System

Abstract

A system is provided.SOLUTION: A system comprising: means for generating a personalized nursing care plan based on an analysis result; means for notifying a dedicated app of the generated nursing care plan; means for managing a progress of the nursing care plan through the dedicated app; and means for adjusting the nursing care plan based on feedback. A system comprising: means for generating a personalized nursing care plan based on an analysis result; means for executing a generative AI model; and means for executing a feedback model.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 aging society, the number of people requiring care is steadily increasing, and providing such care requires a great deal of effort and specialized knowledge. In particular, rapid response is required when changes in the health or living conditions of those requiring care occur. Conventional methods make it difficult for caregivers and family members to accurately grasp the condition of those requiring care and immediately provide optimal care plans, making it difficult to address individual needs. This reduces the quality of life of those requiring care and places a heavy burden on caregivers and family members. This invention aims to help those requiring care and their supporters build better lives by quickly responding to changes in their health and living conditions and providing individualized care plans. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. Specifically, the system includes a means for collecting data from a sensor worn by the care recipient, a means for executing a generative AI model that analyzes the collected data, a means for generating an individualized care plan based on the analysis results, a means for notifying a dedicated app of the generated care plan, a means for managing the progress of the care plan through the dedicated app, and a means for adjusting the care plan based on feedback. This makes it possible to monitor the health condition of the care recipient in real time and quickly provide an appropriate care plan to meet individual needs.

[0006] A "sensor" is a device that is worn on the body of a person requiring care and collects data on their health condition and daily activities.

[0007] A "generative AI model" is a machine learning algorithm that analyzes collected data and evaluates the health and living conditions of those in need of care.

[0008] A "nursing care plan" is a plan that includes specific medical care, rehabilitation, and methods of assistance with daily life that should be provided based on the health condition and lifestyle needs of the person requiring care.

[0009] A "dedicated app" is a mobile application or digital platform that allows caregivers and family members to check the progress of nursing care plans and provide feedback.

[0010] "Persons requiring care" refers to elderly or disabled people who require help from others in their daily lives.

[0011] "Data collection means" refers to the methods and technologies used to incorporate information obtained from sensors into the system.

[0012] "Analysis means" refers to the technology or method for processing collected data based on a generative AI model to assess the health status of the person requiring care.

[0013] "Notification means" refers to the technology or method for communicating the generated nursing care plan to caregivers and family members via a dedicated app.

[0014] The "management tool" is a function that tracks and records the progress of nursing care plans through a dedicated app.

[0015] "Feedback" is information and opinions provided by caregivers and family members that are used to improve and adjust nursing care plans. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The system of the present invention aims to monitor the health and living conditions of a person requiring care in real time and provide an individualized care plan. This system is composed of sensors, a generative AI model, and a dedicated application (hereinafter referred to as the dedicated app). Specific embodiments of the system of the present invention will be described in detail below.

[0038] 1. System Configuration

[0039] sensor

[0040] The server collects real-time health data (heart rate, blood pressure, body temperature, walking distance, sleep time, etc.) from sensors worn by the care recipient. These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data.

[0041] Generative AI Models

[0042] The server inputs the collected data into a generative AI model, which is based on machine learning algorithms that analyze the care recipient's health and lifestyle conditions to predict specific abnormalities and risks. Based on the analysis results, a care plan is created that addresses the care recipient's individual needs.

[0043] Dedicated app

[0044] Users (caregivers and family members) using devices (smartphones and tablets) can check the generated care plan through a dedicated app and manage progress in real time. The dedicated app includes a function to display details, priorities, and progress of the care plan.

[0045] 2. Program Processing

[0046] Data collection and preprocessing

[0047] The server receives the data collected from the sensors and filters it for outliers and missing values, and the collected data is stored in a database for subsequent analysis.

[0048] Data analysis

[0049] The server inputs the preprocessed data into a generative AI model to analyze the current health status of the care recipient, which then performs pattern recognition and anomaly detection to assess the care recipient's health risks.

[0050] Generate a care plan

[0051] Based on the analysis results of the AI ​​model, the server generates an optimal nursing care plan, which includes necessary medical care, activities of daily living assistance, and rehabilitation schedules.

[0052] Plan notification and management

[0053] The generated care plan is sent from the server to the device and displayed on a dedicated app, where the user can check the progress of the plan and record the action items that have been implemented.

[0054] Specific examples

[0055] For example, if data on heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) are obtained from sensors worn by care recipient A at 10:00 on October 10, the server collects this data and inputs it into the generative AI model. The AI ​​model detects that care recipient A's recent heart rate pattern is irregular and predicts that his stress level is increasing.

[0056] Based on the analysis results, the server generates a specific care plan, including a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplement intake. The plan is immediately sent to the device, and the user can check the plan through a dedicated app, perform deep breathing exercises at 11:00, and record this as "completed."

[0057] This enables the system to monitor the health status of those in need of care in real time, quickly provide appropriate care plans, and reduce the burden on caregivers and family members.

[0058] The processing flow will be explained below.

[0059] Step 1: Data collection

[0060] The server collects data in real time from sensors worn by the care recipient. Information such as heart rate, blood pressure, body temperature, walking distance, and sleep time is received via Bluetooth or Wi-Fi. The collected data is stored in a database with a timestamp. For example, the server might record "October 10th, 10:00: Heart rate 80 bpm, blood pressure 120 / 80 mmHg, body temperature 36.5°C."

[0061] Step 2: Data Preprocessing

[0062] The server converts the collected data into a format suitable for analysis. If there are incomplete data or outliers, filtering is performed. For example, data with abnormal heart rates (extremely high or low values) is removed. After filtering, the data is normalized and missing values ​​are imputed with the mean.

[0063] Step 3: Data analysis

[0064] The server inputs the preprocessed data into the generative AI model, which then uses machine learning algorithms to analyze the data and predict the care recipient's health status and trends. For example, the result might be, "Care recipient A's recent heart rate has been irregular, suggesting a high level of mental stress."

[0065] Step 4: Generate a care plan

[0066] The server generates an individualized care plan based on the analysis results. This plan includes necessary medical care, activities of daily living assistance, a rehabilitation schedule, and minor lifestyle changes. Specific recommendations include a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplementation.

[0067] Step 5: Plan Notification

[0068] The server sends the generated nursing care plan to a dedicated app. Each item in the plan is displayed in a timeline format and prioritized. Users (caregivers and family members) using devices (smartphones and tablets) are notified that the plan is available.

[0069] Step 6: Implement and manage the plan

[0070] The user on the device opens the dedicated app and checks the care plan. As each action item is implemented, progress is recorded within the app. For example, the user might enter "2023-10-10 11:00: 5 minutes of deep breathing exercises - completed." The server receives real-time feedback from the dedicated app and records it in a database.

[0071] Step 7: Feedback and plan adjustments

[0072] Users can send feedback through a dedicated app to report on the effectiveness of the care plan and areas for improvement. For example, they can provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the received feedback and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can check the latest instructions.

[0073] Example 1

[0074] 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."

[0075] Current nursing care systems make it difficult to monitor the health status of care recipients in real time and provide appropriate care plans immediately. Furthermore, if the collected data is analyzed without properly handling outliers or missing values, accurate analysis results cannot be obtained. Furthermore, if the generated nursing care plan is not optimized to the individual needs of the care recipient, the quality of care may decline and the burden on caregivers and families may increase.

[0076] 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.

[0077] In this invention, the server includes means for collecting data from sensors worn by the care recipient, means for filtering the collected data to remove outliers and missing values, means for inputting the preprocessed data into a generative AI model and analyzing health conditions and risks, means for generating an individual nursing care plan based on the analysis results, means for notifying a terminal of the generated nursing care plan, and means for managing the progress of the care plan through a dedicated app and adjusting the care plan based on feedback. This makes it possible to accurately monitor the health condition of the care recipient in real time, quickly provide an appropriate nursing care plan, and reduce the burden on caregivers and family members.

[0078] A "sensor" is a device that measures health data (heart rate, blood pressure, body temperature, walking distance, sleep time, etc.) of a person requiring care and transmits it to a server.

[0079] The "server" is a computing device that receives and stores data collected from sensors, preprocesses and analyzes the data, and generates and notifies nursing care plans.

[0080] "Filtering" is a process that removes outliers and missing values ​​from collected data to provide accurate data to generative AI models.

[0081] A "generative AI model" is a model that uses machine learning algorithms to analyze the health status and risks of individuals requiring care based on preprocessed health data and propose care plans.

[0082] A "nursing care plan" is a set of specific instructions based on the analysis results of the generated AI model, including the medical care, daily life support activities, and rehabilitation schedule that should be provided to the person in need of care.

[0083] The "terminal" is a device (smartphone or tablet) that notifies the caregiver of the created care plan and allows the caregiver or family member to check and manage the plan details through a dedicated app.

[0084] The "dedicated app" is software that allows caregivers and family members to check plan details, manage progress, and enter feedback.

[0085] "Real-time" refers to a situation in which data is collected and processed almost immediately, providing information in a timely manner.

[0086] "Feedback" refers to information provided by caregivers and family members through a dedicated app, and includes information on the implementation status and effectiveness of the generated nursing care plan.

[0087] The present invention relates to a system that monitors the health and living conditions of a person requiring care in real time and provides an individualized care plan. This system is configured using sensors, a generative AI model, and a dedicated application (hereinafter referred to as the dedicated app). Specific embodiments of the system of the present invention are described in detail below.

[0088] 1. System Configuration

[0089] sensor

[0090] The server collects real-time health data from sensors worn by the care recipient (e.g., heart rate monitors, blood pressure monitors, thermometers, pedometers, sleep trackers, etc.) These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data.

[0091] Generative AI Models

[0092] The server preprocesses the collected data and inputs it into a generative AI model (e.g., a TensorFlow-based model). The generative AI model is based on machine learning algorithms and analyzes the care recipient's health and living conditions to predict specific abnormalities and risks. Based on the analysis results, a care plan is created that addresses the care recipient's individual needs.

[0093] Dedicated app

[0094] Users (caregivers and family members) using devices (smartphones and tablets) can check the generated care plan through a dedicated app and manage progress in real time. The dedicated app includes a function to display details, priorities, and progress of the care plan.

[0095] 2. Program Processing

[0096] Data collection and preprocessing

[0097] The server receives the data collected from the sensors and filters it for outliers and missing values. The collected data is stored in a database (e.g., MySQL or PostgreSQL) for subsequent analysis.

[0098] Data analysis

[0099] The server inputs the preprocessed data into a generative AI model to analyze the current health status of the care recipient, which then performs pattern recognition and anomaly detection to assess the care recipient's health risks.

[0100] Generate a care plan

[0101] Based on the analysis results of the generative AI model, the server generates an optimal nursing care plan, which includes necessary medical care, daily living assistance activities, and rehabilitation schedules.

[0102] Plan notification and management

[0103] The generated care plan is sent from the server to the device and displayed on a dedicated app, where the user can check the progress of the plan and record the action items that have been implemented.

[0104] Specific examples

[0105] For example, if data on heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) are obtained from sensors worn by care recipient A at 10:00 on October 10, the server collects this data and inputs it into the generative AI model. The AI ​​model detects that care recipient A's recent heart rate pattern is irregular and predicts that his stress level is increasing.

[0106] Based on the analysis results, the server generates a specific care plan, including a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplement intake. The plan is immediately sent to the device, and the user can check the plan through a dedicated app, perform deep breathing exercises at 11:00, and record this as "completed."

[0107] An example of a prompt is, "Based on the data of heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) obtained at 10:00 on October 10th, analyze the recent heart rate pattern of care recipient A and generate a specific care plan."

[0108] This system can monitor the health status of those in need of care in real time, quickly provide appropriate care plans, and reduce the burden on caregivers and families.

[0109] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0110] Step 1: Collect sensor data

[0111] The server obtains real-time health data from sensors worn by the care recipient (e.g., heart rate monitor, blood pressure monitor, thermometer, pedometer, sleep tracker, etc.) Input data from the sensors (e.g., heart rate 80 bpm) is received via Bluetooth or Wi-Fi.

[0112] Specific operation: The server receives the heart rate data (80 bpm) of care recipient A at 10:00 on October 10th, and transmits it to the data collection module.

[0113] Step 2: Preprocessing the data

[0114] The server filters the received data to remove outliers and missing values. This filtering process validates the collected input data (e.g., heart rate 80 bpm) and removes outliers (e.g., 0 bpm and 300 bpm). The preprocessed data is stored in a database.

[0115] Specific operation: The server checks whether the received heart rate data is within the correct range and whether there is any abnormal data, and then stores it in the MySQL database.

[0116] Step 3: Data analysis

[0117] The server inputs the preprocessed data into a generative AI model, which uses machine learning algorithms to analyze the care recipient's health condition. Based on the input data (e.g., heart rate data of 80 bpm, data from the past week), the generative AI model performs pattern recognition and anomaly detection to assess the care recipient's health risk.

[0118] Specific operation: The server inputs heart rate data into a TensorFlow-based generative AI model, analyzes irregularities in care recipient A's heart rate pattern, and predicts that his or her stress level may be high.

[0119] Step 4: Generate a care plan

[0120] The server generates an individualized care plan based on the analysis results of the generative AI model. This care plan includes schedules for necessary medical care, activities of daily living assistance, and rehabilitation. The generated plan is then stored in a database.

[0121] Specific operation: The server determines that the stress level of care recipient A is high, generates a care plan including a 20-minute morning walk, 5 minutes of deep breathing exercises, and taking vitamin D supplements, and saves it in the database.

[0122] Step 5: Plan Notification and Management

[0123] The server then notifies the device of the generated care plan, which then displays the plan details through a dedicated app, allowing the user to manage progress in real time.

[0124] Specific operation: The server sends the generated care plan to a smartphone, where the plan details can be displayed in a dedicated app, allowing progress to be managed.

[0125] Step 6: Real-time monitoring

[0126] Users can check the health status of their care recipients in real time using a dedicated app, which displays collected data and progress of care plans in real time.

[0127] Specific operation: The user checks the current heart rate and progress of the care plan for care recipient A using a dedicated app, and for example, performs deep breathing exercises at 11:00 and records this as "completed."

[0128] (Application example 1)

[0129] 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."

[0130] In modern factories, it is extremely important to monitor the health status of workers in real time and make appropriate work adjustments and break suggestions, and a system for this purpose is needed. However, current systems have difficulty quickly generating and notifying appropriate health management suggestions for individual workers, making it difficult to minimize worker health risks.

[0131] 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.

[0132] In this invention, the server includes means for collecting data from sensors worn by workers, means for executing a generative AI model that analyzes the collected data, means for generating appropriate health management suggestions based on the analysis results, means for notifying a dedicated app of the generated health management suggestions, means for managing the progress of the health management suggestions through the dedicated app, and means for adjusting the health management suggestions based on feedback. This makes it possible to monitor the health status of workers in real time, quickly provide appropriate health management suggestions, and improve the safety of the working environment.

[0133] "Essential workers" refer to workers who are responsible for certain tasks at work sites such as factories.

[0134] A "sensor" refers to a device that can measure physiological data such as heart rate, blood pressure, body temperature, number of steps, and sleep time, and transmit it as a digital signal.

[0135] A "generative AI model" refers to a machine learning algorithm that analyzes collected data and performs health status and risk assessments.

[0136] "Health management suggestions" refer to recommendations such as breaks and work adjustments that are generated for workers based on the analysis results of the generative AI model.

[0137] A "dedicated app" refers to software that allows workers and managers to check health management proposals and manage progress.

[0138] "Data collection means" refers to a system component that has the function of collecting physiological data from sensors and transmitting it to a server.

[0139] "Analysis means" refers to a system component that has the ability to analyze collected data based on a generative AI model.

[0140] "Notification means" refers to a system component that has the function of sending the generated health management suggestions to a dedicated app.

[0141] "Progress management means" refers to a system component that has the function of grasping and managing the implementation status of health management proposals through a dedicated app.

[0142] "Feedback means" refers to a system component that has the ability to adjust health management suggestions based on information obtained from a dedicated app.

[0143] The present invention aims to monitor the health status and work status of key workers in real time and provide individualized health management suggestions. Specifically, the system is composed of sensors, a generative AI model, and a dedicated application (hereinafter referred to as the dedicated app). Specific embodiments of the system of the present invention are described in detail below.

[0144] 1. System Configuration

[0145] sensor

[0146] The server collects real-time health data (heart rate, blood pressure, body temperature, number of steps, sleep time, etc.) from sensors worn by key workers. These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data. The sensors can be general wearable devices or dedicated devices for measuring specific physiological indicators.

[0147] Generative AI Models

[0148] The server inputs the collected data into a generative AI model, which uses machine learning algorithms such as TensorFlow and Scikit-learn to perform health and risk assessments of critical workers. The model performs pattern recognition and anomaly detection to predict worker stress and fatigue levels.

[0149] Dedicated app

[0150] The server sends health management suggestions generated based on the analysis results of the generative AI model to devices (smartphones and tablets). Users (workers and managers) can check these health management suggestions through a dedicated app and manage their progress in real time. The dedicated app includes a function to display the details, priority, and progress of health management suggestions. Users can also provide feedback, and this information is used to adjust the health management suggestions.

[0151] 2. Program Processing

[0152] The server receives the data collected from the sensors and filters it for outliers and missing values. The collected data is stored in a database for subsequent analysis. The server then inputs the preprocessed data into a generative AI model to analyze the worker's current health status.

[0153] This generative AI model generates optimal health management suggestions based on the analysis results. These suggestions include necessary breaks, work adjustments, and rehabilitation schedules. The generated health management suggestions are sent from the server to the device and displayed in a dedicated app. The user can check the progress of the suggestions through the dedicated app and record the action items that have been implemented.

[0154] For example, if data on heart rate (90 bpm), blood pressure (130 / 85 mmHg), and body temperature (37.0°C) are obtained from a sensor worn by essential worker A at 10:00 on October 10th, the server collects this data and inputs it into the generative AI model. The AI ​​model predicts that essential worker A's stress level is rising and generates a specific health management suggestion that "he should take a break." This suggestion is immediately sent to the device, and the user can confirm and implement the suggestion through a dedicated app.

[0155] 3. Example prompts

[0156] "Analyze the collected worker health data (heart rate: 90 bpm, blood pressure: 130 / 85 mmHg, body temperature: 37.0°C) and use a generative AI model to assess the stress level. Based on the assessment results, generate suggestions for appropriate break timing and work adjustments."

[0157] In this way, the present invention makes it possible to monitor the health status of workers in real time, quickly provide appropriate health management suggestions, and improve the safety of the work environment.

[0158] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0159] Step 1:

[0160] The server collects biometric data (heart rate, blood pressure, body temperature, number of steps, sleep time, etc.) from sensors. The sensors send the data to the server via Bluetooth or Wi-Fi. This input data is saved on the server in CSV or JSON format.

[0161] Step 2:

[0162] The server filters the received biometric data, specifically checking for missing values ​​and removing outliers, to generate a preprocessed dataset. The input is the raw dataset, and the output is the filtered dataset.

[0163] Step 3:

[0164] The server inputs the preprocessed data into a generative AI model, which is built using TensorFlow and Scikit-learn and performs health status analysis and risk assessment based on the input data. The input is the filtered dataset, and the output is the analysis results.

[0165] Step 4:

[0166] The server generates health management suggestions based on the analysis results of the generative AI model. Health management suggestions include specific actions such as "take a break," "hydrate," and "perform specific stretches." The input is the analysis results, and the output is the health management suggestions.

[0167] Step 5:

[0168] The server sends the generated health management suggestions to a device. The device consists of a smartphone or tablet with a dedicated app installed. The input is the health management suggestions, and the output is a notification to the device.

[0169] Step 6:

[0170] Users (workers and managers) check the health management suggestions through a dedicated app. They then carry out the suggested actions and record their progress in the app. The input is the health management suggestions, and the output is a record of the progress.

[0171] Step 7:

[0172] Feedback is sent from the dedicated app to the server, which evaluates the effectiveness of health management suggestions based on the feedback information and adjusts the suggestions as necessary. The input is progress and feedback, and the output is adjusted health management suggestions.

[0173] 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.

[0174] The system of the present invention monitors the health and living conditions of the care recipient in real time, provides an individual care plan, and also realizes more detailed care by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the system of the present invention will be described in detail below.

[0175] 1. System Configuration

[0176] sensor

[0177] The server collects real-time health data (heart rate, blood pressure, body temperature, walking distance, sleep time, etc.) from sensors worn by the care recipient. These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data.

[0178] Generative AI Models

[0179] The server inputs the collected data into a generative AI model, which is based on machine learning algorithms and analyzes the care recipient's health and lifestyle to predict specific abnormalities and risks. Based on the analysis results, a care plan is created that addresses the care recipient's individual needs.

[0180] Emotion Engine

[0181] The device is equipped with an emotion engine that identifies the emotions of users (caregivers and family members) through voice analysis and facial expression recognition. This emotion engine extracts emotion data from the user's voice and camera footage and sends it to the server as feedback.

[0182] Dedicated app

[0183] Users using a device (smartphone or tablet) can check the generated care plan through a dedicated app and manage progress in real time. The dedicated app includes functions to display details, priorities, and progress of the care plan. It also displays emotional data obtained by an emotion engine.

[0184] 2. Program Processing

[0185] Data collection and preprocessing

[0186] The server receives the data collected from the sensors and filters it for outliers and missing values, and the collected data is stored in a database for subsequent analysis.

[0187] Data analysis

[0188] The server inputs the preprocessed data into a generative AI model to analyze the current health status of the care recipient, which then performs pattern recognition and anomaly detection to assess the care recipient's health risks.

[0189] Generate a care plan

[0190] Based on the analysis results of the AI ​​model, the server generates an optimal nursing care plan, which includes necessary medical care, activities of daily living assistance, and rehabilitation schedules.

[0191] Emotion data collection and analysis

[0192] The device extracts emotional data from the user's voice and facial expressions. For example, a speech recognition engine identifies emotions such as joy, sadness, and anger from the user's speaking style and tone. The recognized emotional data is sent to the server in real time.

[0193] Plan notification and management

[0194] The generated care plan is sent from the server to the device and displayed on a dedicated app. The user can check the progress of the plan through the dedicated app and record the action items that have been implemented. In addition, emotion data obtained from the emotion engine can also be viewed within the app.

[0195] Feedback and plan adjustments

[0196] Users can send feedback through a dedicated app to report on the effectiveness of the care plan and areas for improvement. For example, they can provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the received feedback and emotional data and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can check the latest instructions.

[0197] Specific examples

[0198] For example, if data on heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) are obtained from sensors worn by care recipient A at 10:00 on October 10, the server collects this data and inputs it into the generative AI model. The AI ​​model detects that care recipient A's recent heart rate pattern is irregular and predicts that his stress level is increasing.

[0199] Based on the analysis results, the server generates a specific care plan, such as a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplements. The plan is immediately sent to the device, and the user can view it through a dedicated app.

[0200] In addition, the emotion engine identifies emotions from the user's tone of voice and camera footage, and if, for example, stress or anxiety is elevated, that information is displayed within the dedicated app. Users can check their emotional state in the dedicated app and request that parts of their care plan be readjusted if necessary.

[0201] This enables the system to monitor the health status of the care recipient and the emotional state of the caregiver or family member in real time, and provide appropriate care individually and quickly, thereby improving the quality of life of the care recipient and their caregiver.

[0202] The processing flow will be explained below.

[0203] Step 1: Data collection

[0204] The server collects real-time health data (heart rate, blood pressure, body temperature, walking distance, and sleep time) from sensors worn by the care recipient. These sensors communicate with the server via Bluetooth or Wi-Fi and periodically send data. For example, data is recorded in the format "October 10th, 10:00: Heart rate 80 bpm, blood pressure 120 / 80 mmHg, body temperature 36.5°C."

[0205] Step 2: Data Preprocessing

[0206] The server filters the collected data to identify outliers and missing values, removes incomplete data if present, imputes missing values ​​with the mean, and normalizes the data and converts it into a format suitable for analysis.

[0207] Step 3: Data analysis

[0208] The server inputs the preprocessed data into a generative AI model, which then uses machine learning algorithms to analyze the data and perform a health status and risk assessment of the care recipient. For example, the model might generate an analysis result such as, "Recent heart rate patterns have been irregular, and stress levels are high."

[0209] Step 4: Generate a care plan

[0210] The server generates an individualized care plan based on the analysis results of the AI ​​model. Specific plans include "a 20-minute morning walk," "5 minutes of deep breathing exercises," and "taking vitamin D supplements." The generated care plan is saved in a database and used in subsequent steps.

[0211] Step 5: Collecting sentiment data

[0212] The device analyzes the voice and facial expressions of the user (caregiver or family member) to collect emotional data. The emotion engine reads the tone of the voice, speaking style, and facial expressions from camera footage to identify the emotional state in real time. For example, the result may be, "The user's voice has a depressed tone, and anxiety is increasing."

[0213] Step 6: Notification of Emotion Data

[0214] The server stores the collected emotion data in a database in real time and sends it along with the analysis results to a dedicated app. The device displays the emotion data within the app, allowing the user to check the situation.

[0215] Step 7: Plan Notification and Management

[0216] The server sends the generated care plan to a dedicated app. The device displays each item in the plan in a timeline format and notifies the user. The user can check the progress of the plan through the dedicated app and record the action items that have been completed. For example, the user could enter "2023-10-10 11:00: 5 minutes of deep breathing exercises - completed."

[0217] Step 8: Feedback and Adjustments

[0218] Users send feedback through a dedicated app, reporting the effectiveness of the care plan and areas for improvement. For example, they may provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the feedback and emotional data and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can view the latest care plan.

[0219] This processing flow enables the system to monitor the health status of the care recipient and the emotional state of the caregiver and family in real time, and provide appropriate care plans individually and quickly, thereby improving the quality of life of the care recipient and their caregiver.

[0220] Example 2

[0221] 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."

[0222] In modern society, monitoring the health status of those requiring care in real time and providing appropriate care according to their circumstances is a crucial issue. However, conventional systems only collect and analyze the health data of those requiring care, and are unable to provide care plans that take into account the emotional state of the caregiver or family. This makes it difficult to provide attentive care, and improving the satisfaction of both the care recipient and the caregiver is a challenge.

[0223] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0224] In this invention, the server includes means for collecting data from a sensor worn by the care recipient, means for executing a generative AI model that analyzes the collected data, means for generating an individual nursing care plan based on the analysis results, means for notifying a dedicated app of the generated nursing care plan, means for managing the progress of the nursing care plan through the dedicated app, means for adjusting the nursing care plan based on feedback, a terminal equipped with an emotion engine that collects and analyzes user emotion data, and means for analyzing the emotion data and feeding it back to the dedicated app. This enables the provision of detailed and prompt care that takes into account both the health state of the care recipient and the emotional states of the caregiver and family.

[0225] "Individuals requiring care" refers to elderly people or individuals with illnesses or disabilities who require assistance with daily living or medical care.

[0226] "Sensors" refer to devices used to measure and collect data on the health status of care recipients, including devices that measure heart rate, blood pressure, body temperature, walking distance, sleep time, etc. in real time.

[0227] "Server" refers to a computer system that receives data collected from sensors and processes and analyzes it.

[0228] A "generative AI model" refers to a machine learning model that analyzes the health condition of a person requiring care based on collected data and generates an appropriate nursing care plan.

[0229] A "nursing care plan" refers to a specific action plan that includes medical care, assistance with daily life, rehabilitation schedules, etc., according to the health condition of the person requiring care.

[0230] "Dedicated app" refers to a software application that displays the generated nursing care plan and allows the user to manage its progress.

[0231] An "emotion engine" is a technology that collects and analyzes emotional data from the user's voice and facial expressions, and sends it to a server as feedback.

[0232] "User" refers to an individual, including a caregiver or family member providing nursing care.

[0233] "Feedback" refers to information provided by the user, including data on the effectiveness of the care plan and areas for improvement.

[0234] The present invention is a system for monitoring the health and living conditions of a person requiring care in real time and providing an individualized care plan. Specific embodiments of this system will be described in detail below.

[0235] System Configuration

[0236] The system consists of a sensor worn by the care recipient, a server that analyzes the data, a device that collects emotional data, and a dedicated app that manages the generated care plan.

[0237] sensor

[0238] The server collects real-time data from sensors worn by the care recipient. The sensors then transmit the data to the server via Bluetooth or Wi-Fi. The collected data includes multiple health indicators such as heart rate, blood pressure, body temperature, walking distance, and sleep time.

[0239] Data analysis

[0240] The server receives the collected health data and runs a generative AI model to analyze it. The generative AI model is based on machine learning algorithms to assess the care recipient's health status and risks. For example, it analyzes irregular heart rate patterns and blood pressure fluctuations to predict the care recipient's health risks. Based on the analysis results, an individualized care plan is generated.

[0241] Care plan generation and notification

[0242] Based on the analysis results of the AI ​​model, the server generates a specific action plan, such as "a 20-minute morning walk," "five minutes of deep breathing exercises," or "taking vitamin D supplements." The generated care plan is then sent to a dedicated app.

[0243] Collecting Emotional Data

[0244] The device collects emotional data from the user's voice and facial expressions. It uses a voice analysis engine and a camera to identify emotions such as joy, sadness, and anger from the user's speaking style, tone, and facial expressions. This emotional data is sent to a server in real time.

[0245] Dedicated app functions

[0246] Users using a device (smartphone or tablet) can check the generated care plan through a dedicated app and manage progress in real time. The app also includes a function to report results and areas for improvement as feedback. For example, users can send feedback such as, "My physical condition did not improve after rehabilitation exercises."

[0247] Specific examples

[0248] For example, if heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) data are obtained from a sensor worn by care recipient A at 10:00 on October 10th, the server collects this data and inputs it into the generative AI model. The generative AI model detects that care recipient A's recent heart rate pattern is irregular and predicts that his or her stress level is increasing. Based on the results of this analysis, the server generates a specific care plan that includes "a 20-minute morning walk," "five minutes of deep breathing exercises," and "taking vitamin D supplements." The generated plan is immediately sent to the device, and the user can check the plan through a dedicated app.

[0249] Prompt Sentence Examples

[0250] Below are some examples of specific prompts to input to a generative AI model:

[0251] "Based on recent data, care recipient A's heart rate is irregular, and their blood pressure and temperature are within normal ranges. However, we have recognized a pattern that suggests their stress levels may be increasing. Please generate an appropriate care plan, including specific care items and how to implement them."

[0252] Based on this prompt, the AI ​​model generates an individualized nursing care plan.

[0253] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0254] Step 1: Data collection and preprocessing

[0255] The server receives data in real time from sensors worn by the care recipient. The sensors measure health indicators such as heart rate, blood pressure, body temperature, walking distance, and sleep time, and transmit the data to the server via Bluetooth or Wi-Fi. The received data is stored in a database and checked for outliers and missing values. For example, if the heart rate data sent from the sensor is irregular, the data is filtered.

[0256] Input: Real-time data from sensors

[0257] Output: Filtered health data

[0258] Step 2: Data analysis

[0259] The server inputs the preprocessed data into a generative AI model, which uses machine learning algorithms to analyze the care recipient's health status and detect specific patterns or abnormalities. For example, it analyzes heart rate data from the past week to detect irregular heart rate patterns. The analysis results are stored on the server.

[0260] Input: Preprocessed health data

[0261] Output: Health status analysis results

[0262] Step 3: Generate a care plan

[0263] The server generates an optimal care plan based on the analysis results. This care plan includes specific care items (e.g., a 20-minute morning walk, 5 minutes of deep breathing exercises, vitamin D supplement intake) and how to implement them. The generated plan is notified to the dedicated app.

[0264] Input: Health status analysis results

[0265] Output: Generated nursing care plan

[0266] Step 4: Collect and analyze emotion data

[0267] The device collects the voice and facial expressions of the user (caregiver or family member) and analyzes the emotional data. It uses a voice analysis engine and a camera to identify the user's emotions and sends the emotional data to the server. For example, it can detect whether the user is feeling stressed from the tone of their voice.

[0268] Input: User's voice and facial expression data

[0269] Output: Emotional state analysis results

[0270] Step 5: Plan Notification and Management

[0271] The generated care plan is sent from the server to the device and displayed on a dedicated app. The user manages the progress of the plan through the app and records the care items that have been carried out. For example, the user can record on the app that "a 20-minute morning walk was carried out."

[0272] Input: Generated nursing care plan

[0273] Output: Display of care plan and progress management on dedicated app

[0274] Step 6: Feedback and plan adjustments

[0275] The user provides feedback through a dedicated app. For example, they may provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the feedback and emotional data and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can check the latest instructions.

[0276] Input: User feedback

[0277] Output: Coordinated nursing care plan

[0278] (Application example 2)

[0279] 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."

[0280] In today's world, health management for those requiring care has become an important issue, but conventional systems have been unable to provide adequate individualized care and have made it difficult to provide care that takes into account the emotional state of caregivers and their families. Furthermore, systems for providing prompt and appropriate responses in emergencies were also inadequate. As a result, there was a risk of sudden changes in the health status of those requiring care and an increased burden on caregivers and their families.

[0281] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0282] In this invention, the server includes means for collecting data from a sensor worn by the care recipient, means for executing a generative AI model that analyzes the collected data, means for generating an individualized care plan based on the analysis results, means for notifying a dedicated app of the generated care plan, means for managing the progress of the care plan through the dedicated app, means for using an emotion engine that extracts emotion data from the user's voice and facial expressions, means for automatically notifying in an emergency based on the emotion data, and means for adjusting the care plan based on feedback. This makes it possible to monitor the health condition of the care recipient and the emotion state of the caregiver and family in real time and quickly provide an individualized and appropriate care plan.

[0283] A "sensor" is a device worn on the body that collects health-related data such as heart rate, blood pressure, and body temperature in real time.

[0284] A "generative AI model" is software that contains machine learning algorithms to analyze collected health data and predict abnormal patterns and risks.

[0285] A "nursing care plan" is a plan that individually defines the necessary medical care and daily life support activities for a person in need of nursing care, based on the analysis results of the generated AI model.

[0286] The "dedicated app" is an application used by the person requiring care and their caregiver on a smartphone or tablet, and is a platform for checking the generated care plan and managing its progress.

[0287] The "emotion engine" is a technology that analyzes the voices and facial expressions of caregivers and family members to identify their emotional state.

[0288] "Feedback" refers to information provided by users through a dedicated app regarding the effectiveness of nursing care plans and areas for improvement.

[0289] "Emergency notification" is a means of automatically transmitting information to emergency contacts and medical services when an abnormality is detected.

[0290] "Health status" refers to the physical condition of the care recipient, including heart rate, blood pressure, and body temperature, and is analyzed by the generative AI model.

[0291] "Progress management" is the process by which users check the progress of their nursing care plan through a dedicated app and record any necessary actions.

[0292] The present invention is a system that monitors the health status of a care recipient in real time and provides a personalized care plan, which can also take into account the emotional state of the caregiver and family. The configuration and operation of the system are described in detail below.

[0293] System Configuration

[0294] The system consists of the following main components:

[0295] 1. Sensors: Collect health data such as heart rate, blood pressure, and body temperature, and send the data to a server via Bluetooth or Wi-Fi.

[0296] 2. Server: Receives health data, analyzes it using a generative AI model, generates a care plan, and analyzes the user's emotional state using an emotion engine and stores the results.

[0297] 3. Dedicated app: Runs on smartphones and tablets, displays the generated nursing care plan and emotional data, and manages progress and provides feedback.

[0298] Program processing

[0299] Data collection and preprocessing

[0300] The server receives real-time health data from sensors. The collected data is filtered for outliers and missing values ​​and stored in a database. This processing is performed using internet-connected wearable devices (e.g., Fitbit, Apple Watch) for hardware and cloud computing services (e.g., AWS, Google Cloud) for the server.

[0301] Data analysis and care plan generation

[0302] The server inputs the collected and preprocessed data into a generative AI model to analyze the health status of the care recipient. The generative AI model includes machine learning algorithms for pattern recognition and risk assessment. Based on the analysis results, an individual care plan is generated. This is done using a database (e.g., MySQL, PostgreSQL).

[0303] Emotion data collection and analysis

[0304] The device extracts the user's emotional data using an emotion engine that recognizes voice and facial expressions. This emotion engine uses voice analysis and facial expression recognition technologies (e.g., Microsoft Azure Cognitive Services and Google Cloud AI). The collected emotional data is sent to a server and analyzed together with health data.

[0305] Emergency notifications and progress management

[0306] If an abnormality is detected based on the health data, the server automatically notifies emergency contacts and medical services. The generated care plan is sent to a dedicated app, allowing the user to manage the progress. The dedicated app is used on smartphones or tablets (e.g., iPhones and Android devices).

[0307] Specific examples

[0308] For example, if heart rate (80 bpm), blood pressure (130 / 85 mmHg), and body temperature (36.7°C) data are acquired from a sensor worn by care recipient A, the server analyzes this data and detects that recent heart rate fluctuations have increased. As a result, it generates a care plan to relieve stress, such as "10 minutes of deep breathing exercises" and "15 minutes of relaxation music." Furthermore, if the device's camera is used to detect caregiver B's facial expressions and the emotion engine identifies a high stress level, it suggests a guided meditation for relaxation using a dedicated app.

[0309] Example prompts for generative AI models

[0310] "Please explain health monitoring for nursing care systems, and methods for detecting abnormal patterns and generating appropriate care plans based on large amounts of heart rate, blood pressure, and temperature data."

[0311] As a result, the present invention makes it possible to monitor the health condition of the care recipient and the emotional state of the caregiver and family in real time, and to quickly provide an individual and appropriate care plan.

[0312] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0313] Step 1:

[0314] The sensors collect real-time health data such as the heart rate, blood pressure, and body temperature of the care recipient, and the collected data is sent to a server via Bluetooth or Wi-Fi.

[0315] Input: Health data (heart rate, blood pressure, temperature, etc.)

[0316] Output: Send data to the server (heart rate, blood pressure, body temperature)

[0317] Step 2:

[0318] The server filters the data received from the sensors, detects and corrects outliers and missing values, and stores the corrected data in a database.

[0319] Input: Data sent from the sensor

[0320] Output: Save the corrected health data to the database.

[0321] Step 3:

[0322] The server inputs the corrected data into the generative AI model to analyze the health status of the care recipient, which then recognizes abnormal patterns and risks based on the collected data.

[0323] Input: Corrected health data

[0324] Output: Health status analysis results

[0325] Step 4:

[0326] The server generates an individualized care plan for the care recipient based on the analysis results of the generative AI model, which includes necessary medical care and activities to support daily living.

[0327] Input: Health status analysis results

[0328] Output: Generated nursing care plan

[0329] Step 5:

[0330] The generated care plan is sent from the server to the device, and the user can check the plan contents using a dedicated app that runs on a smartphone or tablet.

[0331] Input: Generated nursing care plan

[0332] Output: Plan display on dedicated app

[0333] Step 6:

[0334] The device uses an emotion engine to analyze the user's voice and facial expressions, extracting emotional data, which is then sent to a server in real time.

[0335] Input: Voice data, facial expression data

[0336] Output: Extract emotion data and send it to the server

[0337] Step 7:

[0338] Based on the analyzed emotional data, the server automatically notifies emergency contacts and medical services in the event of an emergency, enabling a prompt response.

[0339] Input: Emotion data, health data

[0340] Output: Urgent notification

[0341] Step 8:

[0342] Users provide feedback and manage progress on their care plans through a dedicated app, which provides an interface for users to view progress and record any necessary actions.

[0343] Input: Feedback, progress data

[0344] Output: Feedback and progress recording

[0345] Step 9:

[0346] The server reevaluates the care plan based on user feedback and new emotional data, adjusts the plan as needed, and sends the adjusted plan back to the device.

[0347] Input: Feedback, emotion data

[0348] Output: Coordinated care plan

[0349] This enables the system to monitor the health status of the care recipient and the emotional state of the caregiver or family member in real time, providing appropriate care individually and quickly.

[0350] 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.

[0351] 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.

[0352] 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.

[0353] [Second embodiment]

[0354] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0355] 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.

[0356] 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).

[0357] 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.

[0358] 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.

[0359] 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).

[0360] 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.

[0361] 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.

[0362] 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.

[0363] 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.

[0364] 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.

[0365] 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."

[0366] The system of the present invention aims to monitor the health and living conditions of a person requiring care in real time and provide an individualized care plan. This system is composed of sensors, a generative AI model, and a dedicated application (hereinafter referred to as the dedicated app). Specific embodiments of the system of the present invention will be described in detail below.

[0367] 1. System Configuration

[0368] sensor

[0369] The server collects real-time health data (heart rate, blood pressure, body temperature, walking distance, sleep time, etc.) from sensors worn by the care recipient. These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data.

[0370] Generative AI Models

[0371] The server inputs the collected data into a generative AI model, which is based on machine learning algorithms that analyze the care recipient's health and lifestyle conditions to predict specific abnormalities and risks. Based on the analysis results, a care plan is created that addresses the care recipient's individual needs.

[0372] Dedicated app

[0373] Users (caregivers and family members) using devices (smartphones and tablets) can check the generated care plan through a dedicated app and manage progress in real time. The dedicated app includes a function to display details, priorities, and progress of the care plan.

[0374] 2. Program Processing

[0375] Data collection and preprocessing

[0376] The server receives the data collected from the sensors and filters it for outliers and missing values, and the collected data is stored in a database for subsequent analysis.

[0377] Data analysis

[0378] The server inputs the preprocessed data into a generative AI model to analyze the current health status of the care recipient, which then performs pattern recognition and anomaly detection to assess the care recipient's health risks.

[0379] Generate a care plan

[0380] Based on the analysis results of the AI ​​model, the server generates an optimal nursing care plan, which includes necessary medical care, activities of daily living assistance, and rehabilitation schedules.

[0381] Plan notification and management

[0382] The generated care plan is sent from the server to the device and displayed on a dedicated app, where the user can check the progress of the plan and record the action items that have been implemented.

[0383] Specific examples

[0384] For example, if data on heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) are obtained from sensors worn by care recipient A at 10:00 on October 10, the server collects this data and inputs it into the generative AI model. The AI ​​model detects that care recipient A's recent heart rate pattern is irregular and predicts that his stress level is increasing.

[0385] Based on the analysis results, the server generates a specific care plan, including a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplement intake. The plan is immediately sent to the device, and the user can check the plan through a dedicated app, perform deep breathing exercises at 11:00, and record this as "completed."

[0386] This enables the system to monitor the health status of those in need of care in real time, quickly provide appropriate care plans, and reduce the burden on caregivers and family members.

[0387] The processing flow will be explained below.

[0388] Step 1: Data collection

[0389] The server collects data in real time from sensors worn by the care recipient. Information such as heart rate, blood pressure, body temperature, walking distance, and sleep time is received via Bluetooth or Wi-Fi. The collected data is stored in a database with a timestamp. For example, the server might record "October 10th, 10:00: Heart rate 80 bpm, blood pressure 120 / 80 mmHg, body temperature 36.5°C."

[0390] Step 2: Data Preprocessing

[0391] The server converts the collected data into a format suitable for analysis. If there are incomplete data or outliers, filtering is performed. For example, data with abnormal heart rates (extremely high or low values) is removed. After filtering, the data is normalized and missing values ​​are imputed with the mean.

[0392] Step 3: Data analysis

[0393] The server inputs the preprocessed data into the generative AI model, which then uses machine learning algorithms to analyze the data and predict the care recipient's health status and trends. For example, the result might be, "Care recipient A's recent heart rate has been irregular, suggesting a high level of mental stress."

[0394] Step 4: Generate a care plan

[0395] The server generates an individualized care plan based on the analysis results. This plan includes necessary medical care, activities of daily living assistance, a rehabilitation schedule, and minor lifestyle changes. Specific recommendations include a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplementation.

[0396] Step 5: Plan Notification

[0397] The server sends the generated nursing care plan to a dedicated app. Each item in the plan is displayed in a timeline format and prioritized. Users (caregivers and family members) using devices (smartphones and tablets) are notified that the plan is available.

[0398] Step 6: Implement and manage the plan

[0399] The user on the device opens the dedicated app and checks the care plan. As each action item is implemented, progress is recorded within the app. For example, the user might enter "2023-10-10 11:00: 5 minutes of deep breathing exercises - completed." The server receives real-time feedback from the dedicated app and records it in a database.

[0400] Step 7: Feedback and plan adjustments

[0401] Users can send feedback through a dedicated app to report on the effectiveness of the care plan and areas for improvement. For example, they can provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the received feedback and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can check the latest instructions.

[0402] Example 1

[0403] 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."

[0404] Current nursing care systems make it difficult to monitor the health status of care recipients in real time and provide appropriate care plans immediately. Furthermore, if the collected data is analyzed without properly handling outliers or missing values, accurate analysis results cannot be obtained. Furthermore, if the generated nursing care plan is not optimized to the individual needs of the care recipient, the quality of care may decline and the burden on caregivers and families may increase.

[0405] 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.

[0406] In this invention, the server includes means for collecting data from sensors worn by the care recipient, means for filtering the collected data to remove outliers and missing values, means for inputting the preprocessed data into a generative AI model and analyzing health conditions and risks, means for generating an individual nursing care plan based on the analysis results, means for notifying a terminal of the generated nursing care plan, and means for managing the progress of the care plan through a dedicated app and adjusting the care plan based on feedback. This makes it possible to accurately monitor the health condition of the care recipient in real time, quickly provide an appropriate nursing care plan, and reduce the burden on caregivers and family members.

[0407] A "sensor" is a device that measures health data (heart rate, blood pressure, body temperature, walking distance, sleep time, etc.) of a person requiring care and transmits it to a server.

[0408] The "server" is a computing device that receives and stores data collected from sensors, preprocesses and analyzes the data, and generates and notifies nursing care plans.

[0409] "Filtering" is a process that removes outliers and missing values ​​from collected data to provide accurate data to generative AI models.

[0410] A "generative AI model" is a model that uses machine learning algorithms to analyze the health status and risks of individuals requiring care based on preprocessed health data and propose care plans.

[0411] A "nursing care plan" is a set of specific instructions based on the analysis results of the generated AI model, including the medical care, daily life support activities, and rehabilitation schedule that should be provided to the person in need of care.

[0412] The "terminal" is a device (smartphone or tablet) that notifies the caregiver of the created care plan and allows the caregiver or family member to check and manage the plan details through a dedicated app.

[0413] The "dedicated app" is software that allows caregivers and family members to check plan details, manage progress, and enter feedback.

[0414] "Real-time" refers to a situation in which data is collected and processed almost immediately, providing information in a timely manner.

[0415] "Feedback" refers to information provided by caregivers and family members through a dedicated app, and includes information on the implementation status and effectiveness of the generated nursing care plan.

[0416] The present invention relates to a system that monitors the health and living conditions of a person requiring care in real time and provides an individualized care plan. This system is configured using sensors, a generative AI model, and a dedicated application (hereinafter referred to as the dedicated app). Specific embodiments of the system of the present invention are described in detail below.

[0417] 1. System Configuration

[0418] sensor

[0419] The server collects real-time health data from sensors worn by the care recipient (e.g., heart rate monitors, blood pressure monitors, thermometers, pedometers, sleep trackers, etc.) These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data.

[0420] Generative AI Models

[0421] The server preprocesses the collected data and inputs it into a generative AI model (e.g., a TensorFlow-based model). The generative AI model is based on machine learning algorithms and analyzes the care recipient's health and living conditions to predict specific abnormalities and risks. Based on the analysis results, a care plan is created that addresses the care recipient's individual needs.

[0422] Dedicated app

[0423] Users (caregivers and family members) using devices (smartphones and tablets) can check the generated care plan through a dedicated app and manage progress in real time. The dedicated app includes a function to display details, priorities, and progress of the care plan.

[0424] 2. Program Processing

[0425] Data collection and preprocessing

[0426] The server receives the data collected from the sensors and filters it for outliers and missing values. The collected data is stored in a database (e.g., MySQL or PostgreSQL) for subsequent analysis.

[0427] Data analysis

[0428] The server inputs the preprocessed data into a generative AI model to analyze the current health status of the care recipient, which then performs pattern recognition and anomaly detection to assess the care recipient's health risks.

[0429] Generate a care plan

[0430] Based on the analysis results of the generative AI model, the server generates an optimal nursing care plan, which includes necessary medical care, daily living assistance activities, and rehabilitation schedules.

[0431] Plan notification and management

[0432] The generated care plan is sent from the server to the device and displayed on a dedicated app, where the user can check the progress of the plan and record the action items that have been implemented.

[0433] Specific examples

[0434] For example, if data on heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) are obtained from sensors worn by care recipient A at 10:00 on October 10, the server collects this data and inputs it into the generative AI model. The AI ​​model detects that care recipient A's recent heart rate pattern is irregular and predicts that his stress level is increasing.

[0435] Based on the analysis results, the server generates a specific care plan, including a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplement intake. The plan is immediately sent to the device, and the user can check the plan through a dedicated app, perform deep breathing exercises at 11:00, and record this as "completed."

[0436] An example of a prompt is, "Based on the data of heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) obtained at 10:00 on October 10th, analyze the recent heart rate pattern of care recipient A and generate a specific care plan."

[0437] This system can monitor the health status of those in need of care in real time, quickly provide appropriate care plans, and reduce the burden on caregivers and families.

[0438] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0439] Step 1: Collect sensor data

[0440] The server obtains real-time health data from sensors worn by the care recipient (e.g., heart rate monitor, blood pressure monitor, thermometer, pedometer, sleep tracker, etc.) Input data from the sensors (e.g., heart rate 80 bpm) is received via Bluetooth or Wi-Fi.

[0441] Specific operation: The server receives the heart rate data (80 bpm) of care recipient A at 10:00 on October 10th, and transmits it to the data collection module.

[0442] Step 2: Preprocessing the data

[0443] The server filters the received data to remove outliers and missing values. This filtering process validates the collected input data (e.g., heart rate 80 bpm) and removes outliers (e.g., 0 bpm and 300 bpm). The preprocessed data is stored in a database.

[0444] Specific operation: The server checks whether the received heart rate data is within the correct range and whether there is any abnormal data, and then stores it in the MySQL database.

[0445] Step 3: Data analysis

[0446] The server inputs the preprocessed data into a generative AI model, which uses machine learning algorithms to analyze the care recipient's health condition. Based on the input data (e.g., heart rate data of 80 bpm, data from the past week), the generative AI model performs pattern recognition and anomaly detection to assess the care recipient's health risk.

[0447] Specific operation: The server inputs heart rate data into a TensorFlow-based generative AI model, analyzes irregularities in care recipient A's heart rate pattern, and predicts that his or her stress level may be high.

[0448] Step 4: Generate a care plan

[0449] The server generates an individualized care plan based on the analysis results of the generative AI model. This care plan includes schedules for necessary medical care, activities of daily living assistance, and rehabilitation. The generated plan is then stored in a database.

[0450] Specific operation: The server determines that the stress level of care recipient A is high, generates a care plan including a 20-minute morning walk, 5 minutes of deep breathing exercises, and taking vitamin D supplements, and saves it in the database.

[0451] Step 5: Plan Notification and Management

[0452] The server then notifies the device of the generated care plan, which then displays the plan details through a dedicated app, allowing the user to manage progress in real time.

[0453] Specific operation: The server sends the generated care plan to a smartphone, where the plan details can be displayed in a dedicated app, allowing progress to be managed.

[0454] Step 6: Real-time monitoring

[0455] Users can check the health status of their care recipients in real time using a dedicated app, which displays collected data and progress of care plans in real time.

[0456] Specific operation: The user checks the current heart rate and progress of the care plan for care recipient A using a dedicated app, and for example, performs deep breathing exercises at 11:00 and records this as "completed."

[0457] (Application example 1)

[0458] 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."

[0459] In modern factories, it is extremely important to monitor the health status of workers in real time and make appropriate work adjustments and break suggestions, and a system for this purpose is needed. However, current systems have difficulty quickly generating and notifying appropriate health management suggestions for individual workers, making it difficult to minimize worker health risks.

[0460] 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.

[0461] In this invention, the server includes means for collecting data from sensors worn by workers, means for executing a generative AI model that analyzes the collected data, means for generating appropriate health management suggestions based on the analysis results, means for notifying a dedicated app of the generated health management suggestions, means for managing the progress of the health management suggestions through the dedicated app, and means for adjusting the health management suggestions based on feedback. This makes it possible to monitor the health status of workers in real time, quickly provide appropriate health management suggestions, and improve the safety of the working environment.

[0462] "Essential workers" refer to workers who are responsible for certain tasks at work sites such as factories.

[0463] A "sensor" refers to a device that can measure physiological data such as heart rate, blood pressure, body temperature, number of steps, and sleep time, and transmit it as a digital signal.

[0464] A "generative AI model" refers to a machine learning algorithm that analyzes collected data and performs health status and risk assessments.

[0465] "Health management suggestions" refer to recommendations such as breaks and work adjustments that are generated for workers based on the analysis results of the generative AI model.

[0466] A "dedicated app" refers to software that allows workers and managers to check health management proposals and manage progress.

[0467] "Data collection means" refers to a system component that has the function of collecting physiological data from sensors and transmitting it to a server.

[0468] "Analysis means" refers to a system component that has the ability to analyze collected data based on a generative AI model.

[0469] "Notification means" refers to a system component that has the function of sending the generated health management suggestions to a dedicated app.

[0470] "Progress management means" refers to a system component that has the function of grasping and managing the implementation status of health management proposals through a dedicated app.

[0471] "Feedback means" refers to a system component that has the ability to adjust health management suggestions based on information obtained from a dedicated app.

[0472] The present invention aims to monitor the health status and work status of key workers in real time and provide individualized health management suggestions. Specifically, the system is composed of sensors, a generative AI model, and a dedicated application (hereinafter referred to as the dedicated app). Specific embodiments of the system of the present invention are described in detail below.

[0473] 1. System Configuration

[0474] sensor

[0475] The server collects real-time health data (heart rate, blood pressure, body temperature, number of steps, sleep time, etc.) from sensors worn by key workers. These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data. The sensors can be general wearable devices or dedicated devices for measuring specific physiological indicators.

[0476] Generative AI Models

[0477] The server inputs the collected data into a generative AI model, which uses machine learning algorithms such as TensorFlow and Scikit-learn to perform health and risk assessments of critical workers. The model performs pattern recognition and anomaly detection to predict worker stress and fatigue levels.

[0478] Dedicated app

[0479] The server sends health management suggestions generated based on the analysis results of the generative AI model to devices (smartphones and tablets). Users (workers and managers) can check these health management suggestions through a dedicated app and manage their progress in real time. The dedicated app includes a function to display the details, priority, and progress of health management suggestions. Users can also provide feedback, and this information is used to adjust the health management suggestions.

[0480] 2. Program Processing

[0481] The server receives the data collected from the sensors and filters it for outliers and missing values. The collected data is stored in a database for subsequent analysis. The server then inputs the preprocessed data into a generative AI model to analyze the worker's current health status.

[0482] This generative AI model generates optimal health management suggestions based on the analysis results. These suggestions include necessary breaks, work adjustments, and rehabilitation schedules. The generated health management suggestions are sent from the server to the device and displayed in a dedicated app. The user can check the progress of the suggestions through the dedicated app and record the action items that have been implemented.

[0483] For example, if data on heart rate (90 bpm), blood pressure (130 / 85 mmHg), and body temperature (37.0°C) are obtained from a sensor worn by essential worker A at 10:00 on October 10th, the server collects this data and inputs it into the generative AI model. The AI ​​model predicts that essential worker A's stress level is rising and generates a specific health management suggestion that "he should take a break." This suggestion is immediately sent to the device, and the user can confirm and implement the suggestion through a dedicated app.

[0484] 3. Example prompts

[0485] "Analyze the collected worker health data (heart rate: 90 bpm, blood pressure: 130 / 85 mmHg, body temperature: 37.0°C) and use a generative AI model to assess the stress level. Based on the assessment results, generate suggestions for appropriate break timing and work adjustments."

[0486] In this way, the present invention makes it possible to monitor the health status of workers in real time, quickly provide appropriate health management suggestions, and improve the safety of the work environment.

[0487] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0488] Step 1:

[0489] The server collects biometric data (heart rate, blood pressure, body temperature, number of steps, sleep time, etc.) from sensors. The sensors send the data to the server via Bluetooth or Wi-Fi. This input data is saved on the server in CSV or JSON format.

[0490] Step 2:

[0491] The server filters the received biometric data, specifically checking for missing values ​​and removing outliers, to generate a preprocessed dataset. The input is the raw dataset, and the output is the filtered dataset.

[0492] Step 3:

[0493] The server inputs the preprocessed data into a generative AI model, which is built using TensorFlow and Scikit-learn and performs health status analysis and risk assessment based on the input data. The input is the filtered dataset, and the output is the analysis results.

[0494] Step 4:

[0495] The server generates health management suggestions based on the analysis results of the generative AI model. Health management suggestions include specific actions such as "take a break," "hydrate," and "perform specific stretches." The input is the analysis results, and the output is the health management suggestions.

[0496] Step 5:

[0497] The server sends the generated health management suggestions to a device. The device consists of a smartphone or tablet with a dedicated app installed. The input is the health management suggestions, and the output is a notification to the device.

[0498] Step 6:

[0499] Users (workers and managers) check the health management suggestions through a dedicated app. They then carry out the suggested actions and record their progress in the app. The input is the health management suggestions, and the output is a record of the progress.

[0500] Step 7:

[0501] Feedback is sent from the dedicated app to the server, which evaluates the effectiveness of health management suggestions based on the feedback information and adjusts the suggestions as necessary. The input is progress and feedback, and the output is adjusted health management suggestions.

[0502] 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.

[0503] The system of the present invention monitors the health and living conditions of the care recipient in real time, provides an individual care plan, and also realizes more detailed care by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the system of the present invention will be described in detail below.

[0504] 1. System Configuration

[0505] sensor

[0506] The server collects real-time health data (heart rate, blood pressure, body temperature, walking distance, sleep time, etc.) from sensors worn by the care recipient. These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data.

[0507] Generative AI Models

[0508] The server inputs the collected data into a generative AI model, which is based on machine learning algorithms and analyzes the care recipient's health and lifestyle to predict specific abnormalities and risks. Based on the analysis results, a care plan is created that addresses the care recipient's individual needs.

[0509] Emotion Engine

[0510] The device is equipped with an emotion engine that identifies the emotions of users (caregivers and family members) through voice analysis and facial expression recognition. This emotion engine extracts emotion data from the user's voice and camera footage and sends it to the server as feedback.

[0511] Dedicated app

[0512] Users using a device (smartphone or tablet) can check the generated care plan through a dedicated app and manage progress in real time. The dedicated app includes functions to display details, priorities, and progress of the care plan. It also displays emotional data obtained by an emotion engine.

[0513] 2. Program Processing

[0514] Data collection and preprocessing

[0515] The server receives the data collected from the sensors and filters it for outliers and missing values, and the collected data is stored in a database for subsequent analysis.

[0516] Data analysis

[0517] The server inputs the preprocessed data into a generative AI model to analyze the current health status of the care recipient, which then performs pattern recognition and anomaly detection to assess the care recipient's health risks.

[0518] Generate a care plan

[0519] Based on the analysis results of the AI ​​model, the server generates an optimal nursing care plan, which includes necessary medical care, activities of daily living assistance, and rehabilitation schedules.

[0520] Emotion data collection and analysis

[0521] The device extracts emotional data from the user's voice and facial expressions. For example, a speech recognition engine identifies emotions such as joy, sadness, and anger from the user's speaking style and tone. The recognized emotional data is sent to the server in real time.

[0522] Plan notification and management

[0523] The generated care plan is sent from the server to the device and displayed on a dedicated app. The user can check the progress of the plan through the dedicated app and record the action items that have been implemented. In addition, emotion data obtained from the emotion engine can also be viewed within the app.

[0524] Feedback and plan adjustments

[0525] Users can send feedback through a dedicated app to report on the effectiveness of the care plan and areas for improvement. For example, they can provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the received feedback and emotional data and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can check the latest instructions.

[0526] Specific examples

[0527] For example, if data on heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) are obtained from sensors worn by care recipient A at 10:00 on October 10, the server collects this data and inputs it into the generative AI model. The AI ​​model detects that care recipient A's recent heart rate pattern is irregular and predicts that his stress level is increasing.

[0528] Based on the analysis results, the server generates a specific care plan, such as a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplements. The plan is immediately sent to the device, and the user can view it through a dedicated app.

[0529] In addition, the emotion engine identifies emotions from the user's tone of voice and camera footage, and if, for example, stress or anxiety is elevated, that information is displayed within the dedicated app. Users can check their emotional state in the dedicated app and request that parts of their care plan be readjusted if necessary.

[0530] This enables the system to monitor the health status of the care recipient and the emotional state of the caregiver or family member in real time, and provide appropriate care individually and quickly, thereby improving the quality of life of the care recipient and their caregiver.

[0531] The processing flow will be explained below.

[0532] Step 1: Data collection

[0533] The server collects real-time health data (heart rate, blood pressure, body temperature, walking distance, and sleep time) from sensors worn by the care recipient. These sensors communicate with the server via Bluetooth or Wi-Fi and periodically send data. For example, data is recorded in the format "October 10th, 10:00: Heart rate 80 bpm, blood pressure 120 / 80 mmHg, body temperature 36.5°C."

[0534] Step 2: Data Preprocessing

[0535] The server filters the collected data to identify outliers and missing values, removes incomplete data if present, imputes missing values ​​with the mean, and normalizes the data and converts it into a format suitable for analysis.

[0536] Step 3: Data analysis

[0537] The server inputs the preprocessed data into a generative AI model, which then uses machine learning algorithms to analyze the data and perform a health status and risk assessment of the care recipient. For example, the model might generate an analysis result such as, "Recent heart rate patterns have been irregular, and stress levels are high."

[0538] Step 4: Generate a care plan

[0539] The server generates an individualized care plan based on the analysis results of the AI ​​model. Specific plans include "a 20-minute morning walk," "5 minutes of deep breathing exercises," and "taking vitamin D supplements." The generated care plan is saved in a database and used in subsequent steps.

[0540] Step 5: Collecting sentiment data

[0541] The device analyzes the voice and facial expressions of the user (caregiver or family member) to collect emotional data. The emotion engine reads the tone of the voice, speaking style, and facial expressions from camera footage to identify the emotional state in real time. For example, the result may be, "The user's voice has a depressed tone, and anxiety is increasing."

[0542] Step 6: Notification of Emotion Data

[0543] The server stores the collected emotion data in a database in real time and sends it along with the analysis results to a dedicated app. The device displays the emotion data within the app, allowing the user to check the situation.

[0544] Step 7: Plan Notification and Management

[0545] The server sends the generated care plan to a dedicated app. The device displays each item in the plan in a timeline format and notifies the user. The user can check the progress of the plan through the dedicated app and record the action items that have been completed. For example, the user could enter "2023-10-10 11:00: 5 minutes of deep breathing exercises - completed."

[0546] Step 8: Feedback and Adjustments

[0547] Users send feedback through a dedicated app, reporting the effectiveness of the care plan and areas for improvement. For example, they may provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the feedback and emotional data and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can view the latest care plan.

[0548] This processing flow enables the system to monitor the health status of the care recipient and the emotional state of the caregiver and family in real time, and provide appropriate care plans individually and quickly, thereby improving the quality of life of the care recipient and their caregiver.

[0549] Example 2

[0550] 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."

[0551] In modern society, monitoring the health status of those requiring care in real time and providing appropriate care according to their circumstances is a crucial issue. However, conventional systems only collect and analyze the health data of those requiring care, and are unable to provide care plans that take into account the emotional state of the caregiver or family. This makes it difficult to provide attentive care, and improving the satisfaction of both the care recipient and the caregiver is a challenge.

[0552] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0553] In this invention, the server includes means for collecting data from a sensor worn by the care recipient, means for executing a generative AI model that analyzes the collected data, means for generating an individual nursing care plan based on the analysis results, means for notifying a dedicated app of the generated nursing care plan, means for managing the progress of the nursing care plan through the dedicated app, means for adjusting the nursing care plan based on feedback, a terminal equipped with an emotion engine that collects and analyzes user emotion data, and means for analyzing the emotion data and feeding it back to the dedicated app. This enables the provision of detailed and prompt care that takes into account both the health state of the care recipient and the emotional states of the caregiver and family.

[0554] "Individuals requiring care" refers to elderly people or individuals with illnesses or disabilities who require assistance with daily living or medical care.

[0555] "Sensors" refer to devices used to measure and collect data on the health status of care recipients, including devices that measure heart rate, blood pressure, body temperature, walking distance, sleep time, etc. in real time.

[0556] "Server" refers to a computer system that receives data collected from sensors and processes and analyzes it.

[0557] A "generative AI model" refers to a machine learning model that analyzes the health condition of a person requiring care based on collected data and generates an appropriate nursing care plan.

[0558] A "nursing care plan" refers to a specific action plan that includes medical care, assistance with daily life, rehabilitation schedules, etc., according to the health condition of the person requiring care.

[0559] "Dedicated app" refers to a software application that displays the generated nursing care plan and allows the user to manage its progress.

[0560] An "emotion engine" is a technology that collects and analyzes emotional data from the user's voice and facial expressions, and sends it to a server as feedback.

[0561] "User" refers to an individual, including a caregiver or family member providing nursing care.

[0562] "Feedback" refers to information provided by the user, including data on the effectiveness of the care plan and areas for improvement.

[0563] The present invention is a system for monitoring the health and living conditions of a person requiring care in real time and providing an individualized care plan. Specific embodiments of this system will be described in detail below.

[0564] System Configuration

[0565] The system consists of a sensor worn by the care recipient, a server that analyzes the data, a device that collects emotional data, and a dedicated app that manages the generated care plan.

[0566] sensor

[0567] The server collects real-time data from sensors worn by the care recipient. The sensors then transmit the data to the server via Bluetooth or Wi-Fi. The collected data includes multiple health indicators such as heart rate, blood pressure, body temperature, walking distance, and sleep time.

[0568] Data analysis

[0569] The server receives the collected health data and runs a generative AI model to analyze it. The generative AI model is based on machine learning algorithms to assess the care recipient's health status and risks. For example, it analyzes irregular heart rate patterns and blood pressure fluctuations to predict the care recipient's health risks. Based on the analysis results, an individualized care plan is generated.

[0570] Care plan generation and notification

[0571] Based on the analysis results of the AI ​​model, the server generates a specific action plan, such as "a 20-minute morning walk," "five minutes of deep breathing exercises," or "taking vitamin D supplements." The generated care plan is then sent to a dedicated app.

[0572] Collecting Emotional Data

[0573] The device collects emotional data from the user's voice and facial expressions. It uses a voice analysis engine and a camera to identify emotions such as joy, sadness, and anger from the user's speaking style, tone, and facial expressions. This emotional data is sent to a server in real time.

[0574] Dedicated app functions

[0575] Users using a device (smartphone or tablet) can check the generated care plan through a dedicated app and manage progress in real time. The app also includes a function to report results and areas for improvement as feedback. For example, users can send feedback such as, "My physical condition did not improve after rehabilitation exercises."

[0576] Specific examples

[0577] For example, if heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) data are obtained from a sensor worn by care recipient A at 10:00 on October 10th, the server collects this data and inputs it into the generative AI model. The generative AI model detects that care recipient A's recent heart rate pattern is irregular and predicts that his or her stress level is increasing. Based on the results of this analysis, the server generates a specific care plan that includes "a 20-minute morning walk," "five minutes of deep breathing exercises," and "taking vitamin D supplements." The generated plan is immediately sent to the device, and the user can check the plan through a dedicated app.

[0578] Prompt Sentence Examples

[0579] Below are some examples of specific prompts to input to a generative AI model:

[0580] "Based on recent data, care recipient A's heart rate is irregular, and their blood pressure and temperature are within normal ranges. However, we have recognized a pattern that suggests their stress levels may be increasing. Please generate an appropriate care plan, including specific care items and how to implement them."

[0581] Based on this prompt, the AI ​​model generates an individualized nursing care plan.

[0582] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0583] Step 1: Data collection and preprocessing

[0584] The server receives data in real time from sensors worn by the care recipient. The sensors measure health indicators such as heart rate, blood pressure, body temperature, walking distance, and sleep time, and transmit the data to the server via Bluetooth or Wi-Fi. The received data is stored in a database and checked for outliers and missing values. For example, if the heart rate data sent from the sensor is irregular, the data is filtered.

[0585] Input: Real-time data from sensors

[0586] Output: Filtered health data

[0587] Step 2: Data analysis

[0588] The server inputs the preprocessed data into a generative AI model, which uses machine learning algorithms to analyze the care recipient's health status and detect specific patterns or abnormalities. For example, it analyzes heart rate data from the past week to detect irregular heart rate patterns. The analysis results are stored on the server.

[0589] Input: Preprocessed health data

[0590] Output: Health status analysis results

[0591] Step 3: Generate a care plan

[0592] The server generates an optimal care plan based on the analysis results. This care plan includes specific care items (e.g., a 20-minute morning walk, 5 minutes of deep breathing exercises, vitamin D supplement intake) and how to implement them. The generated plan is notified to the dedicated app.

[0593] Input: Health status analysis results

[0594] Output: Generated nursing care plan

[0595] Step 4: Collect and analyze emotion data

[0596] The device collects the voice and facial expressions of the user (caregiver or family member) and analyzes the emotional data. It uses a voice analysis engine and a camera to identify the user's emotions and sends the emotional data to the server. For example, it can detect whether the user is feeling stressed from the tone of their voice.

[0597] Input: User's voice and facial expression data

[0598] Output: Emotional state analysis results

[0599] Step 5: Plan Notification and Management

[0600] The generated care plan is sent from the server to the device and displayed on a dedicated app. The user manages the progress of the plan through the app and records the care items that have been carried out. For example, the user can record on the app that "a 20-minute morning walk was carried out."

[0601] Input: Generated nursing care plan

[0602] Output: Display of care plan and progress management on dedicated app

[0603] Step 6: Feedback and plan adjustments

[0604] The user provides feedback through a dedicated app. For example, they may provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the feedback and emotional data and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can check the latest instructions.

[0605] Input: User feedback

[0606] Output: Coordinated nursing care plan

[0607] (Application example 2)

[0608] 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."

[0609] In today's world, health management for those requiring care has become an important issue, but conventional systems have been unable to provide adequate individualized care and have made it difficult to provide care that takes into account the emotional state of caregivers and their families. Furthermore, systems for providing prompt and appropriate responses in emergencies were also inadequate. As a result, there was a risk of sudden changes in the health status of those requiring care and an increased burden on caregivers and their families.

[0610] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0611] In this invention, the server includes means for collecting data from a sensor worn by the care recipient, means for executing a generative AI model that analyzes the collected data, means for generating an individualized care plan based on the analysis results, means for notifying a dedicated app of the generated care plan, means for managing the progress of the care plan through the dedicated app, means for using an emotion engine that extracts emotion data from the user's voice and facial expressions, means for automatically notifying in an emergency based on the emotion data, and means for adjusting the care plan based on feedback. This makes it possible to monitor the health condition of the care recipient and the emotion state of the caregiver and family in real time and quickly provide an individualized and appropriate care plan.

[0612] A "sensor" is a device worn on the body that collects health-related data such as heart rate, blood pressure, and body temperature in real time.

[0613] A "generative AI model" is software that contains machine learning algorithms to analyze collected health data and predict abnormal patterns and risks.

[0614] A "nursing care plan" is a plan that individually defines the necessary medical care and daily life support activities for a person in need of nursing care, based on the analysis results of the generated AI model.

[0615] The "dedicated app" is an application used by the person requiring care and their caregiver on a smartphone or tablet, and is a platform for checking the generated care plan and managing its progress.

[0616] The "emotion engine" is a technology that analyzes the voices and facial expressions of caregivers and family members to identify their emotional state.

[0617] "Feedback" refers to information provided by users through a dedicated app regarding the effectiveness of nursing care plans and areas for improvement.

[0618] "Emergency notification" is a means of automatically transmitting information to emergency contacts and medical services when an abnormality is detected.

[0619] "Health status" refers to the physical condition of the care recipient, including heart rate, blood pressure, and body temperature, and is analyzed by the generative AI model.

[0620] "Progress management" is the process by which users check the progress of their nursing care plan through a dedicated app and record any necessary actions.

[0621] The present invention is a system that monitors the health status of a care recipient in real time and provides a personalized care plan, which can also take into account the emotional state of the caregiver and family. The configuration and operation of the system are described in detail below.

[0622] System Configuration

[0623] The system consists of the following main components:

[0624] 1. Sensors: Collect health data such as heart rate, blood pressure, and body temperature, and send the data to a server via Bluetooth or Wi-Fi.

[0625] 2. Server: Receives health data, analyzes it using a generative AI model, generates a care plan, and analyzes the user's emotional state using an emotion engine and stores the results.

[0626] 3. Dedicated app: Runs on smartphones and tablets, displays the generated nursing care plan and emotional data, and manages progress and provides feedback.

[0627] Program processing

[0628] Data collection and preprocessing

[0629] The server receives real-time health data from sensors. The collected data is filtered for outliers and missing values ​​and stored in a database. This processing is performed using internet-connected wearable devices (e.g., Fitbit, Apple Watch) for hardware and cloud computing services (e.g., AWS, Google Cloud) for the server.

[0630] Data analysis and care plan generation

[0631] The server inputs the collected and preprocessed data into a generative AI model to analyze the health status of the care recipient. The generative AI model includes machine learning algorithms for pattern recognition and risk assessment. Based on the analysis results, an individual care plan is generated. This is done using a database (e.g., MySQL, PostgreSQL).

[0632] Emotion data collection and analysis

[0633] The device extracts the user's emotional data using an emotion engine that recognizes voice and facial expressions. This emotion engine uses voice analysis and facial expression recognition technologies (e.g., Microsoft Azure Cognitive Services and Google Cloud AI). The collected emotional data is sent to a server and analyzed together with health data.

[0634] Emergency notifications and progress management

[0635] If an abnormality is detected based on the health data, the server automatically notifies emergency contacts and medical services. The generated care plan is sent to a dedicated app, allowing the user to manage the progress. The dedicated app is used on smartphones or tablets (e.g., iPhones and Android devices).

[0636] Specific examples

[0637] For example, if heart rate (80 bpm), blood pressure (130 / 85 mmHg), and body temperature (36.7°C) data are acquired from a sensor worn by care recipient A, the server analyzes this data and detects that recent heart rate fluctuations have increased. As a result, it generates a care plan to relieve stress, such as "10 minutes of deep breathing exercises" and "15 minutes of relaxation music." Furthermore, if the device's camera is used to detect caregiver B's facial expressions and the emotion engine identifies a high stress level, it suggests a guided meditation for relaxation using a dedicated app.

[0638] Example prompts for generative AI models

[0639] "Please explain health monitoring for nursing care systems, and methods for detecting abnormal patterns and generating appropriate care plans based on large amounts of heart rate, blood pressure, and temperature data."

[0640] As a result, the present invention makes it possible to monitor the health condition of the care recipient and the emotional state of the caregiver and family in real time, and to quickly provide an individual and appropriate care plan.

[0641] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0642] Step 1:

[0643] The sensors collect real-time health data such as the heart rate, blood pressure, and body temperature of the care recipient, and the collected data is sent to a server via Bluetooth or Wi-Fi.

[0644] Input: Health data (heart rate, blood pressure, temperature, etc.)

[0645] Output: Send data to the server (heart rate, blood pressure, body temperature)

[0646] Step 2:

[0647] The server filters the data received from the sensors, detects and corrects outliers and missing values, and stores the corrected data in a database.

[0648] Input: Data sent from the sensor

[0649] Output: Save the corrected health data to the database.

[0650] Step 3:

[0651] The server inputs the corrected data into the generative AI model to analyze the health status of the care recipient, which then recognizes abnormal patterns and risks based on the collected data.

[0652] Input: Corrected health data

[0653] Output: Health status analysis results

[0654] Step 4:

[0655] The server generates an individualized care plan for the care recipient based on the analysis results of the generative AI model, which includes necessary medical care and activities to support daily living.

[0656] Input: Health status analysis results

[0657] Output: Generated nursing care plan

[0658] Step 5:

[0659] The generated care plan is sent from the server to the device, and the user can check the plan contents using a dedicated app that runs on a smartphone or tablet.

[0660] Input: Generated nursing care plan

[0661] Output: Plan display on dedicated app

[0662] Step 6:

[0663] The device uses an emotion engine to analyze the user's voice and facial expressions, extracting emotional data, which is then sent to a server in real time.

[0664] Input: Voice data, facial expression data

[0665] Output: Extract emotion data and send it to the server

[0666] Step 7:

[0667] Based on the analyzed emotional data, the server automatically notifies emergency contacts and medical services in the event of an emergency, enabling a prompt response.

[0668] Input: Emotion data, health data

[0669] Output: Urgent notification

[0670] Step 8:

[0671] Users provide feedback and manage progress on their care plans through a dedicated app, which provides an interface for users to view progress and record any necessary actions.

[0672] Input: Feedback, progress data

[0673] Output: Feedback and progress recording

[0674] Step 9:

[0675] The server reevaluates the care plan based on user feedback and new emotional data, adjusts the plan as needed, and sends the adjusted plan back to the device.

[0676] Input: Feedback, emotion data

[0677] Output: Coordinated care plan

[0678] This enables the system to monitor the health status of the care recipient and the emotional state of the caregiver or family member in real time, providing appropriate care individually and quickly.

[0679] 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.

[0680] 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.

[0681] 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.

[0682] [Third embodiment]

[0683] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0684] 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.

[0685] 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).

[0686] 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.

[0687] 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.

[0688] 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).

[0689] 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.

[0690] 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.

[0691] 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.

[0692] 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.

[0693] 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.

[0694] 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."

[0695] The system of the present invention aims to monitor the health and living conditions of a person requiring care in real time and provide an individualized care plan. This system is composed of sensors, a generative AI model, and a dedicated application (hereinafter referred to as the dedicated app). Specific embodiments of the system of the present invention will be described in detail below.

[0696] 1. System Configuration

[0697] sensor

[0698] The server collects real-time health data (heart rate, blood pressure, body temperature, walking distance, sleep time, etc.) from sensors worn by the care recipient. These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data.

[0699] Generative AI Models

[0700] The server inputs the collected data into a generative AI model, which is based on machine learning algorithms that analyze the care recipient's health and lifestyle conditions to predict specific abnormalities and risks. Based on the analysis results, a care plan is created that addresses the care recipient's individual needs.

[0701] Dedicated app

[0702] Users (caregivers and family members) using devices (smartphones and tablets) can check the generated care plan through a dedicated app and manage progress in real time. The dedicated app includes a function to display details, priorities, and progress of the care plan.

[0703] 2. Program Processing

[0704] Data collection and preprocessing

[0705] The server receives the data collected from the sensors and filters it for outliers and missing values, and the collected data is stored in a database for subsequent analysis.

[0706] Data analysis

[0707] The server inputs the preprocessed data into a generative AI model to analyze the current health status of the care recipient, which then performs pattern recognition and anomaly detection to assess the care recipient's health risks.

[0708] Generate a care plan

[0709] Based on the analysis results of the AI ​​model, the server generates an optimal nursing care plan, which includes necessary medical care, activities of daily living assistance, and rehabilitation schedules.

[0710] Plan notification and management

[0711] The generated care plan is sent from the server to the device and displayed on a dedicated app, where the user can check the progress of the plan and record the action items that have been implemented.

[0712] Specific examples

[0713] For example, if data on heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) are obtained from sensors worn by care recipient A at 10:00 on October 10, the server collects this data and inputs it into the generative AI model. The AI ​​model detects that care recipient A's recent heart rate pattern is irregular and predicts that his stress level is increasing.

[0714] Based on the analysis results, the server generates a specific care plan, including a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplement intake. The plan is immediately sent to the device, and the user can check the plan through a dedicated app, perform deep breathing exercises at 11:00, and record this as "completed."

[0715] This enables the system to monitor the health status of those in need of care in real time, quickly provide appropriate care plans, and reduce the burden on caregivers and family members.

[0716] The processing flow will be explained below.

[0717] Step 1: Data collection

[0718] The server collects data in real time from sensors worn by the care recipient. Information such as heart rate, blood pressure, body temperature, walking distance, and sleep time is received via Bluetooth or Wi-Fi. The collected data is stored in a database with a timestamp. For example, the server might record "October 10th, 10:00: Heart rate 80 bpm, blood pressure 120 / 80 mmHg, body temperature 36.5°C."

[0719] Step 2: Data Preprocessing

[0720] The server converts the collected data into a format suitable for analysis. If there are incomplete data or outliers, filtering is performed. For example, data with abnormal heart rates (extremely high or low values) is removed. After filtering, the data is normalized and missing values ​​are imputed with the mean.

[0721] Step 3: Data analysis

[0722] The server inputs the preprocessed data into the generative AI model, which then uses machine learning algorithms to analyze the data and predict the care recipient's health status and trends. For example, the result might be, "Care recipient A's recent heart rate has been irregular, suggesting a high level of mental stress."

[0723] Step 4: Generate a care plan

[0724] The server generates an individualized care plan based on the analysis results. This plan includes necessary medical care, activities of daily living assistance, a rehabilitation schedule, and minor lifestyle changes. Specific recommendations include a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplementation.

[0725] Step 5: Plan Notification

[0726] The server sends the generated nursing care plan to a dedicated app. Each item in the plan is displayed in a timeline format and prioritized. Users (caregivers and family members) using devices (smartphones and tablets) are notified that the plan is available.

[0727] Step 6: Implement and manage the plan

[0728] The user on the device opens the dedicated app and checks the care plan. As each action item is implemented, progress is recorded within the app. For example, the user might enter "2023-10-10 11:00: 5 minutes of deep breathing exercises - completed." The server receives real-time feedback from the dedicated app and records it in a database.

[0729] Step 7: Feedback and plan adjustments

[0730] Users can send feedback through a dedicated app to report on the effectiveness of the care plan and areas for improvement. For example, they can provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the received feedback and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can check the latest instructions.

[0731] Example 1

[0732] 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."

[0733] Current nursing care systems make it difficult to monitor the health status of care recipients in real time and provide appropriate care plans immediately. Furthermore, if the collected data is analyzed without properly handling outliers or missing values, accurate analysis results cannot be obtained. Furthermore, if the generated nursing care plan is not optimized to the individual needs of the care recipient, the quality of care may decline and the burden on caregivers and families may increase.

[0734] 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.

[0735] In this invention, the server includes means for collecting data from sensors worn by the care recipient, means for filtering the collected data to remove outliers and missing values, means for inputting the preprocessed data into a generative AI model and analyzing health conditions and risks, means for generating an individual nursing care plan based on the analysis results, means for notifying a terminal of the generated nursing care plan, and means for managing the progress of the care plan through a dedicated app and adjusting the care plan based on feedback. This makes it possible to accurately monitor the health condition of the care recipient in real time, quickly provide an appropriate nursing care plan, and reduce the burden on caregivers and family members.

[0736] A "sensor" is a device that measures health data (heart rate, blood pressure, body temperature, walking distance, sleep time, etc.) of a person requiring care and transmits it to a server.

[0737] The "server" is a computing device that receives and stores data collected from sensors, preprocesses and analyzes the data, and generates and notifies nursing care plans.

[0738] "Filtering" is a process that removes outliers and missing values ​​from collected data to provide accurate data to generative AI models.

[0739] A "generative AI model" is a model that uses machine learning algorithms to analyze the health status and risks of individuals requiring care based on preprocessed health data and propose care plans.

[0740] A "nursing care plan" is a set of specific instructions based on the analysis results of the generated AI model, including the medical care, daily life support activities, and rehabilitation schedule that should be provided to the person in need of care.

[0741] The "terminal" is a device (smartphone or tablet) that notifies the caregiver of the created care plan and allows the caregiver or family member to check and manage the plan details through a dedicated app.

[0742] The "dedicated app" is software that allows caregivers and family members to check plan details, manage progress, and enter feedback.

[0743] "Real-time" refers to a situation in which data is collected and processed almost immediately, providing information in a timely manner.

[0744] "Feedback" refers to information provided by caregivers and family members through a dedicated app, and includes information on the implementation status and effectiveness of the generated nursing care plan.

[0745] The present invention relates to a system that monitors the health and living conditions of a person requiring care in real time and provides an individualized care plan. This system is configured using sensors, a generative AI model, and a dedicated application (hereinafter referred to as the dedicated app). Specific embodiments of the system of the present invention are described in detail below.

[0746] 1. System Configuration

[0747] sensor

[0748] The server collects real-time health data from sensors worn by the care recipient (e.g., heart rate monitors, blood pressure monitors, thermometers, pedometers, sleep trackers, etc.) These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data.

[0749] Generative AI Models

[0750] The server preprocesses the collected data and inputs it into a generative AI model (e.g., a TensorFlow-based model). The generative AI model is based on machine learning algorithms and analyzes the care recipient's health and living conditions to predict specific abnormalities and risks. Based on the analysis results, a care plan is created that addresses the care recipient's individual needs.

[0751] Dedicated app

[0752] Users (caregivers and family members) using devices (smartphones and tablets) can check the generated care plan through a dedicated app and manage progress in real time. The dedicated app includes a function to display details, priorities, and progress of the care plan.

[0753] 2. Program Processing

[0754] Data collection and preprocessing

[0755] The server receives the data collected from the sensors and filters it for outliers and missing values. The collected data is stored in a database (e.g., MySQL or PostgreSQL) for subsequent analysis.

[0756] Data analysis

[0757] The server inputs the preprocessed data into a generative AI model to analyze the current health status of the care recipient, which then performs pattern recognition and anomaly detection to assess the care recipient's health risks.

[0758] Generate a care plan

[0759] Based on the analysis results of the generative AI model, the server generates an optimal nursing care plan, which includes necessary medical care, daily living assistance activities, and rehabilitation schedules.

[0760] Plan notification and management

[0761] The generated care plan is sent from the server to the device and displayed on a dedicated app, where the user can check the progress of the plan and record the action items that have been implemented.

[0762] Specific examples

[0763] For example, if data on heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) are obtained from sensors worn by care recipient A at 10:00 on October 10, the server collects this data and inputs it into the generative AI model. The AI ​​model detects that care recipient A's recent heart rate pattern is irregular and predicts that his stress level is increasing.

[0764] Based on the analysis results, the server generates a specific care plan, including a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplement intake. The plan is immediately sent to the device, and the user can check the plan through a dedicated app, perform deep breathing exercises at 11:00, and record this as "completed."

[0765] An example of a prompt is, "Based on the data of heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) obtained at 10:00 on October 10th, analyze the recent heart rate pattern of care recipient A and generate a specific care plan."

[0766] This system can monitor the health status of those in need of care in real time, quickly provide appropriate care plans, and reduce the burden on caregivers and families.

[0767] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0768] Step 1: Collect sensor data

[0769] The server obtains real-time health data from sensors worn by the care recipient (e.g., heart rate monitor, blood pressure monitor, thermometer, pedometer, sleep tracker, etc.) Input data from the sensors (e.g., heart rate 80 bpm) is received via Bluetooth or Wi-Fi.

[0770] Specific operation: The server receives the heart rate data (80 bpm) of care recipient A at 10:00 on October 10th, and transmits it to the data collection module.

[0771] Step 2: Preprocessing the data

[0772] The server filters the received data to remove outliers and missing values. This filtering process validates the collected input data (e.g., heart rate 80 bpm) and removes outliers (e.g., 0 bpm and 300 bpm). The preprocessed data is stored in a database.

[0773] Specific operation: The server checks whether the received heart rate data is within the correct range and whether there is any abnormal data, and then stores it in the MySQL database.

[0774] Step 3: Data analysis

[0775] The server inputs the preprocessed data into a generative AI model, which uses machine learning algorithms to analyze the care recipient's health condition. Based on the input data (e.g., heart rate data of 80 bpm, data from the past week), the generative AI model performs pattern recognition and anomaly detection to assess the care recipient's health risk.

[0776] Specific operation: The server inputs heart rate data into a TensorFlow-based generative AI model, analyzes irregularities in care recipient A's heart rate pattern, and predicts that his or her stress level may be high.

[0777] Step 4: Generate a care plan

[0778] The server generates an individualized care plan based on the analysis results of the generative AI model. This care plan includes schedules for necessary medical care, activities of daily living assistance, and rehabilitation. The generated plan is then stored in a database.

[0779] Specific operation: The server determines that the stress level of care recipient A is high, generates a care plan including a 20-minute morning walk, 5 minutes of deep breathing exercises, and taking vitamin D supplements, and saves it in the database.

[0780] Step 5: Plan Notification and Management

[0781] The server then notifies the device of the generated care plan, which then displays the plan details through a dedicated app, allowing the user to manage progress in real time.

[0782] Specific operation: The server sends the generated care plan to a smartphone, where the plan details can be displayed in a dedicated app, allowing progress to be managed.

[0783] Step 6: Real-time monitoring

[0784] Users can check the health status of their care recipients in real time using a dedicated app, which displays collected data and progress of care plans in real time.

[0785] Specific operation: The user checks the current heart rate and progress of the care plan for care recipient A using a dedicated app, and for example, performs deep breathing exercises at 11:00 and records this as "completed."

[0786] (Application example 1)

[0787] 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."

[0788] In modern factories, it is extremely important to monitor the health status of workers in real time and make appropriate work adjustments and break suggestions, and a system for this purpose is needed. However, current systems have difficulty quickly generating and notifying appropriate health management suggestions for individual workers, making it difficult to minimize worker health risks.

[0789] 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.

[0790] In this invention, the server includes means for collecting data from sensors worn by workers, means for executing a generative AI model that analyzes the collected data, means for generating appropriate health management suggestions based on the analysis results, means for notifying a dedicated app of the generated health management suggestions, means for managing the progress of the health management suggestions through the dedicated app, and means for adjusting the health management suggestions based on feedback. This makes it possible to monitor the health status of workers in real time, quickly provide appropriate health management suggestions, and improve the safety of the working environment.

[0791] "Essential workers" refer to workers who are responsible for certain tasks at work sites such as factories.

[0792] A "sensor" refers to a device that can measure physiological data such as heart rate, blood pressure, body temperature, number of steps, and sleep time, and transmit it as a digital signal.

[0793] A "generative AI model" refers to a machine learning algorithm that analyzes collected data and performs health status and risk assessments.

[0794] "Health management suggestions" refer to recommendations such as breaks and work adjustments that are generated for workers based on the analysis results of the generative AI model.

[0795] A "dedicated app" refers to software that allows workers and managers to check health management proposals and manage progress.

[0796] "Data collection means" refers to a system component that has the function of collecting physiological data from sensors and transmitting it to a server.

[0797] "Analysis means" refers to a system component that has the ability to analyze collected data based on a generative AI model.

[0798] "Notification means" refers to a system component that has the function of sending the generated health management suggestions to a dedicated app.

[0799] "Progress management means" refers to a system component that has the function of grasping and managing the implementation status of health management proposals through a dedicated app.

[0800] "Feedback means" refers to a system component that has the ability to adjust health management suggestions based on information obtained from a dedicated app.

[0801] The present invention aims to monitor the health status and work status of key workers in real time and provide individualized health management suggestions. Specifically, the system is composed of sensors, a generative AI model, and a dedicated application (hereinafter referred to as the dedicated app). Specific embodiments of the system of the present invention are described in detail below.

[0802] 1. System Configuration

[0803] sensor

[0804] The server collects real-time health data (heart rate, blood pressure, body temperature, number of steps, sleep time, etc.) from sensors worn by key workers. These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data. The sensors can be general wearable devices or dedicated devices for measuring specific physiological indicators.

[0805] Generative AI Models

[0806] The server inputs the collected data into a generative AI model, which uses machine learning algorithms such as TensorFlow and Scikit-learn to perform health and risk assessments of critical workers. The model performs pattern recognition and anomaly detection to predict worker stress and fatigue levels.

[0807] Dedicated app

[0808] The server sends health management suggestions generated based on the analysis results of the generative AI model to devices (smartphones and tablets). Users (workers and managers) can check these health management suggestions through a dedicated app and manage their progress in real time. The dedicated app includes a function to display the details, priority, and progress of health management suggestions. Users can also provide feedback, and this information is used to adjust the health management suggestions.

[0809] 2. Program Processing

[0810] The server receives the data collected from the sensors and filters it for outliers and missing values. The collected data is stored in a database for subsequent analysis. The server then inputs the preprocessed data into a generative AI model to analyze the worker's current health status.

[0811] This generative AI model generates optimal health management suggestions based on the analysis results. These suggestions include necessary breaks, work adjustments, and rehabilitation schedules. The generated health management suggestions are sent from the server to the device and displayed in a dedicated app. The user can check the progress of the suggestions through the dedicated app and record the action items that have been implemented.

[0812] For example, if data on heart rate (90 bpm), blood pressure (130 / 85 mmHg), and body temperature (37.0°C) are obtained from a sensor worn by essential worker A at 10:00 on October 10th, the server collects this data and inputs it into the generative AI model. The AI ​​model predicts that essential worker A's stress level is rising and generates a specific health management suggestion that "he should take a break." This suggestion is immediately sent to the device, and the user can confirm and implement the suggestion through a dedicated app.

[0813] 3. Example prompts

[0814] "Analyze the collected worker health data (heart rate: 90 bpm, blood pressure: 130 / 85 mmHg, body temperature: 37.0°C) and use a generative AI model to assess the stress level. Based on the assessment results, generate suggestions for appropriate break timing and work adjustments."

[0815] In this way, the present invention makes it possible to monitor the health status of workers in real time, quickly provide appropriate health management suggestions, and improve the safety of the work environment.

[0816] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0817] Step 1:

[0818] The server collects biometric data (heart rate, blood pressure, body temperature, number of steps, sleep time, etc.) from sensors. The sensors send the data to the server via Bluetooth or Wi-Fi. This input data is saved on the server in CSV or JSON format.

[0819] Step 2:

[0820] The server filters the received biometric data, specifically checking for missing values ​​and removing outliers, to generate a preprocessed dataset. The input is the raw dataset, and the output is the filtered dataset.

[0821] Step 3:

[0822] The server inputs the preprocessed data into a generative AI model, which is built using TensorFlow and Scikit-learn and performs health status analysis and risk assessment based on the input data. The input is the filtered dataset, and the output is the analysis results.

[0823] Step 4:

[0824] The server generates health management suggestions based on the analysis results of the generative AI model. Health management suggestions include specific actions such as "take a break," "hydrate," and "perform specific stretches." The input is the analysis results, and the output is the health management suggestions.

[0825] Step 5:

[0826] The server sends the generated health management suggestions to a device. The device consists of a smartphone or tablet with a dedicated app installed. The input is the health management suggestions, and the output is a notification to the device.

[0827] Step 6:

[0828] Users (workers and managers) check the health management suggestions through a dedicated app. They then carry out the suggested actions and record their progress in the app. The input is the health management suggestions, and the output is a record of the progress.

[0829] Step 7:

[0830] Feedback is sent from the dedicated app to the server, which evaluates the effectiveness of health management suggestions based on the feedback information and adjusts the suggestions as necessary. The input is progress and feedback, and the output is adjusted health management suggestions.

[0831] 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.

[0832] The system of the present invention monitors the health and living conditions of the care recipient in real time, provides an individual care plan, and also realizes more detailed care by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the system of the present invention will be described in detail below.

[0833] 1. System Configuration

[0834] sensor

[0835] The server collects real-time health data (heart rate, blood pressure, body temperature, walking distance, sleep time, etc.) from sensors worn by the care recipient. These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data.

[0836] Generative AI Models

[0837] The server inputs the collected data into a generative AI model, which is based on machine learning algorithms and analyzes the care recipient's health and lifestyle to predict specific abnormalities and risks. Based on the analysis results, a care plan is created that addresses the care recipient's individual needs.

[0838] Emotion Engine

[0839] The device is equipped with an emotion engine that identifies the emotions of users (caregivers and family members) through voice analysis and facial expression recognition. This emotion engine extracts emotion data from the user's voice and camera footage and sends it to the server as feedback.

[0840] Dedicated app

[0841] Users using a device (smartphone or tablet) can check the generated care plan through a dedicated app and manage progress in real time. The dedicated app includes functions to display details, priorities, and progress of the care plan. It also displays emotional data obtained by an emotion engine.

[0842] 2. Program Processing

[0843] Data collection and preprocessing

[0844] The server receives the data collected from the sensors and filters it for outliers and missing values, and the collected data is stored in a database for subsequent analysis.

[0845] Data analysis

[0846] The server inputs the preprocessed data into a generative AI model to analyze the current health status of the care recipient, which then performs pattern recognition and anomaly detection to assess the care recipient's health risks.

[0847] Generate a care plan

[0848] Based on the analysis results of the AI ​​model, the server generates an optimal nursing care plan, which includes necessary medical care, activities of daily living assistance, and rehabilitation schedules.

[0849] Emotion data collection and analysis

[0850] The device extracts emotional data from the user's voice and facial expressions. For example, a speech recognition engine identifies emotions such as joy, sadness, and anger from the user's speaking style and tone. The recognized emotional data is sent to the server in real time.

[0851] Plan notification and management

[0852] The generated care plan is sent from the server to the device and displayed on a dedicated app. The user can check the progress of the plan through the dedicated app and record the action items that have been implemented. In addition, emotion data obtained from the emotion engine can also be viewed within the app.

[0853] Feedback and plan adjustments

[0854] Users can send feedback through a dedicated app to report on the effectiveness of the care plan and areas for improvement. For example, they can provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the received feedback and emotional data and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can check the latest instructions.

[0855] Specific examples

[0856] For example, if data on heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) are obtained from sensors worn by care recipient A at 10:00 on October 10, the server collects this data and inputs it into the generative AI model. The AI ​​model detects that care recipient A's recent heart rate pattern is irregular and predicts that his stress level is increasing.

[0857] Based on the analysis results, the server generates a specific care plan, such as a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplements. The plan is immediately sent to the device, and the user can view it through a dedicated app.

[0858] In addition, the emotion engine identifies emotions from the user's tone of voice and camera footage, and if, for example, stress or anxiety is elevated, that information is displayed within the dedicated app. Users can check their emotional state in the dedicated app and request that parts of their care plan be readjusted if necessary.

[0859] This enables the system to monitor the health status of the care recipient and the emotional state of the caregiver or family member in real time, and provide appropriate care individually and quickly, thereby improving the quality of life of the care recipient and their caregiver.

[0860] The processing flow will be explained below.

[0861] Step 1: Data collection

[0862] The server collects real-time health data (heart rate, blood pressure, body temperature, walking distance, and sleep time) from sensors worn by the care recipient. These sensors communicate with the server via Bluetooth or Wi-Fi and periodically send data. For example, data is recorded in the format "October 10th, 10:00: Heart rate 80 bpm, blood pressure 120 / 80 mmHg, body temperature 36.5°C."

[0863] Step 2: Data Preprocessing

[0864] The server filters the collected data to identify outliers and missing values, removes incomplete data if present, imputes missing values ​​with the mean, and normalizes the data and converts it into a format suitable for analysis.

[0865] Step 3: Data analysis

[0866] The server inputs the preprocessed data into a generative AI model, which then uses machine learning algorithms to analyze the data and perform a health status and risk assessment of the care recipient. For example, the model might generate an analysis result such as, "Recent heart rate patterns have been irregular, and stress levels are high."

[0867] Step 4: Generate a care plan

[0868] The server generates an individualized care plan based on the analysis results of the AI ​​model. Specific plans include "a 20-minute morning walk," "5 minutes of deep breathing exercises," and "taking vitamin D supplements." The generated care plan is saved in a database and used in subsequent steps.

[0869] Step 5: Collecting sentiment data

[0870] The device analyzes the voice and facial expressions of the user (caregiver or family member) to collect emotional data. The emotion engine reads the tone of the voice, speaking style, and facial expressions from camera footage to identify the emotional state in real time. For example, the result may be, "The user's voice has a depressed tone, and anxiety is increasing."

[0871] Step 6: Notification of Emotion Data

[0872] The server stores the collected emotion data in a database in real time and sends it along with the analysis results to a dedicated app. The device displays the emotion data within the app, allowing the user to check the situation.

[0873] Step 7: Plan Notification and Management

[0874] The server sends the generated care plan to a dedicated app. The device displays each item in the plan in a timeline format and notifies the user. The user can check the progress of the plan through the dedicated app and record the action items that have been completed. For example, the user could enter "2023-10-10 11:00: 5 minutes of deep breathing exercises - completed."

[0875] Step 8: Feedback and Adjustments

[0876] Users send feedback through a dedicated app, reporting the effectiveness of the care plan and areas for improvement. For example, they may provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the feedback and emotional data and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can view the latest care plan.

[0877] This processing flow enables the system to monitor the health status of the care recipient and the emotional state of the caregiver and family in real time, and provide appropriate care plans individually and quickly, thereby improving the quality of life of the care recipient and their caregiver.

[0878] Example 2

[0879] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0880] In modern society, monitoring the health status of those requiring care in real time and providing appropriate care according to their circumstances is a crucial issue. However, conventional systems only collect and analyze the health data of those requiring care, and are unable to provide care plans that take into account the emotional state of the caregiver or family. This makes it difficult to provide attentive care, and improving the satisfaction of both the care recipient and the caregiver is a challenge.

[0881] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0882] In this invention, the server includes means for collecting data from a sensor worn by the care recipient, means for executing a generative AI model that analyzes the collected data, means for generating an individual nursing care plan based on the analysis results, means for notifying a dedicated app of the generated nursing care plan, means for managing the progress of the nursing care plan through the dedicated app, means for adjusting the nursing care plan based on feedback, a terminal equipped with an emotion engine that collects and analyzes user emotion data, and means for analyzing the emotion data and feeding it back to the dedicated app. This enables the provision of detailed and prompt care that takes into account both the health state of the care recipient and the emotional states of the caregiver and family.

[0883] "Individuals requiring care" refers to elderly people or individuals with illnesses or disabilities who require assistance with daily living or medical care.

[0884] "Sensors" refer to devices used to measure and collect data on the health status of care recipients, including devices that measure heart rate, blood pressure, body temperature, walking distance, sleep time, etc. in real time.

[0885] "Server" refers to a computer system that receives data collected from sensors and processes and analyzes it.

[0886] A "generative AI model" refers to a machine learning model that analyzes the health condition of a person requiring care based on collected data and generates an appropriate nursing care plan.

[0887] A "nursing care plan" refers to a specific action plan that includes medical care, assistance with daily life, rehabilitation schedules, etc., according to the health condition of the person requiring care.

[0888] "Dedicated app" refers to a software application that displays the generated nursing care plan and allows the user to manage its progress.

[0889] An "emotion engine" is a technology that collects and analyzes emotional data from the user's voice and facial expressions, and sends it to a server as feedback.

[0890] "User" refers to an individual, including a caregiver or family member providing nursing care.

[0891] "Feedback" refers to information provided by the user, including data on the effectiveness of the care plan and areas for improvement.

[0892] The present invention is a system for monitoring the health and living conditions of a person requiring care in real time and providing an individualized care plan. Specific embodiments of this system will be described in detail below.

[0893] System Configuration

[0894] The system consists of a sensor worn by the care recipient, a server that analyzes the data, a device that collects emotional data, and a dedicated app that manages the generated care plan.

[0895] sensor

[0896] The server collects real-time data from sensors worn by the care recipient. The sensors then transmit the data to the server via Bluetooth or Wi-Fi. The collected data includes multiple health indicators such as heart rate, blood pressure, body temperature, walking distance, and sleep time.

[0897] Data analysis

[0898] The server receives the collected health data and runs a generative AI model to analyze it. The generative AI model is based on machine learning algorithms to assess the care recipient's health status and risks. For example, it analyzes irregular heart rate patterns and blood pressure fluctuations to predict the care recipient's health risks. Based on the analysis results, an individualized care plan is generated.

[0899] Care plan generation and notification

[0900] Based on the analysis results of the AI ​​model, the server generates a specific action plan, such as "a 20-minute morning walk," "five minutes of deep breathing exercises," or "taking vitamin D supplements." The generated care plan is then sent to a dedicated app.

[0901] Collecting Emotional Data

[0902] The device collects emotional data from the user's voice and facial expressions. It uses a voice analysis engine and a camera to identify emotions such as joy, sadness, and anger from the user's speaking style, tone, and facial expressions. This emotional data is sent to a server in real time.

[0903] Dedicated app functions

[0904] Users using a device (smartphone or tablet) can check the generated care plan through a dedicated app and manage progress in real time. The app also includes a function to report results and areas for improvement as feedback. For example, users can send feedback such as, "My physical condition did not improve after rehabilitation exercises."

[0905] Specific examples

[0906] For example, if heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) data are obtained from a sensor worn by care recipient A at 10:00 on October 10th, the server collects this data and inputs it into the generative AI model. The generative AI model detects that care recipient A's recent heart rate pattern is irregular and predicts that his or her stress level is increasing. Based on the results of this analysis, the server generates a specific care plan that includes "a 20-minute morning walk," "five minutes of deep breathing exercises," and "taking vitamin D supplements." The generated plan is immediately sent to the device, and the user can check the plan through a dedicated app.

[0907] Prompt Sentence Examples

[0908] Below are some examples of specific prompts to input to a generative AI model:

[0909] "Based on recent data, care recipient A's heart rate is irregular, and their blood pressure and temperature are within normal ranges. However, we have recognized a pattern that suggests their stress levels may be increasing. Please generate an appropriate care plan, including specific care items and how to implement them."

[0910] Based on this prompt, the AI ​​model generates an individualized nursing care plan.

[0911] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0912] Step 1: Data collection and preprocessing

[0913] The server receives data in real time from sensors worn by the care recipient. The sensors measure health indicators such as heart rate, blood pressure, body temperature, walking distance, and sleep time, and transmit the data to the server via Bluetooth or Wi-Fi. The received data is stored in a database and checked for outliers and missing values. For example, if the heart rate data sent from the sensor is irregular, the data is filtered.

[0914] Input: Real-time data from sensors

[0915] Output: Filtered health data

[0916] Step 2: Data analysis

[0917] The server inputs the preprocessed data into a generative AI model, which uses machine learning algorithms to analyze the care recipient's health status and detect specific patterns or abnormalities. For example, it analyzes heart rate data from the past week to detect irregular heart rate patterns. The analysis results are stored on the server.

[0918] Input: Preprocessed health data

[0919] Output: Health status analysis results

[0920] Step 3: Generate a care plan

[0921] The server generates an optimal care plan based on the analysis results. This care plan includes specific care items (e.g., a 20-minute morning walk, 5 minutes of deep breathing exercises, vitamin D supplement intake) and how to implement them. The generated plan is notified to the dedicated app.

[0922] Input: Health status analysis results

[0923] Output: Generated nursing care plan

[0924] Step 4: Collect and analyze emotion data

[0925] The device collects the voice and facial expressions of the user (caregiver or family member) and analyzes the emotional data. It uses a voice analysis engine and a camera to identify the user's emotions and sends the emotional data to the server. For example, it can detect whether the user is feeling stressed from the tone of their voice.

[0926] Input: User's voice and facial expression data

[0927] Output: Emotional state analysis results

[0928] Step 5: Plan Notification and Management

[0929] The generated care plan is sent from the server to the device and displayed on a dedicated app. The user manages the progress of the plan through the app and records the care items that have been carried out. For example, the user can record on the app that "a 20-minute morning walk was carried out."

[0930] Input: Generated nursing care plan

[0931] Output: Display of care plan and progress management on dedicated app

[0932] Step 6: Feedback and plan adjustments

[0933] The user provides feedback through a dedicated app. For example, they may provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the feedback and emotional data and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can check the latest instructions.

[0934] Input: User feedback

[0935] Output: Coordinated nursing care plan

[0936] (Application example 2)

[0937] 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."

[0938] In today's world, health management for those requiring care has become an important issue, but conventional systems have been unable to provide adequate individualized care and have made it difficult to provide care that takes into account the emotional state of caregivers and their families. Furthermore, systems for providing prompt and appropriate responses in emergencies were also inadequate. As a result, there was a risk of sudden changes in the health status of those requiring care and an increased burden on caregivers and their families.

[0939] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0940] In this invention, the server includes means for collecting data from a sensor worn by the care recipient, means for executing a generative AI model that analyzes the collected data, means for generating an individualized care plan based on the analysis results, means for notifying a dedicated app of the generated care plan, means for managing the progress of the care plan through the dedicated app, means for using an emotion engine that extracts emotion data from the user's voice and facial expressions, means for automatically notifying in an emergency based on the emotion data, and means for adjusting the care plan based on feedback. This makes it possible to monitor the health condition of the care recipient and the emotion state of the caregiver and family in real time and quickly provide an individualized and appropriate care plan.

[0941] A "sensor" is a device worn on the body that collects health-related data such as heart rate, blood pressure, and body temperature in real time.

[0942] A "generative AI model" is software that contains machine learning algorithms to analyze collected health data and predict abnormal patterns and risks.

[0943] A "nursing care plan" is a plan that individually defines the necessary medical care and daily life support activities for a person in need of nursing care, based on the analysis results of the generated AI model.

[0944] The "dedicated app" is an application used by the person requiring care and their caregiver on a smartphone or tablet, and is a platform for checking the generated care plan and managing its progress.

[0945] The "emotion engine" is a technology that analyzes the voices and facial expressions of caregivers and family members to identify their emotional state.

[0946] "Feedback" refers to information provided by users through a dedicated app regarding the effectiveness of nursing care plans and areas for improvement.

[0947] "Emergency notification" is a means of automatically transmitting information to emergency contacts and medical services when an abnormality is detected.

[0948] "Health status" refers to the physical condition of the care recipient, including heart rate, blood pressure, and body temperature, and is analyzed by the generative AI model.

[0949] "Progress management" is the process by which users check the progress of their nursing care plan through a dedicated app and record any necessary actions.

[0950] The present invention is a system that monitors the health status of a care recipient in real time and provides a personalized care plan, which can also take into account the emotional state of the caregiver and family. The configuration and operation of the system are described in detail below.

[0951] System Configuration

[0952] The system consists of the following main components:

[0953] 1. Sensors: Collect health data such as heart rate, blood pressure, and body temperature, and send the data to a server via Bluetooth or Wi-Fi.

[0954] 2. Server: Receives health data, analyzes it using a generative AI model, generates a care plan, and analyzes the user's emotional state using an emotion engine and stores the results.

[0955] 3. Dedicated app: Runs on smartphones and tablets, displays the generated nursing care plan and emotional data, and manages progress and provides feedback.

[0956] Program processing

[0957] Data collection and preprocessing

[0958] The server receives real-time health data from sensors. The collected data is filtered for outliers and missing values ​​and stored in a database. This processing is performed using internet-connected wearable devices (e.g., Fitbit, Apple Watch) for hardware and cloud computing services (e.g., AWS, Google Cloud) for the server.

[0959] Data analysis and care plan generation

[0960] The server inputs the collected and preprocessed data into a generative AI model to analyze the health status of the care recipient. The generative AI model includes machine learning algorithms for pattern recognition and risk assessment. Based on the analysis results, an individual care plan is generated. This is done using a database (e.g., MySQL, PostgreSQL).

[0961] Emotion data collection and analysis

[0962] The device extracts the user's emotional data using an emotion engine that recognizes voice and facial expressions. This emotion engine uses voice analysis and facial expression recognition technologies (e.g., Microsoft Azure Cognitive Services and Google Cloud AI). The collected emotional data is sent to a server and analyzed together with health data.

[0963] Emergency notifications and progress management

[0964] If an abnormality is detected based on the health data, the server automatically notifies emergency contacts and medical services. The generated care plan is sent to a dedicated app, allowing the user to manage the progress. The dedicated app is used on smartphones or tablets (e.g., iPhones and Android devices).

[0965] Specific examples

[0966] For example, if heart rate (80 bpm), blood pressure (130 / 85 mmHg), and body temperature (36.7°C) data are acquired from a sensor worn by care recipient A, the server analyzes this data and detects that recent heart rate fluctuations have increased. As a result, it generates a care plan to relieve stress, such as "10 minutes of deep breathing exercises" and "15 minutes of relaxation music." Furthermore, if the device's camera is used to detect caregiver B's facial expressions and the emotion engine identifies a high stress level, it suggests a guided meditation for relaxation using a dedicated app.

[0967] Example prompts for generative AI models

[0968] "Please explain health monitoring for nursing care systems, and methods for detecting abnormal patterns and generating appropriate care plans based on large amounts of heart rate, blood pressure, and temperature data."

[0969] As a result, the present invention makes it possible to monitor the health condition of the care recipient and the emotional state of the caregiver and family in real time, and to quickly provide an individual and appropriate care plan.

[0970] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0971] Step 1:

[0972] The sensors collect real-time health data such as the heart rate, blood pressure, and body temperature of the care recipient, and the collected data is sent to a server via Bluetooth or Wi-Fi.

[0973] Input: Health data (heart rate, blood pressure, temperature, etc.)

[0974] Output: Send data to the server (heart rate, blood pressure, body temperature)

[0975] Step 2:

[0976] The server filters the data received from the sensors, detects and corrects outliers and missing values, and stores the corrected data in a database.

[0977] Input: Data sent from the sensor

[0978] Output: Save the corrected health data to the database.

[0979] Step 3:

[0980] The server inputs the corrected data into the generative AI model to analyze the health status of the care recipient, which then recognizes abnormal patterns and risks based on the collected data.

[0981] Input: Corrected health data

[0982] Output: Health status analysis results

[0983] Step 4:

[0984] The server generates an individualized care plan for the care recipient based on the analysis results of the generative AI model, which includes necessary medical care and activities to support daily living.

[0985] Input: Health status analysis results

[0986] Output: Generated nursing care plan

[0987] Step 5:

[0988] The generated care plan is sent from the server to the device, and the user can check the plan contents using a dedicated app that runs on a smartphone or tablet.

[0989] Input: Generated nursing care plan

[0990] Output: Plan display on dedicated app

[0991] Step 6:

[0992] The device uses an emotion engine to analyze the user's voice and facial expressions, extracting emotional data, which is then sent to a server in real time.

[0993] Input: Voice data, facial expression data

[0994] Output: Extract emotion data and send it to the server

[0995] Step 7:

[0996] Based on the analyzed emotional data, the server automatically notifies emergency contacts and medical services in the event of an emergency, enabling a prompt response.

[0997] Input: Emotion data, health data

[0998] Output: Urgent notification

[0999] Step 8:

[1000] Users provide feedback and manage progress on their care plans through a dedicated app, which provides an interface for users to view progress and record any necessary actions.

[1001] Input: Feedback, progress data

[1002] Output: Feedback and progress recording

[1003] Step 9:

[1004] The server reevaluates the care plan based on user feedback and new emotional data, adjusts the plan as needed, and sends the adjusted plan back to the device.

[1005] Input: Feedback, emotion data

[1006] Output: Coordinated care plan

[1007] This enables the system to monitor the health status of the care recipient and the emotional state of the caregiver or family member in real time, providing appropriate care individually and quickly.

[1008] 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.

[1009] 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.

[1010] 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.

[1011] [Fourth embodiment]

[1012] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1013] 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.

[1014] 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).

[1015] 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.

[1016] 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.

[1017] 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).

[1018] 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.

[1019] 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.

[1020] 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.

[1021] 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.

[1022] 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.

[1023] 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.

[1024] 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."

[1025] The system of the present invention aims to monitor the health and living conditions of a person requiring care in real time and provide an individualized care plan. This system is composed of sensors, a generative AI model, and a dedicated application (hereinafter referred to as the dedicated app). Specific embodiments of the system of the present invention will be described in detail below.

[1026] 1. System Configuration

[1027] sensor

[1028] The server collects real-time health data (heart rate, blood pressure, body temperature, walking distance, sleep time, etc.) from sensors worn by the care recipient. These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data.

[1029] Generative AI Models

[1030] The server inputs the collected data into a generative AI model, which is based on machine learning algorithms that analyze the care recipient's health and lifestyle conditions to predict specific abnormalities and risks. Based on the analysis results, a care plan is created that addresses the care recipient's individual needs.

[1031] Dedicated app

[1032] Users (caregivers and family members) using devices (smartphones and tablets) can check the generated care plan through a dedicated app and manage progress in real time. The dedicated app includes a function to display details, priorities, and progress of the care plan.

[1033] 2. Program Processing

[1034] Data collection and preprocessing

[1035] The server receives the data collected from the sensors and filters it for outliers and missing values, and the collected data is stored in a database for subsequent analysis.

[1036] Data analysis

[1037] The server inputs the preprocessed data into a generative AI model to analyze the current health status of the care recipient, which then performs pattern recognition and anomaly detection to assess the care recipient's health risks.

[1038] Generate a care plan

[1039] Based on the analysis results of the AI ​​model, the server generates an optimal nursing care plan, which includes necessary medical care, activities of daily living assistance, and rehabilitation schedules.

[1040] Plan notification and management

[1041] The generated care plan is sent from the server to the device and displayed on a dedicated app, where the user can check the progress of the plan and record the action items that have been implemented.

[1042] Specific examples

[1043] For example, if data on heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) are obtained from sensors worn by care recipient A at 10:00 on October 10, the server collects this data and inputs it into the generative AI model. The AI ​​model detects that care recipient A's recent heart rate pattern is irregular and predicts that his stress level is increasing.

[1044] Based on the analysis results, the server generates a specific care plan, including a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplement intake. The plan is immediately sent to the device, and the user can check the plan through a dedicated app, perform deep breathing exercises at 11:00, and record this as "completed."

[1045] This enables the system to monitor the health status of those in need of care in real time, quickly provide appropriate care plans, and reduce the burden on caregivers and family members.

[1046] The processing flow will be explained below.

[1047] Step 1: Data collection

[1048] The server collects data in real time from sensors worn by the care recipient. Information such as heart rate, blood pressure, body temperature, walking distance, and sleep time is received via Bluetooth or Wi-Fi. The collected data is stored in a database with a timestamp. For example, the server might record "October 10th, 10:00: Heart rate 80 bpm, blood pressure 120 / 80 mmHg, body temperature 36.5°C."

[1049] Step 2: Data Preprocessing

[1050] The server converts the collected data into a format suitable for analysis. If there are incomplete data or outliers, filtering is performed. For example, data with abnormal heart rates (extremely high or low values) is removed. After filtering, the data is normalized and missing values ​​are imputed with the mean.

[1051] Step 3: Data analysis

[1052] The server inputs the preprocessed data into the generative AI model, which then uses machine learning algorithms to analyze the data and predict the care recipient's health status and trends. For example, the result might be, "Care recipient A's recent heart rate has been irregular, suggesting a high level of mental stress."

[1053] Step 4: Generate a care plan

[1054] The server generates an individualized care plan based on the analysis results. This plan includes necessary medical care, activities of daily living assistance, a rehabilitation schedule, and minor lifestyle changes. Specific recommendations include a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplementation.

[1055] Step 5: Plan Notification

[1056] The server sends the generated nursing care plan to a dedicated app. Each item in the plan is displayed in a timeline format and prioritized. Users (caregivers and family members) using devices (smartphones and tablets) are notified that the plan is available.

[1057] Step 6: Implement and manage the plan

[1058] The user on the device opens the dedicated app and checks the care plan. As each action item is implemented, progress is recorded within the app. For example, the user might enter "2023-10-10 11:00: 5 minutes of deep breathing exercises - completed." The server receives real-time feedback from the dedicated app and records it in a database.

[1059] Step 7: Feedback and plan adjustments

[1060] Users can send feedback through a dedicated app to report on the effectiveness of the care plan and areas for improvement. For example, they can provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the received feedback and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can check the latest instructions.

[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 robot 414 will be referred to as a "terminal."

[1063] Current nursing care systems make it difficult to monitor the health status of care recipients in real time and provide appropriate care plans immediately. Furthermore, if the collected data is analyzed without properly handling outliers or missing values, accurate analysis results cannot be obtained. Furthermore, if the generated nursing care plan is not optimized to the individual needs of the care recipient, the quality of care may decline and the burden on caregivers and families may increase.

[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 means for collecting data from sensors worn by the care recipient, means for filtering the collected data to remove outliers and missing values, means for inputting the preprocessed data into a generative AI model and analyzing health conditions and risks, means for generating an individual nursing care plan based on the analysis results, means for notifying a terminal of the generated nursing care plan, and means for managing the progress of the care plan through a dedicated app and adjusting the care plan based on feedback. This makes it possible to accurately monitor the health condition of the care recipient in real time, quickly provide an appropriate nursing care plan, and reduce the burden on caregivers and family members.

[1066] A "sensor" is a device that measures health data (heart rate, blood pressure, body temperature, walking distance, sleep time, etc.) of a person requiring care and transmits it to a server.

[1067] The "server" is a computing device that receives and stores data collected from sensors, preprocesses and analyzes the data, and generates and notifies nursing care plans.

[1068] "Filtering" is a process that removes outliers and missing values ​​from collected data to provide accurate data to generative AI models.

[1069] A "generative AI model" is a model that uses machine learning algorithms to analyze the health status and risks of individuals requiring care based on preprocessed health data and propose care plans.

[1070] A "nursing care plan" is a set of specific instructions based on the analysis results of the generated AI model, including the medical care, daily life support activities, and rehabilitation schedule that should be provided to the person in need of care.

[1071] The "terminal" is a device (smartphone or tablet) that notifies the caregiver of the created care plan and allows the caregiver or family member to check and manage the plan details through a dedicated app.

[1072] The "dedicated app" is software that allows caregivers and family members to check plan details, manage progress, and enter feedback.

[1073] "Real-time" refers to a situation in which data is collected and processed almost immediately, providing information in a timely manner.

[1074] "Feedback" refers to information provided by caregivers and family members through a dedicated app, and includes information on the implementation status and effectiveness of the generated nursing care plan.

[1075] The present invention relates to a system that monitors the health and living conditions of a person requiring care in real time and provides an individualized care plan. This system is configured using sensors, a generative AI model, and a dedicated application (hereinafter referred to as the dedicated app). Specific embodiments of the system of the present invention are described in detail below.

[1076] 1. System Configuration

[1077] sensor

[1078] The server collects real-time health data from sensors worn by the care recipient (e.g., heart rate monitors, blood pressure monitors, thermometers, pedometers, sleep trackers, etc.) These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data.

[1079] Generative AI Models

[1080] The server preprocesses the collected data and inputs it into a generative AI model (e.g., a TensorFlow-based model). The generative AI model is based on machine learning algorithms and analyzes the care recipient's health and living conditions to predict specific abnormalities and risks. Based on the analysis results, a care plan is created that addresses the care recipient's individual needs.

[1081] Dedicated app

[1082] Users (caregivers and family members) using devices (smartphones and tablets) can check the generated care plan through a dedicated app and manage progress in real time. The dedicated app includes a function to display details, priorities, and progress of the care plan.

[1083] 2. Program Processing

[1084] Data collection and preprocessing

[1085] The server receives the data collected from the sensors and filters it for outliers and missing values. The collected data is stored in a database (e.g., MySQL or PostgreSQL) for subsequent analysis.

[1086] Data analysis

[1087] The server inputs the preprocessed data into a generative AI model to analyze the current health status of the care recipient, which then performs pattern recognition and anomaly detection to assess the care recipient's health risks.

[1088] Generate a care plan

[1089] Based on the analysis results of the generative AI model, the server generates an optimal nursing care plan, which includes necessary medical care, daily living assistance activities, and rehabilitation schedules.

[1090] Plan notification and management

[1091] The generated care plan is sent from the server to the device and displayed on a dedicated app, where the user can check the progress of the plan and record the action items that have been implemented.

[1092] Specific examples

[1093] For example, if data on heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) are obtained from sensors worn by care recipient A at 10:00 on October 10, the server collects this data and inputs it into the generative AI model. The AI ​​model detects that care recipient A's recent heart rate pattern is irregular and predicts that his stress level is increasing.

[1094] Based on the analysis results, the server generates a specific care plan, including a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplement intake. The plan is immediately sent to the device, and the user can check the plan through a dedicated app, perform deep breathing exercises at 11:00, and record this as "completed."

[1095] An example of a prompt is, "Based on the data of heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) obtained at 10:00 on October 10th, analyze the recent heart rate pattern of care recipient A and generate a specific care plan."

[1096] This system can monitor the health status of those in need of care in real time, quickly provide appropriate care plans, and reduce the burden on caregivers and families.

[1097] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1098] Step 1: Collect sensor data

[1099] The server obtains real-time health data from sensors worn by the care recipient (e.g., heart rate monitor, blood pressure monitor, thermometer, pedometer, sleep tracker, etc.) Input data from the sensors (e.g., heart rate 80 bpm) is received via Bluetooth or Wi-Fi.

[1100] Specific operation: The server receives the heart rate data (80 bpm) of care recipient A at 10:00 on October 10th, and transmits it to the data collection module.

[1101] Step 2: Preprocessing the data

[1102] The server filters the received data to remove outliers and missing values. This filtering process validates the collected input data (e.g., heart rate 80 bpm) and removes outliers (e.g., 0 bpm and 300 bpm). The preprocessed data is stored in a database.

[1103] Specific operation: The server checks whether the received heart rate data is within the correct range and whether there is any abnormal data, and then stores it in the MySQL database.

[1104] Step 3: Data analysis

[1105] The server inputs the preprocessed data into a generative AI model, which uses machine learning algorithms to analyze the care recipient's health condition. Based on the input data (e.g., heart rate data of 80 bpm, data from the past week), the generative AI model performs pattern recognition and anomaly detection to assess the care recipient's health risk.

[1106] Specific operation: The server inputs heart rate data into a TensorFlow-based generative AI model, analyzes irregularities in care recipient A's heart rate pattern, and predicts that his or her stress level may be high.

[1107] Step 4: Generate a care plan

[1108] The server generates an individualized care plan based on the analysis results of the generative AI model. This care plan includes schedules for necessary medical care, activities of daily living assistance, and rehabilitation. The generated plan is then stored in a database.

[1109] Specific operation: The server determines that the stress level of care recipient A is high, generates a care plan including a 20-minute morning walk, 5 minutes of deep breathing exercises, and taking vitamin D supplements, and saves it in the database.

[1110] Step 5: Plan Notification and Management

[1111] The server then notifies the device of the generated care plan, which then displays the plan details through a dedicated app, allowing the user to manage progress in real time.

[1112] Specific operation: The server sends the generated care plan to a smartphone, where the plan details can be displayed in a dedicated app, allowing progress to be managed.

[1113] Step 6: Real-time monitoring

[1114] Users can check the health status of their care recipients in real time using a dedicated app, which displays collected data and progress of care plans in real time.

[1115] Specific operation: The user checks the current heart rate and progress of the care plan for care recipient A using a dedicated app, and for example, performs deep breathing exercises at 11:00 and records this as "completed."

[1116] (Application example 1)

[1117] 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."

[1118] In modern factories, it is extremely important to monitor the health status of workers in real time and make appropriate work adjustments and break suggestions, and a system for this purpose is needed. However, current systems have difficulty quickly generating and notifying appropriate health management suggestions for individual workers, making it difficult to minimize worker health risks.

[1119] 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.

[1120] In this invention, the server includes means for collecting data from sensors worn by workers, means for executing a generative AI model that analyzes the collected data, means for generating appropriate health management suggestions based on the analysis results, means for notifying a dedicated app of the generated health management suggestions, means for managing the progress of the health management suggestions through the dedicated app, and means for adjusting the health management suggestions based on feedback. This makes it possible to monitor the health status of workers in real time, quickly provide appropriate health management suggestions, and improve the safety of the working environment.

[1121] "Essential workers" refer to workers who are responsible for certain tasks at work sites such as factories.

[1122] A "sensor" refers to a device that can measure physiological data such as heart rate, blood pressure, body temperature, number of steps, and sleep time, and transmit it as a digital signal.

[1123] A "generative AI model" refers to a machine learning algorithm that analyzes collected data and performs health status and risk assessments.

[1124] "Health management suggestions" refer to recommendations such as breaks and work adjustments that are generated for workers based on the analysis results of the generative AI model.

[1125] A "dedicated app" refers to software that allows workers and managers to check health management proposals and manage progress.

[1126] "Data collection means" refers to a system component that has the function of collecting physiological data from sensors and transmitting it to a server.

[1127] "Analysis means" refers to a system component that has the ability to analyze collected data based on a generative AI model.

[1128] "Notification means" refers to a system component that has the function of sending the generated health management suggestions to a dedicated app.

[1129] "Progress management means" refers to a system component that has the function of grasping and managing the implementation status of health management proposals through a dedicated app.

[1130] "Feedback means" refers to a system component that has the ability to adjust health management suggestions based on information obtained from a dedicated app.

[1131] The present invention aims to monitor the health status and work status of key workers in real time and provide individualized health management suggestions. Specifically, the system is composed of sensors, a generative AI model, and a dedicated application (hereinafter referred to as the dedicated app). Specific embodiments of the system of the present invention are described in detail below.

[1132] 1. System Configuration

[1133] sensor

[1134] The server collects real-time health data (heart rate, blood pressure, body temperature, number of steps, sleep time, etc.) from sensors worn by key workers. These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data. The sensors can be general wearable devices or dedicated devices for measuring specific physiological indicators.

[1135] Generative AI Models

[1136] The server inputs the collected data into a generative AI model, which uses machine learning algorithms such as TensorFlow and Scikit-learn to perform health and risk assessments of critical workers. The model performs pattern recognition and anomaly detection to predict worker stress and fatigue levels.

[1137] Dedicated app

[1138] The server sends health management suggestions generated based on the analysis results of the generative AI model to devices (smartphones and tablets). Users (workers and managers) can check these health management suggestions through a dedicated app and manage their progress in real time. The dedicated app includes a function to display the details, priority, and progress of health management suggestions. Users can also provide feedback, and this information is used to adjust the health management suggestions.

[1139] 2. Program Processing

[1140] The server receives the data collected from the sensors and filters it for outliers and missing values. The collected data is stored in a database for subsequent analysis. The server then inputs the preprocessed data into a generative AI model to analyze the worker's current health status.

[1141] This generative AI model generates optimal health management suggestions based on the analysis results. These suggestions include necessary breaks, work adjustments, and rehabilitation schedules. The generated health management suggestions are sent from the server to the device and displayed in a dedicated app. The user can check the progress of the suggestions through the dedicated app and record the action items that have been implemented.

[1142] For example, if data on heart rate (90 bpm), blood pressure (130 / 85 mmHg), and body temperature (37.0°C) are obtained from a sensor worn by essential worker A at 10:00 on October 10th, the server collects this data and inputs it into the generative AI model. The AI ​​model predicts that essential worker A's stress level is rising and generates a specific health management suggestion that "he should take a break." This suggestion is immediately sent to the device, and the user can confirm and implement the suggestion through a dedicated app.

[1143] 3. Example prompts

[1144] "Analyze the collected worker health data (heart rate: 90 bpm, blood pressure: 130 / 85 mmHg, body temperature: 37.0°C) and use a generative AI model to assess the stress level. Based on the assessment results, generate suggestions for appropriate break timing and work adjustments."

[1145] In this way, the present invention makes it possible to monitor the health status of workers in real time, quickly provide appropriate health management suggestions, and improve the safety of the work environment.

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

[1147] Step 1:

[1148] The server collects biometric data (heart rate, blood pressure, body temperature, number of steps, sleep time, etc.) from sensors. The sensors send the data to the server via Bluetooth or Wi-Fi. This input data is saved on the server in CSV or JSON format.

[1149] Step 2:

[1150] The server filters the received biometric data, specifically checking for missing values ​​and removing outliers, to generate a preprocessed dataset. The input is the raw dataset, and the output is the filtered dataset.

[1151] Step 3:

[1152] The server inputs the preprocessed data into a generative AI model, which is built using TensorFlow and Scikit-learn and performs health status analysis and risk assessment based on the input data. The input is the filtered dataset, and the output is the analysis results.

[1153] Step 4:

[1154] The server generates health management suggestions based on the analysis results of the generative AI model. Health management suggestions include specific actions such as "take a break," "hydrate," and "perform specific stretches." The input is the analysis results, and the output is the health management suggestions.

[1155] Step 5:

[1156] The server sends the generated health management suggestions to a device. The device consists of a smartphone or tablet with a dedicated app installed. The input is the health management suggestions, and the output is a notification to the device.

[1157] Step 6:

[1158] Users (workers and managers) check the health management suggestions through a dedicated app. They then carry out the suggested actions and record their progress in the app. The input is the health management suggestions, and the output is a record of the progress.

[1159] Step 7:

[1160] Feedback is sent from the dedicated app to the server, which evaluates the effectiveness of health management suggestions based on the feedback information and adjusts the suggestions as necessary. The input is progress and feedback, and the output is adjusted health management suggestions.

[1161] 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.

[1162] The system of the present invention monitors the health and living conditions of the care recipient in real time, provides an individual care plan, and also realizes more detailed care by combining it with an emotion engine that recognizes the user's emotions. Specific embodiments of the system of the present invention will be described in detail below.

[1163] 1. System Configuration

[1164] sensor

[1165] The server collects real-time health data (heart rate, blood pressure, body temperature, walking distance, sleep time, etc.) from sensors worn by the care recipient. These sensors communicate with the server via Bluetooth or Wi-Fi and continuously transmit data.

[1166] Generative AI Models

[1167] The server inputs the collected data into a generative AI model, which is based on machine learning algorithms and analyzes the care recipient's health and lifestyle to predict specific abnormalities and risks. Based on the analysis results, a care plan is created that addresses the care recipient's individual needs.

[1168] Emotion Engine

[1169] The device is equipped with an emotion engine that identifies the emotions of users (caregivers and family members) through voice analysis and facial expression recognition. This emotion engine extracts emotion data from the user's voice and camera footage and sends it to the server as feedback.

[1170] Dedicated app

[1171] Users using a device (smartphone or tablet) can check the generated care plan through a dedicated app and manage progress in real time. The dedicated app includes functions to display details, priorities, and progress of the care plan. It also displays emotional data obtained by an emotion engine.

[1172] 2. Program Processing

[1173] Data collection and preprocessing

[1174] The server receives the data collected from the sensors and filters it for outliers and missing values, and the collected data is stored in a database for subsequent analysis.

[1175] Data analysis

[1176] The server inputs the preprocessed data into a generative AI model to analyze the current health status of the care recipient, which then performs pattern recognition and anomaly detection to assess the care recipient's health risks.

[1177] Generate a care plan

[1178] Based on the analysis results of the AI ​​model, the server generates an optimal nursing care plan, which includes necessary medical care, activities of daily living assistance, and rehabilitation schedules.

[1179] Emotion data collection and analysis

[1180] The device extracts emotional data from the user's voice and facial expressions. For example, a speech recognition engine identifies emotions such as joy, sadness, and anger from the user's speaking style and tone. The recognized emotional data is sent to the server in real time.

[1181] Plan notification and management

[1182] The generated care plan is sent from the server to the device and displayed on a dedicated app. The user can check the progress of the plan through the dedicated app and record the action items that have been implemented. In addition, emotion data obtained from the emotion engine can also be viewed within the app.

[1183] Feedback and plan adjustments

[1184] Users can send feedback through a dedicated app to report on the effectiveness of the care plan and areas for improvement. For example, they can provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the received feedback and emotional data and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can check the latest instructions.

[1185] Specific examples

[1186] For example, if data on heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) are obtained from sensors worn by care recipient A at 10:00 on October 10, the server collects this data and inputs it into the generative AI model. The AI ​​model detects that care recipient A's recent heart rate pattern is irregular and predicts that his stress level is increasing.

[1187] Based on the analysis results, the server generates a specific care plan, such as a 20-minute morning walk, five minutes of deep breathing exercises, and vitamin D supplements. The plan is immediately sent to the device, and the user can view it through a dedicated app.

[1188] In addition, the emotion engine identifies emotions from the user's tone of voice and camera footage, and if, for example, stress or anxiety is elevated, that information is displayed within the dedicated app. Users can check their emotional state in the dedicated app and request that parts of their care plan be readjusted if necessary.

[1189] This enables the system to monitor the health status of the care recipient and the emotional state of the caregiver or family member in real time, and provide appropriate care individually and quickly, thereby improving the quality of life of the care recipient and their caregiver.

[1190] The processing flow will be explained below.

[1191] Step 1: Data collection

[1192] The server collects real-time health data (heart rate, blood pressure, body temperature, walking distance, and sleep time) from sensors worn by the care recipient. These sensors communicate with the server via Bluetooth or Wi-Fi and periodically send data. For example, data is recorded in the format "October 10th, 10:00: Heart rate 80 bpm, blood pressure 120 / 80 mmHg, body temperature 36.5°C."

[1193] Step 2: Data Preprocessing

[1194] The server filters the collected data to identify outliers and missing values, removes incomplete data if present, imputes missing values ​​with the mean, and normalizes the data and converts it into a format suitable for analysis.

[1195] Step 3: Data analysis

[1196] The server inputs the preprocessed data into a generative AI model, which then uses machine learning algorithms to analyze the data and perform a health status and risk assessment of the care recipient. For example, the model might generate an analysis result such as, "Recent heart rate patterns have been irregular, and stress levels are high."

[1197] Step 4: Generate a care plan

[1198] The server generates an individualized care plan based on the analysis results of the AI ​​model. Specific plans include "a 20-minute morning walk," "5 minutes of deep breathing exercises," and "taking vitamin D supplements." The generated care plan is saved in a database and used in subsequent steps.

[1199] Step 5: Collecting sentiment data

[1200] The device analyzes the voice and facial expressions of the user (caregiver or family member) to collect emotional data. The emotion engine reads the tone of the voice, speaking style, and facial expressions from camera footage to identify the emotional state in real time. For example, the result may be, "The user's voice has a depressed tone, and anxiety is increasing."

[1201] Step 6: Notification of Emotion Data

[1202] The server stores the collected emotion data in a database in real time and sends it along with the analysis results to a dedicated app. The device displays the emotion data within the app, allowing the user to check the situation.

[1203] Step 7: Plan Notification and Management

[1204] The server sends the generated care plan to a dedicated app. The device displays each item in the plan in a timeline format and notifies the user. The user can check the progress of the plan through the dedicated app and record the action items that have been completed. For example, the user could enter "2023-10-10 11:00: 5 minutes of deep breathing exercises - completed."

[1205] Step 8: Feedback and Adjustments

[1206] Users send feedback through a dedicated app, reporting the effectiveness of the care plan and areas for improvement. For example, they may provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the feedback and emotional data and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can view the latest care plan.

[1207] This processing flow enables the system to monitor the health status of the care recipient and the emotional state of the caregiver and family in real time, and provide appropriate care plans individually and quickly, thereby improving the quality of life of the care recipient and their caregiver.

[1208] Example 2

[1209] 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."

[1210] In modern society, monitoring the health status of those requiring care in real time and providing appropriate care according to their circumstances is a crucial issue. However, conventional systems only collect and analyze the health data of those requiring care, and are unable to provide care plans that take into account the emotional state of the caregiver or family. This makes it difficult to provide attentive care, and improving the satisfaction of both the care recipient and the caregiver is a challenge.

[1211] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1212] In this invention, the server includes means for collecting data from a sensor worn by the care recipient, means for executing a generative AI model that analyzes the collected data, means for generating an individual nursing care plan based on the analysis results, means for notifying a dedicated app of the generated nursing care plan, means for managing the progress of the nursing care plan through the dedicated app, means for adjusting the nursing care plan based on feedback, a terminal equipped with an emotion engine that collects and analyzes user emotion data, and means for analyzing the emotion data and feeding it back to the dedicated app. This enables the provision of detailed and prompt care that takes into account both the health state of the care recipient and the emotional states of the caregiver and family.

[1213] "Individuals requiring care" refers to elderly people or individuals with illnesses or disabilities who require assistance with daily living or medical care.

[1214] "Sensors" refer to devices used to measure and collect data on the health status of care recipients, including devices that measure heart rate, blood pressure, body temperature, walking distance, sleep time, etc. in real time.

[1215] "Server" refers to a computer system that receives data collected from sensors and processes and analyzes it.

[1216] A "generative AI model" refers to a machine learning model that analyzes the health condition of a person requiring care based on collected data and generates an appropriate nursing care plan.

[1217] A "nursing care plan" refers to a specific action plan that includes medical care, assistance with daily life, rehabilitation schedules, etc., according to the health condition of the person requiring care.

[1218] "Dedicated app" refers to a software application that displays the generated nursing care plan and allows the user to manage its progress.

[1219] An "emotion engine" is a technology that collects and analyzes emotional data from the user's voice and facial expressions, and sends it to a server as feedback.

[1220] "User" refers to an individual, including a caregiver or family member providing nursing care.

[1221] "Feedback" refers to information provided by the user, including data on the effectiveness of the care plan and areas for improvement.

[1222] The present invention is a system for monitoring the health and living conditions of a person requiring care in real time and providing an individualized care plan. Specific embodiments of this system will be described in detail below.

[1223] System Configuration

[1224] The system consists of a sensor worn by the care recipient, a server that analyzes the data, a device that collects emotional data, and a dedicated app that manages the generated care plan.

[1225] sensor

[1226] The server collects real-time data from sensors worn by the care recipient. The sensors then transmit the data to the server via Bluetooth or Wi-Fi. The collected data includes multiple health indicators such as heart rate, blood pressure, body temperature, walking distance, and sleep time.

[1227] Data analysis

[1228] The server receives the collected health data and runs a generative AI model to analyze it. The generative AI model is based on machine learning algorithms to assess the care recipient's health status and risks. For example, it analyzes irregular heart rate patterns and blood pressure fluctuations to predict the care recipient's health risks. Based on the analysis results, an individualized care plan is generated.

[1229] Care plan generation and notification

[1230] Based on the analysis results of the AI ​​model, the server generates a specific action plan, such as "a 20-minute morning walk," "five minutes of deep breathing exercises," or "taking vitamin D supplements." The generated care plan is then sent to a dedicated app.

[1231] Collecting Emotional Data

[1232] The device collects emotional data from the user's voice and facial expressions. It uses a voice analysis engine and a camera to identify emotions such as joy, sadness, and anger from the user's speaking style, tone, and facial expressions. This emotional data is sent to a server in real time.

[1233] Dedicated app functions

[1234] Users using a device (smartphone or tablet) can check the generated care plan through a dedicated app and manage progress in real time. The app also includes a function to report results and areas for improvement as feedback. For example, users can send feedback such as, "My physical condition did not improve after rehabilitation exercises."

[1235] Specific examples

[1236] For example, if heart rate (80 bpm), blood pressure (120 / 80 mmHg), and body temperature (36.5°C) data are obtained from a sensor worn by care recipient A at 10:00 on October 10th, the server collects this data and inputs it into the generative AI model. The generative AI model detects that care recipient A's recent heart rate pattern is irregular and predicts that his or her stress level is increasing. Based on the results of this analysis, the server generates a specific care plan that includes "a 20-minute morning walk," "five minutes of deep breathing exercises," and "taking vitamin D supplements." The generated plan is immediately sent to the device, and the user can check the plan through a dedicated app.

[1237] Prompt Sentence Examples

[1238] Below are some examples of specific prompts to input to a generative AI model:

[1239] "Based on recent data, care recipient A's heart rate is irregular, and their blood pressure and temperature are within normal ranges. However, we have recognized a pattern that suggests their stress levels may be increasing. Please generate an appropriate care plan, including specific care items and how to implement them."

[1240] Based on this prompt, the AI ​​model generates an individualized nursing care plan.

[1241] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1242] Step 1: Data collection and preprocessing

[1243] The server receives data in real time from sensors worn by the care recipient. The sensors measure health indicators such as heart rate, blood pressure, body temperature, walking distance, and sleep time, and transmit the data to the server via Bluetooth or Wi-Fi. The received data is stored in a database and checked for outliers and missing values. For example, if the heart rate data sent from the sensor is irregular, the data is filtered.

[1244] Input: Real-time data from sensors

[1245] Output: Filtered health data

[1246] Step 2: Data analysis

[1247] The server inputs the preprocessed data into a generative AI model, which uses machine learning algorithms to analyze the care recipient's health status and detect specific patterns or abnormalities. For example, it analyzes heart rate data from the past week to detect irregular heart rate patterns. The analysis results are stored on the server.

[1248] Input: Preprocessed health data

[1249] Output: Health status analysis results

[1250] Step 3: Generate a care plan

[1251] The server generates an optimal care plan based on the analysis results. This care plan includes specific care items (e.g., a 20-minute morning walk, 5 minutes of deep breathing exercises, vitamin D supplement intake) and how to implement them. The generated plan is notified to the dedicated app.

[1252] Input: Health status analysis results

[1253] Output: Generated nursing care plan

[1254] Step 4: Collect and analyze emotion data

[1255] The device collects the voice and facial expressions of the user (caregiver or family member) and analyzes the emotional data. It uses a voice analysis engine and a camera to identify the user's emotions and sends the emotional data to the server. For example, it can detect whether the user is feeling stressed from the tone of their voice.

[1256] Input: User's voice and facial expression data

[1257] Output: Emotional state analysis results

[1258] Step 5: Plan Notification and Management

[1259] The generated care plan is sent from the server to the device and displayed on a dedicated app. The user manages the progress of the plan through the app and records the care items that have been carried out. For example, the user can record on the app that "a 20-minute morning walk was carried out."

[1260] Input: Generated nursing care plan

[1261] Output: Display of care plan and progress management on dedicated app

[1262] Step 6: Feedback and plan adjustments

[1263] The user provides feedback through a dedicated app. For example, they may provide information such as, "My physical condition did not improve after rehabilitation exercises." The server analyzes the feedback and emotional data and adjusts the care plan as necessary. The adjusted plan is then sent back to the device, where the user can check the latest instructions.

[1264] Input: User feedback

[1265] Output: Coordinated nursing care plan

[1266] (Application example 2)

[1267] 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."

[1268] In today's world, health management for those requiring care has become an important issue, but conventional systems have been unable to provide adequate individualized care and have made it difficult to provide care that takes into account the emotional state of caregivers and their families. Furthermore, systems for providing prompt and appropriate responses in emergencies were also inadequate. As a result, there was a risk of sudden changes in the health status of those requiring care and an increased burden on caregivers and their families.

[1269] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1270] In this invention, the server includes means for collecting data from a sensor worn by the care recipient, means for executing a generative AI model that analyzes the collected data, means for generating an individualized care plan based on the analysis results, means for notifying a dedicated app of the generated care plan, means for managing the progress of the care plan through the dedicated app, means for using an emotion engine that extracts emotion data from the user's voice and facial expressions, means for automatically notifying in an emergency based on the emotion data, and means for adjusting the care plan based on feedback. This makes it possible to monitor the health condition of the care recipient and the emotion state of the caregiver and family in real time and quickly provide an individualized and appropriate care plan.

[1271] A "sensor" is a device worn on the body that collects health-related data such as heart rate, blood pressure, and body temperature in real time.

[1272] A "generative AI model" is software that contains machine learning algorithms to analyze collected health data and predict abnormal patterns and risks.

[1273] A "nursing care plan" is a plan that individually defines the necessary medical care and daily life support activities for a person in need of nursing care, based on the analysis results of the generated AI model.

[1274] The "dedicated app" is an application used by the person requiring care and their caregiver on a smartphone or tablet, and is a platform for checking the generated care plan and managing its progress.

[1275] The "emotion engine" is a technology that analyzes the voices and facial expressions of caregivers and family members to identify their emotional state.

[1276] "Feedback" refers to information provided by users through a dedicated app regarding the effectiveness of nursing care plans and areas for improvement.

[1277] "Emergency notification" is a means of automatically transmitting information to emergency contacts and medical services when an abnormality is detected.

[1278] "Health status" refers to the physical condition of the care recipient, including heart rate, blood pressure, and body temperature, and is analyzed by the generative AI model.

[1279] "Progress management" is the process by which users check the progress of their nursing care plan through a dedicated app and record any necessary actions.

[1280] The present invention is a system that monitors the health status of a care recipient in real time and provides a personalized care plan, which can also take into account the emotional state of the caregiver and family. The configuration and operation of the system are described in detail below.

[1281] System Configuration

[1282] The system consists of the following main components:

[1283] 1. Sensors: Collect health data such as heart rate, blood pressure, and body temperature, and send the data to a server via Bluetooth or Wi-Fi.

[1284] 2. Server: Receives health data, analyzes it using a generative AI model, generates a care plan, and analyzes the user's emotional state using an emotion engine and stores the results.

[1285] 3. Dedicated app: Runs on smartphones and tablets, displays the generated nursing care plan and emotional data, and manages progress and provides feedback.

[1286] Program processing

[1287] Data collection and preprocessing

[1288] The server receives real-time health data from sensors. The collected data is filtered for outliers and missing values ​​and stored in a database. This processing is performed using internet-connected wearable devices (e.g., Fitbit, Apple Watch) for hardware and cloud computing services (e.g., AWS, Google Cloud) for the server.

[1289] Data analysis and care plan generation

[1290] The server inputs the collected and preprocessed data into a generative AI model to analyze the health status of the care recipient. The generative AI model includes machine learning algorithms for pattern recognition and risk assessment. Based on the analysis results, an individual care plan is generated. This is done using a database (e.g., MySQL, PostgreSQL).

[1291] Emotion data collection and analysis

[1292] The device extracts the user's emotional data using an emotion engine that recognizes voice and facial expressions. This emotion engine uses voice analysis and facial expression recognition technologies (e.g., Microsoft Azure Cognitive Services and Google Cloud AI). The collected emotional data is sent to a server and analyzed together with health data.

[1293] Emergency notifications and progress management

[1294] If an abnormality is detected based on the health data, the server automatically notifies emergency contacts and medical services. The generated care plan is sent to a dedicated app, allowing the user to manage the progress. The dedicated app is used on smartphones or tablets (e.g., iPhones and Android devices).

[1295] Specific examples

[1296] For example, if heart rate (80 bpm), blood pressure (130 / 85 mmHg), and body temperature (36.7°C) data are acquired from a sensor worn by care recipient A, the server analyzes this data and detects that recent heart rate fluctuations have increased. As a result, it generates a care plan to relieve stress, such as "10 minutes of deep breathing exercises" and "15 minutes of relaxation music." Furthermore, if the device's camera is used to detect caregiver B's facial expressions and the emotion engine identifies a high stress level, it suggests a guided meditation for relaxation using a dedicated app.

[1297] Example prompts for generative AI models

[1298] "Please explain health monitoring for nursing care systems, and methods for detecting abnormal patterns and generating appropriate care plans based on large amounts of heart rate, blood pressure, and temperature data."

[1299] As a result, the present invention makes it possible to monitor the health condition of the care recipient and the emotional state of the caregiver and family in real time, and to quickly provide an individual and appropriate care plan.

[1300] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1301] Step 1:

[1302] The sensors collect real-time health data such as the heart rate, blood pressure, and body temperature of the care recipient, and the collected data is sent to a server via Bluetooth or Wi-Fi.

[1303] Input: Health data (heart rate, blood pressure, temperature, etc.)

[1304] Output: Send data to the server (heart rate, blood pressure, body temperature)

[1305] Step 2:

[1306] The server filters the data received from the sensors, detects and corrects outliers and missing values, and stores the corrected data in a database.

[1307] Input: Data sent from the sensor

[1308] Output: Save the corrected health data to the database.

[1309] Step 3:

[1310] The server inputs the corrected data into the generative AI model to analyze the health status of the care recipient, which then recognizes abnormal patterns and risks based on the collected data.

[1311] Input: Corrected health data

[1312] Output: Health status analysis results

[1313] Step 4:

[1314] The server generates an individualized care plan for the care recipient based on the analysis results of the generative AI model, which includes necessary medical care and activities to support daily living.

[1315] Input: Health status analysis results

[1316] Output: Generated nursing care plan

[1317] Step 5:

[1318] The generated care plan is sent from the server to the device, and the user can check the plan contents using a dedicated app that runs on a smartphone or tablet.

[1319] Input: Generated nursing care plan

[1320] Output: Plan display on dedicated app

[1321] Step 6:

[1322] The device uses an emotion engine to analyze the user's voice and facial expressions, extracting emotional data, which is then sent to a server in real time.

[1323] Input: Voice data, facial expression data

[1324] Output: Extract emotion data and send it to the server

[1325] Step 7:

[1326] Based on the analyzed emotional data, the server automatically notifies emergency contacts and medical services in the event of an emergency, enabling a prompt response.

[1327] Input: Emotion data, health data

[1328] Output: Urgent notification

[1329] Step 8:

[1330] Users provide feedback and manage progress on their care plans through a dedicated app, which provides an interface for users to view progress and record any necessary actions.

[1331] Input: Feedback, progress data

[1332] Output: Feedback and progress recording

[1333] Step 9:

[1334] The server reevaluates the care plan based on user feedback and new emotional data, adjusts the plan as needed, and sends the adjusted plan back to the device.

[1335] Input: Feedback, emotion data

[1336] Output: Coordinated care plan

[1337] This enables the system to monitor the health status of the care recipient and the emotional state of the caregiver or family member in real time, providing appropriate care individually and quickly.

[1338] 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.

[1339] 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.

[1340] 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.

[1341] 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.

[1342] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1343] 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.

[1344] 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).

[1345] 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.

[1346] 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."

[1347] 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.

[1348] 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).

[1349] 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.

[1350] 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.

[1351] 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.

[1352] 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.

[1353] 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.

[1354] 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.

[1355] 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.

[1356] 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.

[1357] 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.

[1358] 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.

[1359] The following is further disclosed regarding the above embodiment.

[1360] (Claim 1)

[1361] A means of collecting data from sensors worn by the care recipient;

[1362] a means for executing a generative AI model that analyzes the collected data;

[1363] A means for generating an individualized nursing care plan based on the analysis results;

[1364] A means for notifying the generated nursing care plan to a dedicated app;

[1365] A means to manage the progress of nursing care plans through a dedicated app,

[1366] A means to adjust nursing care plans based on feedback

[1367] A system including:

[1368] (Claim 2)

[1369] 2. The system of claim 1, wherein the data collection means acquires a plurality of data including heart rate, blood pressure, body temperature, walking distance, and sleep time in real time.

[1370] (Claim 3)

[1371] The system of claim 1, wherein the generative AI model performs a health status and risk assessment of the care recipient from the collected data.

[1372] "Example 1"

[1373] (Claim 1)

[1374] A means of collecting data from sensors worn by the care recipient;

[1375] A means of filtering the collected data to remove outliers and missing values;

[1376] A means to input pre-processed data into a generative AI model to analyze health status and risk;

[1377] A means for generating an individualized nursing care plan based on the analysis results;

[1378] a means for notifying the terminal of the generated nursing care plan;

[1379] A means to manage progress through a dedicated app and adjust care plans based on feedback

[1380] A system including:

[1381] (Claim 2)

[1382] 2. The system of claim 1, wherein the data collection means includes means for acquiring and preprocessing multiple data including heart rate, blood pressure, body temperature, walking distance, and sleep time in real time.

[1383] (Claim 3)

[1384] The system of claim 1, wherein the generative AI model includes a means for assessing the health status and risks of the person requiring care from the preprocessed data and proposing an optimal nursing care plan based on the analysis results.

[1385] "Application Example 1"

[1386] (Claim 1)

[1387] a means for collecting data from sensors worn by essential workers;

[1388] a means for executing a generative AI model that analyzes the collected data;

[1389] means for generating appropriate health care recommendations based on the analysis results;

[1390] A means for notifying a dedicated app of the generated health management proposal;

[1391] A means to manage the progress of health management proposals through a dedicated app,

[1392] A means to adjust health management recommendations based on feedback

[1393] A system including:

[1394] (Claim 2)

[1395] 2. The system of claim 1, wherein the data collection means acquires a plurality of data including heart rate, blood pressure, body temperature, number of steps, and sleep time in real time.

[1396] (Claim 3)

[1397] 10. The system of claim 1, wherein the generative AI model performs a worker health status and risk assessment from the collected data.

[1398] "Example 2: Combining Emotion Engines"

[1399] (Claim 1)

[1400] A means of collecting data from sensors worn by the care recipient;

[1401] a means for executing a generative AI model that analyzes the collected data;

[1402] A means for generating an individualized nursing care plan based on the analysis results;

[1403] A means for notifying the generated nursing care plan to a dedicated app;

[1404] A means to manage the progress of nursing care plans through a dedicated app,

[1405] a means to adjust nursing care plans based on feedback; and

[1406] A device equipped with an emotion engine that collects and analyzes user emotion data,

[1407] A means of analyzing emotional data and providing feedback to a dedicated app

[1408] A system including:

[1409] (Claim 2)

[1410] 2. The system of claim 1, wherein the data collection means acquires a plurality of data including heart rate, blood pressure, body temperature, walking distance, and sleep time in real time.

[1411] (Claim 3)

[1412] The system of claim 1, wherein the generative AI model performs a health status and risk assessment of the care recipient from the collected data.

[1413] "Application example 2 when combining emotion engines"

[1414] (Claim 1)

[1415] A means of collecting data from sensors worn by the care recipient;

[1416] a means for executing a generative AI model that analyzes the collected data;

[1417] A means for generating an individualized nursing care plan based on the analysis results;

[1418] A means for notifying the generated nursing care plan to a dedicated app;

[1419] A means to manage the progress of nursing care plans through a dedicated app,

[1420] A means for using an emotion engine that extracts emotion data from the user's voice and facial expressions;

[1421] a means for automatically notifying users in an emergency based on emotion data;

[1422] A means to adjust nursing care plans based on feedback

[1423] A system including:

[1424] (Claim 2)

[1425] 2. The system of claim 1, wherein the data collection means acquires a plurality of data including heart rate, blood pressure, body temperature, walking distance, and sleep time in real time.

[1426] (Claim 3)

[1427] The system of claim 1, wherein the generative AI model performs a health status and risk assessment of the care recipient from the collected data and evaluates the emotional state of the caregiver or family member based on the emotional data. [Explanation of symbols]

[1428] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting data from sensors worn by the care recipient; a means for executing a generative AI model that analyzes the collected data; A means for generating an individualized nursing care plan based on the analysis results; A means for notifying the generated nursing care plan to a dedicated app; A means to manage the progress of nursing care plans through a dedicated app, A means to adjust nursing care plans based on feedback A system including:

2. 2. The system according to claim 1, wherein the data collection means acquires a plurality of data including heart rate, blood pressure, body temperature, walking distance, and sleep time in real time.

3. The system of claim 1, wherein the generative AI model performs a health status and risk assessment of the care recipient from the collected data.

Images