Operational Overview

[0614] Terminal

[0615] The terminal collects motion data, image data, and voice data in real time, converts them into appropriate formats, and transmits them to the server.

[0616] server

[0617] The server analyzes the received data to identify behavioral patterns, health conditions, and abnormalities, and generates a personalized care plan and notifies the user.

[0618] User

[0619] Users input information about their health and daily life through the chatbot, which then analyzes the information and provides appropriate responses.

[0620] Specific examples

[0621] Collecting operational data

[0622] Based on the data obtained from the bed sensor, the device records the user's bedtime and wake-up time and sends the data to the server.

[0623] Image and audio data collection

[0624] The device uses a camera and microphone to collect image and audio data of the user's daily activities and transmits them to a server.

[0625] Data analysis

[0626] The server analyzes the received data and uses machine learning and generative AI models to identify the user's behavioral patterns and health status, for example, detecting trends of sleep deprivation based on weekly sleep patterns.

[0627] Providing analysis results

[0628] Based on the analysis results, the server generates a personalized care plan (e.g., exercise program, dietary advice) and provides it to the user via the terminal.

[0629] Chatbot conversation

[0630] Users talk to the chatbot and input information about their health and psychological state. The chatbot analyzes the information and provides appropriate responses and advice. For example, if a user inputs "I'm feeling unwell today," the chatbot will respond, "I suggest you reflect on your recent activities and take a short break."

[0631] Example prompts for generative AI models

[0632] "Show how to analyze the user's health status using the behavioral data collected by the device."

[0633] "Explain the steps a chatbot can take to provide health advice based on user input."

[0634] In this way, this system can significantly improve the quality of life of users by monitoring the daily lives of elderly people from various angles and providing personalized care services.

[0635] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0636] Step 1: Collecting behavioral data

[0637] input

[0638] The device obtains real-time movement data from bed sensors and movement line sensors.

[0639] process

[0640] The device uses a bed sensor to record the user's bedtime and wake-up time, and a movement sensor to track the user's movement patterns within the room. The collected data is then converted into an appropriate format.

[0641] output

[0642] The converted motion data is generated and ready for transmission in the next step.

[0643] Specific operation example

[0644] The device records your sleep patterns each night and also tracks your movement patterns during the night, accumulating data.

[0645] Step 2: Collect image and audio data

[0646] input

[0647] Image and audio data acquired by the device from the camera and microphone.

[0648] process

[0649] The device uses image data to record the user's daily activities and audio data to capture conversations and sounds, then processes the data in real time to detect specific abnormal sounds or keywords.

[0650] output

[0651] The collected image and audio data is converted into an appropriate format and stored.

[0652] Specific operation example

[0653] The device uses a camera installed in the living room to record activity between 9am and 9pm, and a microphone to pick up conversations.

[0654] Step 3: Sending data

[0655] input

[0656] Motion data, image data, and voice data collected and converted by the device.

[0657] process

[0658] The device encrypts this data to ensure security and sends it to the server.

[0659] output

[0660] The encrypted data package is sent to the server.

[0661] Specific operation example

[0662] The device encrypts all data for the day at midnight and sends it to the server. Once the transmission is complete, the device waits for a confirmation response from the server.

[0663] Step 4: Analyze the data

[0664] input

[0665] The motion data, image data, and audio data received by the server.

[0666] process

[0667] The server analyzes this data using machine learning and generative AI models to identify user behavioral patterns and health conditions, and generates emergency alerts if anomalies are detected.

[0668] output

[0669] Analysis results and insights are generated and saved as the basis for generating care plans in the next step.

[0670] Specific operation example

[0671] The server analyzes a week's worth of sleep data to detect trends of sleep deprivation, and recognizes occurrences of the word "help" in the voice data, generating emergency alerts if necessary.

[0672] Step 5: Generate a care plan

[0673] input

[0674] The result data analyzed by the server.

[0675] process

[0676] The server generates a personalized care plan based on the analysis results, which includes a daily schedule, health management advice, and specific care techniques.

[0677] output

[0678] The generated care plan is sent to the terminal and notified to the user.

[0679] Specific operation example

[0680] Based on the results of the user's sleep analysis, the server generates a weekly sleep improvement program with the goal of ensuring "at least seven hours of sleep per day."

[0681] Step 6: Chatbot interaction

[0682] input

[0683] Information about health and daily life entered by users into the chatbot.

[0684] process

[0685] The chatbot uses generative AI models to analyze the input information and generate appropriate responses and advice.

[0686] output

[0687] Appropriate advice or responses are generated to be provided to the user.

[0688] Specific operation example

[0689] A user tells the chatbot, "I'm not feeling well today," and the chatbot compares this with past health data and offers advice such as, "I recommend you take a short break."

[0690] Through the above steps, this system can monitor the daily lives of elderly people from various angles and significantly improve the quality of life of users.

[0691] (Application example 1)

[0692] 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."

[0693] Conventional nursing care systems have struggled to comprehensively and in real time monitor the daily lives and health status of elderly people and provide personalized nursing care services tailored to their individual needs. Furthermore, in work environments such as factories, there was a lack of mechanisms to monitor the health status of employees and provide appropriate health management and work support. As a result, it was difficult to detect overwork and abnormal work patterns early on, increasing the risk of reduced labor productivity and safety.

[0694] 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.

[0695] In this invention, the server includes a sensor means for collecting user motion data, a collection means for collecting image data and voice data of the user's daily activities, an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health condition, a provision means for providing the user with a personalized care plan created based on the analysis results, a dialogue means for interacting with the user and collecting and analyzing information from the user, and a health monitoring means for detecting abnormalities and providing appropriate health management advice and work plans based on the analysis results using a machine learning model. This makes it possible to monitor the health condition of employees in real time and detect abnormalities early, thereby preventing overwork and improving work efficiency.

[0696] "Sensor means" refers to a set of devices for collecting user motion data.

[0697] The "collection means" is a device for collecting image data and audio data relating to the user's daily activities.

[0698] "Analysis means" means a computer-based system for analyzing collected motion data, image data, and audio data to identify user behavior patterns and health conditions.

[0699] The "provision means" is a mechanism for providing a personalized care plan generated based on the analysis results to the user.

[0700] An "interaction means" is an interface or system for collecting and analyzing information through interaction with a user.

[0701] The "health monitoring tool" is a system that detects abnormalities and provides appropriate health management advice and work plans based on the analysis results using machine learning models.

[0702] A "machine learning model" is a set of algorithms for analyzing large amounts of data and identifying patterns.

[0703] A "generative AI model" is a type of artificial intelligence algorithm that generates new data and answers based on specific tasks.

[0704] The system for implementing the present invention collects and analyzes motion data, image data, and voice data of a user, and provides a personalized care plan. This system is composed of the following means.

[0705] Sensor Means

[0706] The sensor means is a device for collecting user movement data. For example, a bed sensor or a movement line sensor is used to monitor the user's bedtime, wake-up time, and movement patterns within the room.

[0707] Collection Method

[0708] The collection means is a device that uses a camera and a microphone to collect image and audio data of the user's daily activities, allowing the user to record their meals, television viewing, conversations, and so on.

[0709] Analysis means

[0710] The analysis method is a system that analyzes the collected data using machine learning models and generative AI models on a server. This analysis identifies the user's behavioral patterns, health status, and abnormalities (e.g., falls). For example, it can detect trends of sleep deprivation from past data and generate emergency alerts.

[0711] Providing means

[0712] The provision method is a system that provides users with a personalized care plan created based on the analysis results, which includes a daily schedule, health management advice, exercise programs, etc.

[0713] Interaction methods

[0714] The dialogue means is an interface that interacts with the user and collects and analyzes information from the user. For example, a chatbot can be used to collect information such as "I'm feeling unwell today," and provide advice by comparing it with past data.

[0715] health monitoring measures

[0716] Health monitoring tools are systems that detect abnormalities and provide appropriate health management advice and work plans based on the results of analysis using machine learning models. For example, they can monitor the heart rates and movement patterns of employees working in a factory, and encourage them to take breaks if an abnormality is detected.

[0717] Hardware and software used

[0718] The system is implemented using the following hardware and software:

[0719] Sensor devices: bed sensors, movement sensors

[0720] Collection devices: camera, microphone

[0721] Analysis server: TensorFlow for machine learning, OpenCV for image processing

[0722] Devices provided: Smartphone, robot display

[0723] Conversational Interface: Chatbots

[0724] Specific examples

[0725] For example, if a user says "I'm feeling tired today" into their smartphone, the voice data is collected and compared with past health data by the server's generative AI model. As a result of the analysis, advice such as "I recommend you take a 15-minute break" is generated based on heart rate and movement patterns. This advice is then displayed on the smartphone screen.

[0726] Prompt Sentence Examples

[0727] "Please analyze my recent heart rate data and let me know what advice I need."

[0728] "What steps do you take when you detect abnormal employee behavior patterns?"

[0729] In this way, the system based on the present invention can comprehensively monitor the health status of elderly people and employees, detect abnormalities early, and provide care and health management that meets individual needs.

[0730] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0731] Step 1: Collecting Sensor Data

[0732] The server collects user behavior data through sensor means (bed sensors, movement line sensors). The input data obtained from the sensor means includes bedtime, wake-up time, and indoor movement patterns, and records these in real time. The output is a record of the user's activity.

[0733] Step 2: Collect image and audio data

[0734] The device uses collection means (camera, microphone) to collect image data and audio data related to the user's daily activities. The input includes the user's mealtimes and conversations, which are recorded as video clips and audio files. The output is the user's daily activity data.

[0735] Step 3: Sending data

[0736] The device sends the collected motion data, image data, and audio data to the server. The input is all sensor data and image / audio data stored in the device, which is converted into an appropriate format (e.g., JSON) and sent. The received data is saved on the server as output.

[0737] Step 4: Data analysis

[0738] The server analyzes the received data using a machine learning model (TensorFlow) and a generative AI model. The input data consists of motion data, image data, and audio data, which are analyzed to detect anomalies and identify behavioral patterns. Specifically, the server analyzes trends in sleep deprivation and the frequency of the keyword "help." The output generates analysis results related to the user's health condition and behavioral patterns.

[0739] Step 5: Generate analysis results

[0740] The server generates a personalized care plan based on the analysis results. The input is the analysis results obtained in the previous step, and based on this, it designs a daily schedule, health management advice, exercise programs, etc. The output is an individually tailored care plan.

[0741] Step 6: Notification by Delivery Method

[0742] The terminal notifies the user of the generated personalized care plan. The input data is the content of the care plan, which is displayed on the smartphone or robot's display. Specific actions include displaying a weekly exercise program and dietary advice. The output is a care plan in a format that the user can understand.

[0743] Step 7: Gather information through conversation

[0744] The user inputs information through an interactive means, which the device collects and analyzes. The input is voice input from the user (e.g., "I'm feeling unwell today"), which is analyzed to generate an appropriate response or advice. Using a generative AI model and comparing it with past data, appropriate advice such as advice on resting can be generated. Specific advice is provided to the user as an output.

[0745] Step 8: Health monitoring

[0746] The server detects anomalies and provides health management advice and work plans based on the analysis results using a machine learning model. Real-time sensor data and past analysis results are used as input, and based on this, it detects elevated heart rates and signs of overwork. Specifically, if the heart rate is abnormally high, the system outputs advice to "take a break," and the instruction is displayed on the device.

[0747] 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.

[0748] This invention is a system for improving the quality of care for the elderly. It collects and analyzes user motion data, image data of daily activities, and voice data to provide personalized care services tailored to individual needs. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it also supports emotional care. Below, we will explain in detail how the program of this system is implemented.

[0749] System configuration

[0750] 1. Sensor means

[0751] Terminal

[0752] To collect user behavior data, we use bed sensors and movement sensors. The bed sensors record the user's bedtime and wake-up time, and the movement sensors track the user's movement patterns within the room.

[0753] Specific examples

[0754] The device records the user's sleep patterns each night through sensors placed on the user's bed and understands the user's activity level.

[0755] 2. Collection Method

[0756] Terminal

[0757] Cameras and microphones are used to collect image and audio data of users' daily activities. For example, the camera records video of users cooking in the kitchen, and the microphone records their voices and conversations.

[0758] Specific examples

[0759] The device uses a camera installed in the living room to record video of the user watching TV or eating, and picks up conversations and audio through a microphone.

[0760] 3. Analysis method

[0761] server

[0762] The collected motion data, image data, and voice data are analyzed using machine learning and generative AI models. Specifically, the system analyzes the user's behavioral patterns from the motion data, detects specific motions (e.g., falls) from the image data, and recognizes specific keywords (e.g., "help me") from the voice data.

[0763] Specific examples

[0764] The server analyzes a month's worth of sleep pattern data to detect sleep deprivation trends, and recognizes the word "help" from voice data to generate an emergency alert.

[0765] 4. Means of provision

[0766] server

[0767] Based on the analysis results, a personalized care plan is generated and provided to the user, which includes a daily schedule, health management advice, and specific care techniques.

[0768] Specific examples

[0769] The server generates a weekly exercise program for the user to exercise regularly and transmits it to the user via the terminal.

[0770] 5. Means of interaction

[0771] User

[0772] Users input information by speaking to the chatbot installed in the system, which uses generative AI models to generate responses and assess the user's health and psychological state.

[0773] Specific examples

[0774] A user can tell the chatbot, "I'm not feeling well today," and the chatbot will compare the user's past health data and provide advice on getting adequate rest.

[0775] 6. Emotion Engine

[0776] server

[0777] The system is equipped with an emotion engine that recognizes emotions based on the user's image and voice data. The emotion engine analyzes the user's facial expressions and tone of voice to identify their emotional state.

[0778] Specific examples

[0779] The server analyzes the user's facial expressions captured by the camera to recognize signs of smiles or sadness, and analyzes the tone of voice from audio data to determine stress or relaxation.

[0780] Operational Overview

[0781] Terminal

[0782] It collects motion data, image data, and audio data in real time, converts them into appropriate formats, and transmits them to a server.

[0783] server

[0784] The received data is analyzed to identify behavioral patterns, health conditions, and emotional states, and a personalized care plan is generated and communicated to the user via delivery methods.

[0785] User

[0786] Users enter information about their health and daily life through the chatbot, which then analyzes the information and provides appropriate responses.

[0787] Specific program operation example

[0788] Collecting operational data

[0789] Based on the data obtained from the bed sensor, the device records the user's bedtime and wake-up time and sends the data to the server.

[0790] Image and audio data collection

[0791] The device uses a camera and microphone to collect image and audio data of the user's daily activities (e.g., eating, watching TV) and transmits them to a server.

[0792] Data analysis

[0793] The server analyzes the received data and uses machine learning and generative AI models to identify the user's behavioral patterns and health status. The emotion engine recognizes the user's emotional state based on image and audio data.

[0794] Providing analysis results

[0795] Based on the analysis results, the server generates a personalized care plan (e.g., exercise program, dietary advice) and provides it to the user via the device. Based on the results of the emotion engine, emotional care is also included.

[0796] Chatbot conversation

[0797] Users talk to the chatbot and input information about their health and psychological state. The chatbot analyzes the information and provides appropriate responses and advice. For example, if a user inputs "I'm feeling unwell today," the chatbot will respond, "I recommend you reduce your recent activities and take some rest."

[0798] In this way, this system utilizes multifaceted data to understand the user's behavior, health, and emotional state in real time, and provides personalized care services, thereby significantly improving the user's quality of life.

[0799] The processing flow will be explained below.

[0800] Step 1:

[0801] The device activates the bed sensor and the movement sensor to collect user behavior data. The bed sensor records the user's bedtime and wake-up time, and the movement sensor tracks the user's movement patterns within the room.

[0802] Step 2:

[0803] The device uses a camera and microphone to collect image and audio data of the user's daily activities. The camera records video of the user cooking in the kitchen, and the microphone records audio.

[0804] Step 3:

[0805] The terminal divides the collected motion data, image data, and voice data into packets, converts them into an appropriate format, and transmits them to the server.

[0806] Step 4:

[0807] The server receives the data packets sent by the devices and reconstructs the data stream, making the collected data in a form that can be analyzed.

[0808] Step 5:

[0809] The server then uses machine learning and generative AI models to analyze the reconstructed data. Specifically, it analyzes the user's behavioral patterns from the motion data, detects specific actions (e.g., falls) from the image data, and recognizes specific keywords (e.g., "help me") from the voice data.

[0810] Step 6:

[0811] The server uses an emotion engine to analyze the user's emotions from image and audio data, specifically analyzing facial expressions and tone of voice to identify their emotional state.

[0812] Step 7:

[0813] Based on the analysis results, the server generates insights into the user's health, behavioral patterns, and emotional state. These insights are stored in a database and used for future data analysis and updating of care plans.

[0814] Step 8:

[0815] Based on the generated insights, the server creates a personalized care plan for the user, which includes daily schedules, health management advice, specific care techniques, emotional care, and more.

[0816] Step 9:

[0817] The server provides the created care plan to the user via the terminal, which displays or provides audio guidance of the contents of the care plan in a format that is easy for the user to understand.

[0818] Step 10:

[0819] The user speaks to the chatbot installed in the system, which uses a generative AI model and an emotion engine to analyze the user's voice and text and understand their intentions and emotions.

[0820] Step 11:

[0821] The chatbot generates and provides appropriate responses based on the user's past data and current health and emotional state. For example, if the user says, "I'm not feeling well today," the chatbot will respond, "I suggest you review your recent activities and take a short break. Is there anything you're worried about?"

[0822] Step 12:

[0823] The server analyzes the chatbot's dialogue and the results of the emotion engine analysis, updates the care plan as needed, and sends notifications to caregivers and family members if an emergency or abnormality is detected.

[0824] Step 13:

[0825] The server periodically retrains the generated AI and machine learning models with new data to improve the accuracy of the service, thereby continuously improving overall system performance and user satisfaction.

[0826] Example 2

[0827] 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."

[0828] The challenge is to improve the quality of care for the elderly and provide personalized care according to their individual needs, especially by recognizing their emotional state and emergency situations in real time and providing appropriate responses.

[0829] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a detection means for collecting motion data, an acquisition means for collecting image data and voice data of daily activities, an analysis means for analyzing the collected motion data, image data, and voice data to identify behavioral patterns and health conditions, a supply means for providing an individual care plan generated based on the analysis results, a dialogue means for dialogue with the user and collecting and analyzing information from the user, and an emotion recognition means for identifying an emotional state from facial expressions and voice. This makes it possible to grasp the motion and emotional state of the user in real time and to respond quickly to emergencies.

[0830] "Motion data" is data that collects information about the user's body movements and position.

[0831] "Sensing means" refers to a device or sensor system for collecting operational data.

[0832] "Image data of daily activities" is video data that captures the user's daily life.

[0833] "Voice data" refers to data that records the user's speech and surrounding sounds.

[0834] "Capture means" refers to a device or system for collecting image and audio data of daily activities.

[0835] "Analysis means" refers to devices or algorithms that analyze collected motion data, image data, and audio data to identify a user's behavioral patterns and health status.

[0836] "Supply means" refers to a system for providing users with individual care plans generated based on the analysis results.

[0837] "Interaction means" refers to means for interacting with users and collecting and analyzing information from users.

[0838] "Emotion recognition means" refers to systems or algorithms that identify a user's emotional state from facial expressions and voice.

[0839] A "machine learning model" is a statistical model that recognizes patterns based on collected data and makes predictions and classifications.

[0840] A "generative AI model" is an artificial intelligence model for performing natural language processing and generation tasks.

[0841] "Anomaly detection" refers to the process of detecting deviations from normal behavior or data patterns.

[0842] "Insight generation" is the process of deriving important findings and insights gained through data analysis.

[0843] This invention is a system for improving the quality of care for the elderly. It collects and analyzes user motion data, image data of daily activities, and voice data to provide personalized care services according to individual needs. In addition, by combining it with an emotion engine, it also supports emotional care.

[0844] System Configuration

[0845] Detection Method

[0846] To collect motion data, the device uses bed sensors and movement sensors. These sensors are typically home IoT devices (e.g., Withings Sleep) that record the user's bedtime, wake-up time, and movement patterns within the room.

[0847] Specific examples

[0848] The device records the user's sleep patterns each night through a sensor placed on the user's bed, and determines the user's activity level. For example, the device collects data that the user went to bed at 10 p.m. and woke up at 7 a.m.

[0849] Acquisition means

[0850] The device uses a camera and a microphone to collect image and audio data of daily activities. For example, a network camera (e.g., Nest Cam Indoor) and a microphone installed in the living room are used to record the user's daily activities.

[0851] Specific examples

[0852] The device uses a camera installed in the living room to record video of the user watching TV or eating, and a microphone to pick up conversations and voices, such as "I'm going to make curry today."

[0853] analytical means

[0854] The server analyzes the collected motion, image, and audio data, using Google Cloud's machine learning services and OpenAI's generative AI models (e.g., GPT-4) to analyze behavioral patterns and health conditions.

[0855] Specific examples

[0856] The server analyzes one month's worth of sleep pattern data to detect whether the user is experiencing sleep deprivation. The server also automatically detects the word "help" from the voice data and determines this as an abnormality.

[0857] supply means

[0858] Based on the analysis results, the server generates an individually customized care plan and provides it to the user via their device, including health management advice and a daily schedule.

[0859] Specific examples

[0860] The server generates a weekly exercise program to encourage regular exercise and notifies the user via the device. For example, it recommends "stretching for 10 minutes every morning."

[0861] Interaction methods

[0862] Users input information by speaking to the chatbot installed on their device, which uses OpenAI GPT-4 to generate appropriate responses and assess the user's health and psychological state.

[0863] Specific examples

[0864] If a user tells the chatbot, "I'm not feeling well today," the chatbot will respond, "I recommend you limit your recent activities and take some rest."

[0865] emotion recognition means

[0866] The server runs an emotion engine based on the user's image and voice data to recognize their emotional state, which includes common recognition algorithms for analyzing facial expressions and tone of voice.

[0867] Specific examples

[0868] The server analyzes the user's facial expressions captured by the camera to recognize signs of smiles or sadness, and also uses voice data to determine stress or relaxation levels based on the tone of the voice.

[0869] In this way, the system of the present invention utilizes multifaceted data to grasp the user's behavior, health condition, and emotional state in real time, and provides personalized care services, thereby significantly improving the quality of life of the elderly.

[0870] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0871] Step 1:

[0872] Collecting operational data

[0873] The device collects the user's movement data. Using the bed sensor and movement line sensor, the device records the user's bedtime, wake-up time, and movement patterns within the room. As input, the device receives real-time data from the bed sensor and movement line sensor, and as output, it sends the collected movement data to a cloud server. This data includes precise time information and the type of movement (e.g., going to sleep, waking up, moving).

[0874] Specific examples

[0875] The device collects data that the user went to bed at 10 p.m. and woke up at 7 a.m. This data is sent to a cloud server.

[0876] Step 2:

[0877] Image and audio data collection

[0878] The device uses a camera and a microphone to collect image and audio data of the user's daily activities. As input, it receives video data from the camera and audio data from the microphone, and as output, it transmits these data to a cloud server.

[0879] Specific examples

[0880] The device uses a camera installed in the living room to record video of users watching TV or eating, and a microphone to pick up conversations and voices, and sends the collected data to a cloud server.

[0881] Step 3:

[0882] Data Preprocessing

[0883] The server receives the data sent from the device and converts it into an analyzable format. It receives raw motion, image, and audio data as input, and produces pre-processed data as output, including noise filtering and cropping. This includes noise filtering for audio data and adjusting the resolution of video data.

[0884] Specific examples

[0885] The server removes noise from the image data and crops only the necessary parts, and filters background noise from the audio data and extracts the main dialogue.

[0886] Step 4:

[0887] Data analysis

[0888] The server performs analysis using the preprocessed data. It receives the preprocessed data as input and generates a report of movement patterns, health status, and emotional state as output. This analysis uses machine learning models from Google Cloud Machine Learning Engine and OpenAI GPT-4.

[0889] Specific examples

[0890] The server analyzes one month's worth of sleep pattern data to detect whether the user is experiencing sleep deprivation. It also detects the keyword "help" from the voice data and recognizes it as an abnormality.

[0891] Step 5:

[0892] Generate analysis results

[0893] The server then generates a report based on the user's behavioral patterns and health status based on the analysis results. It receives the analysis data as input and generates a detailed report and recommended actions as output, including an assessment of the user's emotional state.

[0894] Specific examples

[0895] The server creates a report recommending that the user "get some rest early" based on their recent lack of sleep.

[0896] Step 6:

[0897] Providing personalized care plans

[0898] Based on the report generated by the server, an individually customized care plan is designed and provided to the user via the terminal.The report is received as input, and a care plan tailored to the user is generated as output.

[0899] Specific examples

[0900] The server creates a weekly exercise program to encourage regular exercise and communicates it to the user via the device. For example, it recommends "stretching for 10 minutes every morning."

[0901] Step 7:

[0902] Interacting with a chatbot

[0903] Users input information into the system by speaking to a chatbot installed on their device. The system receives the user's speech data as input, and generates an appropriate response as output using a generative AI model (e.g., OpenAI GPT-4).

[0904] Specific examples

[0905] If a user tells the chatbot, "I'm not feeling well today," the chatbot will respond, "I recommend you limit your recent activities and take some rest."

[0906] Step 8:

[0907] Emotion Recognition in Action

[0908] The server performs emotion recognition based on the user's image and audio data. It receives preprocessed image and audio data as input and generates data identifying the user's emotional state as output.

[0909] Specific examples

[0910] The server analyzes the user's facial expressions captured by the camera to recognize signs of smiles or sadness, and analyzes the tone of voice from audio data to determine stress or relaxation.

[0911] Step 9:

[0912] Emergency alert generation

[0913] If the server detects an abnormality, it generates an emergency alert and takes appropriate action. It receives anomaly detection data as input and generates an emergency alert notification as output.

[0914] Specific examples

[0915] The server detects the voice data saying "help," generates an emergency alert, and notifies the designated contacts. For example, it performs a process such as "the emergency button was pressed, so contact the care staff."

[0916] In this way, through the input, data processing, and output of each processing step, the user's movements, health condition, and emotional state can be grasped in real time, and appropriate nursing care services can be provided.

[0917] (Application example 2)

[0918] 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."

[0919] Current elderly care systems simply collect and analyze users' motion data and image and audio data of their daily activities, and provide personalized care plans based on the results. However, it is difficult to grasp the users' emotional state and provide appropriate emotional care. Furthermore, especially in brick-and-mortar stores, there is a need for a system that recognizes users' real-time emotional state and provides emotional care based on that. To solve this problem, it is necessary to build a system that includes an emotion recognition method.

[0920] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a sensor means for collecting user motion data, a collection means for collecting image data and voice data of the user's daily activities, an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health condition, a provision means for providing the user with a personalized care plan generated based on the analysis results, a dialogue means for dialogue with the user and collecting and analyzing information from the user, and an emotion recognition means for recognizing the user's emotional state and providing emotional care based on the emotional state. This makes it possible to comprehensively understand the user's behavior, health condition, and emotional state and provide a personalized care plan.

[0921] "Sensor means" refers to a plurality of sensor devices used to collect user motion data.

[0922] The "collection means" refers to a camera and microphone installed to record image data and audio data relating to the user's daily activities.

[0923] The "analysis means" is a system that analyzes collected motion data, image data, and audio data using machine learning models and generative AI models to identify the user's behavioral patterns and health status.

[0924] The "provision means" is a means for notifying the user of a personalized care plan generated based on the analysis results.

[0925] The "interactive means" is a system for interacting with users and collecting and analyzing information from users.

[0926] The "emotion recognition means" is a mechanism for recognizing the user's emotional state based on image data and voice data and providing emotional care.

[0927] A "personalized care plan" is a care service plan that is customized according to the specific needs and conditions of the user.

[0928] "Motion data" refers to data relating to the user's body movements and position.

[0929] "Image data" refers to data that records images of the user's daily activities.

[0930] "Audio data" refers to data that records the user's everyday conversations and environmental sounds.

[0931] A "machine learning model" is a model based on algorithms used for pattern recognition and data analysis.

[0932] A "generative AI model" is an artificial intelligence model used for natural language processing and response generation.

[0933] A "physical store" is a place that provides care services for the elderly in a physical location.

[0934] A "chatbot" is a program that interacts with users through text and voice.

[0935] The system for implementing this invention collects and analyzes motion data, image data, and voice data of a user, and provides a personalized care plan that also includes emotional state. The specific configuration and operation of this system are described in detail below.

[0936] System configuration

[0937] Hardware

[0938] 1. Sensor means: Includes bed sensors and movement line sensors for collecting user movement data. These are often installed in physical stores to detect user presence information and behavioral patterns.

[0939] 2. Collection methods: These include cameras and microphones to record users' daily activities, and are expected to be installed especially in physical stores.

[0940] 3. Emotion recognition means: These include cameras and microphones to analyze the user's facial expressions and tone of voice. These are also typically installed in physical stores.

[0941] 4. User terminal: A device carried by the user, such as a smartphone or smart glasses, used to display the collected and analyzed results.

[0942] software

[0943] 1. Machine learning models: These include algorithm-based models that analyze motion and image data to identify user behavior patterns and health conditions.

[0944] 2. Generative AI models: These include artificial intelligence models used for natural language processing and response generation. They are used to generate responses for chatbots as a means of dialogue.

[0945] 3. Emotion Engine: Includes software for recognizing the user's emotional state from image and audio data.

[0946] 4. Cloud servers: Includes cloud computing platforms for data analysis and storage, such as AWS and GCP.

[0947] System Operation

[0948] Data collection

[0949] The terminal uses the sensor means, the collection means, and the emotion recognition means to collect the user's motion data, image data, and voice data in real time, and transmits this data to a cloud server via the Internet.

[0950] Data analysis

[0951] The server analyzes the received data, specifically using machine learning and generative AI models to analyze motion, image, and audio data to identify the user's behavioral patterns, health, and emotional state.

[0952] Providing results

[0953] Based on the analysis results, personalized care plans and activity suggestions are generated and notified to the user via their device. Emotional care is also provided based on the results of the emotion engine.

[0954] Interactive features

[0955] When users input information about their health and daily life through the chatbot, the generative AI model uses that information to generate an appropriate response. For example, if a user inputs "I'm not feeling well today," the model will respond with "I recommend you limit your recent activities and take some time to rest."

[0956] Specific examples

[0957] Example prompt:

[0958] 1. "I've been analyzing your sleep patterns lately and have found that you're waking up frequently during the night. Should I try making some changes to my exercise program?"

[0959] 2. "According to your facial expression analysis, you seem to be stressed. Try taking a deep breath."

[0960] The system provides a comprehensive understanding of the user's behavior, health and emotional state, enabling it to provide personalized care plans.

[0961] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0962] Step 1:

[0963] The device uses sensor means, collection means, and emotion recognition means to collect the user's behavioral data (e.g., bedtime, wake-up time, movement patterns), image data (e.g., footage of cooking), and audio data (e.g., conversation content) in real time. The input is data from numerous sensors and devices, and the output is data converted into a format for sending to a cloud server. In terms of specific operations, the bed sensor records the time the user goes to bed and wakes up, the movement line sensor traces movement patterns within the room, and the camera and microphone record daily activities.

[0964] Step 2:

[0965] The data collected by the device is sent to the cloud server via the Internet. The input is the data collected in step 1, and the output is the data stored on the cloud server. Specifically, the data is sent to the server using an appropriate protocol (e.g., HTTP, MQTT) and stored in a database.

[0966] Step 3:

[0967] The server uses machine learning models and generative AI models to analyze the motion data, image data, and voice data stored on the cloud server. The input is the data stored on the server, and the output is the analysis results that identify the user's behavioral patterns, health status, and emotional state. Specific actions include extracting behavioral patterns from motion data, detecting specific actions (e.g., falling) from image data, and recognizing specific keywords (e.g., "help me") from voice data.

[0968] Step 4:

[0969] The server creates a personalized care plan based on the analysis results and provides it to the user via the terminal. The input is the analysis results obtained in step 3, and the output is a personalized care plan. Specifically, it generates an exercise program and dietary advice based on the user's health condition and behavioral patterns, and notifies them via the user's terminal.

[0970] Step 5:

[0971] Users input information about their health and daily life through the chatbot, and the generative AI model generates an appropriate response based on that information. The input is the user's voice and text information, and the output is the generated response. For example, if a user says, "I'm not feeling well today," the chatbot will respond, "I recommend you reduce your recent activities and take some rest."

[0972] Step 6:

[0973] The server uses an emotion recognition engine to identify the emotional state from image and audio data and provide emotional care based on that. The input is image and audio data, and the output is the identified emotional state and care suggestions based on that. Specific operations include recognizing signs of smiles and sadness from facial expression analysis, and displaying advice on the user's device to relieve stress as needed.

[0974] 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.

[0975] 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.

[0976] 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.

[0977] [Third embodiment]

[0978] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0979] 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.

[0980] 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).

[0981] 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.

[0982] 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.

[0983] 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).

[0984] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0985] 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.

[0986] 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.

[0987] 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.

[0988] 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.

[0989] 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."

[0990] This invention is a system designed to improve the quality of care for the elderly, by collecting and analyzing a wide variety of data and providing personalized care services according to individual needs. Below, we will explain in detail how the program of this system is implemented.

[0991] System configuration

[0992] 1. Sensor means

[0993] Terminal

[0994] Various sensors, such as bed sensors and movement sensors, are used to collect user behavior data. For example, the bed sensors record the user's bedtime and wake-up time, and the movement sensors track the user's movement patterns within the room.

[0995] Specific examples

[0996] The device records the user's sleep patterns each night through sensors installed in the user's bed and understands the user's activity level.

[0997] 2. Collection Method

[0998] Terminal

[0999] Using a camera and microphone, it collects image and audio data of the user's daily activities, which can detect specific actions (e.g., falling) and specific keywords (e.g., "help me").

[1000] Specific examples

[1001] The device uses a camera installed in the living room to record video of the user watching TV or eating, and picks up conversations and audio through a microphone.

[1002] 3. Analysis method

[1003] server

[1004] Analyze collected motion, image, and audio data and use machine learning and generative AI models to identify user behavior patterns, health conditions, and abnormalities (e.g., falls).

[1005] Specific examples

[1006] The server analyzes a month's worth of sleep pattern data to detect sleep deprivation trends, and recognizes the word "help" from voice data to generate an emergency alert.

[1007] 4. Means of provision

[1008] server

[1009] Based on the analysis, users are provided with a personalized care plan that includes a daily schedule, health management advice, and specific care techniques.

[1010] Specific examples

[1011] The server generates a weekly exercise program for the user to exercise regularly and transmits the contents of the program to the user via the terminal.

[1012] 5. Means of interaction

[1013] User

[1014] Users input information by speaking to the chatbot, which uses generative AI models to generate responses and assess the user's health and psychological state.

[1015] Specific examples

[1016] A user can tell the chatbot, "I'm not feeling well today," and the chatbot will compare the user's past health data and provide advice on getting adequate rest.

[1017] Operational Overview

[1018] Terminal

[1019] It collects motion data, image data, and audio data in real time, converts them into appropriate formats, and transmits them to a server.

[1020] server

[1021] The received data is analyzed to identify behavioral patterns, health conditions, and abnormalities, and a personalized care plan is generated and notified to the user.

[1022] User

[1023] Users enter information about their health and daily life through the chatbot, which then analyzes the information and provides appropriate responses.

[1024] Specific program operation example

[1025] Collecting operational data

[1026] Based on the data obtained from the bed sensor, the device records the user's bedtime and wake-up time and sends the data to the server.

[1027] Image and audio data collection

[1028] The device uses a camera and microphone to collect image and audio data of the user's daily activities (e.g., eating, watching TV) and transmits them to a server.

[1029] Data analysis

[1030] The server analyzes the received data and uses machine learning and generative AI models to identify the user's behavioral patterns and health status, for example, detecting trends of sleep deprivation based on weekly sleep patterns.

[1031] Providing analysis results

[1032] Based on the analysis results, the server generates a personalized care plan (e.g., exercise program, dietary advice) and provides it to the user via the terminal.

[1033] Chatbot conversation

[1034] Users talk to the chatbot and input information about their health and psychological state. The chatbot analyzes the information and provides appropriate responses and advice. For example, if a user inputs "I'm feeling unwell today," the chatbot will respond, "I suggest you reflect on your recent activities and take a short break."

[1035] In this way, this system can significantly improve the quality of life of users by monitoring the daily lives of elderly people from various angles and providing personalized care services.

[1036] The processing flow will be explained below.

[1037] Step 1:

[1038] The device activates the bed sensor and movement line sensor to collect user behavior data. Each sensor detects the user's bedtime, wake-up time, and movement patterns within the room in real time and records them as data.

[1039] Step 2:

[1040] The device uses a camera and microphone to collect image and audio data about the user's daily activities. For example, the camera records video of the user cooking in the kitchen, and the microphone records the user's voice and conversations.

[1041] Step 3:

[1042] The device then packetizes the collected motion data, image data, and audio data and transmits them in the appropriate format to a server over a local network or the Internet.

[1043] Step 4:

[1044] The server receives the data packets sent by the devices and reconstructs the data stream, making all the collected data available for analysis.

[1045] Step 5:

[1046] The server then uses machine learning and generative AI models to analyze the reconstructed data. Specifically, it analyzes the user's behavioral patterns from the motion data, detects specific actions (e.g., falls) from the image data, and recognizes specific keywords (e.g., "help me") from the voice data.

[1047] Step 6:

[1048] The server generates insights into the user's health status and behavioral patterns based on the analysis results. These insights are stored in a database and used for future data analysis and updating of care plans.

[1049] Step 7:

[1050] Based on the generated insights, the server creates a personalized care plan that includes a daily schedule, health management advice, and specific care techniques.

[1051] Step 8:

[1052] The server provides the created care plan to the user via the terminal, which displays or provides audio guidance of the contents of the care plan in a format that is easy for the user to understand.

[1053] Step 9:

[1054] The user speaks to the chatbot installed in the system, which uses a generative AI model to analyze the user's voice and text and understand their intent.

[1055] Step 10:

[1056] The chatbot generates and provides appropriate responses based on the user's past data and current health status. For example, if the user says, "I'm not feeling well today," the chatbot will respond, "I recommend you limit your recent activities and get some rest."

[1057] Step 11:

[1058] The server analyzes the chatbot's dialogue and updates the care plan as needed. It also sends notifications to caregivers and family members if an emergency or abnormality is detected.

[1059] Step 12:

[1060] The server periodically retrains the generated AI and machine learning models with new data to improve the accuracy of the service, thereby continuously improving overall system performance and user satisfaction.

[1061] Example 1

[1062] 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."

[1063] Improving the quality of nursing care services for users, such as the elderly, is a socially important issue. In particular, collecting and analyzing diverse data is essential to provide personalized nursing care plans tailored to the needs of each user. However, conventional technologies have not fully established methods for integrating and analyzing motion data, image data, and voice data to identify users' behavioral patterns and health conditions. Furthermore, there is a lack of mechanisms for collecting information in real time through dialogue with users and providing appropriate care. Against this background, this invention aims to build a comprehensive system that enables the provision of more effective nursing care services.

[1064] 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.

[1065] In this invention, the server includes an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health condition, a provision means for providing the user with a personalized care plan created based on the analysis results, and a transmission means for converting the collected data into an appropriate format and transmitting it to the server. This makes it possible to comprehensively analyze a variety of data and provide appropriate care in real time.

[1066] The term "sensor means" refers to a device for collecting user movement data, and includes, for example, a bed sensor and a movement line sensor.

[1067] "Collection means" refers to a device for collecting image data and audio data of a user's daily activities, and includes, for example, a camera and a microphone.

[1068] "Analysis Means" means means, including machine learning models and generative AI models, for analyzing collected motion data, image data, and audio data to identify user behavior patterns and health conditions.

[1069] "Provision means" refers to a means for providing a personalized care plan generated based on the analysis results to a user.

[1070] "Interactive means" refers to means for interacting with users and collecting and analyzing information from users, including chatbots.

[1071] "Transmission means" refers to means for converting collected data into an appropriate format and transmitting it to the server.

[1072] This invention is a system designed to improve the quality of care for users such as the elderly. This system collects and analyzes a wide variety of data to provide personalized care services tailored to individual needs.

[1073] System configuration

[1074] Sensor Means

[1075] Terminal

[1076] The device is equipped with a bed sensor and a movement line sensor, which are used to collect user behavior data. Specifically, the bed sensor records the time of going to bed and waking up, and the movement line sensor tracks the movement patterns within the room.

[1077] Collection Method

[1078] Terminal

[1079] The device is equipped with a camera and microphone, which are used to collect image and audio data of the user's daily activities. The camera is installed in the living room and records the user's activities. The microphone picks up conversations and voices and detects specific abnormal sounds and words.

[1080] Analysis means

[1081] server

[1082] The server analyzes the collected motion data, image data, and voice data. It uses machine learning and generative AI models to identify the user's behavioral patterns, health status, and abnormalities. For example, the server analyzes a week's worth of sleep data to detect trends of sleep deprivation. It also recognizes the word "help" in voice data and generates an emergency alert.

[1083] Providing means

[1084] server

[1085] Based on the analysis results, the server generates a personalized care plan, which includes a daily schedule, health management advice, and specific care techniques. For example, the server uses the user's sleep analysis results to generate a weekly sleep improvement program with the goal of "ensuring at least seven hours of sleep per day," and notifies the user of the program via their device.

[1086] Interaction methods

[1087] User

[1088] Users input information by speaking to the chatbot, which then uses generative AI models to assess the user's health and psychological state. For example, if a user says to the chatbot, "I'm feeling unwell today," the chatbot will compare that with past health data and provide advice on getting adequate rest.

[1089] Operational Overview

[1090] Terminal

[1091] The terminal collects motion data, image data, and voice data in real time, converts them into appropriate formats, and transmits them to the server.

[1092] server

[1093] The server analyzes the received data to identify behavioral patterns, health conditions, and abnormalities, and generates a personalized care plan and notifies the user.

[1094] User

[1095] Users input information about their health and daily life through the chatbot, which then analyzes the information and provides appropriate responses.

[1096] Specific examples

[1097] Collecting operational data

[1098] Based on the data obtained from the bed sensor, the device records the user's bedtime and wake-up time and sends the data to the server.

[1099] Image and audio data collection

[1100] The device uses a camera and microphone to collect image and audio data of the user's daily activities and transmits them to a server.

[1101] Data analysis

[1102] The server analyzes the received data and uses machine learning and generative AI models to identify the user's behavioral patterns and health status, for example, detecting trends of sleep deprivation based on weekly sleep patterns.

[1103] Providing analysis results

[1104] Based on the analysis results, the server generates a personalized care plan (e.g., exercise program, dietary advice) and provides it to the user via the terminal.

[1105] Chatbot conversation

[1106] Users talk to the chatbot and input information about their health and psychological state. The chatbot analyzes the information and provides appropriate responses and advice. For example, if a user inputs "I'm feeling unwell today," the chatbot will respond, "I suggest you reflect on your recent activities and take a short break."

[1107] Example prompts for generative AI models

[1108] "Show how to analyze the user's health status using the behavioral data collected by the device."

[1109] "Explain the steps a chatbot can take to provide health advice based on user input."

[1110] In this way, this system can significantly improve the quality of life of users by monitoring the daily lives of elderly people from various angles and providing personalized care services.

[1111] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1112] Step 1: Collecting behavioral data

[1113] input

[1114] The device obtains real-time movement data from bed sensors and movement line sensors.

[1115] process

[1116] The device uses a bed sensor to record the user's bedtime and wake-up time, and a movement sensor to track the user's movement patterns within the room. The collected data is then converted into an appropriate format.

[1117] output

[1118] The converted motion data is generated and ready for transmission in the next step.

[1119] Specific operation example

[1120] The device records your sleep patterns each night and also tracks your movement patterns during the night, accumulating data.

[1121] Step 2: Collect image and audio data

[1122] input

[1123] Image and audio data acquired by the device from the camera and microphone.

[1124] process

[1125] The device uses image data to record the user's daily activities and audio data to capture conversations and sounds, then processes the data in real time to detect specific abnormal sounds or keywords.

[1126] output

[1127] The collected image and audio data is converted into an appropriate format and stored.

[1128] Specific operation example

[1129] The device uses a camera installed in the living room to record activity between 9am and 9pm, and a microphone to pick up conversations.

[1130] Step 3: Sending data

[1131] input

[1132] Motion data, image data, and voice data collected and converted by the device.

[1133] process

[1134] The device encrypts this data to ensure security and sends it to the server.

[1135] output

[1136] The encrypted data package is sent to the server.

[1137] Specific operation example

[1138] The device encrypts all data for the day at midnight and sends it to the server. Once the transmission is complete, the device waits for a confirmation response from the server.

[1139] Step 4: Analyze the data

[1140] input

[1141] The motion data, image data, and audio data received by the server.

[1142] process

[1143] The server analyzes this data using machine learning and generative AI models to identify user behavioral patterns and health conditions, and generates emergency alerts if anomalies are detected.

[1144] output

[1145] Analysis results and insights are generated and saved as the basis for generating care plans in the next step.

[1146] Specific operation example

[1147] The server analyzes a week's worth of sleep data to detect trends of sleep deprivation, and recognizes occurrences of the word "help" in the voice data, generating emergency alerts if necessary.

[1148] Step 5: Generate a care plan

[1149] input

[1150] The result data analyzed by the server.

[1151] process

[1152] The server generates a personalized care plan based on the analysis results, which includes a daily schedule, health management advice, and specific care techniques.

[1153] output

[1154] The generated care plan is sent to the terminal and notified to the user.

[1155] Specific operation example

[1156] Based on the results of the user's sleep analysis, the server generates a weekly sleep improvement program with the goal of ensuring "at least seven hours of sleep per day."

[1157] Step 6: Chatbot interaction

[1158] input

[1159] Information about health and daily life entered by users into the chatbot.

[1160] process

[1161] The chatbot uses generative AI models to analyze the input information and generate appropriate responses and advice.

[1162] output

[1163] Appropriate advice or responses are generated to be provided to the user.

[1164] Specific operation example

[1165] A user tells the chatbot, "I'm not feeling well today," and the chatbot compares this with past health data and offers advice such as, "I recommend you take a short break."

[1166] Through the above steps, this system can monitor the daily lives of elderly people from various angles and significantly improve the quality of life of users.

[1167] (Application example 1)

[1168] 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."

[1169] Conventional nursing care systems have struggled to comprehensively and in real time monitor the daily lives and health status of elderly people and provide personalized nursing care services tailored to their individual needs. Furthermore, in work environments such as factories, there was a lack of mechanisms to monitor the health status of employees and provide appropriate health management and work support. As a result, it was difficult to detect overwork and abnormal work patterns early on, increasing the risk of reduced labor productivity and safety.

[1170] 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.

[1171] In this invention, the server includes a sensor means for collecting user motion data, a collection means for collecting image data and voice data of the user's daily activities, an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health condition, a provision means for providing the user with a personalized care plan created based on the analysis results, a dialogue means for interacting with the user and collecting and analyzing information from the user, and a health monitoring means for detecting abnormalities and providing appropriate health management advice and work plans based on the analysis results using a machine learning model. This makes it possible to monitor the health condition of employees in real time and detect abnormalities early, thereby preventing overwork and improving work efficiency.

[1172] "Sensor means" refers to a set of devices for collecting user motion data.

[1173] The "collection means" is a device for collecting image data and audio data relating to the user's daily activities.

[1174] "Analysis means" means a computer-based system for analyzing collected motion data, image data, and audio data to identify user behavior patterns and health conditions.

[1175] The "provision means" is a mechanism for providing a personalized care plan generated based on the analysis results to the user.

[1176] An "interaction means" is an interface or system for collecting and analyzing information through interaction with a user.

[1177] The "health monitoring tool" is a system that detects abnormalities and provides appropriate health management advice and work plans based on the analysis results using machine learning models.

[1178] A "machine learning model" is a set of algorithms for analyzing large amounts of data and identifying patterns.

[1179] A "generative AI model" is a type of artificial intelligence algorithm that generates new data and answers based on specific tasks.

[1180] The system for implementing the present invention collects and analyzes motion data, image data, and voice data of a user, and provides a personalized care plan. This system is composed of the following means.

[1181] Sensor Means

[1182] The sensor means is a device for collecting user movement data. For example, a bed sensor or a movement line sensor is used to monitor the user's bedtime, wake-up time, and movement patterns within the room.

[1183] Collection Method

[1184] The collection means is a device that uses a camera and a microphone to collect image and audio data of the user's daily activities, allowing the user to record their meals, television viewing, conversations, and so on.

[1185] Analysis means

[1186] The analysis method is a system that analyzes the collected data using machine learning models and generative AI models on a server. This analysis identifies the user's behavioral patterns, health status, and abnormalities (e.g., falls). For example, it can detect trends of sleep deprivation from past data and generate emergency alerts.

[1187] Providing means

[1188] The provision method is a system that provides users with a personalized care plan created based on the analysis results, which includes a daily schedule, health management advice, exercise programs, etc.

[1189] Interaction methods

[1190] The dialogue means is an interface that interacts with the user and collects and analyzes information from the user. For example, a chatbot can be used to collect information such as "I'm feeling unwell today," and provide advice by comparing it with past data.

[1191] health monitoring measures

[1192] Health monitoring tools are systems that detect abnormalities and provide appropriate health management advice and work plans based on the results of analysis using machine learning models. For example, they can monitor the heart rates and movement patterns of employees working in a factory, and encourage them to take breaks if an abnormality is detected.

[1193] Hardware and software used

[1194] The system is implemented using the following hardware and software:

[1195] Sensor devices: bed sensors, movement sensors

[1196] Collection devices: camera, microphone

[1197] Analysis server: TensorFlow for machine learning, OpenCV for image processing

[1198] Devices provided: Smartphone, robot display

[1199] Conversational Interface: Chatbots

[1200] Specific examples

[1201] For example, if a user says "I'm feeling tired today" into their smartphone, the voice data is collected and compared with past health data by the server's generative AI model. As a result of the analysis, advice such as "I recommend you take a 15-minute break" is generated based on heart rate and movement patterns. This advice is then displayed on the smartphone screen.

[1202] Prompt Sentence Examples

[1203] "Please analyze my recent heart rate data and let me know what advice I need."

[1204] "What steps do you take when you detect abnormal employee behavior patterns?"

[1205] In this way, the system based on the present invention can comprehensively monitor the health status of elderly people and employees, detect abnormalities early, and provide care and health management that meets individual needs.

[1206] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1207] Step 1: Collecting Sensor Data

[1208] The server collects user behavior data through sensor means (bed sensors, movement line sensors). The input data obtained from the sensor means includes bedtime, wake-up time, and indoor movement patterns, and records these in real time. The output is a record of the user's activity.

[1209] Step 2: Collect image and audio data

[1210] The device uses collection means (camera, microphone) to collect image data and audio data related to the user's daily activities. The input includes the user's mealtimes and conversations, which are recorded as video clips and audio files. The output is the user's daily activity data.

[1211] Step 3: Sending data

[1212] The device sends the collected motion data, image data, and audio data to the server. The input is all sensor data and image / audio data stored in the device, which is converted into an appropriate format (e.g., JSON) and sent. The received data is saved on the server as output.

[1213] Step 4: Data analysis

[1214] The server analyzes the received data using a machine learning model (TensorFlow) and a generative AI model. The input data consists of motion data, image data, and audio data, which are analyzed to detect anomalies and identify behavioral patterns. Specifically, the server analyzes trends in sleep deprivation and the frequency of the keyword "help." The output generates analysis results related to the user's health condition and behavioral patterns.

[1215] Step 5: Generate analysis results

[1216] The server generates a personalized care plan based on the analysis results. The input is the analysis results obtained in the previous step, and based on this, it designs a daily schedule, health management advice, exercise programs, etc. The output is an individually tailored care plan.

[1217] Step 6: Notification by Delivery Method

[1218] The terminal notifies the user of the generated personalized care plan. The input data is the content of the care plan, which is displayed on the smartphone or robot's display. Specific actions include displaying a weekly exercise program and dietary advice. The output is a care plan in a format that the user can understand.

[1219] Step 7: Gather information through conversation

[1220] The user inputs information through an interactive means, which the device collects and analyzes. The input is voice input from the user (e.g., "I'm feeling unwell today"), which is analyzed to generate an appropriate response or advice. Using a generative AI model and comparing it with past data, appropriate advice such as advice on resting can be generated. Specific advice is provided to the user as an output.

[1221] Step 8: Health monitoring

[1222] The server detects anomalies and provides health management advice and work plans based on the analysis results using a machine learning model. Real-time sensor data and past analysis results are used as input, and based on this, it detects elevated heart rates and signs of overwork. Specifically, if the heart rate is abnormally high, the system outputs advice to "take a break," and the instruction is displayed on the device.

[1223] 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.

[1224] This invention is a system for improving the quality of care for the elderly. It collects and analyzes user motion data, image data of daily activities, and voice data to provide personalized care services tailored to individual needs. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it also supports emotional care. Below, we will explain in detail how the program of this system is implemented.

[1225] System configuration

[1226] 1. Sensor means

[1227] Terminal

[1228] To collect user behavior data, we use bed sensors and movement sensors. The bed sensors record the user's bedtime and wake-up time, and the movement sensors track the user's movement patterns within the room.

[1229] Specific examples

[1230] The device records the user's sleep patterns each night through sensors placed on the user's bed and understands the user's activity level.

[1231] 2. Collection Method

[1232] Terminal

[1233] Cameras and microphones are used to collect image and audio data of users' daily activities. For example, the camera records video of users cooking in the kitchen, and the microphone records their voices and conversations.

[1234] Specific examples

[1235] The device uses a camera installed in the living room to record video of the user watching TV or eating, and picks up conversations and audio through a microphone.

[1236] 3. Analysis method

[1237] server

[1238] The collected motion data, image data, and voice data are analyzed using machine learning and generative AI models. Specifically, the system analyzes the user's behavioral patterns from the motion data, detects specific motions (e.g., falls) from the image data, and recognizes specific keywords (e.g., "help me") from the voice data.

[1239] Specific examples

[1240] The server analyzes a month's worth of sleep pattern data to detect sleep deprivation trends, and recognizes the word "help" from voice data to generate an emergency alert.

[1241] 4. Means of provision

[1242] server

[1243] Based on the analysis results, a personalized care plan is generated and provided to the user, which includes a daily schedule, health management advice, and specific care techniques.

[1244] Specific examples

[1245] The server generates a weekly exercise program for the user to exercise regularly and transmits it to the user via the terminal.

[1246] 5. Means of interaction

[1247] User

[1248] Users input information by speaking to the chatbot installed in the system, which uses generative AI models to generate responses and assess the user's health and psychological state.

[1249] Specific examples

[1250] A user can tell the chatbot, "I'm not feeling well today," and the chatbot will compare the user's past health data and provide advice on getting adequate rest.

[1251] 6. Emotion Engine

[1252] server

[1253] The system is equipped with an emotion engine that recognizes emotions based on the user's image and voice data. The emotion engine analyzes the user's facial expressions and tone of voice to identify their emotional state.

[1254] Specific examples

[1255] The server analyzes the user's facial expressions captured by the camera to recognize signs of smiles or sadness, and analyzes the tone of voice from audio data to determine stress or relaxation.

[1256] Operational Overview

[1257] Terminal

[1258] It collects motion data, image data, and audio data in real time, converts them into appropriate formats, and transmits them to a server.

[1259] server

[1260] The received data is analyzed to identify behavioral patterns, health conditions, and emotional states, and a personalized care plan is generated and communicated to the user via delivery methods.

[1261] User

[1262] Users enter information about their health and daily life through the chatbot, which then analyzes the information and provides appropriate responses.

[1263] Specific program operation example

[1264] Collecting operational data

[1265] Based on the data obtained from the bed sensor, the device records the user's bedtime and wake-up time and sends the data to the server.

[1266] Image and audio data collection

[1267] The device uses a camera and microphone to collect image and audio data of the user's daily activities (e.g., eating, watching TV) and transmits them to a server.

[1268] Data analysis

[1269] The server analyzes the received data and uses machine learning and generative AI models to identify the user's behavioral patterns and health status. The emotion engine recognizes the user's emotional state based on image and audio data.

[1270] Providing analysis results

[1271] Based on the analysis results, the server generates a personalized care plan (e.g., exercise program, dietary advice) and provides it to the user via the device. Based on the results of the emotion engine, emotional care is also included.

[1272] Chatbot conversation

[1273] Users talk to the chatbot and input information about their health and psychological state. The chatbot analyzes the information and provides appropriate responses and advice. For example, if a user inputs "I'm feeling unwell today," the chatbot will respond, "I recommend you reduce your recent activities and take some rest."

[1274] In this way, this system utilizes multifaceted data to understand the user's behavior, health, and emotional state in real time, and provides personalized care services, thereby significantly improving the user's quality of life.

[1275] The processing flow will be explained below.

[1276] Step 1:

[1277] The device activates the bed sensor and the movement sensor to collect user behavior data. The bed sensor records the user's bedtime and wake-up time, and the movement sensor tracks the user's movement patterns within the room.

[1278] Step 2:

[1279] The device uses a camera and microphone to collect image and audio data of the user's daily activities. The camera records video of the user cooking in the kitchen, and the microphone records audio.

[1280] Step 3:

[1281] The terminal divides the collected motion data, image data, and voice data into packets, converts them into an appropriate format, and transmits them to the server.

[1282] Step 4:

[1283] The server receives the data packets sent by the devices and reconstructs the data stream, making the collected data in a form that can be analyzed.

[1284] Step 5:

[1285] The server then uses machine learning and generative AI models to analyze the reconstructed data. Specifically, it analyzes the user's behavioral patterns from the motion data, detects specific actions (e.g., falls) from the image data, and recognizes specific keywords (e.g., "help me") from the voice data.

[1286] Step 6:

[1287] The server uses an emotion engine to analyze the user's emotions from image and audio data, specifically analyzing facial expressions and tone of voice to identify their emotional state.

[1288] Step 7:

[1289] Based on the analysis results, the server generates insights into the user's health, behavioral patterns, and emotional state. These insights are stored in a database and used for future data analysis and updating of care plans.

[1290] Step 8:

[1291] Based on the generated insights, the server creates a personalized care plan for the user, which includes daily schedules, health management advice, specific care techniques, emotional care, and more.

[1292] Step 9:

[1293] The server provides the created care plan to the user via the terminal, which displays or provides audio guidance of the contents of the care plan in a format that is easy for the user to understand.

[1294] Step 10:

[1295] The user speaks to the chatbot installed in the system, which uses a generative AI model and an emotion engine to analyze the user's voice and text and understand their intentions and emotions.

[1296] Step 11:

[1297] The chatbot generates and provides appropriate responses based on the user's past data and current health and emotional state. For example, if the user says, "I'm not feeling well today," the chatbot will respond, "I suggest you review your recent activities and take a short break. Is there anything you're worried about?"

[1298] Step 12:

[1299] The server analyzes the chatbot's dialogue and the results of the emotion engine analysis, updates the care plan as needed, and sends notifications to caregivers and family members if an emergency or abnormality is detected.

[1300] Step 13:

[1301] The server periodically retrains the generated AI and machine learning models with new data to improve the accuracy of the service, thereby continuously improving overall system performance and user satisfaction.

[1302] Example 2

[1303] 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."

[1304] The challenge is to improve the quality of care for the elderly and provide personalized care according to their individual needs, especially by recognizing their emotional state and emergency situations in real time and providing appropriate responses.

[1305] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a detection means for collecting motion data, an acquisition means for collecting image data and voice data of daily activities, an analysis means for analyzing the collected motion data, image data, and voice data to identify behavioral patterns and health conditions, a supply means for providing an individual care plan generated based on the analysis results, a dialogue means for dialogue with the user and collecting and analyzing information from the user, and an emotion recognition means for identifying an emotional state from facial expressions and voice. This makes it possible to grasp the motion and emotional state of the user in real time and to respond quickly to emergencies.

[1306] "Motion data" is data that collects information about the user's body movements and position.

[1307] "Sensing means" refers to a device or sensor system for collecting operational data.

[1308] "Image data of daily activities" is video data that captures the user's daily life.

[1309] "Voice data" refers to data that records the user's speech and surrounding sounds.

[1310] "Capture means" refers to a device or system for collecting image and audio data of daily activities.

[1311] "Analysis means" refers to devices or algorithms that analyze collected motion data, image data, and audio data to identify a user's behavioral patterns and health status.

[1312] "Supply means" refers to a system for providing users with individual care plans generated based on the analysis results.

[1313] "Interaction means" refers to means for interacting with users and collecting and analyzing information from users.

[1314] "Emotion recognition means" refers to systems or algorithms that identify a user's emotional state from facial expressions and voice.

[1315] A "machine learning model" is a statistical model that recognizes patterns based on collected data and makes predictions and classifications.

[1316] A "generative AI model" is an artificial intelligence model for performing natural language processing and generation tasks.

[1317] "Anomaly detection" refers to the process of detecting deviations from normal behavior or data patterns.

[1318] "Insight generation" is the process of deriving important findings and insights gained through data analysis.

[1319] This invention is a system for improving the quality of care for the elderly. It collects and analyzes user motion data, image data of daily activities, and voice data to provide personalized care services according to individual needs. In addition, by combining it with an emotion engine, it also supports emotional care.

[1320] System Configuration

[1321] Detection Method

[1322] To collect motion data, the device uses bed sensors and movement sensors. These sensors are typically home IoT devices (e.g., Withings Sleep) that record the user's bedtime, wake-up time, and movement patterns within the room.

[1323] Specific examples

[1324] The device records the user's sleep patterns each night through a sensor placed on the user's bed, and determines the user's activity level. For example, the device collects data that the user went to bed at 10 p.m. and woke up at 7 a.m.

[1325] Acquisition means

[1326] The device uses a camera and a microphone to collect image and audio data of daily activities. For example, a network camera (e.g., Nest Cam Indoor) and a microphone installed in the living room are used to record the user's daily activities.

[1327] Specific examples

[1328] The device uses a camera installed in the living room to record video of the user watching TV or eating, and a microphone to pick up conversations and voices, such as "I'm going to make curry today."

[1329] analytical means

[1330] The server analyzes the collected motion, image, and audio data, using Google Cloud's machine learning services and OpenAI's generative AI models (e.g., GPT-4) to analyze behavioral patterns and health conditions.

[1331] Specific examples

[1332] The server analyzes one month's worth of sleep pattern data to detect whether the user is experiencing sleep deprivation. The server also automatically detects the word "help" from the voice data and determines this as an abnormality.

[1333] supply means

[1334] Based on the analysis results, the server generates an individually customized care plan and provides it to the user via their device, including health management advice and a daily schedule.

[1335] Specific examples

[1336] The server generates a weekly exercise program to encourage regular exercise and notifies the user via the device. For example, it recommends "stretching for 10 minutes every morning."

[1337] Interaction methods

[1338] Users input information by speaking to the chatbot installed on their device, which uses OpenAI GPT-4 to generate appropriate responses and assess the user's health and psychological state.

[1339] Specific examples

[1340] If a user tells the chatbot, "I'm not feeling well today," the chatbot will respond, "I recommend you limit your recent activities and take some rest."

[1341] emotion recognition means

[1342] The server runs an emotion engine based on the user's image and voice data to recognize their emotional state, which includes common recognition algorithms for analyzing facial expressions and tone of voice.

[1343] Specific examples

[1344] The server analyzes the user's facial expressions captured by the camera to recognize signs of smiles or sadness, and also uses voice data to determine stress or relaxation levels based on the tone of the voice.

[1345] In this way, the system of the present invention utilizes multifaceted data to grasp the user's behavior, health condition, and emotional state in real time, and provides personalized care services, thereby significantly improving the quality of life of the elderly.

[1346] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1347] Step 1:

[1348] Collecting operational data

[1349] The device collects the user's movement data. Using the bed sensor and movement line sensor, the device records the user's bedtime, wake-up time, and movement patterns within the room. As input, the device receives real-time data from the bed sensor and movement line sensor, and as output, it sends the collected movement data to a cloud server. This data includes precise time information and the type of movement (e.g., going to sleep, waking up, moving).

[1350] Specific examples

[1351] The device collects data that the user went to bed at 10 p.m. and woke up at 7 a.m. This data is sent to a cloud server.

[1352] Step 2:

[1353] Image and audio data collection

[1354] The device uses a camera and a microphone to collect image and audio data of the user's daily activities. As input, it receives video data from the camera and audio data from the microphone, and as output, it transmits these data to a cloud server.

[1355] Specific examples

[1356] The device uses a camera installed in the living room to record video of users watching TV or eating, and a microphone to pick up conversations and voices, and sends the collected data to a cloud server.

[1357] Step 3:

[1358] Data Preprocessing

[1359] The server receives the data sent from the device and converts it into an analyzable format. It receives raw motion, image, and audio data as input, and produces pre-processed data as output, including noise filtering and cropping. This includes noise filtering for audio data and adjusting the resolution of video data.

[1360] Specific examples

[1361] The server removes noise from the image data and crops only the necessary parts, and filters background noise from the audio data and extracts the main dialogue.

[1362] Step 4:

[1363] Data analysis

[1364] The server performs analysis using the preprocessed data. It receives the preprocessed data as input and generates a report of movement patterns, health status, and emotional state as output. This analysis uses machine learning models from Google Cloud Machine Learning Engine and OpenAI GPT-4.

[1365] Specific examples

[1366] The server analyzes one month's worth of sleep pattern data to detect whether the user is experiencing sleep deprivation. It also detects the keyword "help" from the voice data and recognizes it as an abnormality.

[1367] Step 5:

[1368] Generate analysis results

[1369] The server then generates a report based on the user's behavioral patterns and health status based on the analysis results. It receives the analysis data as input and generates a detailed report and recommended actions as output, including an assessment of the user's emotional state.

[1370] Specific examples

[1371] The server creates a report recommending that the user "get some rest early" based on their recent lack of sleep.

[1372] Step 6:

[1373] Providing personalized care plans

[1374] Based on the report generated by the server, an individually customized care plan is designed and provided to the user via the terminal.The report is received as input, and a care plan tailored to the user is generated as output.

[1375] Specific examples

[1376] The server creates a weekly exercise program to encourage regular exercise and communicates it to the user via the device. For example, it recommends "stretching for 10 minutes every morning."

[1377] Step 7:

[1378] Interacting with a chatbot

[1379] Users input information into the system by speaking to a chatbot installed on their device. The system receives the user's speech data as input, and generates an appropriate response as output using a generative AI model (e.g., OpenAI GPT-4).

[1380] Specific examples

[1381] If a user tells the chatbot, "I'm not feeling well today," the chatbot will respond, "I recommend you limit your recent activities and take some rest."

[1382] Step 8:

[1383] Emotion Recognition in Action

[1384] The server performs emotion recognition based on the user's image and audio data. It receives preprocessed image and audio data as input and generates data identifying the user's emotional state as output.

[1385] Specific examples

[1386] The server analyzes the user's facial expressions captured by the camera to recognize signs of smiles or sadness, and analyzes the tone of voice from audio data to determine stress or relaxation.

[1387] Step 9:

[1388] Emergency alert generation

[1389] If the server detects an abnormality, it generates an emergency alert and takes appropriate action. It receives anomaly detection data as input and generates an emergency alert notification as output.

[1390] Specific examples

[1391] The server detects the voice data saying "help," generates an emergency alert, and notifies the designated contacts. For example, it performs a process such as "the emergency button was pressed, so contact the care staff."

[1392] In this way, through the input, data processing, and output of each processing step, the user's movements, health condition, and emotional state can be grasped in real time, and appropriate nursing care services can be provided.

[1393] (Application example 2)

[1394] 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."

[1395] Current elderly care systems simply collect and analyze users' motion data and image and audio data of their daily activities, and provide personalized care plans based on the results. However, it is difficult to grasp the users' emotional state and provide appropriate emotional care. Furthermore, especially in brick-and-mortar stores, there is a need for a system that recognizes users' real-time emotional state and provides emotional care based on that. To solve this problem, it is necessary to build a system that includes an emotion recognition method.

[1396] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a sensor means for collecting user motion data, a collection means for collecting image data and voice data of the user's daily activities, an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health condition, a provision means for providing the user with a personalized care plan generated based on the analysis results, a dialogue means for dialogue with the user and collecting and analyzing information from the user, and an emotion recognition means for recognizing the user's emotional state and providing emotional care based on the emotional state. This makes it possible to comprehensively understand the user's behavior, health condition, and emotional state and provide a personalized care plan.

[1397] "Sensor means" refers to a plurality of sensor devices used to collect user motion data.

[1398] The "collection means" refers to a camera and microphone installed to record image data and audio data relating to the user's daily activities.

[1399] The "analysis means" is a system that analyzes collected motion data, image data, and audio data using machine learning models and generative AI models to identify the user's behavioral patterns and health status.

[1400] The "provision means" is a means for notifying the user of a personalized care plan generated based on the analysis results.

[1401] The "interactive means" is a system for interacting with users and collecting and analyzing information from users.

[1402] The "emotion recognition means" is a mechanism for recognizing the user's emotional state based on image data and voice data and providing emotional care.

[1403] A "personalized care plan" is a care service plan that is customized according to the specific needs and conditions of the user.

[1404] "Motion data" refers to data relating to the user's body movements and position.

[1405] "Image data" refers to data that records images of the user's daily activities.

[1406] "Audio data" refers to data that records the user's everyday conversations and environmental sounds.

[1407] A "machine learning model" is a model based on algorithms used for pattern recognition and data analysis.

[1408] A "generative AI model" is an artificial intelligence model used for natural language processing and response generation.

[1409] A "physical store" is a place that provides care services for the elderly in a physical location.

[1410] A "chatbot" is a program that interacts with users through text and voice.

[1411] The system for implementing this invention collects and analyzes motion data, image data, and voice data of a user, and provides a personalized care plan that also includes emotional state. The specific configuration and operation of this system are described in detail below.

[1412] System configuration

[1413] Hardware

[1414] 1. Sensor means: Includes bed sensors and movement line sensors for collecting user movement data. These are often installed in physical stores to detect user presence information and behavioral patterns.

[1415] 2. Collection methods: These include cameras and microphones to record users' daily activities, and are expected to be installed especially in physical stores.

[1416] 3. Emotion recognition means: These include cameras and microphones to analyze the user's facial expressions and tone of voice. These are also typically installed in physical stores.

[1417] 4. User terminal: A device carried by the user, such as a smartphone or smart glasses, used to display the collected and analyzed results.

[1418] software

[1419] 1. Machine learning models: These include algorithm-based models that analyze motion and image data to identify user behavior patterns and health conditions.

[1420] 2. Generative AI models: These include artificial intelligence models used for natural language processing and response generation. They are used to generate responses for chatbots as a means of dialogue.

[1421] 3. Emotion Engine: Includes software for recognizing the user's emotional state from image and audio data.

[1422] 4. Cloud servers: Includes cloud computing platforms for data analysis and storage, such as AWS and GCP.

[1423] System Operation

[1424] Data collection

[1425] The terminal uses the sensor means, the collection means, and the emotion recognition means to collect the user's motion data, image data, and voice data in real time, and transmits this data to a cloud server via the Internet.

[1426] Data analysis

[1427] The server analyzes the received data, specifically using machine learning and generative AI models to analyze motion, image, and audio data to identify the user's behavioral patterns, health, and emotional state.

[1428] Providing results

[1429] Based on the analysis results, personalized care plans and activity suggestions are generated and notified to the user via their device. Emotional care is also provided based on the results of the emotion engine.

[1430] Interactive features

[1431] When users input information about their health and daily life through the chatbot, the generative AI model uses that information to generate an appropriate response. For example, if a user inputs "I'm not feeling well today," the model will respond with "I recommend you limit your recent activities and take some time to rest."

[1432] Specific examples

[1433] Example prompt:

[1434] 1. "I've been analyzing your sleep patterns lately and have found that you're waking up frequently during the night. Should I try making some changes to my exercise program?"

[1435] 2. "According to your facial expression analysis, you seem to be stressed. Try taking a deep breath."

[1436] The system provides a comprehensive understanding of the user's behavior, health and emotional state, enabling it to provide personalized care plans.

[1437] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1438] Step 1:

[1439] The device uses sensor means, collection means, and emotion recognition means to collect the user's behavioral data (e.g., bedtime, wake-up time, movement patterns), image data (e.g., footage of cooking), and audio data (e.g., conversation content) in real time. The input is data from numerous sensors and devices, and the output is data converted into a format for sending to a cloud server. In terms of specific operations, the bed sensor records the time the user goes to bed and wakes up, the movement line sensor traces movement patterns within the room, and the camera and microphone record daily activities.

[1440] Step 2:

[1441] The data collected by the device is sent to the cloud server via the Internet. The input is the data collected in step 1, and the output is the data stored on the cloud server. Specifically, the data is sent to the server using an appropriate protocol (e.g., HTTP, MQTT) and stored in a database.

[1442] Step 3:

[1443] The server uses machine learning models and generative AI models to analyze the motion data, image data, and voice data stored on the cloud server. The input is the data stored on the server, and the output is the analysis results that identify the user's behavioral patterns, health status, and emotional state. Specific actions include extracting behavioral patterns from motion data, detecting specific actions (e.g., falling) from image data, and recognizing specific keywords (e.g., "help me") from voice data.

[1444] Step 4:

[1445] The server creates a personalized care plan based on the analysis results and provides it to the user via the terminal. The input is the analysis results obtained in step 3, and the output is a personalized care plan. Specifically, it generates an exercise program and dietary advice based on the user's health condition and behavioral patterns, and notifies them via the user's terminal.

[1446] Step 5:

[1447] Users input information about their health and daily life through the chatbot, and the generative AI model generates an appropriate response based on that information. The input is the user's voice and text information, and the output is the generated response. For example, if a user says, "I'm not feeling well today," the chatbot will respond, "I recommend you reduce your recent activities and take some rest."

[1448] Step 6:

[1449] The server uses an emotion recognition engine to identify the emotional state from image and audio data and provide emotional care based on that. The input is image and audio data, and the output is the identified emotional state and care suggestions based on that. Specific operations include recognizing signs of smiles and sadness from facial expression analysis, and displaying advice on the user's device to relieve stress as needed.

[1450] 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.

[1451] 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.

[1452] 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.

[1453] [Fourth embodiment]

[1454] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1455] 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.

[1456] 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).

[1457] 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.

[1458] 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.

[1459] 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).

[1460] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1461] 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.

[1462] 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.

[1463] 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.

[1464] 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.

[1465] 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.

[1466] 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."

[1467] This invention is a system designed to improve the quality of care for the elderly, by collecting and analyzing a wide variety of data and providing personalized care services according to individual needs. Below, we will explain in detail how the program of this system is implemented.

[1468] System configuration

[1469] 1. Sensor means

[1470] Terminal

[1471] Various sensors, such as bed sensors and movement sensors, are used to collect user behavior data. For example, the bed sensors record the user's bedtime and wake-up time, and the movement sensors track the user's movement patterns within the room.

[1472] Specific examples

[1473] The device records the user's sleep patterns each night through sensors installed in the user's bed and understands the user's activity level.

[1474] 2. Collection Method

[1475] Terminal

[1476] Using a camera and microphone, it collects image and audio data of the user's daily activities, which can detect specific actions (e.g., falling) and specific keywords (e.g., "help me").

[1477] Specific examples

[1478] The device uses a camera installed in the living room to record video of the user watching TV or eating, and picks up conversations and audio through a microphone.

[1479] 3. Analysis method

[1480] server

[1481] Analyze collected motion, image, and audio data and use machine learning and generative AI models to identify user behavior patterns, health conditions, and abnormalities (e.g., falls).

[1482] Specific examples

[1483] The server analyzes a month's worth of sleep pattern data to detect sleep deprivation trends, and recognizes the word "help" from voice data to generate an emergency alert.

[1484] 4. Means of provision

[1485] server

[1486] Based on the analysis, users are provided with a personalized care plan that includes a daily schedule, health management advice, and specific care techniques.

[1487] Specific examples

[1488] The server generates a weekly exercise program for the user to exercise regularly and transmits the contents of the program to the user via the terminal.

[1489] 5. Means of interaction

[1490] User

[1491] Users input information by speaking to the chatbot, which uses generative AI models to generate responses and assess the user's health and psychological state.

[1492] Specific examples

[1493] A user can tell the chatbot, "I'm not feeling well today," and the chatbot will compare the user's past health data and provide advice on getting adequate rest.

[1494] Operational Overview

[1495] Terminal

[1496] It collects motion data, image data, and audio data in real time, converts them into appropriate formats, and transmits them to a server.

[1497] server

[1498] The received data is analyzed to identify behavioral patterns, health conditions, and abnormalities, and a personalized care plan is generated and notified to the user.

[1499] User

[1500] Users enter information about their health and daily life through the chatbot, which then analyzes the information and provides appropriate responses.

[1501] Specific program operation example

[1502] Collecting operational data

[1503] Based on the data obtained from the bed sensor, the device records the user's bedtime and wake-up time and sends the data to the server.

[1504] Image and audio data collection

[1505] The device uses a camera and microphone to collect image and audio data of the user's daily activities (e.g., eating, watching TV) and transmits them to a server.

[1506] Data analysis

[1507] The server analyzes the received data and uses machine learning and generative AI models to identify the user's behavioral patterns and health status, for example, detecting trends of sleep deprivation based on weekly sleep patterns.

[1508] Providing analysis results

[1509] Based on the analysis results, the server generates a personalized care plan (e.g., exercise program, dietary advice) and provides it to the user via the terminal.

[1510] Chatbot conversation

[1511] Users talk to the chatbot and input information about their health and psychological state. The chatbot analyzes the information and provides appropriate responses and advice. For example, if a user inputs "I'm feeling unwell today," the chatbot will respond, "I suggest you reflect on your recent activities and take a short break."

[1512] In this way, this system can significantly improve the quality of life of users by monitoring the daily lives of elderly people from various angles and providing personalized care services.

[1513] The processing flow will be explained below.

[1514] Step 1:

[1515] The device activates the bed sensor and movement line sensor to collect user behavior data. Each sensor detects the user's bedtime, wake-up time, and movement patterns within the room in real time and records them as data.

[1516] Step 2:

[1517] The device uses a camera and microphone to collect image and audio data about the user's daily activities. For example, the camera records video of the user cooking in the kitchen, and the microphone records the user's voice and conversations.

[1518] Step 3:

[1519] The device then packetizes the collected motion data, image data, and audio data and transmits them in the appropriate format to a server over a local network or the Internet.

[1520] Step 4:

[1521] The server receives the data packets sent by the devices and reconstructs the data stream, making all the collected data available for analysis.

[1522] Step 5:

[1523] The server then uses machine learning and generative AI models to analyze the reconstructed data. Specifically, it analyzes the user's behavioral patterns from the motion data, detects specific actions (e.g., falls) from the image data, and recognizes specific keywords (e.g., "help me") from the voice data.

[1524] Step 6:

[1525] The server generates insights into the user's health status and behavioral patterns based on the analysis results. These insights are stored in a database and used for future data analysis and updating of care plans.

[1526] Step 7:

[1527] Based on the generated insights, the server creates a personalized care plan that includes a daily schedule, health management advice, and specific care techniques.

[1528] Step 8:

[1529] The server provides the created care plan to the user via the terminal, which displays or provides audio guidance of the contents of the care plan in a format that is easy for the user to understand.

[1530] Step 9:

[1531] The user speaks to the chatbot installed in the system, which uses a generative AI model to analyze the user's voice and text and understand their intent.

[1532] Step 10:

[1533] The chatbot generates and provides appropriate responses based on the user's past data and current health status. For example, if the user says, "I'm not feeling well today," the chatbot will respond, "I recommend you limit your recent activities and get some rest."

[1534] Step 11:

[1535] The server analyzes the chatbot's dialogue and updates the care plan as needed. It also sends notifications to caregivers and family members if an emergency or abnormality is detected.

[1536] Step 12:

[1537] The server periodically retrains the generated AI and machine learning models with new data to improve the accuracy of the service, thereby continuously improving overall system performance and user satisfaction.

[1538] Example 1

[1539] 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."

[1540] Improving the quality of nursing care services for users, such as the elderly, is a socially important issue. In particular, collecting and analyzing diverse data is essential to provide personalized nursing care plans tailored to the needs of each user. However, conventional technologies have not fully established methods for integrating and analyzing motion data, image data, and voice data to identify users' behavioral patterns and health conditions. Furthermore, there is a lack of mechanisms for collecting information in real time through dialogue with users and providing appropriate care. Against this background, this invention aims to build a comprehensive system that enables the provision of more effective nursing care services.

[1541] 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.

[1542] In this invention, the server includes an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health condition, a provision means for providing the user with a personalized care plan created based on the analysis results, and a transmission means for converting the collected data into an appropriate format and transmitting it to the server. This makes it possible to comprehensively analyze a variety of data and provide appropriate care in real time.

[1543] The term "sensor means" refers to a device for collecting user movement data, and includes, for example, a bed sensor and a movement line sensor.

[1544] "Collection means" refers to a device for collecting image data and audio data of a user's daily activities, and includes, for example, a camera and a microphone.

[1545] "Analysis Means" means means, including machine learning models and generative AI models, for analyzing collected motion data, image data, and audio data to identify user behavior patterns and health conditions.

[1546] "Provision means" refers to a means for providing a personalized care plan generated based on the analysis results to a user.

[1547] "Interactive means" refers to means for interacting with users and collecting and analyzing information from users, including chatbots.

[1548] "Transmission means" refers to means for converting collected data into an appropriate format and transmitting it to the server.

[1549] This invention is a system designed to improve the quality of care for users such as the elderly. This system collects and analyzes a wide variety of data to provide personalized care services tailored to individual needs.

[1550] System configuration

[1551] Sensor Means

[1552] Terminal

[1553] The device is equipped with a bed sensor and a movement line sensor, which are used to collect user behavior data. Specifically, the bed sensor records the time of going to bed and waking up, and the movement line sensor tracks the movement patterns within the room.

[1554] Collection Method

[1555] Terminal

[1556] The device is equipped with a camera and microphone, which are used to collect image and audio data of the user's daily activities. The camera is installed in the living room and records the user's activities. The microphone picks up conversations and voices and detects specific abnormal sounds and words.

[1557] Analysis means

[1558] server

[1559] The server analyzes the collected motion data, image data, and voice data. It uses machine learning and generative AI models to identify the user's behavioral patterns, health status, and abnormalities. For example, the server analyzes a week's worth of sleep data to detect trends of sleep deprivation. It also recognizes the word "help" in voice data and generates an emergency alert.

[1560] Providing means

[1561] server

[1562] Based on the analysis results, the server generates a personalized care plan, which includes a daily schedule, health management advice, and specific care techniques. For example, the server uses the user's sleep analysis results to generate a weekly sleep improvement program with the goal of "ensuring at least seven hours of sleep per day," and notifies the user of the program via their device.

[1563] Interaction methods

[1564] User

[1565] Users input information by speaking to the chatbot, which then uses generative AI models to assess the user's health and psychological state. For example, if a user says to the chatbot, "I'm feeling unwell today," the chatbot will compare that with past health data and provide advice on getting adequate rest.

[1566] Operational Overview

[1567] Terminal

[1568] The terminal collects motion data, image data, and voice data in real time, converts them into appropriate formats, and transmits them to the server.

[1569] server

[1570] The server analyzes the received data to identify behavioral patterns, health conditions, and abnormalities, and generates a personalized care plan and notifies the user.

[1571] User

[1572] Users input information about their health and daily life through the chatbot, which then analyzes the information and provides appropriate responses.

[1573] Specific examples

[1574] Collecting operational data

[1575] Based on the data obtained from the bed sensor, the device records the user's bedtime and wake-up time and sends the data to the server.

[1576] Image and audio data collection

[1577] The device uses a camera and microphone to collect image and audio data of the user's daily activities and transmits them to a server.

[1578] Data analysis

[1579] The server analyzes the received data and uses machine learning and generative AI models to identify the user's behavioral patterns and health status, for example, detecting trends of sleep deprivation based on weekly sleep patterns.

[1580] Providing analysis results

[1581] Based on the analysis results, the server generates a personalized care plan (e.g., exercise program, dietary advice) and provides it to the user via the terminal.

[1582] Chatbot conversation

[1583] Users talk to the chatbot and input information about their health and psychological state. The chatbot analyzes the information and provides appropriate responses and advice. For example, if a user inputs "I'm feeling unwell today," the chatbot will respond, "I suggest you reflect on your recent activities and take a short break."

[1584] Example prompts for generative AI models

[1585] "Show how to analyze the user's health status using the behavioral data collected by the device."

[1586] "Explain the steps a chatbot can take to provide health advice based on user input."

[1587] In this way, this system can significantly improve the quality of life of users by monitoring the daily lives of elderly people from various angles and providing personalized care services.

[1588] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1589] Step 1: Collecting behavioral data

[1590] input

[1591] The device obtains real-time movement data from bed sensors and movement line sensors.

[1592] process

[1593] The device uses a bed sensor to record the user's bedtime and wake-up time, and a movement sensor to track the user's movement patterns within the room. The collected data is then converted into an appropriate format.

[1594] output

[1595] The converted motion data is generated and ready for transmission in the next step.

[1596] Specific operation example

[1597] The device records your sleep patterns each night and also tracks your movement patterns during the night, accumulating data.

[1598] Step 2: Collect image and audio data

[1599] input

[1600] Image and audio data acquired by the device from the camera and microphone.

[1601] process

[1602] The device uses image data to record the user's daily activities and audio data to capture conversations and sounds, then processes the data in real time to detect specific abnormal sounds or keywords.

[1603] output

[1604] The collected image and audio data is converted into an appropriate format and stored.

[1605] Specific operation example

[1606] The device uses a camera installed in the living room to record activity between 9am and 9pm, and a microphone to pick up conversations.

[1607] Step 3: Sending data

[1608] input

[1609] Motion data, image data, and voice data collected and converted by the device.

[1610] process

[1611] The device encrypts this data to ensure security and sends it to the server.

[1612] output

[1613] The encrypted data package is sent to the server.

[1614] Specific operation example

[1615] The device encrypts all data for the day at midnight and sends it to the server. Once the transmission is complete, the device waits for a confirmation response from the server.

[1616] Step 4: Analyze the data

[1617] input

[1618] The motion data, image data, and audio data received by the server.

[1619] process

[1620] The server analyzes this data using machine learning and generative AI models to identify user behavioral patterns and health conditions, and generates emergency alerts if anomalies are detected.

[1621] output

[1622] Analysis results and insights are generated and saved as the basis for generating care plans in the next step.

[1623] Specific operation example

[1624] The server analyzes a week's worth of sleep data to detect trends of sleep deprivation, and recognizes occurrences of the word "help" in the voice data, generating emergency alerts if necessary.

[1625] Step 5: Generate a care plan

[1626] input

[1627] The result data analyzed by the server.

[1628] process

[1629] The server generates a personalized care plan based on the analysis results, which includes a daily schedule, health management advice, and specific care techniques.

[1630] output

[1631] The generated care plan is sent to the terminal and notified to the user.

[1632] Specific operation example

[1633] Based on the results of the user's sleep analysis, the server generates a weekly sleep improvement program with the goal of ensuring "at least seven hours of sleep per day."

[1634] Step 6: Chatbot interaction

[1635] input

[1636] Information about health and daily life entered by users into the chatbot.

[1637] process

[1638] The chatbot uses generative AI models to analyze the input information and generate appropriate responses and advice.

[1639] output

[1640] Appropriate advice or responses are generated to be provided to the user.

[1641] Specific operation example

[1642] A user tells the chatbot, "I'm not feeling well today," and the chatbot compares this with past health data and offers advice such as, "I recommend you take a short break."

[1643] Through the above steps, this system can monitor the daily lives of elderly people from various angles and significantly improve the quality of life of users.

[1644] (Application example 1)

[1645] 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."

[1646] Conventional nursing care systems have struggled to comprehensively and in real time monitor the daily lives and health status of elderly people and provide personalized nursing care services tailored to their individual needs. Furthermore, in work environments such as factories, there was a lack of mechanisms to monitor the health status of employees and provide appropriate health management and work support. As a result, it was difficult to detect overwork and abnormal work patterns early on, increasing the risk of reduced labor productivity and safety.

[1647] 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.

[1648] In this invention, the server includes a sensor means for collecting user motion data, a collection means for collecting image data and voice data of the user's daily activities, an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health condition, a provision means for providing the user with a personalized care plan created based on the analysis results, a dialogue means for interacting with the user and collecting and analyzing information from the user, and a health monitoring means for detecting abnormalities and providing appropriate health management advice and work plans based on the analysis results using a machine learning model. This makes it possible to monitor the health condition of employees in real time and detect abnormalities early, thereby preventing overwork and improving work efficiency.

[1649] "Sensor means" refers to a set of devices for collecting user motion data.

[1650] The "collection means" is a device for collecting image data and audio data relating to the user's daily activities.

[1651] "Analysis means" means a computer-based system for analyzing collected motion data, image data, and audio data to identify user behavior patterns and health conditions.

[1652] The "provision means" is a mechanism for providing a personalized care plan generated based on the analysis results to the user.

[1653] An "interaction means" is an interface or system for collecting and analyzing information through interaction with a user.

[1654] The "health monitoring tool" is a system that detects abnormalities and provides appropriate health management advice and work plans based on the analysis results using machine learning models.

[1655] A "machine learning model" is a set of algorithms for analyzing large amounts of data and identifying patterns.

[1656] A "generative AI model" is a type of artificial intelligence algorithm that generates new data and answers based on specific tasks.

[1657] The system for implementing the present invention collects and analyzes motion data, image data, and voice data of a user, and provides a personalized care plan. This system is composed of the following means.

[1658] Sensor Means

[1659] The sensor means is a device for collecting user movement data. For example, a bed sensor or a movement line sensor is used to monitor the user's bedtime, wake-up time, and movement patterns within the room.

[1660] Collection Method

[1661] The collection means is a device that uses a camera and a microphone to collect image and audio data of the user's daily activities, allowing the user to record their meals, television viewing, conversations, and so on.

[1662] Analysis means

[1663] The analysis method is a system that analyzes the collected data using machine learning models and generative AI models on a server. This analysis identifies the user's behavioral patterns, health status, and abnormalities (e.g., falls). For example, it can detect trends of sleep deprivation from past data and generate emergency alerts.

[1664] Providing means

[1665] The provision method is a system that provides users with a personalized care plan created based on the analysis results, which includes a daily schedule, health management advice, exercise programs, etc.

[1666] Interaction methods

[1667] The dialogue means is an interface that interacts with the user and collects and analyzes information from the user. For example, a chatbot can be used to collect information such as "I'm feeling unwell today," and provide advice by comparing it with past data.

[1668] health monitoring measures

[1669] Health monitoring tools are systems that detect abnormalities and provide appropriate health management advice and work plans based on the results of analysis using machine learning models. For example, they can monitor the heart rates and movement patterns of employees working in a factory, and encourage them to take breaks if an abnormality is detected.

[1670] Hardware and software used

[1671] The system is implemented using the following hardware and software:

[1672] Sensor devices: bed sensors, movement sensors

[1673] Collection devices: camera, microphone

[1674] Analysis server: TensorFlow for machine learning, OpenCV for image processing

[1675] Devices provided: Smartphone, robot display

[1676] Conversational Interface: Chatbots

[1677] Specific examples

[1678] For example, if a user says "I'm feeling tired today" into their smartphone, the voice data is collected and compared with past health data by the server's generative AI model. As a result of the analysis, advice such as "I recommend you take a 15-minute break" is generated based on heart rate and movement patterns. This advice is then displayed on the smartphone screen.

[1679] Prompt Sentence Examples

[1680] "Please analyze my recent heart rate data and let me know what advice I need."

[1681] "What steps do you take when you detect abnormal employee behavior patterns?"

[1682] In this way, the system based on the present invention can comprehensively monitor the health status of elderly people and employees, detect abnormalities early, and provide care and health management that meets individual needs.

[1683] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1684] Step 1: Collecting Sensor Data

[1685] The server collects user behavior data through sensor means (bed sensors, movement line sensors). The input data obtained from the sensor means includes bedtime, wake-up time, and indoor movement patterns, and records these in real time. The output is a record of the user's activity.

[1686] Step 2: Collect image and audio data

[1687] The device uses collection means (camera, microphone) to collect image data and audio data related to the user's daily activities. The input includes the user's mealtimes and conversations, which are recorded as video clips and audio files. The output is the user's daily activity data.

[1688] Step 3: Sending data

[1689] The device sends the collected motion data, image data, and audio data to the server. The input is all sensor data and image / audio data stored in the device, which is converted into an appropriate format (e.g., JSON) and sent. The received data is saved on the server as output.

[1690] Step 4: Data analysis

[1691] The server analyzes the received data using a machine learning model (TensorFlow) and a generative AI model. The input data consists of motion data, image data, and audio data, which are analyzed to detect anomalies and identify behavioral patterns. Specifically, the server analyzes trends in sleep deprivation and the frequency of the keyword "help." The output generates analysis results related to the user's health condition and behavioral patterns.

[1692] Step 5: Generate analysis results

[1693] The server generates a personalized care plan based on the analysis results. The input is the analysis results obtained in the previous step, and based on this, it designs a daily schedule, health management advice, exercise programs, etc. The output is an individually tailored care plan.

[1694] Step 6: Notification by Delivery Method

[1695] The terminal notifies the user of the generated personalized care plan. The input data is the content of the care plan, which is displayed on the smartphone or robot's display. Specific actions include displaying a weekly exercise program and dietary advice. The output is a care plan in a format that the user can understand.

[1696] Step 7: Gather information through conversation

[1697] The user inputs information through an interactive means, which the device collects and analyzes. The input is voice input from the user (e.g., "I'm feeling unwell today"), which is analyzed to generate an appropriate response or advice. Using a generative AI model and comparing it with past data, appropriate advice such as advice on resting can be generated. Specific advice is provided to the user as an output.

[1698] Step 8: Health monitoring

[1699] The server detects anomalies and provides health management advice and work plans based on the analysis results using a machine learning model. Real-time sensor data and past analysis results are used as input, and based on this, it detects elevated heart rates and signs of overwork. Specifically, if the heart rate is abnormally high, the system outputs advice to "take a break," and the instruction is displayed on the device.

[1700] 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.

[1701] This invention is a system for improving the quality of care for the elderly. It collects and analyzes user motion data, image data of daily activities, and voice data to provide personalized care services tailored to individual needs. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it also supports emotional care. Below, we will explain in detail how the program of this system is implemented.

[1702] System configuration

[1703] 1. Sensor means

[1704] Terminal

[1705] To collect user behavior data, we use bed sensors and movement sensors. The bed sensors record the user's bedtime and wake-up time, and the movement sensors track the user's movement patterns within the room.

[1706] Specific examples

[1707] The device records the user's sleep patterns each night through sensors placed on the user's bed and understands the user's activity level.

[1708] 2. Collection Method

[1709] Terminal

[1710] Cameras and microphones are used to collect image and audio data of users' daily activities. For example, the camera records video of users cooking in the kitchen, and the microphone records their voices and conversations.

[1711] Specific examples

[1712] The device uses a camera installed in the living room to record video of the user watching TV or eating, and picks up conversations and audio through a microphone.

[1713] 3. Analysis method

[1714] server

[1715] The collected motion data, image data, and voice data are analyzed using machine learning and generative AI models. Specifically, the system analyzes the user's behavioral patterns from the motion data, detects specific motions (e.g., falls) from the image data, and recognizes specific keywords (e.g., "help me") from the voice data.

[1716] Specific examples

[1717] The server analyzes a month's worth of sleep pattern data to detect sleep deprivation trends, and recognizes the word "help" from voice data to generate an emergency alert.

[1718] 4. Means of provision

[1719] server

[1720] Based on the analysis results, a personalized care plan is generated and provided to the user, which includes a daily schedule, health management advice, and specific care techniques.

[1721] Specific examples

[1722] The server generates a weekly exercise program for the user to exercise regularly and transmits it to the user via the terminal.

[1723] 5. Means of interaction

[1724] User

[1725] Users input information by speaking to the chatbot installed in the system, which uses generative AI models to generate responses and assess the user's health and psychological state.

[1726] Specific examples

[1727] A user can tell the chatbot, "I'm not feeling well today," and the chatbot will compare the user's past health data and provide advice on getting adequate rest.

[1728] 6. Emotion Engine

[1729] server

[1730] The system is equipped with an emotion engine that recognizes emotions based on the user's image and voice data. The emotion engine analyzes the user's facial expressions and tone of voice to identify their emotional state.

[1731] Specific examples

[1732] The server analyzes the user's facial expressions captured by the camera to recognize signs of smiles or sadness, and analyzes the tone of voice from audio data to determine stress or relaxation.

[1733] Operational Overview

[1734] Terminal

[1735] It collects motion data, image data, and audio data in real time, converts them into appropriate formats, and transmits them to a server.

[1736] server

[1737] The received data is analyzed to identify behavioral patterns, health conditions, and emotional states, and a personalized care plan is generated and communicated to the user via delivery methods.

[1738] User

[1739] Users enter information about their health and daily life through the chatbot, which then analyzes the information and provides appropriate responses.

[1740] Specific program operation example

[1741] Collecting operational data

[1742] Based on the data obtained from the bed sensor, the device records the user's bedtime and wake-up time and sends the data to the server.

[1743] Image and audio data collection

[1744] The device uses a camera and microphone to collect image and audio data of the user's daily activities (e.g., eating, watching TV) and transmits them to a server.

[1745] Data analysis

[1746] The server analyzes the received data and uses machine learning and generative AI models to identify the user's behavioral patterns and health status. The emotion engine recognizes the user's emotional state based on image and audio data.

[1747] Providing analysis results

[1748] Based on the analysis results, the server generates a personalized care plan (e.g., exercise program, dietary advice) and provides it to the user via the device. Based on the results of the emotion engine, emotional care is also included.

[1749] Chatbot conversation

[1750] Users talk to the chatbot and input information about their health and psychological state. The chatbot analyzes the information and provides appropriate responses and advice. For example, if a user inputs "I'm feeling unwell today," the chatbot will respond, "I recommend you reduce your recent activities and take some rest."

[1751] In this way, this system utilizes multifaceted data to understand the user's behavior, health, and emotional state in real time, and provides personalized care services, thereby significantly improving the user's quality of life.

[1752] The processing flow will be explained below.

[1753] Step 1:

[1754] The device activates the bed sensor and the movement sensor to collect user behavior data. The bed sensor records the user's bedtime and wake-up time, and the movement sensor tracks the user's movement patterns within the room.

[1755] Step 2:

[1756] The device uses a camera and microphone to collect image and audio data of the user's daily activities. The camera records video of the user cooking in the kitchen, and the microphone records audio.

[1757] Step 3:

[1758] The terminal divides the collected motion data, image data, and voice data into packets, converts them into an appropriate format, and transmits them to the server.

[1759] Step 4:

[1760] The server receives the data packets sent by the devices and reconstructs the data stream, making the collected data in a form that can be analyzed.

[1761] Step 5:

[1762] The server then uses machine learning and generative AI models to analyze the reconstructed data. Specifically, it analyzes the user's behavioral patterns from the motion data, detects specific actions (e.g., falls) from the image data, and recognizes specific keywords (e.g., "help me") from the voice data.

[1763] Step 6:

[1764] The server uses an emotion engine to analyze the user's emotions from image and audio data, specifically analyzing facial expressions and tone of voice to identify their emotional state.

[1765] Step 7:

[1766] Based on the analysis results, the server generates insights into the user's health, behavioral patterns, and emotional state. These insights are stored in a database and used for future data analysis and updating of care plans.

[1767] Step 8:

[1768] Based on the generated insights, the server creates a personalized care plan for the user, which includes daily schedules, health management advice, specific care techniques, emotional care, and more.

[1769] Step 9:

[1770] The server provides the created care plan to the user via the terminal, which displays or provides audio guidance of the contents of the care plan in a format that is easy for the user to understand.

[1771] Step 10:

[1772] The user speaks to the chatbot installed in the system, which uses a generative AI model and an emotion engine to analyze the user's voice and text and understand their intentions and emotions.

[1773] Step 11:

[1774] The chatbot generates and provides appropriate responses based on the user's past data and current health and emotional state. For example, if the user says, "I'm not feeling well today," the chatbot will respond, "I suggest you review your recent activities and take a short break. Is there anything you're worried about?"

[1775] Step 12:

[1776] The server analyzes the chatbot's dialogue and the results of the emotion engine analysis, updates the care plan as needed, and sends notifications to caregivers and family members if an emergency or abnormality is detected.

[1777] Step 13:

[1778] The server periodically retrains the generated AI and machine learning models with new data to improve the accuracy of the service, thereby continuously improving overall system performance and user satisfaction.

[1779] Example 2

[1780] 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."

[1781] The challenge is to improve the quality of care for the elderly and provide personalized care according to their individual needs, especially by recognizing their emotional state and emergency situations in real time and providing appropriate responses.

[1782] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a detection means for collecting motion data, an acquisition means for collecting image data and voice data of daily activities, an analysis means for analyzing the collected motion data, image data, and voice data to identify behavioral patterns and health conditions, a supply means for providing an individual care plan generated based on the analysis results, a dialogue means for dialogue with the user and collecting and analyzing information from the user, and an emotion recognition means for identifying an emotional state from facial expressions and voice. This makes it possible to grasp the motion and emotional state of the user in real time and to respond quickly to emergencies.

[1783] "Motion data" is data that collects information about the user's body movements and position.

[1784] "Sensing means" refers to a device or sensor system for collecting operational data.

[1785] "Image data of daily activities" is video data that captures the user's daily life.

[1786] "Voice data" refers to data that records the user's speech and surrounding sounds.

[1787] "Capture means" refers to a device or system for collecting image and audio data of daily activities.

[1788] "Analysis means" refers to devices or algorithms that analyze collected motion data, image data, and audio data to identify a user's behavioral patterns and health status.

[1789] "Supply means" refers to a system for providing users with individual care plans generated based on the analysis results.

[1790] "Interaction means" refers to means for interacting with users and collecting and analyzing information from users.

[1791] "Emotion recognition means" refers to systems or algorithms that identify a user's emotional state from facial expressions and voice.

[1792] A "machine learning model" is a statistical model that recognizes patterns based on collected data and makes predictions and classifications.

[1793] A "generative AI model" is an artificial intelligence model for performing natural language processing and generation tasks.

[1794] "Anomaly detection" refers to the process of detecting deviations from normal behavior or data patterns.

[1795] "Insight generation" is the process of deriving important findings and insights gained through data analysis.

[1796] This invention is a system for improving the quality of care for the elderly. It collects and analyzes user motion data, image data of daily activities, and voice data to provide personalized care services according to individual needs. In addition, by combining it with an emotion engine, it also supports emotional care.

[1797] System Configuration

[1798] Detection Method

[1799] To collect motion data, the device uses bed sensors and movement sensors. These sensors are typically home IoT devices (e.g., Withings Sleep) that record the user's bedtime, wake-up time, and movement patterns within the room.

[1800] Specific examples

[1801] The device records the user's sleep patterns each night through a sensor placed on the user's bed, and determines the user's activity level. For example, the device collects data that the user went to bed at 10 p.m. and woke up at 7 a.m.

[1802] Acquisition means

[1803] The device uses a camera and a microphone to collect image and audio data of daily activities. For example, a network camera (e.g., Nest Cam Indoor) and a microphone installed in the living room are used to record the user's daily activities.

[1804] Specific examples

[1805] The device uses a camera installed in the living room to record video of the user watching TV or eating, and a microphone to pick up conversations and voices, such as "I'm going to make curry today."

[1806] analytical means

[1807] The server analyzes the collected motion, image, and audio data, using Google Cloud's machine learning services and OpenAI's generative AI models (e.g., GPT-4) to analyze behavioral patterns and health conditions.

[1808] Specific examples

[1809] The server analyzes one month's worth of sleep pattern data to detect whether the user is experiencing sleep deprivation. The server also automatically detects the word "help" from the voice data and determines this as an abnormality.

[1810] supply means

[1811] Based on the analysis results, the server generates an individually customized care plan and provides it to the user via their device, including health management advice and a daily schedule.

[1812] Specific examples

[1813] The server generates a weekly exercise program to encourage regular exercise and notifies the user via the device. For example, it recommends "stretching for 10 minutes every morning."

[1814] Interaction methods

[1815] Users input information by speaking to the chatbot installed on their device, which uses OpenAI GPT-4 to generate appropriate responses and assess the user's health and psychological state.

[1816] Specific examples

[1817] If a user tells the chatbot, "I'm not feeling well today," the chatbot will respond, "I recommend you limit your recent activities and take some rest."

[1818] emotion recognition means

[1819] The server runs an emotion engine based on the user's image and voice data to recognize their emotional state, which includes common recognition algorithms for analyzing facial expressions and tone of voice.

[1820] Specific examples

[1821] The server analyzes the user's facial expressions captured by the camera to recognize signs of smiles or sadness, and also uses voice data to determine stress or relaxation levels based on the tone of the voice.

[1822] In this way, the system of the present invention utilizes multifaceted data to grasp the user's behavior, health condition, and emotional state in real time, and provides personalized care services, thereby significantly improving the quality of life of the elderly.

[1823] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1824] Step 1:

[1825] Collecting operational data

[1826] The device collects the user's movement data. Using the bed sensor and movement line sensor, the device records the user's bedtime, wake-up time, and movement patterns within the room. As input, the device receives real-time data from the bed sensor and movement line sensor, and as output, it sends the collected movement data to a cloud server. This data includes precise time information and the type of movement (e.g., going to sleep, waking up, moving).

[1827] Specific examples

[1828] The device collects data that the user went to bed at 10 p.m. and woke up at 7 a.m. This data is sent to a cloud server.

[1829] Step 2:

[1830] Image and audio data collection

[1831] The device uses a camera and a microphone to collect image and audio data of the user's daily activities. As input, it receives video data from the camera and audio data from the microphone, and as output, it transmits these data to a cloud server.

[1832] Specific examples

[1833] The device uses a camera installed in the living room to record video of users watching TV or eating, and a microphone to pick up conversations and voices, and sends the collected data to a cloud server.

[1834] Step 3:

[1835] Data Preprocessing

[1836] The server receives the data sent from the device and converts it into an analyzable format. It receives raw motion, image, and audio data as input, and produces pre-processed data as output, including noise filtering and cropping. This includes noise filtering for audio data and adjusting the resolution of video data.

[1837] Specific examples

[1838] The server removes noise from the image data and crops only the necessary parts, and filters background noise from the audio data and extracts the main dialogue.

[1839] Step 4:

[1840] Data analysis

[1841] The server performs analysis using the preprocessed data. It receives the preprocessed data as input and generates a report of movement patterns, health status, and emotional state as output. This analysis uses machine learning models from Google Cloud Machine Learning Engine and OpenAI GPT-4.

[1842] Specific examples

[1843] The server analyzes one month's worth of sleep pattern data to detect whether the user is experiencing sleep deprivation. It also detects the keyword "help" from the voice data and recognizes it as an abnormality.

[1844] Step 5:

[1845] Generate analysis results

[1846] The server then generates a report based on the user's behavioral patterns and health status based on the analysis results. It receives the analysis data as input and generates a detailed report and recommended actions as output, including an assessment of the user's emotional state.

[1847] Specific examples

[1848] The server creates a report recommending that the user "get some rest early" based on their recent lack of sleep.

[1849] Step 6:

[1850] Providing personalized care plans

[1851] Based on the report generated by the server, an individually customized care plan is designed and provided to the user via the terminal.The report is received as input, and a care plan tailored to the user is generated as output.

[1852] Specific examples

[1853] The server creates a weekly exercise program to encourage regular exercise and communicates it to the user via the device. For example, it recommends "stretching for 10 minutes every morning."

[1854] Step 7:

[1855] Interacting with a chatbot

[1856] Users input information into the system by speaking to a chatbot installed on their device. The system receives the user's speech data as input, and generates an appropriate response as output using a generative AI model (e.g., OpenAI GPT-4).

[1857] Specific examples

[1858] If a user tells the chatbot, "I'm not feeling well today," the chatbot will respond, "I recommend you limit your recent activities and take some rest."

[1859] Step 8:

[1860] Emotion Recognition in Action

[1861] The server performs emotion recognition based on the user's image and audio data. It receives preprocessed image and audio data as input and generates data identifying the user's emotional state as output.

[1862] Specific examples

[1863] The server analyzes the user's facial expressions captured by the camera to recognize signs of smiles or sadness, and analyzes the tone of voice from audio data to determine stress or relaxation.

[1864] Step 9:

[1865] Emergency alert generation

[1866] If the server detects an abnormality, it generates an emergency alert and takes appropriate action. It receives anomaly detection data as input and generates an emergency alert notification as output.

[1867] Specific examples

[1868] The server detects the voice data saying "help," generates an emergency alert, and notifies the designated contacts. For example, it performs a process such as "the emergency button was pressed, so contact the care staff."

[1869] In this way, through the input, data processing, and output of each processing step, the user's movements, health condition, and emotional state can be grasped in real time, and appropriate nursing care services can be provided.

[1870] (Application example 2)

[1871] 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."

[1872] Current elderly care systems simply collect and analyze users' motion data and image and audio data of their daily activities, and provide personalized care plans based on the results. However, it is difficult to grasp the users' emotional state and provide appropriate emotional care. Furthermore, especially in brick-and-mortar stores, there is a need for a system that recognizes users' real-time emotional state and provides emotional care based on that. To solve this problem, it is necessary to build a system that includes an emotion recognition method.

[1873] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a sensor means for collecting user motion data, a collection means for collecting image data and voice data of the user's daily activities, an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health condition, a provision means for providing the user with a personalized care plan generated based on the analysis results, a dialogue means for dialogue with the user and collecting and analyzing information from the user, and an emotion recognition means for recognizing the user's emotional state and providing emotional care based on the emotional state. This makes it possible to comprehensively understand the user's behavior, health condition, and emotional state and provide a personalized care plan.

[1874] "Sensor means" refers to a plurality of sensor devices used to collect user motion data.

[1875] The "collection means" refers to a camera and microphone installed to record image data and audio data relating to the user's daily activities.

[1876] The "analysis means" is a system that analyzes collected motion data, image data, and audio data using machine learning models and generative AI models to identify the user's behavioral patterns and health status.

[1877] The "provision means" is a means for notifying the user of a personalized care plan generated based on the analysis results.

[1878] The "interactive means" is a system for interacting with users and collecting and analyzing information from users.

[1879] The "emotion recognition means" is a mechanism for recognizing the user's emotional state based on image data and voice data and providing emotional care.

[1880] A "personalized care plan" is a care service plan that is customized according to the specific needs and conditions of the user.

[1881] "Motion data" refers to data relating to the user's body movements and position.

[1882] "Image data" refers to data that records images of the user's daily activities.

[1883] "Audio data" refers to data that records the user's everyday conversations and environmental sounds.

[1884] A "machine learning model" is a model based on algorithms used for pattern recognition and data analysis.

[1885] A "generative AI model" is an artificial intelligence model used for natural language processing and response generation.

[1886] A "physical store" is a place that provides care services for the elderly in a physical location.

[1887] A "chatbot" is a program that interacts with users through text and voice.

[1888] The system for implementing this invention collects and analyzes motion data, image data, and voice data of a user, and provides a personalized care plan that also includes emotional state. The specific configuration and operation of this system are described in detail below.

[1889] System configuration

[1890] Hardware

[1891] 1. Sensor means: Includes bed sensors and movement line sensors for collecting user movement data. These are often installed in physical stores to detect user presence information and behavioral patterns.

[1892] 2. Collection methods: These include cameras and microphones to record users' daily activities, and are expected to be installed especially in physical stores.

[1893] 3. Emotion recognition means: These include cameras and microphones to analyze the user's facial expressions and tone of voice. These are also typically installed in physical stores.

[1894] 4. User terminal: A device carried by the user, such as a smartphone or smart glasses, used to display the collected and analyzed results.

[1895] software

[1896] 1. Machine learning models: These include algorithm-based models that analyze motion and image data to identify user behavior patterns and health conditions.

[1897] 2. Generative AI models: These include artificial intelligence models used for natural language processing and response generation. They are used to generate responses for chatbots as a means of dialogue.

[1898] 3. Emotion Engine: Includes software for recognizing the user's emotional state from image and audio data.

[1899] 4. Cloud servers: Includes cloud computing platforms for data analysis and storage, such as AWS and GCP.

[1900] System Operation

[1901] Data collection

[1902] The terminal uses the sensor means, the collection means, and the emotion recognition means to collect the user's motion data, image data, and voice data in real time, and transmits this data to a cloud server via the Internet.

[1903] Data analysis

[1904] The server analyzes the received data, specifically using machine learning and generative AI models to analyze motion, image, and audio data to identify the user's behavioral patterns, health, and emotional state.

[1905] Providing results

[1906] Based on the analysis results, personalized care plans and activity suggestions are generated and notified to the user via their device. Emotional care is also provided based on the results of the emotion engine.

[1907] Interactive features

[1908] When users input information about their health and daily life through the chatbot, the generative AI model uses that information to generate an appropriate response. For example, if a user inputs "I'm not feeling well today," the model will respond with "I recommend you limit your recent activities and take some time to rest."

[1909] Specific examples

[1910] Example prompt:

[1911] 1. "I've been analyzing your sleep patterns lately and have found that you're waking up frequently during the night. Should I try making some changes to my exercise program?"

[1912] 2. "According to your facial expression analysis, you seem to be stressed. Try taking a deep breath."

[1913] The system provides a comprehensive understanding of the user's behavior, health and emotional state, enabling it to provide personalized care plans.

[1914] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1915] Step 1:

[1916] The device uses sensor means, collection means, and emotion recognition means to collect the user's behavioral data (e.g., bedtime, wake-up time, movement patterns), image data (e.g., footage of cooking), and audio data (e.g., conversation content) in real time. The input is data from numerous sensors and devices, and the output is data converted into a format for sending to a cloud server. In terms of specific operations, the bed sensor records the time the user goes to bed and wakes up, the movement line sensor traces movement patterns within the room, and the camera and microphone record daily activities.

[1917] Step 2:

[1918] The data collected by the device is sent to the cloud server via the Internet. The input is the data collected in step 1, and the output is the data stored on the cloud server. Specifically, the data is sent to the server using an appropriate protocol (e.g., HTTP, MQTT) and stored in a database.

[1919] Step 3:

[1920] The server uses machine learning models and generative AI models to analyze the motion data, image data, and voice data stored on the cloud server. The input is the data stored on the server, and the output is the analysis results that identify the user's behavioral patterns, health status, and emotional state. Specific actions include extracting behavioral patterns from motion data, detecting specific actions (e.g., falling) from image data, and recognizing specific keywords (e.g., "help me") from voice data.

[1921] Step 4:

[1922] The server creates a personalized care plan based on the analysis results and provides it to the user via the terminal. The input is the analysis results obtained in step 3, and the output is a personalized care plan. Specifically, it generates an exercise program and dietary advice based on the user's health condition and behavioral patterns, and notifies them via the user's terminal.

[1923] Step 5:

[1924] Users input information about their health and daily life through the chatbot, and the generative AI model generates an appropriate response based on that information. The input is the user's voice and text information, and the output is the generated response. For example, if a user says, "I'm not feeling well today," the chatbot will respond, "I recommend you reduce your recent activities and take some rest."

[1925] Step 6:

[1926] The server uses an emotion recognition engine to identify the emotional state from image and audio data and provide emotional care based on that. The input is image and audio data, and the output is the identified emotional state and care suggestions based on that. Specific operations include recognizing signs of smiles and sadness from facial expression analysis, and displaying advice on the user's device to relieve stress as needed.

[1927] 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.

[1928] 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.

[1929] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1930] 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.

[1931] 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.

[1932] 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.

[1933] 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).

[1934] 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.

[1935] 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."

[1936] 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.

[1937] 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).

[1938] 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.

[1939] 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.

[1940] 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.

[1941] 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.

[1942] 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.

[1943] 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.

[1944] 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.

[1945] 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.

[1946] 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.

[1947] 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.

[1948] The following is further disclosed regarding the above embodiment.

[1949] (Claim 1)

[1950] a sensor means for collecting user motion data;

[1951] A collection means for collecting image data and audio data of the user's daily activities;

[1952] an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health status;

[1953] a provision means for providing a personalized care plan generated based on the analysis results to the user;

[1954] An interaction means for interacting with a user and collecting and analyzing information from the user;

[1955] A system including:

[1956] (Claim 2)

[1957] 2. The system of claim 1, wherein the sensor means includes a bed sensor and a movement sensor, and the collecting means includes a camera and a microphone.

[1958] (Claim 3)

[1959] The system of claim 1, wherein the analysis means analyzes the motion data, image data, and audio data using a machine learning model and a generative AI model to detect anomalies and generate insights.

[1960] (Claim 4)

[1961] The system according to claim 1, wherein the dialogue means uses a generative AI model to engage in dialogue with the user, evaluate the user's health and psychological state, and provide a response.

[1962] "Example 1"

[1963] (Claim 1)

[1964] a sensor means for collecting user motion data;

[1965] A collection means for collecting image data and audio data of the user's daily activities;

[1966] an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health status;

[1967] a provision means for providing a user with a personalized care plan generated based on the analysis results;

[1968] An interaction means for interacting with a user and collecting and analyzing information from the user;

[1969] a transmitting means for converting the collected data into an appropriate format and transmitting the data to a server;

[1970] A system including:

[1971] (Claim 2)

[1972] 2. The system of claim 1, wherein the sensor means includes a bed sensor and a movement sensor, and the collecting means includes a camera and a microphone.

[1973] (Claim 3)

[1974] The system of claim 1, wherein the analysis means analyzes the motion data, image data, and audio data using a machine learning model and a generative AI model to detect anomalies and generate insights.

[1975] "Application Example 1"

[1976] (Claim 1)

[1977] a sensor means for collecting user motion data;

[1978] A collection means for collecting image data and audio data of the user's daily activities;

[1979] an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health status;

[1980] a provision means for providing a personalized care plan generated based on the analysis results to the user;

[1981] An interaction means for interacting with a user and collecting and analyzing information from the user;

[1982] A health monitoring method that detects abnormalities and provides appropriate health management advice and work plans based on the analysis results using a machine learning model;

[1983] A system including:

[1984] (Claim 2)

[1985] 2. The system of claim 1, wherein the sensor means includes a bed sensor and a movement sensor, and the collecting means includes a camera and a microphone.

[1986] (Claim 3)

[1987] The system of claim 1, wherein the analysis means analyzes the motion data, image data, and audio data using a machine learning model and a generative AI model to detect anomalies and generate insights.

[1988] "Example 2: Combining Emotion Engines"

[1989] (Claim 1)

[1990] detection means for collecting operational data;

[1991] an acquisition means for collecting image data and audio data of daily activities;

[1992] an analysis means for analyzing the collected motion data, image data, and voice data to identify behavioral patterns and health conditions;

[1993] a supply means for providing an individualized care plan generated based on the analysis results;

[1994] An interaction means for interacting with a user and collecting and analyzing information from the user;

[1995] an emotion recognition means for identifying an emotional state from facial expressions and voice;

[1996] A system including:

[1997] (Claim 2)

[1998] 2. The system of claim 1, wherein the detecting means includes a bed sensor and a movement sensor, and the acquiring means includes a camera and a microphone.

[1999] (Claim 3)

[2000] The system of claim 1, wherein the analysis means analyzes the motion data, image data, and audio data using machine learning models and generative AI models to perform anomaly detection and insight generation.

[2001] "Application example 2 when combining emotion engines"

[2002] (Claim 1)

[2003] a sensor means for collecting user motion data;

[2004] A collection means for collecting image data and audio data of the user's daily activities;

[2005] an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health status;

[2006] a provision means for providing a personalized care plan generated based on the analysis results to the user;

[2007] An interaction means for interacting with a user and collecting and analyzing information from the user;

[2008] an emotion recognition means for recognizing the user's emotional state and providing emotional care based thereon;

[2009] A system including:

[2010] (Claim 2)

[2011] 2. The system of claim 1, wherein the sensor means includes a bed sensor and a movement sensor, the collection means includes a camera and a microphone, and the emotion recognition means includes a camera and a microphone in a physical store.

[2012] (Claim 3)

[2013] The system of claim 1, wherein the analysis means analyzes the motion data, image data, and voice data using a machine learning model and a generative AI model to perform anomaly detection and insight generation, and further includes emotional states in the analysis results as prompt sentences. [Explanation of symbols]

[2014] 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 sensor means for collecting user motion data; A collection means for collecting image data and audio data of the user's daily activities; an analysis means for analyzing the collected motion data, image data, and voice data to identify the user's behavioral patterns and health status; a provision means for providing a personalized care plan generated based on the analysis results to the user; An interaction means for interacting with a user and collecting and analyzing information from the user; A system including:

2. 2. The system of claim 1, wherein the sensor means includes a bed sensor and a movement sensor, and the collecting means includes a camera and a microphone.

3. The system according to claim 1 , wherein the analysis means analyzes the motion data, image data, and audio data using a machine learning model and a generative AI model to detect anomalies and generate insights.

4. The system according to claim 1, wherein the dialogue means uses a generative AI model to engage in dialogue with the user, evaluate the user's health and psychological state, and provide a response.

Images