system

Abstract

We provide the system. [Solution] A means of collecting sensor data to monitor the health status of care recipients in real time, An analysis method using artificial intelligence for analyzing collected sensor data, A means for automatically creating individual care plans for those requiring care based on the analysis results, A means of communicating care plans and analysis results to caregiver robots and enabling them to carry out life support, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the nursing care industry, the shortage of nursing care staff due to the increase in the number of care recipients is becoming serious, and there is a problem that one nurse has to take on many tasks. This makes it difficult to maintain and improve the quality of nursing care and causes an excessive burden on nurses. In addition, since it is required to ensure smooth communication with care recipients, there are limitations in conventional methods. It is necessary to solve these problems and improve the efficiency and service quality at the nursing care site.

Means for Solving the Problems

[0005] This invention provides a system that automatically creates individualized care plans for care recipients by collecting sensor data to monitor their health status in real time and analyzing it using artificial intelligence. This system uses a caregiver robot to execute the care plan and analysis results in real time, and the robot can communicate with the care recipient through natural language. This reduces the burden on caregivers and enables the provision of high-quality care services to care recipients.

[0006] "Sensor data" refers to a collection of information obtained from various sensors used to monitor the health status of individuals requiring care.

[0007] "Artificial intelligence" refers to machine learning and data analysis technologies used to analyze collected sensor data and extract useful information.

[0008] A "care plan" is a document or data set that provides specific guidelines for daily living support and medical care, created based on the health condition and individual needs of the person requiring care.

[0009] A "caregiver robot" is a robot designed to support caregiving tasks for those requiring care, and it is equipped with a variety of functions, including daily living support and communication.

[0010] "Natural language" refers to the language that humans use in their daily lives, and is the linguistic form that care robots use when communicating with those requiring care. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3]This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the 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.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0025] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] This invention aims to realize a system that monitors the health status of care recipients in real time and automatically creates an appropriate care plan. This system collects the health information of care recipients through sensor devices and centrally manages it on a server. Subsequently, the server uses artificial intelligence to analyze this data and automatically formulates an optimal care plan for the care recipient.

[0033] The generated care plan is sent to the user (caregiver robot), and its execution begins. Here, the caregiver robot performs the necessary tasks to support the daily life of the person requiring care, based on the collected information and the plan. Specifically, the user (caregiver robot) communicates with the person requiring care using natural language and provides daily living support such as preparing meals and confirming medication.

[0034] For example, if a care recipient is at risk of hypertension, the server analyzes the measured data and automatically adjusts the day's meal plan to include a low-sodium menu. The user (caregiver robot) then prepares and serves the appropriate meal according to this plan. After the meal, the robot checks the recipient's health status and incorporates the findings into the next care plan.

[0035] In this way, the system comprehensively manages the health and provides support for the daily lives of those requiring care, reducing the burden on caregivers while functioning as a system that can provide high-quality care.

[0036] The following describes the processing flow.

[0037] Step 1:

[0038] The server periodically collects health data such as heart rate, blood pressure, and body temperature from sensor devices attached to the person requiring care, and stores it in a database.

[0039] Step 2:

[0040] The server uses artificial intelligence to analyze the collected health data and detect any anomalies or health risks. The results of this analysis are then used in the next step.

[0041] Step 3:

[0042] Based on the analysis results, the server automatically generates an individually customized care plan, taking into account the health status and lifestyle of the person requiring care.

[0043] Step 4:

[0044] The server transmits the generated care plan to the user (caregiver robot) and sets the execution schedule.

[0045] Step 5:

[0046] The user (caregiver robot) initiates daily communication with the care recipient based on the received care plan. This includes offering words of encouragement and checking on their health, providing a sense of security.

[0047] Step 6:

[0048] The user (caregiver robot) performs daily living support tasks such as providing meals, checking medication timing, and managing daily necessities according to a plan, and provides necessary information to the person requiring care.

[0049] Step 7:

[0050] The terminal allows users to manage the activity status of the care robot and feedback from the care recipient, and feeds this information back to the server to adjust the next schedule and new care plans.

[0051] Step 8:

[0052] The server evaluates the effectiveness of the plan based on the feedback received and performs data analysis to improve and optimize future care plans as needed.

[0053] (Example 1)

[0054] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0055] In an aging society, there is a need to effectively manage the health and provide support for the daily lives of those requiring care. However, traditional care relies heavily on human resources, leading to shortages and burdens of personnel. In particular, there are limitations to monitoring the health status of those requiring care in real time and providing individually optimized care plans quickly. To solve this problem, a system is needed that continuously monitors the health of those requiring care and automatically and efficiently formulates appropriate care plans.

[0056] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0057] In this invention, the server includes means for collecting data from a measuring device for monitoring the health status of a person requiring care in real time, means for an analysis device using a generative AI model to analyze the collected measurement data, and means for automatically creating an individualized care plan for the person requiring care based on the analysis results. This makes it possible to grasp the health status of the person requiring care in real time, quickly formulate an optimal care plan, and provide effective care services while reducing the burden on human resources.

[0058] A "measuring device" is a device used to monitor the health status of a person requiring care in real time, and includes sensors that measure biometric information such as heart rate, blood pressure, and body temperature.

[0059] A "generative AI model" is a part of artificial intelligence used to analyze collected measurement data, and it constitutes an algorithm that recognizes specific patterns and derives individualized care plans.

[0060] An "analysis device" is a set of hardware or software that uses a generative AI model to analyze collected biometric information and performs computational processing to evaluate the health status of a person requiring care.

[0061] A "care plan" is a detailed action plan formulated based on the individual health condition and living situation of a person requiring care, for the purpose of providing appropriate life support and health management.

[0062] "Caregiving equipment" refers to robots and automated devices designed to provide direct support to those requiring care based on care plans and analysis results, and includes life support and communication functions.

[0063] "Feedback" refers to the process by which caregiving machines collect information on the results of their support to care recipients and transmit that information to a data management system such as a server to help improve future care plans.

[0064] This invention provides a system for monitoring the health status of care recipients in real time and automatically generating an optimal care plan. The elements constituting this system and how it is specifically implemented are described below.

[0065] Data collection and transfer

[0066] The terminal uses measuring devices to collect biometric information such as heart rate, blood pressure, and body temperature in order to monitor the health status of those requiring care. Wireless communication technologies such as Bluetooth and Wi-Fi are used to securely transfer this data to a server. The collected data is stored in a database system on the server and prepared for analysis.

[0067] Data Analysis

[0068] The server analyzes the collected biometric information using a generative AI model. This analysis utilizes software such as the AI ​​framework TENSORFLOW®, which uses machine learning models to recognize patterns in biometric information and appropriately assess the health status of the person requiring care. For example, if the heart rate shows an irregular pattern, it is determined that there is a risk of arrhythmia and this is reflected in the care plan.

[0069] Creating a care plan

[0070] Based on the analysis results, the server generates an individualized care plan. This plan includes meal and medication schedules, as well as daily living support details, designing comprehensive support to ensure the care recipient can live comfortably and securely. The generated plan is then transmitted to the care machine and implemented.

[0071] Specific example

[0072] For example, if a care recipient has a risk of hypertension, the server analyzes the day's blood pressure data and incorporates a low-sodium meal plan. Based on this plan, the care machine prepares an appropriate low-sodium meal and provides it to the care recipient. The results of the post-meal health check are also fed back to the server to help in formulating the next care plan.

[0073] Example of a prompt

[0074] "Based on the latest health data of the person requiring care, please create an individualized care plan tailored to their specific needs. If there is a risk of hypertension, please adjust their diet to be low in salt."

[0075] In this way, this invention makes it possible to efficiently manage the health of those requiring care and to provide high-quality care services.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The terminal acquires data from measuring devices to collect health information of care recipients in real time. Specifically, sensors measure heart rate, blood pressure, and body temperature, and transmit this data to the terminal via Bluetooth communication. The input for this step is biometric data from the sensors, and the output is the measurement data accumulated in the terminal.

[0079] Step 2:

[0080] The terminal securely transmits the collected biometric data to the server using the HTTPS protocol. The biometric data stored on the terminal is used as input, and the data is formatted into a format usable by the server. The output is the formatted data being stored in the server's receiving memory.

[0081] Step 3:

[0082] The server stores the received data in a database and analyzes the data using a generative AI model. The input is biometric data sent to the server, and the AI ​​modeling performs data calculations to output an evaluation result of the health status of the person requiring care. In the analysis, the TensorFlow library is used to run a machine learning model and detect anomalies and patterns.

[0083] Step 4:

[0084] The server automatically generates individualized care plans based on the analysis results. The input is the health status assessment results from an AI model, and the planning algorithm is used to create the optimal care plan. The output is a care plan that includes specific details of daily living support. This plan includes meal menus and medication schedules.

[0085] Step 5:

[0086] The server transmits the generated care plan to the care machine, which is the user. The input is the care plan stored on the server, and the plan is transmitted to the care machine using a communication method. The output is the care plan received by the care machine.

[0087] Step 6:

[0088] The user performs daily living support based on the received care plan. Specifically, the care machine provides meals to the care recipient according to the plan and checks their health status. The input is the received care plan, and the output is data on the care recipient's reaction and health status after the plan is implemented. This data is fed back to the server and reflected in future plans.

[0089] (Application Example 1)

[0090] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0091] In factories and workplaces, it is crucial to manage workers' health in real time to prevent overwork and safety risks. However, conventional management systems struggle to provide appropriate management tailored to each worker's health condition and workload, impacting work efficiency and safety. Furthermore, there are concerns that excessive stress and physical strain can harm workers' health due to the work environment. Addressing these challenges is essential to provide a safer and more efficient work environment.

[0092] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0093] In this invention, the server includes means for collecting biometric information to monitor the health status of workers in real time, means for analyzing the collected biometric information using machine learning, and means for automatically creating individual work plans for workers based on the analysis results. This makes it possible to provide an efficient and safe work environment that takes into account the health status of workers.

[0094] "Worker" refers to a worker who performs specific tasks in a factory or work site.

[0095] "Health status" refers to the physical and mental condition of a worker as understood through biometric information.

[0096] "Real-time" refers to the continuous processing, acquisition, or provision of information at the very moment an event occurs.

[0097] "Biometric information" refers to data obtained directly from the worker's body, such as heart rate, body temperature, and stress level.

[0098] "Analysis methods" refer to the process of collecting data and using machine learning techniques to interpret its meaning.

[0099] "Machine learning" refers to the technique of building computational models using large amounts of data and using those models to predict or classify new data.

[0100] A "work plan" refers to a plan that defines the procedures and timing for carrying out work safely and efficiently, based on the health condition of the workers and the work environment.

[0101] A "work support device" refers to a device that assists workers and provides help to perform tasks efficiently and safely.

[0102] The system implementing this invention is designed to manage the health status of workers and provide an efficient and safe working environment. The main components are a biometric information collection device worn by the worker, a server for processing and analyzing the data, and a work support device.

[0103] The server acquires data transmitted in real time from biometric data collection devices via Bluetooth or Wi-Fi. These devices continuously record information such as heart rate, body temperature, and stress levels. The server analyzes this data using Python programs and machine learning models such as TensorFlow. Based on the analysis results, it automatically creates an optimized work plan for each worker, sends instructions to work support devices, and provides workers with an appropriate working environment.

[0104] The work support system prevents ambiguous instructions and provides clear feedback to workers through a natural language interface. A Flask-based API receives analysis results from the server and transmits instructions to the work support system. Specifically, it suggests breaks, performs safety checks, and adjusts work processes based on the worker's health condition.

[0105] For example, if an abnormally high heart rate is detected while a worker is operating a machine, the system will immediately recommend a break and notify both the worker and their supervisor. This helps prevent accidents caused by overwork and protects the health of workers.

[0106] The following are examples of prompts for the generative AI model in this system.

[0107] "Enter worker heart rate data and work process information, and propose methods to optimize work conditions and health status."

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The server receives biometric data such as heart rate, body temperature, and stress level from biometric data collection devices via Bluetooth or Wi-Fi. The input is real-time data from the devices, and the output is recorded in a database. At this stage, data format conversion and missing value imputation are performed.

[0111] Step 2:

[0112] The server passes the received biometric information to a machine learning model for analysis. The input is augmented biometric data, and the output is an evaluation of the worker's health status. TensorFlow is used for analysis to detect anomalies and predict health status.

[0113] Step 3:

[0114] The server generates a work plan for each worker based on the analyzed evaluation results. The input is the health status evaluation result, and the output is the optimized work plan. Python is used to analyze the evaluation results and generate prompt statements to instruct the AI ​​model, thereby optimizing the work plan.

[0115] Step 4:

[0116] The server transmits the generated work plan to the work support device. The input is the work plan, and the output is instructions for the work support device. Information is sent to the work support device via an API using Flask, and instructions are given to the worker via a natural language interface.

[0117] Step 5:

[0118] The work support system provides workers with real-time instructions and feedback through a natural language interface. Input is instructions from the server, and output is voice or text feedback to the worker. This allows workers to perform their tasks safely and efficiently.

[0119] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0120] This invention combines a system that monitors the health status of care recipients in real time and automatically generates individualized care plans with an emotion engine. The system centrally manages the health information of care recipients from sensor devices on a server and analyzes it using artificial intelligence. Based on the results of this analysis, it generates an optimal care plan, which is then transmitted to a caregiver robot for execution.

[0121] Furthermore, the user (caregiver robot) is equipped with an emotion engine that recognizes the tone of voice and facial expressions of the person receiving care and performs emotional analysis. Using the results of this analysis, it can dynamically adjust its communication methods to promote the psychological stability of the person receiving care.

[0122] For example, if a care recipient shows signs of anxiety, the emotion engine detects that anxiety. The server readjusts the care plan to reflect that anxiety, and the user (caregiver robot) responds appropriately to the care recipient through reassuring words and encouragement.

[0123] Furthermore, the server can evaluate long-term psychological trends based on emotional data, which can be used to improve the quality of care for those requiring care. In this way, the system of the present invention, by utilizing emotion recognition, can comprehensively realize physical health management and psychological support, thereby improving the quality of life.

[0124] The following describes the processing flow.

[0125] Step 1:

[0126] The server collects health data from care recipients through sensor devices and stores information such as heart rate and blood pressure in a database.

[0127] Step 2:

[0128] The server uses artificial intelligence to analyze the collected health data, assess the current health status of those requiring care, and determine if there are any abnormalities.

[0129] Step 3:

[0130] The server automatically generates an optimal care plan for the person requiring care based on the analysis results. This plan includes details of daily life support and the timing of that support.

[0131] Step 4:

[0132] The server sends the generated care plan and analysis results to the user (caregiver robot).

[0133] Step 5:

[0134] The user (caregiver robot) initiates contact with the person requiring care and prepares necessary life support based on the received care plan.

[0135] Step 6:

[0136] The user (caregiver robot) uses an emotion engine to recognize emotions from the voice and facial expressions of the person receiving care, and analyzes that information in real time.

[0137] Step 7:

[0138] The user (caregiver robot) communicates appropriately with the care recipient based on the results of emotion analysis. For example, if the care recipient shows signs of anxiety, the robot will offer words of encouragement.

[0139] Step 8:

[0140] The server uses data obtained from the emotion engine to further adjust the care plan. For example, if psychological support is needed, time for that will be incorporated into the plan.

[0141] Step 9:

[0142] The terminal displays server analysis results and updated care plan information, and provides alerts to caregivers when necessary.

[0143] Step 10:

[0144] The server provides feedback that contributes to improving care services by analyzing the health status and emotional data of those receiving care over the long term.

[0145] (Example 2)

[0146] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0147] In modern society, the increasing number of people requiring care due to an aging population is a significant problem. It is crucial to monitor the health status of those requiring care in real time and to provide individualized support plans quickly and appropriately. However, conventional methods have struggled to address psychological aspects, including emotional changes, and have failed to adequately improve the quality of life for those requiring care. To address this, a comprehensive care system is needed that considers not only physical health management but also psychological stability.

[0148] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0149] In this invention, the server includes means for collecting data from a detector to monitor the health status of the person requiring care; means for analyzing the collected data using intelligence; means for automatically creating an individualized support plan for the person requiring care based on the analysis results; means for transmitting the support plan and analysis results to a mobile support device and having it carry out life support; means for dynamically adjusting the interaction with the person requiring care using a device equipped with an emotion engine for analyzing voice and facial expressions to recognize emotions; and means for accumulating long-term data and evaluating the psychological and physical health trends of the person requiring care. This makes it possible to comprehensively manage the health status of the person requiring care and provide appropriate physical and psychological support.

[0150] A "person requiring care" refers to a person who, due to their physical or mental health condition, needs assistance from others to carry out their daily activities.

[0151] "Health status" refers to the state of physical and mental health and serves as a standard for evaluating the quality of daily life.

[0152] A "detector" refers to a device used to acquire physical and environmental data of a person requiring care in real time.

[0153] "Intelligence" refers to algorithms and models that are artificially programmed to perform data analysis and decision support.

[0154] A "mobile support device" refers to a programmed, mobile robot designed to assist in the daily lives of people requiring care.

[0155] The term "emotional engine" refers to a technology that analyzes the voice and facial expressions of those requiring care to estimate their psychological and emotional state.

[0156] "Psychological and physical health tendencies" refer to patterns related to the emotional and physiological states of care recipients that change over time.

[0157] "Dynamically adjusting dialogue" refers to flexibly changing the content and method of communication according to the current emotional state and health condition of the person receiving care.

[0158] This invention is a system for improving the quality of life for those requiring care. The system consists of multiple components, including a server, terminals, and users.

[0159] First, the server collects data related to the health status of the person receiving care from sensor devices. These devices include heart rate monitors and accelerometers. The data from the sensors is transmitted to the server in real time.

[0160] Next, the server performs artificial intelligence analysis on the collected data. Existing machine learning libraries such as TensorFlow and PyTorch are used for this analysis. This AI model assesses the physical and psychological health status of those requiring care and generates individually optimized support plans.

[0161] As a caregiver robot, the user begins actions based on the generated support plan. This robot incorporates an emotion engine and uses a camera and microphone to recognize the tone of voice and facial expressions of the person receiving care. Based on these results, natural language communication with the person receiving care is dynamically adjusted to provide optimal support.

[0162] For example, if a care recipient shows anxiety, the robot can offer reassuring words such as, "Let's make some tea today to help you feel calmer." Furthermore, based on long-term accumulated data, the robot can evaluate the psychological tendencies of care recipients and use this information to improve their care in the future.

[0163] Examples of prompts that utilize this invention include, "Analyze the care needs of elderly individuals and propose an optimized care plan," and "Use the emotion engine to generate a communication strategy suitable for care recipients who are experiencing anxiety."

[0164] Thus, the present invention can significantly improve the quality of life for those requiring care by providing comprehensive physical and psychological support.

[0165] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0166] Step 1:

[0167] The server collects data from sensor devices to monitor the health status of care recipients in real time. Inputs include biometric data such as heart rate, blood pressure, and activity level. This data is transmitted to the server via Bluetooth or Wi-Fi and temporarily stored in a database. Outputs are sensor data in the format stored in the database for future analysis.

[0168] Step 2:

[0169] The server analyzes the collected sensor data using an AI model. The input is the biometric data collected in step 1. The data is processed using TensorFlow or PyTorch, and machine learning algorithms are used to identify abnormal patterns and trends. The output is an assessment of the health status of the person requiring care. Specifically, if the server detects an anomaly during analysis, it generates an alert and notifies healthcare professionals.

[0170] Step 3:

[0171] The server automatically generates a support plan based on the analysis results. The input is the health status assessment results obtained in step 2. Based on these results, an individual support plan is formulated, and necessary care activities (e.g., exercise, diet, medication) are planned. The output is the generated support plan. In terms of specific actions, the server sends the plan to the caregiver robot as a digital message.

[0172] Step 4:

[0173] The user (caregiver robot) begins acting according to the generated support plan. The input is the support plan sent from the server in step 3. Based on the plan, the user provides support for meals and exercise to the person requiring care and interacts with them as needed. The output is a report on the support provided to the person requiring care. In terms of specific actions, the robot automatically moves to the person requiring care and assists with the planned activities.

[0174] Step 5:

[0175] The user recognizes and analyzes emotions from voice tone and facial expressions. The input is voice and video data of the person receiving care. An emotion engine processes this data to identify the person's emotional state (e.g., joy, anxiety). The output is the result of the emotion analysis. Specifically, the robot acquires data through voice and camera input and determines the emotional state in real time.

[0176] Step 6:

[0177] The server accumulates long-term data to assess the health and emotional trends of care recipients. The input is a history of health and emotional data collected to date. The server analyzes the history stored in the database to identify areas for improvement and strategies for promoting health. The output is analytical results that help improve ongoing support plans. Specifically, the server generates monthly reports and provides them to healthcare professionals and family caregivers.

[0178] (Application Example 2)

[0179] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0180] In modern industrial and welfare environments, real-time monitoring of the health and psychological state of workers and those requiring care is crucial for improving safety and comfort. However, conventional methods are not sufficiently automated in assessing health status or creating individualized support plans, making it difficult to provide appropriate support based on emotional states. This has led to problems such as overwork and psychological burden in the work environment.

[0181] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0182] In this invention, the server includes means for collecting sensor data to monitor the health status of care recipients and workers in real time, means for analyzing the collected sensor data using artificial intelligence, and means for automatically creating individual plans for care recipients and workers based on the analysis results. This makes it possible to effectively provide workload reduction and psychological stability in accordance with the health and emotional state of workers.

[0183] A "person requiring care" is an individual who needs care or support to carry out their daily activities.

[0184] A "worker" is an individual who performs a specific task in a factory, industrial setting, or similar location.

[0185] "Health status" refers to various vital signs and physical condition of the body, including heart rate, body temperature, and blood pressure.

[0186] "Psychological state" refers to an individual's emotions and mental condition, including mental conditions such as anxiety, stress, and a sense of security.

[0187] "Sensor data" refers to information obtained from various sensors used to monitor health conditions and work environments.

[0188] Artificial intelligence is a technology that uses machine learning and algorithms to analyze data and support decision-making.

[0189] An "individualized plan" refers to a support plan optimized for each individual based on the collected data.

[0190] A "robot" is a mechanical device that can perform programmed actions, and is particularly intended to assist workers and those requiring care.

[0191] "Emotional analysis" refers to the process of analyzing and evaluating an individual's emotional state based on audio and image data.

[0192] "Methods of communication" refer to the means and techniques used when interacting with others, and include media such as language, nonverbal communication, voice, and text.

[0193] The system for implementing this invention includes multiple means for monitoring the health and psychological state of workers and those requiring care in real time and providing appropriate support. Its specific form is described below.

[0194] The server uses various sensors to acquire vital signs for monitoring health status. Examples include heart rate sensors and thermometers. Sensor data is transmitted to the server via Bluetooth, Wi-Fi, etc. Upon receiving this data, the server performs analysis using artificial intelligence technology (e.g., TensorFlow or PyTorch). Based on the analysis results, an individualized support plan is automatically generated.

[0195] The server also receives audio and image data for sentiment analysis. For this purpose, audio and image input from smart devices worn by workers or care recipients is used. Sentiment analysis software, such as the Affectiva API, is used for sentiment analysis. This allows for real-time monitoring of emotional changes and appropriate responses.

[0196] The user robot communicates appropriately with the worker based on the support plan from the server. For example, if a certain level of stress is detected, the robot will suggest temporarily suspending the work and provide advice on relaxation.

[0197] As a specific example, if a worker's heart rate is higher than normal in a factory and emotional analysis detects signs of stress, the robot will respond by saying, "I suggest a 10-minute break. I will play some relaxing music."

[0198] Examples of prompt statements for a generative AI model are as follows:

[0199] "Please explain how to propose measures to reduce workload based on real-time monitoring of workers' health and emotions in a factory."

[0200] Thus, the present invention functions as a system that can integrate physical health management and psychological support for workers and those requiring care.

[0201] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0202] Step 1:

[0203] The server receives health data from sensors worn by care recipients or workers. Specifically, vital data such as heart rate, body temperature, and blood pressure are input to the server via Bluetooth or Wi-Fi communication. The server stores this data chronologically and uses it as basic data for detecting abnormalities.

[0204] Step 2:

[0205] The server uses artificial intelligence algorithms to analyze the received vital data. For example, TensorFlow is used to detect anomalies and perform trend analysis. The output includes an assessment of whether anomalies were detected and whether the health status is stable. These analysis results serve as foundational information for creating individualized support plans.

[0206] Step 3:

[0207] The server automatically generates individualized support plans for each care recipient and worker based on the results of the health status analysis. The plan generation is performed using a generation AI model and prompts. The output includes a list of the plan and support activity priorities, which are used as instructions in the next processing step.

[0208] Step 4:

[0209] The user robot gives instructions to the target person via a voice output device, based on an individualized support plan sent from the server. Specific actions include voice commands such as "Let's take a break" or "It's time to relax." The robot observes the target person's response and prepares the next action based on the plan.

[0210] Step 5:

[0211] The server receives voice and facial expression data from workers and those receiving care, and performs emotion analysis. Using emotion analysis tools such as the Affectiva API with the voice and image data, it evaluates the degree of stress and anxiety. An emotional state report is generated as output, which is then used as data for providing psychological support.

[0212] Step 6:

[0213] The device dynamically adjusts its communication methods in real time based on the results of emotion analysis. Specifically, it adopts an approach that changes the tone and content of its language according to the target person's emotional state. This allows for the optimization of psychological support for the target person.

[0214] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0215] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0216] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0220] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0221] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0222] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0223] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0224] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0225] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0226] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0227] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0228] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0229] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0230] This invention aims to realize a system that monitors the health status of care recipients in real time and automatically creates an appropriate care plan. This system collects the health information of care recipients through sensor devices and centrally manages it on a server. Subsequently, the server uses artificial intelligence to analyze this data and automatically formulates an optimal care plan for the care recipient.

[0231] The generated care plan is sent to the user (caregiver robot), and its execution begins. Here, the caregiver robot performs the necessary tasks to support the daily life of the person requiring care, based on the collected information and the plan. Specifically, the user (caregiver robot) communicates with the person requiring care using natural language and provides daily living support such as preparing meals and confirming medication.

[0232] For example, if a care recipient is at risk of hypertension, the server analyzes the measured data and automatically adjusts the day's meal plan to include a low-sodium menu. The user (caregiver robot) then prepares and serves the appropriate meal according to this plan. After the meal, the robot checks the recipient's health status and incorporates the findings into the next care plan.

[0233] In this way, the system comprehensively manages the health and provides support for the daily lives of those requiring care, reducing the burden on caregivers while functioning as a system that can provide high-quality care.

[0234] The following describes the processing flow.

[0235] Step 1:

[0236] The server periodically collects health data such as heart rate, blood pressure, and body temperature from sensor devices attached to the person requiring care, and stores it in a database.

[0237] Step 2:

[0238] The server uses artificial intelligence to analyze the collected health data and detect any anomalies or health risks. The results of this analysis are then used in the next step.

[0239] Step 3:

[0240] Based on the analysis results, the server automatically generates an individually customized care plan, taking into account the health status and lifestyle of the person requiring care.

[0241] Step 4:

[0242] The server transmits the generated care plan to the user (caregiver robot) and sets the execution schedule.

[0243] Step 5:

[0244] The user (caregiver robot) initiates daily communication with the care recipient based on the received care plan. This includes offering words of encouragement and checking on their health, providing a sense of security.

[0245] Step 6:

[0246] The user (caregiver robot) performs daily living support tasks such as providing meals, checking medication timing, and managing daily necessities according to a plan, and provides necessary information to the person requiring care.

[0247] Step 7:

[0248] The terminal allows users to manage the activity status of the care robot and feedback from the care recipient, and feeds this information back to the server to adjust the next schedule and new care plans.

[0249] Step 8:

[0250] The server evaluates the effectiveness of the plan based on the feedback received and performs data analysis to improve and optimize future care plans as needed.

[0251] (Example 1)

[0252] Next, we will describe Example 1. 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."

[0253] In an aging society, there is a need to effectively manage the health and provide support for the daily lives of those requiring care. However, traditional care relies heavily on human resources, leading to shortages and burdens of personnel. In particular, there are limitations to monitoring the health status of those requiring care in real time and providing individually optimized care plans quickly. To solve this problem, a system is needed that continuously monitors the health of those requiring care and automatically and efficiently formulates appropriate care plans.

[0254] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0255] In this invention, the server includes means for collecting data from a measuring device for monitoring the health status of a person requiring care in real time, means for an analysis device using a generative AI model to analyze the collected measurement data, and means for automatically creating an individualized care plan for the person requiring care based on the analysis results. This makes it possible to grasp the health status of the person requiring care in real time, quickly formulate an optimal care plan, and provide effective care services while reducing the burden on human resources.

[0256] A "measuring device" is a device used to monitor the health status of a person requiring care in real time, and includes sensors that measure biometric information such as heart rate, blood pressure, and body temperature.

[0257] A "generative AI model" is a part of artificial intelligence used to analyze collected measurement data, and it constitutes an algorithm that recognizes specific patterns and derives individualized care plans.

[0258] An "analysis device" is a set of hardware or software that uses a generative AI model to analyze collected biometric information and performs computational processing to evaluate the health status of a person requiring care.

[0259] A "care plan" is a detailed action plan formulated based on the individual health condition and living situation of a person requiring care, for the purpose of providing appropriate life support and health management.

[0260] "Caregiving equipment" refers to robots and automated devices designed to provide direct support to those requiring care based on care plans and analysis results, and includes life support and communication functions.

[0261] "Feedback" refers to the process by which caregiving machines collect information on the results of their support to care recipients and transmit that information to a data management system such as a server to help improve future care plans.

[0262] This invention provides a system for monitoring the health status of care recipients in real time and automatically generating an optimal care plan. The elements constituting this system and how it is specifically implemented are described below.

[0263] Data collection and transfer

[0264] The terminal uses measuring devices to collect biometric information such as heart rate, blood pressure, and body temperature in order to monitor the health status of those requiring care. Wireless communication technologies such as Bluetooth and Wi-Fi are used to securely transfer this data to a server. The collected data is stored in a database system on the server and prepared for analysis.

[0265] Data Analysis

[0266] The server analyzes the collected biometric information using a generative AI model. This analysis utilizes software such as the AI ​​framework TensorFlow, and the machine learning model recognizes patterns in the biometric information to appropriately assess the health status of the person requiring care. For example, if the heart rate shows an irregular pattern, it is determined that there is a risk of arrhythmia and this is reflected in the care plan.

[0267] Creating a care plan

[0268] Based on the analysis results, the server generates an individualized care plan. This plan includes meal and medication schedules, as well as daily living support details, designing comprehensive support to ensure the care recipient can live comfortably and securely. The generated plan is then transmitted to the care machine and implemented.

[0269] Specific example

[0270] For example, if a care recipient has a risk of hypertension, the server analyzes the day's blood pressure data and incorporates a low-sodium meal plan. Based on this plan, the care machine prepares an appropriate low-sodium meal and provides it to the care recipient. The results of the post-meal health check are also fed back to the server to help in formulating the next care plan.

[0271] Example of a prompt

[0272] "Based on the latest health data of the person requiring care, please create an individualized care plan tailored to their specific needs. If there is a risk of hypertension, please adjust their diet to be low in salt."

[0273] In this way, this invention makes it possible to efficiently manage the health of those requiring care and to provide high-quality care services.

[0274] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0275] Step 1:

[0276] The terminal acquires data from measuring devices to collect health information of care recipients in real time. Specifically, sensors measure heart rate, blood pressure, and body temperature, and transmit this data to the terminal via Bluetooth communication. The input for this step is biometric data from the sensors, and the output is the measurement data accumulated in the terminal.

[0277] Step 2:

[0278] The terminal securely transmits the collected biometric data to the server using the HTTPS protocol. Using the biometric data stored in the terminal as input, as data processing, it formats the data into a format that can be used by the server. The output is that the formatted data is stored in the server's receiving memory.

[0279] Step 3:

[0280] The server stores the received data in the database and analyzes the data using the generated AI model. The input is the biometric data transmitted to the server, performs data operations by AI modeling, and outputs the evaluation result of the health status of the care recipient. In the analysis, a machine learning model is executed using the TensorFlow library to detect outliers and patterns.

[0281] Step 4:

[0282] The server automatically generates an individual care plan based on the analysis results. The input is the evaluation result of the health status by the AI model, and an optimal care plan is created using a planning algorithm. The output is a care plan that includes specific life support contents. This plan includes a diet menu and a medication schedule.

[0283] Step 5:

[0284] The server transmits the generated care plan to the care machine, which is the user. The input is the care plan stored on the server, and the plan is passed to the care machine using communication means. The output is the care plan received by the care machine.

[0285] Step 6:

[0286] The user executes life support based on the received care plan. As specific actions, the care machine provides meals to the care recipient as planned and checks the health status. The input is the received care plan, and the output is the data of the reaction and health status of the care recipient after execution. These data are fed back to the server and reflected in future plans.

[0287] (Application Example 1)

[0288] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal".

[0289] In factories and work sites, it is important to manage the health status of workers in real time and prevent overwork and safety risks. However, in conventional management systems, it is difficult to perform appropriate management according to the health status and work load of individual workers, which affects work efficiency and safety. In addition, there is also concern that the work environment may damage the health of workers due to excessive stress and physical load. By solving these problems, it is necessary to provide a safer and more efficient work environment.

[0290] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0291] In this invention, the server includes means for collecting biometric information for monitoring the health status of workers in real time, analysis means using machine learning for analyzing the collected biometric information, and means for automatically creating an individual work plan for workers based on the analysis results. As a result, it becomes possible to provide an efficient and safe work environment considering the health status of workers.

[0292] "Worker" refers to a worker who performs a specific task in a factory or work site.

[0293] "Health status" indicates the physical and mental condition of a worker grasped through biometric information.

[0294] "Real time" refers to the manner of continuously processing, acquiring, or providing information at the moment an event occurs.

[0295] "Biometric information" refers to data obtained directly from the worker's body, such as heart rate, body temperature, and stress level.

[0296] "Analysis methods" refer to the process of collecting data and using machine learning techniques to interpret its meaning.

[0297] "Machine learning" refers to the technique of building computational models using large amounts of data and using those models to predict or classify new data.

[0298] A "work plan" refers to a plan that defines the procedures and timing for carrying out work safely and efficiently, based on the health condition of the workers and the work environment.

[0299] A "work support device" refers to a device that assists workers and provides help to perform tasks efficiently and safely.

[0300] The system implementing this invention is designed to manage the health status of workers and provide an efficient and safe working environment. The main components are a biometric information collection device worn by the worker, a server for processing and analyzing the data, and a work support device.

[0301] The server acquires data transmitted in real time from biometric data collection devices via Bluetooth or Wi-Fi. These devices continuously record information such as heart rate, body temperature, and stress levels. The server analyzes this data using Python programs and machine learning models such as TensorFlow. Based on the analysis results, it automatically creates an optimized work plan for each worker, sends instructions to work support devices, and provides workers with an appropriate working environment.

[0302] The work support device prevents ambiguous instructions and provides clear feedback to the operator through a natural language interface. An API using Flask receives the analysis results from the server and conducts instructions to the work support device. Specifically, it executes suggestions for breaks, safety checks, and adjustment of work processes according to the operator's health condition.

[0303] As a specific example, when an abnormal increase in the heart rate is detected during the operation of a machine by an operator, the system immediately recommends a break and notifies the operator and the responsible supervisor. This can prevent accidents due to overwork and protect the health of the operator.

[0304] Examples of prompt texts for the generative AI model in this system are shown below.

[0305] "Please input the operator's heart rate data and work process information and propose a method to optimize the work situation and health condition."

[0306] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0307] Step 1:

[0308] The server receives biometric information such as heart rate, body temperature, and stress level from the biometric information collection device via Bluetooth or Wi-Fi. The input is real-time data from the device, and the output is the recording to the database. At this stage, data format conversion and filling of missing values are performed.

[0309] Step 2:

[0310] The server passes the received biometric information to the machine learning model for analysis. The input is the supplemented biometric information data, and the output is the evaluation result of the operator's health condition. The analysis is performed using TensorFlow to detect abnormal values and predict the health condition.

[0311] Step 3:

[0312] The server generates a work plan for each worker based on the analyzed evaluation results. The input is the health status evaluation result, and the output is the optimized work plan. Python is used to analyze the evaluation results and generate prompt statements to instruct the AI ​​model, thereby optimizing the work plan.

[0313] Step 4:

[0314] The server transmits the generated work plan to the work support device. The input is the work plan, and the output is instructions for the work support device. Information is sent to the work support device via an API using Flask, and instructions are given to the worker via a natural language interface.

[0315] Step 5:

[0316] The work support system provides workers with real-time instructions and feedback through a natural language interface. Input is instructions from the server, and output is voice or text feedback to the worker. This allows workers to perform their tasks safely and efficiently.

[0317] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0318] This invention combines a system that monitors the health status of care recipients in real time and automatically generates individualized care plans with an emotion engine. The system centrally manages the health information of care recipients from sensor devices on a server and analyzes it using artificial intelligence. Based on the results of this analysis, it generates an optimal care plan, which is then transmitted to a caregiver robot for execution.

[0319] Furthermore, the user (caregiver robot) is equipped with an emotion engine that recognizes the tone of voice and facial expressions of the person receiving care and performs emotional analysis. Using the results of this analysis, it can dynamically adjust its communication methods to promote the psychological stability of the person receiving care.

[0320] For example, if a care recipient shows signs of anxiety, the emotion engine detects that anxiety. The server readjusts the care plan to reflect that anxiety, and the user (caregiver robot) responds appropriately to the care recipient through reassuring words and encouragement.

[0321] Furthermore, the server can evaluate long-term psychological trends based on emotional data, which can be used to improve the quality of care for those requiring care. In this way, the system of the present invention, by utilizing emotion recognition, can comprehensively realize physical health management and psychological support, thereby improving the quality of life.

[0322] The following describes the processing flow.

[0323] Step 1:

[0324] The server collects health data from care recipients through sensor devices and stores information such as heart rate and blood pressure in a database.

[0325] Step 2:

[0326] The server uses artificial intelligence to analyze the collected health data, assess the current health status of those requiring care, and determine if there are any abnormalities.

[0327] Step 3:

[0328] The server automatically generates an optimal care plan for the person requiring care based on the analysis results. This plan includes details of daily life support and the timing of that support.

[0329] Step 4:

[0330] The server sends the generated care plan and analysis results to the user (caregiver robot).

[0331] Step 5:

[0332] The user (caregiver robot) initiates contact with the person requiring care and prepares necessary life support based on the received care plan.

[0333] Step 6:

[0334] The user (caregiver robot) uses an emotion engine to recognize emotions from the voice and facial expressions of the person receiving care, and analyzes that information in real time.

[0335] Step 7:

[0336] The user (caregiver robot) communicates appropriately with the care recipient based on the results of emotion analysis. For example, if the care recipient shows signs of anxiety, the robot will offer words of encouragement.

[0337] Step 8:

[0338] The server uses data obtained from the emotion engine to further adjust the care plan. For example, if psychological support is needed, time for that will be incorporated into the plan.

[0339] Step 9:

[0340] The terminal displays server analysis results and updated care plan information, and provides alerts to caregivers when necessary.

[0341] Step 10:

[0342] The server provides feedback that contributes to improving care services by analyzing the health status and emotional data of those receiving care over the long term.

[0343] (Example 2)

[0344] Next, we will describe Example 2. 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".

[0345] In modern society, the increasing number of people requiring care due to an aging population is a significant problem. It is crucial to monitor the health status of those requiring care in real time and to provide individualized support plans quickly and appropriately. However, conventional methods have struggled to address psychological aspects, including emotional changes, and have failed to adequately improve the quality of life for those requiring care. To address this, a comprehensive care system is needed that considers not only physical health management but also psychological stability.

[0346] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0347] In this invention, the server includes means for collecting data from a detector to monitor the health status of the person requiring care; means for analyzing the collected data using intelligence; means for automatically creating an individualized support plan for the person requiring care based on the analysis results; means for transmitting the support plan and analysis results to a mobile support device and having it carry out life support; means for dynamically adjusting the interaction with the person requiring care using a device equipped with an emotion engine for analyzing voice and facial expressions to recognize emotions; and means for accumulating long-term data and evaluating the psychological and physical health trends of the person requiring care. This makes it possible to comprehensively manage the health status of the person requiring care and provide appropriate physical and psychological support.

[0348] A "person requiring care" refers to a person who, due to their physical or mental health condition, needs assistance from others to carry out their daily activities.

[0349] "Health status" refers to the state of physical and mental health and serves as a standard for evaluating the quality of daily life.

[0350] A "detector" refers to a device used to acquire physical and environmental data of a person requiring care in real time.

[0351] "Intelligence" refers to algorithms and models that are artificially programmed to perform data analysis and decision support.

[0352] A "mobile support device" refers to a programmed, mobile robot designed to assist in the daily lives of people requiring care.

[0353] The term "emotional engine" refers to a technology that analyzes the voice and facial expressions of those requiring care to estimate their psychological and emotional state.

[0354] "Psychological and physical health tendencies" refer to patterns related to the emotional and physiological states of care recipients that change over time.

[0355] "Dynamically adjusting dialogue" refers to flexibly changing the content and method of communication according to the current emotional state and health condition of the person receiving care.

[0356] This invention is a system for improving the quality of life for those requiring care. The system consists of multiple components, including a server, terminals, and users.

[0357] First, the server collects data related to the health status of the person receiving care from sensor devices. These devices include heart rate monitors and accelerometers. The data from the sensors is transmitted to the server in real time.

[0358] Next, the server performs artificial intelligence analysis on the collected data. Existing machine learning libraries such as TensorFlow and PyTorch are used for this analysis. This AI model assesses the physical and psychological health status of those requiring care and generates individually optimized support plans.

[0359] As a caregiver robot, the user begins actions based on the generated support plan. This robot incorporates an emotion engine and uses a camera and microphone to recognize the tone of voice and facial expressions of the person receiving care. Based on these results, natural language communication with the person receiving care is dynamically adjusted to provide optimal support.

[0360] For example, if a care recipient shows anxiety, the robot can offer reassuring words such as, "Let's make some tea today to help you feel calmer." Furthermore, based on long-term accumulated data, the robot can evaluate the psychological tendencies of care recipients and use this information to improve their care in the future.

[0361] Examples of prompts that utilize this invention include, "Analyze the care needs of elderly individuals and propose an optimized care plan," and "Use the emotion engine to generate a communication strategy suitable for care recipients who are experiencing anxiety."

[0362] Thus, the present invention can significantly improve the quality of life for those requiring care by providing comprehensive physical and psychological support.

[0363] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0364] Step 1:

[0365] The server collects data from sensor devices to monitor the health status of care recipients in real time. Inputs include biometric data such as heart rate, blood pressure, and activity level. This data is transmitted to the server via Bluetooth or Wi-Fi and temporarily stored in a database. Outputs are sensor data in the format stored in the database for future analysis.

[0366] Step 2:

[0367] The server analyzes the collected sensor data using an AI model. The input is the biometric data collected in step 1. The data is processed using TensorFlow or PyTorch, and machine learning algorithms are used to identify abnormal patterns and trends. The output is an assessment of the health status of the person requiring care. Specifically, if the server detects an anomaly during analysis, it generates an alert and notifies healthcare professionals.

[0368] Step 3:

[0369] The server automatically generates a support plan based on the analysis results. The input is the health status assessment results obtained in step 2. Based on these results, an individual support plan is formulated, and necessary care activities (e.g., exercise, diet, medication) are planned. The output is the generated support plan. In terms of specific actions, the server sends the plan to the caregiver robot as a digital message.

[0370] Step 4:

[0371] The user (caregiver robot) begins acting according to the generated support plan. The input is the support plan sent from the server in step 3. Based on the plan, the user provides support for meals and exercise to the person requiring care and interacts with them as needed. The output is a report on the support provided to the person requiring care. In terms of specific actions, the robot automatically moves to the person requiring care and assists with the planned activities.

[0372] Step 5:

[0373] The user recognizes and analyzes emotions from voice tone and facial expressions. The input is voice and video data of the person receiving care. An emotion engine processes this data to identify the person's emotional state (e.g., joy, anxiety). The output is the result of the emotion analysis. Specifically, the robot acquires data through voice and camera input and determines the emotional state in real time.

[0374] Step 6:

[0375] The server accumulates long-term data to assess the health and emotional trends of care recipients. The input is a history of health and emotional data collected to date. The server analyzes the history stored in the database to identify areas for improvement and strategies for promoting health. The output is analytical results that help improve ongoing support plans. Specifically, the server generates monthly reports and provides them to healthcare professionals and family caregivers.

[0376] (Application Example 2)

[0377] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0378] In modern industrial and welfare environments, real-time monitoring of the health and psychological state of workers and those requiring care is crucial for improving safety and comfort. However, conventional methods are not sufficiently automated in assessing health status or creating individualized support plans, making it difficult to provide appropriate support based on emotional states. This has led to problems such as overwork and psychological burden in the work environment.

[0379] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0380] In this invention, the server includes means for collecting sensor data to monitor the health status of care recipients and workers in real time, means for analyzing the collected sensor data using artificial intelligence, and means for automatically creating individual plans for care recipients and workers based on the analysis results. This makes it possible to effectively provide workload reduction and psychological stability in accordance with the health and emotional state of workers.

[0381] A "person requiring care" is an individual who needs care or support to carry out their daily activities.

[0382] A "worker" is an individual who performs a specific task in a factory, industrial setting, or similar location.

[0383] "Health status" refers to various vital signs and physical condition of the body, including heart rate, body temperature, and blood pressure.

[0384] "Psychological state" refers to an individual's emotions and mental condition, including mental conditions such as anxiety, stress, and a sense of security.

[0385] "Sensor data" refers to information obtained from various sensors used to monitor health conditions and work environments.

[0386] Artificial intelligence is a technology that uses machine learning and algorithms to analyze data and support decision-making.

[0387] An "individualized plan" refers to a support plan optimized for each individual based on the collected data.

[0388] A "robot" is a mechanical device that can perform programmed actions, and is particularly intended to assist workers and those requiring care.

[0389] "Emotional analysis" refers to the process of analyzing and evaluating an individual's emotional state based on audio and image data.

[0390] "Methods of communication" refer to the means and techniques used when interacting with others, and include media such as language, nonverbal communication, voice, and text.

[0391] The system for implementing this invention includes multiple means for monitoring the health and psychological state of workers and those requiring care in real time and providing appropriate support. Its specific form is described below.

[0392] The server uses various sensors to acquire vital signs for monitoring health status. Examples include heart rate sensors and thermometers. Sensor data is transmitted to the server via Bluetooth, Wi-Fi, etc. Upon receiving this data, the server performs analysis using artificial intelligence technology (e.g., TensorFlow or PyTorch). Based on the analysis results, an individualized support plan is automatically generated.

[0393] The server also receives audio and image data for sentiment analysis. For this purpose, audio and image input from smart devices worn by workers or care recipients is used. Sentiment analysis software, such as the Affectiva API, is used for sentiment analysis. This allows for real-time monitoring of emotional changes and appropriate responses.

[0394] The user robot communicates appropriately with the worker based on the support plan from the server. For example, if a certain level of stress is detected, the robot will suggest temporarily suspending the work and provide advice on relaxation.

[0395] As a specific example, if a worker's heart rate is higher than normal in a factory and emotional analysis detects signs of stress, the robot will respond by saying, "I suggest a 10-minute break. I will play some relaxing music."

[0396] Examples of prompt statements for a generative AI model are as follows:

[0397] "Please explain how to propose measures to reduce workload based on real-time monitoring of workers' health and emotions in a factory."

[0398] Thus, the present invention functions as a system that can integrate physical health management and psychological support for workers and those requiring care.

[0399] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0400] Step 1:

[0401] The server receives health data from sensors worn by care recipients or workers. Specifically, vital data such as heart rate, body temperature, and blood pressure are input to the server via Bluetooth or Wi-Fi communication. The server stores this data chronologically and uses it as basic data for detecting abnormalities.

[0402] Step 2:

[0403] The server uses artificial intelligence algorithms to analyze the received vital data. For example, TensorFlow is used to detect anomalies and perform trend analysis. The output includes an assessment of whether anomalies were detected and whether the health status is stable. These analysis results serve as foundational information for creating individualized support plans.

[0404] Step 3:

[0405] The server automatically generates individualized support plans for each care recipient and worker based on the results of the health status analysis. The plan generation is performed using a generation AI model and prompts. The output includes a list of the plan and support activity priorities, which are used as instructions in the next processing step.

[0406] Step 4:

[0407] The user robot gives instructions to the target person via a voice output device, based on an individualized support plan sent from the server. Specific actions include voice commands such as "Let's take a break" or "It's time to relax." The robot observes the target person's response and prepares the next action based on the plan.

[0408] Step 5:

[0409] The server receives voice and facial expression data from workers and those receiving care, and performs emotion analysis. Using emotion analysis tools such as the Affectiva API with the voice and image data, it evaluates the degree of stress and anxiety. An emotional state report is generated as output, which is then used as data for providing psychological support.

[0410] Step 6:

[0411] The device dynamically adjusts its communication methods in real time based on the results of emotion analysis. Specifically, it adopts an approach that changes the tone and content of its language according to the target person's emotional state. This allows for the optimization of psychological support for the target person.

[0412] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0413] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0414] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0415] [Third Embodiment]

[0416] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0417] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0418] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0419] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0420] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0421] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0422] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0423] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0424] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0425] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0426] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0427] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0428] This invention aims to realize a system that monitors the health status of care recipients in real time and automatically creates an appropriate care plan. This system collects the health information of care recipients through sensor devices and centrally manages it on a server. Subsequently, the server uses artificial intelligence to analyze this data and automatically formulates an optimal care plan for the care recipient.

[0429] The generated care plan is sent to the user (caregiver robot), and its execution begins. Here, the caregiver robot performs the necessary tasks to support the daily life of the person requiring care, based on the collected information and the plan. Specifically, the user (caregiver robot) communicates with the person requiring care using natural language and provides daily living support such as preparing meals and confirming medication.

[0430] For example, if a care recipient is at risk of hypertension, the server analyzes the measured data and automatically adjusts the day's meal plan to include a low-sodium menu. The user (caregiver robot) then prepares and serves the appropriate meal according to this plan. After the meal, the robot checks the recipient's health status and incorporates the findings into the next care plan.

[0431] In this way, the system comprehensively manages the health and provides support for the daily lives of those requiring care, reducing the burden on caregivers while functioning as a system that can provide high-quality care.

[0432] The following describes the processing flow.

[0433] Step 1:

[0434] The server periodically collects health data such as heart rate, blood pressure, and body temperature from sensor devices attached to the person requiring care, and stores it in a database.

[0435] Step 2:

[0436] The server uses artificial intelligence to analyze the collected health data and detect any anomalies or health risks. The results of this analysis are then used in the next step.

[0437] Step 3:

[0438] Based on the analysis results, the server automatically generates an individually customized care plan, taking into account the health status and lifestyle of the person requiring care.

[0439] Step 4:

[0440] The server transmits the generated care plan to the user (caregiver robot) and sets the execution schedule.

[0441] Step 5:

[0442] The user (caregiver robot) initiates daily communication with the care recipient based on the received care plan. This includes offering words of encouragement and checking on their health, providing a sense of security.

[0443] Step 6:

[0444] The user (caregiver robot) performs daily living support tasks such as providing meals, checking medication timing, and managing daily necessities according to a plan, and provides necessary information to the person requiring care.

[0445] Step 7:

[0446] The terminal allows users to manage the activity status of the care robot and feedback from the care recipient, and feeds this information back to the server to adjust the next schedule and new care plans.

[0447] Step 8:

[0448] The server evaluates the effectiveness of the plan based on the feedback received and performs data analysis to improve and optimize future care plans as needed.

[0449] (Example 1)

[0450] Next, we will describe Example 1. 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."

[0451] In an aging society, there is a need to effectively manage the health and provide support for the daily lives of those requiring care. However, traditional care relies heavily on human resources, leading to shortages and burdens of personnel. In particular, there are limitations to monitoring the health status of those requiring care in real time and providing individually optimized care plans quickly. To solve this problem, a system is needed that continuously monitors the health of those requiring care and automatically and efficiently formulates appropriate care plans.

[0452] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0453] In this invention, the server includes means for collecting data from a measuring device for monitoring the health status of a person requiring care in real time, means for an analysis device using a generative AI model to analyze the collected measurement data, and means for automatically creating an individualized care plan for the person requiring care based on the analysis results. This makes it possible to grasp the health status of the person requiring care in real time, quickly formulate an optimal care plan, and provide effective care services while reducing the burden on human resources.

[0454] A "measuring device" is a device used to monitor the health status of a person requiring care in real time, and includes sensors that measure biometric information such as heart rate, blood pressure, and body temperature.

[0455] A "generative AI model" is a part of artificial intelligence used to analyze collected measurement data, and it constitutes an algorithm that recognizes specific patterns and derives individualized care plans.

[0456] An "analysis device" is a set of hardware or software that uses a generative AI model to analyze collected biometric information and performs computational processing to evaluate the health status of a person requiring care.

[0457] A "care plan" is a detailed action plan formulated based on the individual health condition and living situation of a person requiring care, for the purpose of providing appropriate life support and health management.

[0458] "Caregiving equipment" refers to robots and automated devices designed to provide direct support to those requiring care based on care plans and analysis results, and includes life support and communication functions.

[0459] "Feedback" refers to the process by which caregiving machines collect information on the results of their support to care recipients and transmit that information to a data management system such as a server to help improve future care plans.

[0460] This invention provides a system for monitoring the health status of care recipients in real time and automatically generating an optimal care plan. The elements constituting this system and how it is specifically implemented are described below.

[0461] Data collection and transfer

[0462] The terminal uses measuring devices to collect biometric information such as heart rate, blood pressure, and body temperature in order to monitor the health status of those requiring care. Wireless communication technologies such as Bluetooth and Wi-Fi are used to securely transfer this data to a server. The collected data is stored in a database system on the server and prepared for analysis.

[0463] Data Analysis

[0464] The server analyzes the collected biometric information using a generative AI model. This analysis utilizes software such as the AI ​​framework TensorFlow, and the machine learning model recognizes patterns in the biometric information to appropriately assess the health status of the person requiring care. For example, if the heart rate shows an irregular pattern, it is determined that there is a risk of arrhythmia and this is reflected in the care plan.

[0465] Creating a care plan

[0466] Based on the analysis results, the server generates an individualized care plan. This plan includes meal and medication schedules, as well as daily living support details, designing comprehensive support to ensure the care recipient can live comfortably and securely. The generated plan is then transmitted to the care machine and implemented.

[0467] Specific example

[0468] For example, if a care recipient has a risk of hypertension, the server analyzes the day's blood pressure data and incorporates a low-sodium meal plan. Based on this plan, the care machine prepares an appropriate low-sodium meal and provides it to the care recipient. The results of the post-meal health check are also fed back to the server to help in formulating the next care plan.

[0469] Example of a prompt

[0470] "Based on the latest health data of the person requiring care, please create an individualized care plan tailored to their specific needs. If there is a risk of hypertension, please adjust their diet to be low in salt."

[0471] In this way, this invention makes it possible to efficiently manage the health of those requiring care and to provide high-quality care services.

[0472] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0473] Step 1:

[0474] The terminal acquires data from measuring devices to collect health information of care recipients in real time. Specifically, sensors measure heart rate, blood pressure, and body temperature, and transmit this data to the terminal via Bluetooth communication. The input for this step is biometric data from the sensors, and the output is the measurement data accumulated in the terminal.

[0475] Step 2:

[0476] The terminal securely transmits the collected biometric data to the server using the HTTPS protocol. The biometric data stored on the terminal is used as input, and the data is formatted into a format usable by the server. The output is the formatted data being stored in the server's receiving memory.

[0477] Step 3:

[0478] The server stores the received data in a database and analyzes the data using a generative AI model. The input is biometric data sent to the server, and the AI ​​modeling performs data calculations to output an evaluation result of the health status of the person requiring care. In the analysis, the TensorFlow library is used to run a machine learning model and detect anomalies and patterns.

[0479] Step 4:

[0480] The server automatically generates individualized care plans based on the analysis results. The input is the health status assessment results from an AI model, and the planning algorithm is used to create the optimal care plan. The output is a care plan that includes specific details of daily living support. This plan includes meal menus and medication schedules.

[0481] Step 5:

[0482] The server transmits the generated care plan to the care machine, which is the user. The input is the care plan stored on the server, and the plan is transmitted to the care machine using a communication method. The output is the care plan received by the care machine.

[0483] Step 6:

[0484] The user performs daily living support based on the received care plan. Specifically, the care machine provides meals to the care recipient according to the plan and checks their health status. The input is the received care plan, and the output is data on the care recipient's reaction and health status after the plan is implemented. This data is fed back to the server and reflected in future plans.

[0485] (Application Example 1)

[0486] Next, we will explain Application Example 1. In the following explanation, 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."

[0487] In factories and workplaces, it is crucial to manage workers' health in real time to prevent overwork and safety risks. However, conventional management systems struggle to provide appropriate management tailored to each worker's health condition and workload, impacting work efficiency and safety. Furthermore, there are concerns that excessive stress and physical strain can harm workers' health due to the work environment. Addressing these challenges is essential to provide a safer and more efficient work environment.

[0488] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0489] In this invention, the server includes means for collecting biometric information to monitor the health status of workers in real time, means for analyzing the collected biometric information using machine learning, and means for automatically creating individual work plans for workers based on the analysis results. This makes it possible to provide an efficient and safe work environment that takes into account the health status of workers.

[0490] "Worker" refers to a worker who performs specific tasks in a factory or work site.

[0491] "Health status" refers to the physical and mental condition of a worker as understood through biometric information.

[0492] "Real-time" refers to the continuous processing, acquisition, or provision of information at the very moment an event occurs.

[0493] "Biometric information" refers to data obtained directly from the worker's body, such as heart rate, body temperature, and stress level.

[0494] "Analysis methods" refer to the process of collecting data and using machine learning techniques to interpret its meaning.

[0495] "Machine learning" refers to the technique of building computational models using large amounts of data and using those models to predict or classify new data.

[0496] A "work plan" refers to a plan that defines the procedures and timing for carrying out work safely and efficiently, based on the health condition of the workers and the work environment.

[0497] A "work support device" refers to a device that assists workers and provides help to perform tasks efficiently and safely.

[0498] The system implementing this invention is designed to manage the health status of workers and provide an efficient and safe working environment. The main components are a biometric information collection device worn by the worker, a server for processing and analyzing the data, and a work support device.

[0499] The server acquires data transmitted in real time from biometric data collection devices via Bluetooth or Wi-Fi. These devices continuously record information such as heart rate, body temperature, and stress levels. The server analyzes this data using Python programs and machine learning models such as TensorFlow. Based on the analysis results, it automatically creates an optimized work plan for each worker, sends instructions to work support devices, and provides workers with an appropriate working environment.

[0500] The work support system prevents ambiguous instructions and provides clear feedback to workers through a natural language interface. A Flask-based API receives analysis results from the server and transmits instructions to the work support system. Specifically, it suggests breaks, performs safety checks, and adjusts work processes based on the worker's health condition.

[0501] For example, if an abnormally high heart rate is detected while a worker is operating a machine, the system will immediately recommend a break and notify both the worker and their supervisor. This helps prevent accidents caused by overwork and protects the health of workers.

[0502] The following are examples of prompts for the generative AI model in this system.

[0503] "Enter worker heart rate data and work process information, and propose methods to optimize work conditions and health status."

[0504] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0505] Step 1:

[0506] The server receives biometric data such as heart rate, body temperature, and stress level from biometric data collection devices via Bluetooth or Wi-Fi. The input is real-time data from the devices, and the output is recorded in a database. At this stage, data format conversion and missing value imputation are performed.

[0507] Step 2:

[0508] The server passes the received biometric information to a machine learning model for analysis. The input is augmented biometric data, and the output is an evaluation of the worker's health status. TensorFlow is used for analysis to detect anomalies and predict health status.

[0509] Step 3:

[0510] The server generates a work plan for each worker based on the analyzed evaluation results. The input is the health status evaluation result, and the output is the optimized work plan. Python is used to analyze the evaluation results and generate prompt statements to instruct the AI ​​model, thereby optimizing the work plan.

[0511] Step 4:

[0512] The server transmits the generated work plan to the work support device. The input is the work plan, and the output is instructions for the work support device. Information is sent to the work support device via an API using Flask, and instructions are given to the worker via a natural language interface.

[0513] Step 5:

[0514] The work support system provides workers with real-time instructions and feedback through a natural language interface. Input is instructions from the server, and output is voice or text feedback to the worker. This allows workers to perform their tasks safely and efficiently.

[0515] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0516] This invention combines a system that monitors the health status of care recipients in real time and automatically generates individualized care plans with an emotion engine. The system centrally manages the health information of care recipients from sensor devices on a server and analyzes it using artificial intelligence. Based on the results of this analysis, it generates an optimal care plan, which is then transmitted to a caregiver robot for execution.

[0517] Furthermore, the user (caregiver robot) is equipped with an emotion engine that recognizes the tone of voice and facial expressions of the person receiving care and performs emotional analysis. Using the results of this analysis, it can dynamically adjust its communication methods to promote the psychological stability of the person receiving care.

[0518] For example, if a care recipient shows signs of anxiety, the emotion engine detects that anxiety. The server readjusts the care plan to reflect that anxiety, and the user (caregiver robot) responds appropriately to the care recipient through reassuring words and encouragement.

[0519] Furthermore, the server can evaluate long-term psychological trends based on emotional data, which can be used to improve the quality of care for those requiring care. In this way, the system of the present invention, by utilizing emotion recognition, can comprehensively realize physical health management and psychological support, thereby improving the quality of life.

[0520] The following describes the processing flow.

[0521] Step 1:

[0522] The server collects health data from care recipients through sensor devices and stores information such as heart rate and blood pressure in a database.

[0523] Step 2:

[0524] The server uses artificial intelligence to analyze the collected health data, assess the current health status of those requiring care, and determine if there are any abnormalities.

[0525] Step 3:

[0526] The server automatically generates an optimal care plan for the person requiring care based on the analysis results. This plan includes details of daily life support and the timing of that support.

[0527] Step 4:

[0528] The server sends the generated care plan and analysis results to the user (caregiver robot).

[0529] Step 5:

[0530] The user (caregiver robot) initiates contact with the person requiring care and prepares necessary life support based on the received care plan.

[0531] Step 6:

[0532] The user (caregiver robot) uses an emotion engine to recognize emotions from the voice and facial expressions of the person receiving care, and analyzes that information in real time.

[0533] Step 7:

[0534] The user (caregiver robot) communicates appropriately with the care recipient based on the results of emotion analysis. For example, if the care recipient shows signs of anxiety, the robot will offer words of encouragement.

[0535] Step 8:

[0536] The server uses data obtained from the emotion engine to further adjust the care plan. For example, if psychological support is needed, time for that will be incorporated into the plan.

[0537] Step 9:

[0538] The terminal displays server analysis results and updated care plan information, and provides alerts to caregivers when necessary.

[0539] Step 10:

[0540] The server provides feedback that contributes to improving care services by analyzing the health status and emotional data of those receiving care over the long term.

[0541] (Example 2)

[0542] Next, we will describe Example 2. 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."

[0543] In modern society, the increasing number of people requiring care due to an aging population is a significant problem. It is crucial to monitor the health status of those requiring care in real time and to provide individualized support plans quickly and appropriately. However, conventional methods have struggled to address psychological aspects, including emotional changes, and have failed to adequately improve the quality of life for those requiring care. To address this, a comprehensive care system is needed that considers not only physical health management but also psychological stability.

[0544] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0545] In this invention, the server includes means for collecting data from a detector to monitor the health status of the person requiring care; means for analyzing the collected data using intelligence; means for automatically creating an individualized support plan for the person requiring care based on the analysis results; means for transmitting the support plan and analysis results to a mobile support device and having it carry out life support; means for dynamically adjusting the interaction with the person requiring care using a device equipped with an emotion engine for analyzing voice and facial expressions to recognize emotions; and means for accumulating long-term data and evaluating the psychological and physical health trends of the person requiring care. This makes it possible to comprehensively manage the health status of the person requiring care and provide appropriate physical and psychological support.

[0546] A "person requiring care" refers to a person who, due to their physical or mental health condition, needs assistance from others to carry out their daily activities.

[0547] "Health status" refers to the state of physical and mental health and serves as a standard for evaluating the quality of daily life.

[0548] A "detector" refers to a device used to acquire physical and environmental data of a person requiring care in real time.

[0549] "Intelligence" refers to algorithms and models that are artificially programmed to perform data analysis and decision support.

[0550] A "mobile support device" refers to a programmed, mobile robot designed to assist in the daily lives of people requiring care.

[0551] The term "emotional engine" refers to a technology that analyzes the voice and facial expressions of those requiring care to estimate their psychological and emotional state.

[0552] "Psychological and physical health tendencies" refer to patterns related to the emotional and physiological states of care recipients that change over time.

[0553] "Dynamically adjusting dialogue" refers to flexibly changing the content and method of communication according to the current emotional state and health condition of the person receiving care.

[0554] This invention is a system for improving the quality of life for those requiring care. The system consists of multiple components, including a server, terminals, and users.

[0555] First, the server collects data related to the health status of the person receiving care from sensor devices. These devices include heart rate monitors and accelerometers. The data from the sensors is transmitted to the server in real time.

[0556] Next, the server performs artificial intelligence analysis on the collected data. Existing machine learning libraries such as TensorFlow and PyTorch are used for this analysis. This AI model assesses the physical and psychological health status of those requiring care and generates individually optimized support plans.

[0557] As a caregiver robot, the user begins actions based on the generated support plan. This robot incorporates an emotion engine and uses a camera and microphone to recognize the tone of voice and facial expressions of the person receiving care. Based on these results, natural language communication with the person receiving care is dynamically adjusted to provide optimal support.

[0558] For example, if a care recipient shows anxiety, the robot can offer reassuring words such as, "Let's make some tea today to help you feel calmer." Furthermore, based on long-term accumulated data, the robot can evaluate the psychological tendencies of care recipients and use this information to improve their care in the future.

[0559] Examples of prompts that utilize this invention include, "Analyze the care needs of elderly individuals and propose an optimized care plan," and "Use the emotion engine to generate a communication strategy suitable for care recipients who are experiencing anxiety."

[0560] Thus, the present invention can significantly improve the quality of life for those requiring care by providing comprehensive physical and psychological support.

[0561] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0562] Step 1:

[0563] The server collects data from sensor devices to monitor the health status of care recipients in real time. Inputs include biometric data such as heart rate, blood pressure, and activity level. This data is transmitted to the server via Bluetooth or Wi-Fi and temporarily stored in a database. Outputs are sensor data in the format stored in the database for future analysis.

[0564] Step 2:

[0565] The server analyzes the collected sensor data using an AI model. The input is the biometric data collected in step 1. The data is processed using TensorFlow or PyTorch, and machine learning algorithms are used to identify abnormal patterns and trends. The output is an assessment of the health status of the person requiring care. Specifically, if the server detects an anomaly during analysis, it generates an alert and notifies healthcare professionals.

[0566] Step 3:

[0567] The server automatically generates a support plan based on the analysis results. The input is the health status assessment results obtained in step 2. Based on these results, an individual support plan is formulated, and necessary care activities (e.g., exercise, diet, medication) are planned. The output is the generated support plan. In terms of specific actions, the server sends the plan to the caregiver robot as a digital message.

[0568] Step 4:

[0569] The user (caregiver robot) begins acting according to the generated support plan. The input is the support plan sent from the server in step 3. Based on the plan, the user provides support for meals and exercise to the person requiring care and interacts with them as needed. The output is a report on the support provided to the person requiring care. In terms of specific actions, the robot automatically moves to the person requiring care and assists with the planned activities.

[0570] Step 5:

[0571] The user recognizes and analyzes emotions from voice tone and facial expressions. The input is voice and video data of the person receiving care. An emotion engine processes this data to identify the person's emotional state (e.g., joy, anxiety). The output is the result of the emotion analysis. Specifically, the robot acquires data through voice and camera input and determines the emotional state in real time.

[0572] Step 6:

[0573] The server accumulates long-term data to assess the health and emotional trends of care recipients. The input is a history of health and emotional data collected to date. The server analyzes the history stored in the database to identify areas for improvement and strategies for promoting health. The output is analytical results that help improve ongoing support plans. Specifically, the server generates monthly reports and provides them to healthcare professionals and family caregivers.

[0574] (Application Example 2)

[0575] Next, we will explain application example 2. In the following explanation, 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."

[0576] In modern industrial and welfare environments, real-time monitoring of the health and psychological state of workers and those requiring care is crucial for improving safety and comfort. However, conventional methods are not sufficiently automated in assessing health status or creating individualized support plans, making it difficult to provide appropriate support based on emotional states. This has led to problems such as overwork and psychological burden in the work environment.

[0577] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0578] In this invention, the server includes means for collecting sensor data to monitor the health status of care recipients and workers in real time, means for analyzing the collected sensor data using artificial intelligence, and means for automatically creating individual plans for care recipients and workers based on the analysis results. This makes it possible to effectively provide workload reduction and psychological stability in accordance with the health and emotional state of workers.

[0579] A "person requiring care" is an individual who needs care or support to carry out their daily activities.

[0580] A "worker" is an individual who performs a specific task in a factory, industrial setting, or similar location.

[0581] "Health status" refers to various vital signs and physical condition of the body, including heart rate, body temperature, and blood pressure.

[0582] "Psychological state" refers to an individual's emotions and mental condition, including mental conditions such as anxiety, stress, and a sense of security.

[0583] "Sensor data" refers to information obtained from various sensors used to monitor health conditions and work environments.

[0584] Artificial intelligence is a technology that uses machine learning and algorithms to analyze data and support decision-making.

[0585] An "individualized plan" refers to a support plan optimized for each individual based on the collected data.

[0586] A "robot" is a mechanical device that can perform programmed actions, and is particularly intended to assist workers and those requiring care.

[0587] "Emotional analysis" refers to the process of analyzing and evaluating an individual's emotional state based on audio and image data.

[0588] "Methods of communication" refer to the means and techniques used when interacting with others, and include media such as language, nonverbal communication, voice, and text.

[0589] The system for implementing this invention includes multiple means for monitoring the health and psychological state of workers and those requiring care in real time and providing appropriate support. Its specific form is described below.

[0590] The server uses various sensors to acquire vital signs for monitoring health status. Examples include heart rate sensors and thermometers. Sensor data is transmitted to the server via Bluetooth, Wi-Fi, etc. Upon receiving this data, the server performs analysis using artificial intelligence technology (e.g., TensorFlow or PyTorch). Based on the analysis results, an individualized support plan is automatically generated.

[0591] The server also receives audio and image data for sentiment analysis. For this purpose, audio and image input from smart devices worn by workers or care recipients is used. Sentiment analysis software, such as the Affectiva API, is used for sentiment analysis. This allows for real-time monitoring of emotional changes and appropriate responses.

[0592] The user robot communicates appropriately with the worker based on the support plan from the server. For example, if a certain level of stress is detected, the robot will suggest temporarily suspending the work and provide advice on relaxation.

[0593] As a specific example, if a worker's heart rate is higher than normal in a factory and emotional analysis detects signs of stress, the robot will respond by saying, "I suggest a 10-minute break. I will play some relaxing music."

[0594] Examples of prompt statements for a generative AI model are as follows:

[0595] "Please explain how to propose measures to reduce workload based on real-time monitoring of workers' health and emotions in a factory."

[0596] Thus, the present invention functions as a system that can integrate physical health management and psychological support for workers and those requiring care.

[0597] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0598] Step 1:

[0599] The server receives health data from sensors worn by care recipients or workers. Specifically, vital data such as heart rate, body temperature, and blood pressure are input to the server via Bluetooth or Wi-Fi communication. The server stores this data chronologically and uses it as basic data for detecting abnormalities.

[0600] Step 2:

[0601] The server uses artificial intelligence algorithms to analyze the received vital data. For example, TensorFlow is used to detect anomalies and perform trend analysis. The output includes an assessment of whether anomalies were detected and whether the health status is stable. These analysis results serve as foundational information for creating individualized support plans.

[0602] Step 3:

[0603] The server automatically generates individualized support plans for each care recipient and worker based on the results of the health status analysis. The plan generation is performed using a generation AI model and prompts. The output includes a list of the plan and support activity priorities, which are used as instructions in the next processing step.

[0604] Step 4:

[0605] The user robot gives instructions to the target person via a voice output device, based on an individualized support plan sent from the server. Specific actions include voice commands such as "Let's take a break" or "It's time to relax." The robot observes the target person's response and prepares the next action based on the plan.

[0606] Step 5:

[0607] The server receives voice and facial expression data from workers and those receiving care, and performs emotion analysis. Using emotion analysis tools such as the Affectiva API with the voice and image data, it evaluates the degree of stress and anxiety. An emotional state report is generated as output, which is then used as data for providing psychological support.

[0608] Step 6:

[0609] The device dynamically adjusts its communication methods in real time based on the results of emotion analysis. Specifically, it adopts an approach that changes the tone and content of its language according to the target person's emotional state. This allows for the optimization of psychological support for the target person.

[0610] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0611] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0612] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0613] [Fourth Embodiment]

[0614] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0615] As shown in Figure 7, the 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.

[0616] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0617] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0618] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0619] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0620] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0621] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0622] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0623] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0624] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0625] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0626] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0627] This invention aims to realize a system that monitors the health status of care recipients in real time and automatically creates an appropriate care plan. This system collects the health information of care recipients through sensor devices and centrally manages it on a server. Subsequently, the server uses artificial intelligence to analyze this data and automatically formulates an optimal care plan for the care recipient.

[0628] The generated care plan is sent to the user (caregiver robot), and its execution begins. Here, the caregiver robot performs the necessary tasks to support the daily life of the person requiring care, based on the collected information and the plan. Specifically, the user (caregiver robot) communicates with the person requiring care using natural language and provides daily living support such as preparing meals and confirming medication.

[0629] For example, if a care recipient is at risk of hypertension, the server analyzes the measured data and automatically adjusts the day's meal plan to include a low-sodium menu. The user (caregiver robot) then prepares and serves the appropriate meal according to this plan. After the meal, the robot checks the recipient's health status and incorporates the findings into the next care plan.

[0630] In this way, the system comprehensively manages the health and provides support for the daily lives of those requiring care, reducing the burden on caregivers while functioning as a system that can provide high-quality care.

[0631] The following describes the processing flow.

[0632] Step 1:

[0633] The server periodically collects health data such as heart rate, blood pressure, and body temperature from sensor devices attached to the person requiring care, and stores it in a database.

[0634] Step 2:

[0635] The server uses artificial intelligence to analyze the collected health data and detect any anomalies or health risks. The results of this analysis are then used in the next step.

[0636] Step 3:

[0637] Based on the analysis results, the server automatically generates an individually customized care plan, taking into account the health status and lifestyle of the person requiring care.

[0638] Step 4:

[0639] The server transmits the generated care plan to the user (caregiver robot) and sets the execution schedule.

[0640] Step 5:

[0641] The user (caregiver robot) initiates daily communication with the care recipient based on the received care plan. This includes offering words of encouragement and checking on their health, providing a sense of security.

[0642] Step 6:

[0643] The user (caregiver robot) performs daily living support tasks such as providing meals, checking medication timing, and managing daily necessities according to a plan, and provides necessary information to the person requiring care.

[0644] Step 7:

[0645] The terminal allows users to manage the activity status of the care robot and feedback from the care recipient, and feeds this information back to the server to adjust the next schedule and new care plans.

[0646] Step 8:

[0647] The server evaluates the effectiveness of the plan based on the feedback received and performs data analysis to improve and optimize future care plans as needed.

[0648] (Example 1)

[0649] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0650] In an aging society, there is a need to effectively manage the health and provide support for the daily lives of those requiring care. However, traditional care relies heavily on human resources, leading to shortages and burdens of personnel. In particular, there are limitations to monitoring the health status of those requiring care in real time and providing individually optimized care plans quickly. To solve this problem, a system is needed that continuously monitors the health of those requiring care and automatically and efficiently formulates appropriate care plans.

[0651] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0652] In this invention, the server includes means for collecting data from a measuring device for monitoring the health status of a person requiring care in real time, means for an analysis device using a generative AI model to analyze the collected measurement data, and means for automatically creating an individualized care plan for the person requiring care based on the analysis results. This makes it possible to grasp the health status of the person requiring care in real time, quickly formulate an optimal care plan, and provide effective care services while reducing the burden on human resources.

[0653] A "measuring device" is a device used to monitor the health status of a person requiring care in real time, and includes sensors that measure biometric information such as heart rate, blood pressure, and body temperature.

[0654] A "generative AI model" is a part of artificial intelligence used to analyze collected measurement data, and it constitutes an algorithm that recognizes specific patterns and derives individualized care plans.

[0655] An "analysis device" is a set of hardware or software that uses a generative AI model to analyze collected biometric information and performs computational processing to evaluate the health status of a person requiring care.

[0656] A "care plan" is a detailed action plan formulated based on the individual health condition and living situation of a person requiring care, for the purpose of providing appropriate life support and health management.

[0657] "Caregiving equipment" refers to robots and automated devices designed to provide direct support to those requiring care based on care plans and analysis results, and includes life support and communication functions.

[0658] "Feedback" refers to the process by which caregiving machines collect information on the results of their support to care recipients and transmit that information to a data management system such as a server to help improve future care plans.

[0659] This invention provides a system for monitoring the health status of care recipients in real time and automatically generating an optimal care plan. The elements constituting this system and how it is specifically implemented are described below.

[0660] Data collection and transfer

[0661] The terminal uses measuring devices to collect biometric information such as heart rate, blood pressure, and body temperature in order to monitor the health status of those requiring care. Wireless communication technologies such as Bluetooth and Wi-Fi are used to securely transfer this data to a server. The collected data is stored in a database system on the server and prepared for analysis.

[0662] Data Analysis

[0663] The server analyzes the collected biometric information using a generative AI model. This analysis utilizes software such as the AI ​​framework TensorFlow, and the machine learning model recognizes patterns in the biometric information to appropriately assess the health status of the person requiring care. For example, if the heart rate shows an irregular pattern, it is determined that there is a risk of arrhythmia and this is reflected in the care plan.

[0664] Creating a care plan

[0665] Based on the analysis results, the server generates an individualized care plan. This plan includes meal and medication schedules, as well as daily living support details, designing comprehensive support to ensure the care recipient can live comfortably and securely. The generated plan is then transmitted to the care machine and implemented.

[0666] Specific example

[0667] For example, if a care recipient has a risk of hypertension, the server analyzes the day's blood pressure data and incorporates a low-sodium meal plan. Based on this plan, the care machine prepares an appropriate low-sodium meal and provides it to the care recipient. The results of the post-meal health check are also fed back to the server to help in formulating the next care plan.

[0668] Example of a prompt

[0669] "Based on the latest health data of the person requiring care, please create an individualized care plan tailored to their specific needs. If there is a risk of hypertension, please adjust their diet to be low in salt."

[0670] In this way, this invention makes it possible to efficiently manage the health of those requiring care and to provide high-quality care services.

[0671] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0672] Step 1:

[0673] The terminal acquires data from measuring devices to collect health information of care recipients in real time. Specifically, sensors measure heart rate, blood pressure, and body temperature, and transmit this data to the terminal via Bluetooth communication. The input for this step is biometric data from the sensors, and the output is the measurement data accumulated in the terminal.

[0674] Step 2:

[0675] The terminal securely transmits the collected biometric data to the server using the HTTPS protocol. The biometric data stored on the terminal is used as input, and the data is formatted into a format usable by the server. The output is the formatted data being stored in the server's receiving memory.

[0676] Step 3:

[0677] The server stores the received data in a database and analyzes the data using a generative AI model. The input is biometric data sent to the server, and the AI ​​modeling performs data calculations to output an evaluation result of the health status of the person requiring care. In the analysis, the TensorFlow library is used to run a machine learning model and detect anomalies and patterns.

[0678] Step 4:

[0679] The server automatically generates individualized care plans based on the analysis results. The input is the health status assessment results from an AI model, and the planning algorithm is used to create the optimal care plan. The output is a care plan that includes specific details of daily living support. This plan includes meal menus and medication schedules.

[0680] Step 5:

[0681] The server transmits the generated care plan to the care machine, which is the user. The input is the care plan stored on the server, and the plan is transmitted to the care machine using a communication method. The output is the care plan received by the care machine.

[0682] Step 6:

[0683] The user performs daily living support based on the received care plan. Specifically, the care machine provides meals to the care recipient according to the plan and checks their health status. The input is the received care plan, and the output is data on the care recipient's reaction and health status after the plan is implemented. This data is fed back to the server and reflected in future plans.

[0684] (Application Example 1)

[0685] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0686] In factories and workplaces, it is crucial to manage workers' health in real time to prevent overwork and safety risks. However, conventional management systems struggle to provide appropriate management tailored to each worker's health condition and workload, impacting work efficiency and safety. Furthermore, there are concerns that excessive stress and physical strain can harm workers' health due to the work environment. Addressing these challenges is essential to provide a safer and more efficient work environment.

[0687] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0688] In this invention, the server includes means for collecting biometric information to monitor the health status of workers in real time, means for analyzing the collected biometric information using machine learning, and means for automatically creating individual work plans for workers based on the analysis results. This makes it possible to provide an efficient and safe work environment that takes into account the health status of workers.

[0689] "Worker" refers to a worker who performs specific tasks in a factory or work site.

[0690] "Health status" refers to the physical and mental condition of a worker as understood through biometric information.

[0691] "Real-time" refers to the continuous processing, acquisition, or provision of information at the very moment an event occurs.

[0692] "Biometric information" refers to data obtained directly from the worker's body, such as heart rate, body temperature, and stress level.

[0693] "Analysis methods" refer to the process of collecting data and using machine learning techniques to interpret its meaning.

[0694] "Machine learning" refers to the technique of building computational models using large amounts of data and using those models to predict or classify new data.

[0695] A "work plan" refers to a plan that defines the procedures and timing for carrying out work safely and efficiently, based on the health condition of the workers and the work environment.

[0696] A "work support device" refers to a device that assists workers and provides help to perform tasks efficiently and safely.

[0697] The system implementing this invention is designed to manage the health status of workers and provide an efficient and safe working environment. The main components are a biometric information collection device worn by the worker, a server for processing and analyzing the data, and a work support device.

[0698] The server acquires data transmitted in real time from biometric data collection devices via Bluetooth or Wi-Fi. These devices continuously record information such as heart rate, body temperature, and stress levels. The server analyzes this data using Python programs and machine learning models such as TensorFlow. Based on the analysis results, it automatically creates an optimized work plan for each worker, sends instructions to work support devices, and provides workers with an appropriate working environment.

[0699] The work support system prevents ambiguous instructions and provides clear feedback to workers through a natural language interface. A Flask-based API receives analysis results from the server and transmits instructions to the work support system. Specifically, it suggests breaks, performs safety checks, and adjusts work processes based on the worker's health condition.

[0700] For example, if an abnormally high heart rate is detected while a worker is operating a machine, the system will immediately recommend a break and notify both the worker and their supervisor. This helps prevent accidents caused by overwork and protects the health of workers.

[0701] The following are examples of prompts for the generative AI model in this system.

[0702] "Enter worker heart rate data and work process information, and propose methods to optimize work conditions and health status."

[0703] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0704] Step 1:

[0705] The server receives biometric data such as heart rate, body temperature, and stress level from biometric data collection devices via Bluetooth or Wi-Fi. The input is real-time data from the devices, and the output is recorded in a database. At this stage, data format conversion and missing value imputation are performed.

[0706] Step 2:

[0707] The server passes the received biometric information to a machine learning model for analysis. The input is augmented biometric data, and the output is an evaluation of the worker's health status. TensorFlow is used for analysis to detect anomalies and predict health status.

[0708] Step 3:

[0709] The server generates a work plan for each worker based on the analyzed evaluation results. The input is the health status evaluation result, and the output is the optimized work plan. Python is used to analyze the evaluation results and generate prompt statements to instruct the AI ​​model, thereby optimizing the work plan.

[0710] Step 4:

[0711] The server transmits the generated work plan to the work support device. The input is the work plan, and the output is instructions for the work support device. Information is sent to the work support device via an API using Flask, and instructions are given to the worker via a natural language interface.

[0712] Step 5:

[0713] The work support system provides workers with real-time instructions and feedback through a natural language interface. Input is instructions from the server, and output is voice or text feedback to the worker. This allows workers to perform their tasks safely and efficiently.

[0714] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0715] This invention combines a system that monitors the health status of care recipients in real time and automatically generates individualized care plans with an emotion engine. The system centrally manages the health information of care recipients from sensor devices on a server and analyzes it using artificial intelligence. Based on the results of this analysis, it generates an optimal care plan, which is then transmitted to a caregiver robot for execution.

[0716] Furthermore, the user (caregiver robot) is equipped with an emotion engine that recognizes the tone of voice and facial expressions of the person receiving care and performs emotional analysis. Using the results of this analysis, it can dynamically adjust its communication methods to promote the psychological stability of the person receiving care.

[0717] For example, if a care recipient shows signs of anxiety, the emotion engine detects that anxiety. The server readjusts the care plan to reflect that anxiety, and the user (caregiver robot) responds appropriately to the care recipient through reassuring words and encouragement.

[0718] Furthermore, the server can evaluate long-term psychological trends based on emotional data, which can be used to improve the quality of care for those requiring care. In this way, the system of the present invention, by utilizing emotion recognition, can comprehensively realize physical health management and psychological support, thereby improving the quality of life.

[0719] The following describes the processing flow.

[0720] Step 1:

[0721] The server collects health data from care recipients through sensor devices and stores information such as heart rate and blood pressure in a database.

[0722] Step 2:

[0723] The server uses artificial intelligence to analyze the collected health data, assess the current health status of those requiring care, and determine if there are any abnormalities.

[0724] Step 3:

[0725] The server automatically generates an optimal care plan for the person requiring care based on the analysis results. This plan includes details of daily life support and the timing of that support.

[0726] Step 4:

[0727] The server sends the generated care plan and analysis results to the user (caregiver robot).

[0728] Step 5:

[0729] The user (caregiver robot) initiates contact with the person requiring care and prepares necessary life support based on the received care plan.

[0730] Step 6:

[0731] The user (caregiver robot) uses an emotion engine to recognize emotions from the voice and facial expressions of the person receiving care, and analyzes that information in real time.

[0732] Step 7:

[0733] The user (caregiver robot) communicates appropriately with the care recipient based on the results of emotion analysis. For example, if the care recipient shows signs of anxiety, the robot will offer words of encouragement.

[0734] Step 8:

[0735] The server uses data obtained from the emotion engine to further adjust the care plan. For example, if psychological support is needed, time for that will be incorporated into the plan.

[0736] Step 9:

[0737] The terminal displays server analysis results and updated care plan information, and provides alerts to caregivers when necessary.

[0738] Step 10:

[0739] The server provides feedback that contributes to improving care services by analyzing the health status and emotional data of those receiving care over the long term.

[0740] (Example 2)

[0741] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0742] In modern society, the increasing number of people requiring care due to an aging population is a significant problem. It is crucial to monitor the health status of those requiring care in real time and to provide individualized support plans quickly and appropriately. However, conventional methods have struggled to address psychological aspects, including emotional changes, and have failed to adequately improve the quality of life for those requiring care. To address this, a comprehensive care system is needed that considers not only physical health management but also psychological stability.

[0743] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0744] In this invention, the server includes means for collecting data from a detector to monitor the health status of the person requiring care; means for analyzing the collected data using intelligence; means for automatically creating an individualized support plan for the person requiring care based on the analysis results; means for transmitting the support plan and analysis results to a mobile support device and having it carry out life support; means for dynamically adjusting the interaction with the person requiring care using a device equipped with an emotion engine for analyzing voice and facial expressions to recognize emotions; and means for accumulating long-term data and evaluating the psychological and physical health trends of the person requiring care. This makes it possible to comprehensively manage the health status of the person requiring care and provide appropriate physical and psychological support.

[0745] A "person requiring care" refers to a person who, due to their physical or mental health condition, needs assistance from others to carry out their daily activities.

[0746] "Health status" refers to the state of physical and mental health and serves as a standard for evaluating the quality of daily life.

[0747] A "detector" refers to a device used to acquire physical and environmental data of a person requiring care in real time.

[0748] "Intelligence" refers to algorithms and models that are artificially programmed to perform data analysis and decision support.

[0749] A "mobile support device" refers to a programmed, mobile robot designed to assist in the daily lives of people requiring care.

[0750] The term "emotional engine" refers to a technology that analyzes the voice and facial expressions of those requiring care to estimate their psychological and emotional state.

[0751] "Psychological and physical health tendencies" refer to patterns related to the emotional and physiological states of care recipients that change over time.

[0752] "Dynamically adjusting dialogue" refers to flexibly changing the content and method of communication according to the current emotional state and health condition of the person receiving care.

[0753] This invention is a system for improving the quality of life for those requiring care. The system consists of multiple components, including a server, terminals, and users.

[0754] First, the server collects data related to the health status of the person receiving care from sensor devices. These devices include heart rate monitors and accelerometers. The data from the sensors is transmitted to the server in real time.

[0755] Next, the server performs artificial intelligence analysis on the collected data. Existing machine learning libraries such as TensorFlow and PyTorch are used for this analysis. This AI model assesses the physical and psychological health status of those requiring care and generates individually optimized support plans.

[0756] As a caregiver robot, the user begins actions based on the generated support plan. This robot incorporates an emotion engine and uses a camera and microphone to recognize the tone of voice and facial expressions of the person receiving care. Based on these results, natural language communication with the person receiving care is dynamically adjusted to provide optimal support.

[0757] For example, if a care recipient shows anxiety, the robot can offer reassuring words such as, "Let's make some tea today to help you feel calmer." Furthermore, based on long-term accumulated data, the robot can evaluate the psychological tendencies of care recipients and use this information to improve their care in the future.

[0758] Examples of prompts that utilize this invention include, "Analyze the care needs of elderly individuals and propose an optimized care plan," and "Use the emotion engine to generate a communication strategy suitable for care recipients who are experiencing anxiety."

[0759] Thus, the present invention can significantly improve the quality of life for those requiring care by providing comprehensive physical and psychological support.

[0760] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0761] Step 1:

[0762] The server collects data from sensor devices to monitor the health status of care recipients in real time. Inputs include biometric data such as heart rate, blood pressure, and activity level. This data is transmitted to the server via Bluetooth or Wi-Fi and temporarily stored in a database. Outputs are sensor data in the format stored in the database for future analysis.

[0763] Step 2:

[0764] The server analyzes the collected sensor data using an AI model. The input is the biometric data collected in step 1. The data is processed using TensorFlow or PyTorch, and machine learning algorithms are used to identify abnormal patterns and trends. The output is an assessment of the health status of the person requiring care. Specifically, if the server detects an anomaly during analysis, it generates an alert and notifies healthcare professionals.

[0765] Step 3:

[0766] The server automatically generates a support plan based on the analysis results. The input is the health status assessment results obtained in step 2. Based on these results, an individual support plan is formulated, and necessary care activities (e.g., exercise, diet, medication) are planned. The output is the generated support plan. In terms of specific actions, the server sends the plan to the caregiver robot as a digital message.

[0767] Step 4:

[0768] The user (caregiver robot) begins acting according to the generated support plan. The input is the support plan sent from the server in step 3. Based on the plan, the user provides support for meals and exercise to the person requiring care and interacts with them as needed. The output is a report on the support provided to the person requiring care. In terms of specific actions, the robot automatically moves to the person requiring care and assists with the planned activities.

[0769] Step 5:

[0770] The user recognizes and analyzes emotions from voice tone and facial expressions. The input is voice and video data of the person receiving care. An emotion engine processes this data to identify the person's emotional state (e.g., joy, anxiety). The output is the result of the emotion analysis. Specifically, the robot acquires data through voice and camera input and determines the emotional state in real time.

[0771] Step 6:

[0772] The server accumulates long-term data to assess the health and emotional trends of care recipients. The input is a history of health and emotional data collected to date. The server analyzes the history stored in the database to identify areas for improvement and strategies for promoting health. The output is analytical results that help improve ongoing support plans. Specifically, the server generates monthly reports and provides them to healthcare professionals and family caregivers.

[0773] (Application Example 2)

[0774] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0775] In modern industrial and welfare environments, real-time monitoring of the health and psychological state of workers and those requiring care is crucial for improving safety and comfort. However, conventional methods are not sufficiently automated in assessing health status or creating individualized support plans, making it difficult to provide appropriate support based on emotional states. This has led to problems such as overwork and psychological burden in the work environment.

[0776] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0777] In this invention, the server includes means for collecting sensor data to monitor the health status of care recipients and workers in real time, means for analyzing the collected sensor data using artificial intelligence, and means for automatically creating individual plans for care recipients and workers based on the analysis results. This makes it possible to effectively provide workload reduction and psychological stability in accordance with the health and emotional state of workers.

[0778] A "person requiring care" is an individual who needs care or support to carry out their daily activities.

[0779] A "worker" is an individual who performs a specific task in a factory, industrial setting, or similar location.

[0780] "Health status" refers to various vital signs and physical condition of the body, including heart rate, body temperature, and blood pressure.

[0781] "Psychological state" refers to an individual's emotions and mental condition, including mental conditions such as anxiety, stress, and a sense of security.

[0782] "Sensor data" refers to information obtained from various sensors used to monitor health conditions and work environments.

[0783] Artificial intelligence is a technology that uses machine learning and algorithms to analyze data and support decision-making.

[0784] An "individualized plan" refers to a support plan optimized for each individual based on the collected data.

[0785] A "robot" is a mechanical device that can perform programmed actions, and is particularly intended to assist workers and those requiring care.

[0786] "Emotional analysis" refers to the process of analyzing and evaluating an individual's emotional state based on audio and image data.

[0787] "Methods of communication" refer to the means and techniques used when interacting with others, and include media such as language, nonverbal communication, voice, and text.

[0788] The system for implementing this invention includes multiple means for monitoring the health and psychological state of workers and those requiring care in real time and providing appropriate support. Its specific form is described below.

[0789] The server uses various sensors to acquire vital signs for monitoring health status. Examples include heart rate sensors and thermometers. Sensor data is transmitted to the server via Bluetooth, Wi-Fi, etc. Upon receiving this data, the server performs analysis using artificial intelligence technology (e.g., TensorFlow or PyTorch). Based on the analysis results, an individualized support plan is automatically generated.

[0790] The server also receives audio and image data for sentiment analysis. For this purpose, audio and image input from smart devices worn by workers or care recipients is used. Sentiment analysis software, such as the Affectiva API, is used for sentiment analysis. This allows for real-time monitoring of emotional changes and appropriate responses.

[0791] The user robot communicates appropriately with the worker based on the support plan from the server. For example, if a certain level of stress is detected, the robot will suggest temporarily suspending the work and provide advice on relaxation.

[0792] As a specific example, if a worker's heart rate is higher than normal in a factory and emotional analysis detects signs of stress, the robot will respond by saying, "I suggest a 10-minute break. I will play some relaxing music."

[0793] Examples of prompt statements for a generative AI model are as follows:

[0794] "Please explain how to propose measures to reduce workload based on real-time monitoring of workers' health and emotions in a factory."

[0795] Thus, the present invention functions as a system that can integrate physical health management and psychological support for workers and those requiring care.

[0796] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0797] Step 1:

[0798] The server receives health data from sensors worn by care recipients or workers. Specifically, vital data such as heart rate, body temperature, and blood pressure are input to the server via Bluetooth or Wi-Fi communication. The server stores this data chronologically and uses it as basic data for detecting abnormalities.

[0799] Step 2:

[0800] The server uses artificial intelligence algorithms to analyze the received vital data. For example, TensorFlow is used to detect anomalies and perform trend analysis. The output includes an assessment of whether anomalies were detected and whether the health status is stable. These analysis results serve as foundational information for creating individualized support plans.

[0801] Step 3:

[0802] The server automatically generates individualized support plans for each care recipient and worker based on the results of the health status analysis. The plan generation is performed using a generation AI model and prompts. The output includes a list of the plan and support activity priorities, which are used as instructions in the next processing step.

[0803] Step 4:

[0804] The user robot gives instructions to the target person via a voice output device, based on an individualized support plan sent from the server. Specific actions include voice commands such as "Let's take a break" or "It's time to relax." The robot observes the target person's response and prepares the next action based on the plan.

[0805] Step 5:

[0806] The server receives voice and facial expression data from workers and those receiving care, and performs emotion analysis. Using emotion analysis tools such as the Affectiva API with the voice and image data, it evaluates the degree of stress and anxiety. An emotional state report is generated as output, which is then used as data for providing psychological support.

[0807] Step 6:

[0808] The device dynamically adjusts its communication methods in real time based on the results of emotion analysis. Specifically, it adopts an approach that changes the tone and content of its language according to the target person's emotional state. This allows for the optimization of psychological support for the target person.

[0809] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0810] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0811] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0812] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0813] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0814] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0815] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0816] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0817] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0818] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0819] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0820] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0821] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0822] 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.

[0823] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0824] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0825] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0826] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0827] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0828] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0829] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0830] The following is further disclosed regarding the embodiments described above.

[0831] (Claim 1)

[0832] A means of collecting sensor data to monitor the health status of care recipients in real time,

[0833] An analysis method using artificial intelligence for analyzing collected sensor data,

[0834] A means for automatically creating individual care plans for those requiring care based on the analysis results,

[0835] A means of communicating care plans and analysis results to caregiver robots and enabling them to carry out life support,

[0836] A system that includes this.

[0837] (Claim 2)

[0838] The system according to claim 1, which enables a caregiver robot to communicate with a person requiring care using natural language.

[0839] (Claim 3)

[0840] The system according to claim 1, wherein a caregiver robot performs household chores, meal and medication management to support the daily life of a person requiring care.

[0841] "Example 1"

[0842] (Claim 1)

[0843] A means of collecting data from a measuring device for monitoring the health status of a person requiring care in real time,

[0844] An analysis device using a generative AI model provides means for analyzing collected measurement data,

[0845] A means of automatically creating individualized care plans for those requiring care based on the analysis results,

[0846] A means of transmitting care plans and analysis results to caregiving machines and enabling them to carry out life support,

[0847] A means of managing information to reflect the feedback received in the next care plan,

[0848] A system that includes this.

[0849] (Claim 2)

[0850] The system according to claim 1, which enables a caregiving machine to communicate with a person requiring care in natural language.

[0851] (Claim 3)

[0852] The system according to claim 1, wherein the caregiving machine provides cooking assistance and medication management in order to support the daily life of a person requiring care.

[0853] "Application Example 1"

[0854] (Claim 1)

[0855] A means of collecting biometric information to monitor the health status of workers in real time,

[0856] A machine learning-based analytical method for analyzing collected biological information,

[0857] A means for automatically creating individual work plans for workers based on the analysis results,

[0858] A means of transmitting the work plan and analysis results to a work support device and ensuring the safety of the work,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, wherein the work support device enables a natural language interface with the worker.

[0862] (Claim 3)

[0863] The system according to claim 1, wherein the work support device performs work support, rest, and safety checks for managing the workload of the worker.

[0864] "Example 2 of combining an emotion engine"

[0865] (Claim 1)

[0866] A means of collecting data from a detector to monitor the health status of a person requiring care,

[0867] An intelligent analytical method for analyzing the collected data,

[0868] A means to automatically create individualized support plans for those requiring care based on the analysis results,

[0869] A means of transmitting support plans and analysis results to a mobile support device and enabling it to carry out life support,

[0870] A device equipped with an emotion engine that analyzes voice and facial expressions to recognize emotions, providing a means to dynamically adjust conversations with care recipients,

[0871] A means of accumulating long-term data and evaluating the psychological and physical health trends of those requiring care,

[0872] A system that includes this.

[0873] (Claim 2)

[0874] The system according to claim 1, wherein a mobile support device enables natural language dialogue with a person requiring care.

[0875] (Claim 3)

[0876] The system according to claim 1, wherein a mobile support device performs household assistance, meal management, and medication management to support the daily life of a person requiring care.

[0877] "Application example 2 when combining with an emotional engine"

[0878] (Claim 1)

[0879] A means of collecting sensor data to monitor the health status of care recipients and workers in real time,

[0880] An analysis method using artificial intelligence for analyzing collected sensor data,

[0881] A means to automatically create individual plans for care recipients and workers based on the analysis results,

[0882] A means of communicating automatically generated plans and analysis results to a robot and having it perform the support,

[0883] To perform emotion analysis, a means of analyzing the psychological state of a worker based on audio and image data,

[0884] In order to enhance the psychological stability of workers, means of dynamically adjusting communication methods,

[0885] A system that includes this.

[0886] (Claim 2)

[0887] The system according to claim 1, which proposes workload reduction or breaks based on the health and emotional state of the worker.

[0888] (Claim 3)

[0889] The system according to claim 1, which provides support for simultaneously ensuring safety in the work environment and the psychological stability of workers. [Explanation of Symbols]

[0890] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting sensor data to monitor the health status of care recipients in real time, An analysis method using artificial intelligence for analyzing collected sensor data, A means for automatically creating individual care plans for those requiring care based on the analysis results, A means of communicating care plans and analysis results to caregiver robots and enabling them to carry out life support, A system that includes this.

2. The system according to claim 1, which enables a caregiver robot to communicate with a person requiring care using natural language.

3. The system according to claim 1, wherein a caregiver robot performs household chores, meal management, and medication management to support the daily life of a person requiring care.

Images