system

Abstract

The system according to this embodiment aims to check the health status of elderly people and to promote communication among family members. [Solution] The system according to the embodiment comprises a health confirmation unit, a sharing unit, and a conversation facilitating unit. The health confirmation unit performs health checks. The sharing unit shares the information confirmed by the health confirmation unit with family members. The conversation facilitating unit facilitates conversations among family members based on the information shared by the sharing unit.

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 conventional technology, there is a problem that the health status of the elderly is not sufficiently remotely confirmed and communication between family members is not sufficiently promoted.

[0005] The system according to the embodiment aims to confirm the health status of the elderly and promote communication between family members.

Means for Solving the Problems

[0006] The system according to the embodiment includes a health confirmation unit, a sharing unit, and a conversation promotion unit. The health confirmation unit performs health confirmation. The sharing unit shares the information confirmed by the health confirmation unit with the family members. The conversation promotion unit promotes conversation between family members based on the information shared by the sharing unit. [Effects of the Invention]

[0007] The system according to this embodiment can check the health status of elderly people and promote communication among family members. [Brief explanation of the drawing]

[0008] [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. [Modes for carrying out the invention]

[0009] 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.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The monitoring system according to an embodiment of the present invention is a system targeted at elderly parents, particularly elderly people living alone, and their families. This monitoring system is designed to mitigate the risks associated with elderly parents living alone, especially the risk of mental illness such as dementia. Preventing dementia requires intellectual activity, a balanced diet, moderate exercise, and sufficient sleep, but providing detailed and close support is difficult when living apart. The monitoring system utilizes an AI character and group chat to perform timely health checks, provide health support, and share this information with family members. This creates opportunities for conversation among family members and revitalizes communication. The AI ​​character also provides comprehensive support for the parent's life, including alleviating loneliness, intellectual conversation, meal management, medication management, physical condition management, exercise promotion, sleep management, schedule management, and stress relief. For example, the monitoring system can analyze and record the amount of calories and nutrients from video of meals. Furthermore, the monitoring system can determine the type of medication and intake status from video of medications. The monitoring system can record and analyze vital signs such as heart rate, calories burned, and steps taken, and provide health advice and encourage exercise. It can record sleep quality and duration, and provide advice to promote proper sleep. It can record the timing of events through daily activity logs and conversations, and provide reminders at appropriate times. It can track location information using GPS and issue alerts for unusual movement. It can learn from conversations with the user and family, and provide automated conversations optimized for the user. It can detect signs of mental illnesses such as dementia and depression from conversation content. This allows family members living separately to monitor and support their elderly parents. This improves the quality of life for parents and increases the family's sense of security.

[0029] The monitoring system according to the embodiment comprises a health confirmation unit, a sharing unit, and a conversation facilitating unit. The health confirmation unit performs health checks. The health confirmation unit can perform health checks by methods such as measuring body temperature, measuring blood pressure, and conducting interviews. For example, the health confirmation unit can measure body temperature and detect abnormal body temperature. The health confirmation unit can also measure blood pressure and detect abnormal blood pressure. Furthermore, the health confirmation unit can conduct interviews to confirm the user's health status. The sharing unit shares the information confirmed by the health confirmation unit with family members. The sharing unit can share information by methods such as email, messaging apps, and telephone. For example, the sharing unit can send health information to family members using email. The sharing unit can also send health information to family members using messaging apps. Furthermore, the sharing unit can also convey health information to family members by telephone. The conversation facilitating unit facilitates conversations among family members based on the information shared by the sharing unit. The conversation facilitating unit can facilitate conversations by methods such as suggesting topics and presenting questions. For example, the conversation facilitating unit can facilitate conversations among family members by suggesting topics. Furthermore, the conversation facilitator can also facilitate conversations among family members by presenting questions. In addition, the conversation facilitator can suggest activities to stimulate conversations among family members. As a result, the monitoring system according to the embodiment enables health checks, information sharing, and conversation facilitation.

[0030] The health check unit performs health checks. Specifically, it can perform health checks using methods such as temperature measurement, blood pressure measurement, and medical interviews. Temperature measurement can be performed using non-contact infrared thermometers or ear thermometers, allowing for quick and accurate temperature measurement. When detecting abnormal temperatures, it has a function to issue an alert if the temperature exceeds a pre-set normal range. Blood pressure measurement is performed using upper arm or wrist blood pressure monitors, measuring both systolic and diastolic blood pressure. This allows for early detection of abnormal blood pressure and the taking of necessary measures. Medical interviews involve asking users questions about their health status and evaluating their health status based on their answers. The content of the interviews is wide-ranging, such as recent changes in physical condition, appetite, and sleep quality. This allows for an understanding of the user's overall health status. Furthermore, the health check unit records these measurement and medical interview results as digital data for later reference. This allows for tracking changes in health status by comparing them with past data. The health check unit can also use AI to analyze measurement data and medical interview results to perform early detection of abnormalities and predict health status. For example, AI can learn patterns of anomalies based on past data and predict future risks. AI can also provide personalized health advice based on user responses. This allows the health monitoring unit to comprehensively manage the user's health status and facilitate early detection and prevention of anomalies.

[0031] The sharing unit shares information verified by the health monitoring unit with family members. Specifically, information can be shared via email, messaging apps, or telephone. When using email, data collected by the health monitoring unit is automatically formatted and sent to family members periodically. Emails include temperature and blood pressure measurement results, questionnaire responses, etc., and any detected abnormalities are highlighted. When using messaging apps, health information can be notified to family members in real time. For example, if an abnormality is detected, a notification is sent immediately, allowing family members to respond quickly. When using telephone, health information can be conveyed verbally using speech synthesis technology. This allows visually impaired family members and the elderly to receive the information. Furthermore, the sharing unit can customize how information is received according to the family's preferences. For example, it is possible to set notifications to be received only at specific times or to only receive important information. The sharing unit also takes information security into consideration and is equipped with data encryption and authentication functions. This minimizes the risk of personal information being leaked to third parties. The sharing unit can also provide a dedicated web portal or application to allow family members to easily access health information. This allows family members to check health information and take necessary actions anytime, anywhere.

[0032] The conversation facilitator facilitates conversations among family members based on information shared by the sharing unit. Specifically, it can facilitate conversations by suggesting topics and presenting questions. Topic suggestions are made, for example, by providing the latest health news or topics related to shared health information. This fosters natural conversations among family members and increases their interest in health. Questions are made by asking family members specific questions such as, "How have you been feeling lately?" or "Are you eating properly?" This activates communication among family members and allows for a deeper understanding of the user's health status. Furthermore, the conversation facilitator can also suggest activities to stimulate conversations among family members. For example, it can suggest activities such as cooking healthy meals together, going for walks, or participating in online health seminars. This increases the time families spend together and raises their awareness of health. The conversation facilitator can also use AI to analyze the content of conversations among family members and suggest more effective topics and questions. For example, it can identify topics that family members are likely to be interested in based on past conversation history and suggest topics based on that. The AI ​​can also analyze the tone and emotions of conversations and present questions at the appropriate time. This allows the conversation facilitator to facilitate communication among family members and provide support for a deeper understanding of the user's health condition.

[0033] The meal management unit can analyze and record the amount of calories and nutrients from video footage of meals. For example, the meal management unit can acquire video footage of meals using a camera, analyze the footage, and calculate the amount of calories and nutrients. For example, the meal management unit can set up a camera to film meals, analyze the footage, and calculate the amount of calories and nutrients. Furthermore, the meal management unit can perform more accurate analysis by setting a higher resolution for the video footage. In addition, the meal management unit can also calculate the amount of calories and nutrients of meals using a food database. For example, the meal management unit can calculate the amount of calories and nutrients of meals by referring to a food database. This allows the meal management unit to analyze and record the amount of calories and nutrients of meals. Some or all of the above processing in the meal management unit may be performed using AI, for example, or without AI. For example, the meal management unit can input video footage of meals into a generating AI and have the generating AI perform the analysis of the amount of calories and nutrients.

[0034] The drug management department can determine the type of drug and its intake status from images of the drug. For example, the drug management department can acquire images of the drug using a camera and analyze those images to determine the type of drug and its intake status. For example, the drug management department can install a camera to photograph the drug and analyze those images to determine the type of drug and its intake status. Furthermore, the drug management department can perform a more accurate analysis by setting a higher resolution for the images. In addition, the drug management department can also determine the type of drug and its intake status using drug shape recognition technology. For example, the drug management department can use drug shape recognition technology to identify the type of drug and determine its intake status. This allows the drug management department to determine the type of drug and its intake status. Some or all of the above processes in the drug management department may be performed using AI, for example, or without AI. For example, the drug management department can input images of the drug into a generating AI and have the generating AI perform the determination of the type of drug and its intake status.

[0035] The health management unit can record and analyze vital signs such as heart rate, calories burned, and steps taken. The health management unit can record vital signs using devices such as heart rate sensors, calorie calculators, and pedometers. For example, the health management unit can record heart rate using a heart rate sensor and analyze the data. It can also record calories burned using a calorie calculator and analyze the data. Furthermore, it can record steps taken using a pedometer and analyze the data. For example, the health management unit can record heart rate in real time using a heart rate sensor and issue an alert if there are abnormal fluctuations. The health management unit can also calculate calories burned and issue a warning if there is excessive calorie consumption. The health management unit can record steps using a pedometer and prompt exercise if the target number of steps has not been reached. This allows the health management unit to record and analyze vital signs. Some or all of the above-described processes in the health management unit may be performed using AI, for example, or without AI. For example, the health management department can input vital sign data into a generating AI and have the AI ​​generate health advice.

[0036] The sleep management department can record sleep quality and duration and provide advice to promote proper sleep. For example, the sleep management department can record sleep quality and duration using a sleep tracker. The sleep management department can also record sleep duration using a sleep tracker and analyze that data. Furthermore, the sleep management department can analyze sleep stages and provide advice to promote proper sleep. For example, the sleep management department can record sleep quality in real time using a sleep tracker and issue an alert if quality declines. The sleep management department can also measure sleep duration and suggest appropriate sleep durations. The sleep management department can analyze sleep stages and suggest improvements if deep sleep is insufficient. This allows the sleep management department to record sleep quality and duration and provide advice to promote proper sleep. Some or all of the above processes in the sleep management department may be performed using AI, or not. For example, the sleep management department can input sleep data into a generating AI and have the generating AI generate sleep advice.

[0037] The schedule management unit can record the timing of events through daily activity logs and conversations, and provide reminders at appropriate times. For example, the schedule management unit can analyze conversations using speech recognition technology to record the timing of events. The schedule management unit can also record activity logs, analyze that data, and record the timing of events. Furthermore, the schedule management unit can use a calendar to record the timing of events and set reminders. For example, the schedule management unit can register events in the calendar and provide reminders at appropriate times. This allows the schedule management unit to record the timing of events and provide reminders at appropriate times. Some or all of the above processes in the schedule management unit may be performed using AI, or not. For example, the schedule management unit can input activity log data into a generating AI and have the generating AI execute reminder timings.

[0038] The location management unit can grasp location information using GPS and issue alerts when movement deviates from the norm. For example, the location management unit can acquire location information using a GPS device and analyze that data to detect abnormal movement. For example, the location management unit can acquire location information in real time using a GPS device and issue an alert if there is movement deviating from the norm. The location management unit can also analyze movement patterns and detect abnormal movement. Furthermore, the location management unit can use an anomaly detection algorithm to detect abnormal movement at an early stage. For example, the location management unit analyzes movement patterns and issues an alert if there is movement deviating from the norm. In this way, the location management unit can grasp location information and issue alerts when movement deviates from the norm. Some or all of the above processing in the location management unit may be performed using AI, for example, or without using AI. For example, the location management unit can input location information data into a generating AI and have the generating AI perform the detection of abnormal movement.

[0039] The conversational unit can learn from conversations with the user and their family and conduct automated conversations optimized for the user. For example, the conversational unit can learn from conversation history and generate responses optimized for the user. For example, the conversational unit can analyze conversation history and generate responses based on the user's interests. The conversational unit can also learn from conversation history to generate personalized responses. Furthermore, the conversational unit can learn the user's conversation patterns and generate optimal responses. For example, the conversational unit can learn from conversation history and advance the conversation based on the user's interests. This allows the conversational unit to conduct automated conversations optimized for the user. Some or all of the above processes in the conversational unit may be performed using AI, for example, or without AI. For example, the conversational unit can input conversation history data into a generating AI and have the generating AI perform the generation of optimal responses.

[0040] The health monitoring unit can detect abnormalities early by referring to past health data during health checks. For example, the health monitoring unit can refer to past heart rate data and issue an alert if there are abnormal fluctuations. For example, the health monitoring unit can analyze past heart rate data and issue an alert if there are abnormal fluctuations. The health monitoring unit can also refer to past step count data and detect abnormalities if there is a sudden decrease. Furthermore, the health monitoring unit can refer to past sleep data and detect abnormalities if the quality of sleep has deteriorated. For example, the health monitoring unit can refer to past heart rate data and issue an alert if there are abnormal fluctuations. The health monitoring unit can also analyze past step count data and detect abnormalities if there is a sudden decrease. The health monitoring unit can also refer to past sleep data and detect abnormalities if the quality of sleep has deteriorated. As a result, the health monitoring unit can detect abnormalities early by referring to past health data. Some or all of the above processing in the health monitoring unit may be performed using AI, for example, or without using AI. For example, the health verification unit can input past health data into a generating AI and have the generating AI perform abnormality detection.

[0041] The health check unit can provide customized health advice based on the user's lifestyle habits during health checks. For example, the health check unit can suggest a balanced diet based on the user's eating habits. For example, the health check unit can record the user's eating habits and suggest a balanced diet based on that data. The health check unit can also provide appropriate exercise advice based on the user's exercise habits. Furthermore, the health check unit can provide advice to promote quality sleep based on the user's sleep habits. For example, the health check unit can record the user's eating habits and suggest a balanced diet based on that data. The health check unit can also record the user's exercise habits and provide appropriate exercise advice based on that data. The health check unit can also record the user's sleep habits and provide advice to promote quality sleep based on that data. In this way, the health check unit can provide customized health advice based on the user's lifestyle habits. Some or all of the above processing in the health check unit may be performed using AI, for example, or without using AI. For example, the health monitoring unit can input the user's lifestyle data into a generating AI, which can then generate customized health advice.

[0042] The health verification unit can provide environmentally appropriate health advice based on the user's geographical location information during health verification. For example, the health verification unit can provide environmentally appropriate health advice considering the user's geographical location information. For example, if the user is at high altitude, the health verification unit can provide advice regarding oxygen supply. The health verification unit can also provide advice regarding air quality if the user is in an urban area. Furthermore, if the user is at the beach, the health verification unit can provide advice regarding sun protection. For example, if the user is at high altitude, the health verification unit can provide advice regarding oxygen supply. The health verification unit can also provide advice regarding air quality if the user is in an urban area. The health verification unit can also provide advice regarding sun protection if the user is at the beach. In this way, the health verification unit can provide environmentally appropriate health advice based on the user's geographical location information. Some or all of the above processing in the health verification unit may be performed using AI, for example, or without AI. For example, the health verification unit can input the user's geographical location information into a generating AI and have the generating AI generate environmentally appropriate health advice.

[0043] The health verification unit can analyze the user's social media activity and provide relevant health information during health verification. For example, the health verification unit can analyze the user's social media activity and provide relevant health information. For example, if the user is experiencing stress on social media, the health verification unit can suggest ways to relax. The health verification unit can also provide relevant advice if the user is sharing health-related information on social media. Furthermore, if the user is sharing exercise-related information on social media, the health verification unit can suggest appropriate exercise methods. For example, if the user is experiencing stress on social media, the health verification unit can suggest ways to relax. The health verification unit can also provide relevant advice if the user is sharing health-related information on social media. The health verification unit can also suggest appropriate exercise methods if the user is sharing exercise-related information on social media. This allows the health verification unit to analyze the user's social media activity and provide relevant health information. Some or all of the above processing in the health verification unit may be performed using AI, for example, or without AI. For example, the health verification unit can input the user's social media data into a generating AI and have the generating AI generate relevant health information.

[0044] The sharing unit can analyze the family's past reactions and select the optimal sharing method when sharing information. For example, the sharing unit can record the family's past reactions and analyze that data to select the optimal sharing method. For example, the sharing unit can prioritize sharing information that the family has received favorably in the past. The sharing unit can also avoid sharing information that the family has felt anxious about in the past. Furthermore, the sharing unit can analyze the family's past reactions and share information at the optimal timing. For example, the sharing unit can prioritize sharing information that the family has received favorably in the past. The sharing unit can also avoid sharing information that the family has felt anxious about in the past. The sharing unit can also analyze the family's past reactions and share information at the optimal timing. As a result, the sharing unit can analyze the family's past reactions and select the optimal sharing method. Some or all of the above processing in the sharing unit may be performed using AI, for example, or without AI. For example, the sharing unit can input data on the family's past reactions into a generating AI and have the generating AI select the optimal sharing method.

[0045] The sharing unit can adjust the level of detail of information shared based on its importance. For example, the sharing unit can evaluate the importance of information and adjust the level of detail based on that evaluation. For example, the sharing unit can share important health information in detail. It can also share general health information concisely. Furthermore, it can share urgent information quickly. For example, the sharing unit can share important health information in detail. It can also share general health information concisely. It can also share urgent information quickly. This allows the sharing unit to adjust the level of detail of information shared based on its importance. Some or all of the above processing in the sharing unit may be performed using AI, for example, or without AI. For example, the sharing unit can input information importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of sharing.

[0046] The sharing unit can select the optimal sharing method by considering the geographical location information of family members when sharing information. For example, the sharing unit can acquire the geographical location information of family members and select the optimal sharing method based on that data. For example, if family members are nearby, the sharing unit can share information through direct conversation. The sharing unit can also share information via video call if family members are far away. Furthermore, if family members are on the move, the sharing unit can share information via text message. For example, if family members are nearby, the sharing unit can share information through direct conversation. The sharing unit can also share information via video call if family members are far away. The sharing unit can also share information via text message if family members are on the move. This allows the sharing unit to select the optimal sharing method by considering the geographical location information of family members. Some or all of the above processing in the sharing unit may be performed using AI, for example, or without AI. For example, the sharing unit can input the geographical location information of family members into a generating AI and have the generating AI select the optimal sharing method.

[0047] The sharing unit can analyze the family's social media activity and share relevant information when sharing. For example, the sharing unit can analyze the family's social media activity and share relevant information based on that data. For example, if the family shares health-related information on social media, the sharing unit can provide relevant information. The sharing unit can also suggest relaxation methods if the family is feeling stressed on social media. Furthermore, if the family shares exercise-related information on social media, the sharing unit can suggest appropriate exercise methods. For example, if the family shares health-related information on social media, the sharing unit can provide relevant information. The sharing unit can also suggest relaxation methods if the family is feeling stressed on social media. The sharing unit can also suggest appropriate exercise methods if the family shares exercise-related information on social media. In this way, the sharing unit can analyze the family's social media activity and share relevant information. Some or all of the above processing in the sharing unit may be performed using AI, for example, or not. For example, the sharing unit can input the family's social media data into a generating AI and have the generating AI generate relevant information.

[0048] The conversation facilitator can, when facilitating a conversation, refer to past conversation history to suggest the optimal flow of conversation. For example, the conversation facilitator can record past conversation history and suggest the optimal flow of conversation based on that data. For example, the conversation facilitator can recreate conversation flows that were well-received in the past. The conversation facilitator can also avoid conversation flows that caused anxiety in the past. Furthermore, the conversation facilitator can analyze past conversation history and facilitate conversation at the optimal timing. For example, the conversation facilitator can recreate conversation flows that were well-received in the past. The conversation facilitator can also avoid conversation flows that caused anxiety in the past. The conversation facilitator can analyze past conversation history and facilitate conversation at the optimal timing. As a result, the conversation facilitator can refer to past conversation history to suggest the optimal flow of conversation. Some or all of the above processing in the conversation facilitator may be performed using AI, for example, or without AI. For example, the conversation facilitator can input past conversation history data into a generating AI and have the generating AI propose the optimal flow of conversation.

[0049] The conversation facilitator can customize the content of conversations based on the family's interests when facilitating a conversation. For example, the conversation facilitator can record the family's interests and customize the content of conversations based on that data. For example, if the family is interested in health, the conversation facilitator can facilitate conversations about health. The conversation facilitator can also facilitate conversations about hobbies if the family is interested in those hobbies. Furthermore, if the family is interested in travel, the conversation facilitator can also facilitate conversations about travel. For example, if the family is interested in health, the conversation facilitator can facilitate conversations about health. The conversation facilitator can also facilitate conversations about hobbies if the family is interested in those hobbies. The conversation facilitator can also facilitate conversations about travel if the family is interested in travel. In this way, the conversation facilitator can customize the content of conversations based on the family's interests. Some or all of the above processing in the conversation facilitator may be performed using AI, for example, or without AI. For example, the conversation facilitator can input family interest data into a generating AI and have the generating AI perform the customization of the conversation content.

[0050] The conversation facilitator can select the optimal timing for a conversation by considering the geographical location information of the family members when facilitating a conversation. For example, the conversation facilitator can acquire the geographical location information of the family members and select the optimal timing for a conversation based on that data. For example, if the family members are nearby, the conversation facilitator can facilitate the conversation through direct conversation. The conversation facilitator can also facilitate the conversation through video calls if the family members are far away. Furthermore, if the family members are on the move, the conversation facilitator can facilitate the conversation through text messages. For example, if the family members are nearby, the conversation facilitator can facilitate the conversation through direct conversation. The conversation facilitator can also facilitate the conversation through video calls if the family members are far away. The conversation facilitator can also facilitate the conversation through text messages if the family members are on the move. This allows the conversation facilitator to select the optimal timing for a conversation by considering the geographical location information of the family members. Some or all of the above processing in the conversation facilitator may be performed using AI, for example, or without AI. For example, the conversation facilitator can input the geographical location information of the family members into a generating AI and have the generating AI select the optimal timing for a conversation.

[0051] The conversation facilitator can analyze the family's social media activity and provide relevant conversation topics when facilitating a conversation. For example, the conversation facilitator can analyze the family's social media activity and provide relevant conversation topics based on that data. For example, if the family is sharing health-related information on social media, the conversation facilitator can provide relevant conversation topics. The conversation facilitator can also suggest ways to relax if the family is feeling stressed by social media. Furthermore, if the family is sharing exercise-related information on social media, the conversation facilitator can suggest appropriate exercise methods. For example, if the family is sharing health-related information on social media, the conversation facilitator can provide relevant conversation topics. The conversation facilitator can also suggest ways to relax if the family is feeling stressed by social media. The conversation facilitator can also suggest appropriate exercise methods if the family is sharing exercise-related information on social media. This allows the conversation facilitator to analyze the family's social media activity and provide relevant conversation topics. Some or all of the above processing in the conversation facilitator may be performed using AI, for example, or without AI. For example, the conversation facilitator can input family social media data into a generating AI and have the AI ​​generate relevant conversation topics.

[0052] The meal management department can optimize nutritional balance by referring to past meal data during meal management. For example, the meal management department can record past meal data and optimize nutritional balance based on that data. For example, the meal management department can analyze past meal data and propose meals that compensate for nutrient deficiencies. The meal management department can also refer to past meal data and propose meals that prevent calorie overload. Furthermore, the meal management department can propose well-balanced meal menus based on past meal data. For example, the meal management department can analyze past meal data and propose meals that compensate for nutrient deficiencies. The meal management department can also refer to past meal data and propose meals that prevent calorie overload. The meal management department can also propose well-balanced meal menus based on past meal data. In this way, the meal management department can optimize nutritional balance by referring to past meal data. Some or all of the above processes in the meal management department may be performed using AI, for example, or without AI. For example, the meal management department can input past meal data into a generating AI and have the generating AI perform the optimization of nutritional balance.

[0053] The meal management unit can customize meal content based on the user's health condition during meal management. For example, the meal management unit can record the user's health condition and customize meal content based on that data. For example, the meal management unit can suggest a low-sodium meal considering the user's health condition. The meal management unit can also suggest a low-calorie meal based on the user's health condition. Furthermore, the meal management unit can suggest a meal rich in specific nutrients considering the user's health condition. For example, the meal management unit can suggest a low-sodium meal considering the user's health condition. The meal management unit can also suggest a low-calorie meal based on the user's health condition. The meal management unit can also suggest a meal rich in specific nutrients considering the user's health condition. In this way, the meal management unit can customize meal content based on the user's health condition. Some or all of the above processing in the meal management unit may be performed using AI, for example, or without AI. For example, the meal management unit can input the user's health condition data into a generating AI and have the generating AI perform the customization of meal content.

[0054] The meal management unit can suggest the optimal meal while considering the user's geographical location. For example, the meal management unit can acquire the user's geographical location and suggest the optimal meal based on that data. For example, if the user is at high altitude, the meal management unit can suggest a high-calorie meal. Also, if the user is in an urban area, the meal management unit can suggest a well-balanced meal. Furthermore, if the user is by the sea, the meal management unit can suggest a meal that includes a lot of seafood. For example, if the user is at high altitude, the meal management unit can suggest a high-calorie meal. If the user is in an urban area, the meal management unit can suggest a well-balanced meal. If the user is by the sea, the meal management unit can suggest a meal that includes a lot of seafood. In this way, the meal management unit can suggest the optimal meal while considering the user's geographical location. Some or all of the above processing in the meal management unit may be performed using AI, for example, or without AI. For example, the meal management unit can input the user's geographical location information into a generating AI and have the generating AI suggest the optimal meal.

[0055] The diet management department can analyze a user's social media activity and provide relevant dietary information during dietary management. For example, the diet management department can analyze a user's social media activity and provide relevant dietary information based on that data. For example, if a user shares health-related information on social media, the diet management department can provide relevant dietary information. The diet management department can also suggest relaxing meals if a user is experiencing stress on social media. Furthermore, if a user shares exercise-related information on social media, the diet management department can provide appropriate dietary information. For example, if a user shares health-related information on social media, the diet management department can provide relevant dietary information. The diet management department can also suggest relaxing meals if a user is experiencing stress on social media. The diet management department can also provide appropriate dietary information if a user shares exercise-related information on social media. This allows the diet management department to analyze a user's social media activity and provide relevant dietary information. Some or all of the above processing in the diet management department may be performed using AI, for example, or without AI. For example, the diet management department can input the user's social media data into a generating AI and have the generating AI generate relevant dietary information.

[0056] The medication management department can propose the optimal method of medication intake by referring to past medication intake data during medication management. For example, the medication management department can record past medication intake data and propose the optimal method of intake based on that data. For example, the medication management department can analyze past medication intake data and propose the optimal timing of intake. The medication management department can also refer to past medication intake data and propose the appropriate dosage of medication. Furthermore, the medication management department can customize the method of medication intake based on past medication intake data. For example, the medication management department can analyze past medication intake data and propose the optimal timing of intake. The medication management department can also refer to past medication intake data and propose the appropriate dosage of medication. The medication management department can also customize the method of medication intake based on past medication intake data. As a result, the medication management department can propose the optimal method of medication intake by referring to past medication intake data. Some or all of the above processes in the medication management department may be performed using AI, for example, or not using AI. For example, the medication management department can input past medication intake data into a generating AI and have the generating AI propose the optimal method of intake.

[0057] The drug management department can propose the optimal method of drug intake when managing medication, taking into account the user's geographical location. For example, the drug management department can acquire the user's geographical location and propose the optimal method of drug intake based on that data. For example, if the user is at high altitude, the drug management department can propose taking the medication with a high-calorie meal. Also, if the user is in an urban area, the drug management department can propose taking the medication with a balanced meal. Furthermore, if the user is by the sea, the drug management department can propose taking the medication with a meal rich in seafood. For example, if the user is at high altitude, the drug management department can propose taking the medication with a high-calorie meal. If the user is in an urban area, the drug management department can propose taking the medication with a balanced meal. If the user is by the sea, the drug management department can propose taking the medication with a meal rich in seafood. In this way, the drug management department can propose the optimal method of drug intake, taking into account the user's geographical location. Some or all of the above processing in the drug management department may be performed using AI, for example, or not using AI. For example, the drug management department can input the user's geographical location information into a generating AI and have the AI ​​suggest the optimal way to take the medication.

[0058] The health management department can provide optimal health advice by referring to past vital sign data during health management. For example, the health management department can record past vital sign data and provide optimal health advice based on that data. For example, the health management department can analyze past heart rate data and suggest the optimal exercise method. The health management department can also refer to past calorie expenditure data and suggest appropriate meals. Furthermore, the health management department can suggest the optimal amount of exercise based on past step count data. For example, the health management department can analyze past heart rate data and suggest the optimal exercise method. The health management department can also refer to past calorie expenditure data and suggest appropriate meals. The health management department can also suggest the optimal amount of exercise based on past step count data. As a result, the health management department can provide optimal health advice by referring to past vital sign data. Some or all of the above processing in the health management department may be performed using AI, for example, or without AI. For example, the health management department can input past vital sign data into a generating AI and have the generating AI generate optimal health advice.

[0059] The health management unit can provide optimal health advice by taking into account the user's geographical location information during health management. For example, the health management unit can acquire the user's geographical location information and provide optimal health advice based on that data. For example, if the user is at high altitude, the health management unit can provide advice regarding oxygen supply. The health management unit can also provide advice regarding air quality if the user is in an urban area. Furthermore, if the user is at the beach, the health management unit can provide advice regarding sun protection. For example, if the user is at high altitude, the health management unit can provide advice regarding oxygen supply. The health management unit can also provide advice regarding air quality if the user is in an urban area. The health management unit can also provide advice regarding sun protection if the user is at the beach. In this way, the health management unit can provide optimal health advice by taking into account the user's geographical location information. Some or all of the above processing in the health management unit may be performed using AI, for example, or without AI. For example, the health management unit can input the user's geographical location information into a generating AI and have the generating AI generate optimal health advice.

[0060] The sleep management unit can provide optimal sleep advice by referring to past sleep data during sleep management. For example, the sleep management unit can record past sleep data and provide optimal sleep advice based on that data. For example, the sleep management unit can analyze past sleep data and propose an optimal sleep duration. Furthermore, the sleep management unit can refer to past sleep data and propose an appropriate sleep environment. In addition, the sleep management unit can provide advice to promote quality sleep based on past sleep data. For example, the sleep management unit can analyze past sleep data and propose an optimal sleep duration. The sleep management unit can also refer to past sleep data and propose an appropriate sleep environment. The sleep management unit can also provide advice to promote quality sleep based on past sleep data. Thus, the sleep management unit can provide optimal sleep advice by referring to past sleep data. Some or all of the above processes in the sleep management unit may be performed using AI, for example, or without AI. For example, the sleep management unit can input past sleep data into a generating AI and have the generating AI generate optimal sleep advice.

[0061] The sleep management unit can provide optimal sleep advice while considering the user's geographical location information. For example, the sleep management unit can acquire the user's geographical location information and provide optimal sleep advice based on that data. For example, if the user is at high altitude, the sleep management unit can provide advice regarding oxygen supply. The sleep management unit can also provide advice regarding air quality if the user is in an urban area. Furthermore, if the user is at the beach, the sleep management unit can provide advice regarding sun protection. For example, if the user is at high altitude, the sleep management unit can provide advice regarding oxygen supply. The sleep management unit can also provide advice regarding air quality if the user is in an urban area. The sleep management unit can also provide advice regarding sun protection if the user is at the beach. In this way, the sleep management unit can provide optimal sleep advice while considering the user's geographical location information. Some or all of the above processing in the sleep management unit may be performed using AI, for example, or without AI. For example, the sleep management unit can input the user's geographical location information into a generating AI and have the generating AI generate optimal sleep advice.

[0062] The schedule management unit can provide the optimal reminder method by referring to past activity records when managing schedules. For example, the schedule management unit can record past activity records and provide the optimal reminder method based on that data. For example, the schedule management unit can analyze past activity records and propose the optimal reminder timing. The schedule management unit can also refer to past activity records and propose an appropriate reminder method (voice, text, etc.). Furthermore, the schedule management unit can adjust the frequency of reminders based on past activity records. For example, the schedule management unit can analyze past activity records and propose the optimal reminder timing. The schedule management unit can also refer to past activity records and propose an appropriate reminder method (voice, text, etc.). The schedule management unit can also adjust the frequency of reminders based on past activity records. This allows the schedule management unit to provide the optimal reminder method by referring to past activity records. Some or all of the above processes in the schedule management unit may be performed using AI, for example, or not. For example, the schedule management unit can input past activity record data into a generating AI and have the generating AI propose an optimal reminder method.

[0063] The schedule management unit can provide the optimal reminder method when managing schedules, taking into account the user's geographical location information. For example, the schedule management unit can acquire the user's geographical location information and provide the optimal reminder method based on that data. For example, if the user is at high altitude, the schedule management unit can provide a reminder regarding oxygen supply. Also, if the user is in an urban area, the schedule management unit can provide a reminder regarding air quality. Furthermore, if the user is at the beach, the schedule management unit can provide a reminder regarding sun protection. For example, if the user is at high altitude, the schedule management unit can provide a reminder regarding oxygen supply. If the user is in an urban area, the schedule management unit can provide a reminder regarding air quality. If the user is at the beach, the schedule management unit can provide a reminder regarding sun protection. In this way, the schedule management unit can provide the optimal reminder method, taking into account the user's geographical location information. Some or all of the above processing in the schedule management unit may be performed using AI, for example, or without using AI. For example, the schedule management department can input the user's geographical location information into a generation AI and have the AI ​​generate the optimal reminder method.

[0064] The location management unit can detect anomalies early by referring to past movement data during location management. For example, the location management unit can record past movement data and detect anomalies early based on that data. For example, the location management unit can analyze past movement data and detect abnormal movement patterns. The location management unit can also refer to past movement data and issue an alert if there is movement that is different from the normal. Furthermore, the location management unit can also detect abnormal movement early based on past movement data. For example, the location management unit can analyze past movement data and detect abnormal movement patterns. The location management unit can refer to past movement data and issue an alert if there is movement that is different from the normal. The location management unit can also detect abnormal movement early based on past movement data. As a result, the location management unit can detect anomalies early by referring to past movement data. Some or all of the above processing in the location management unit may be performed using AI, for example, or without using AI. For example, the location management unit can input past movement data into a generating AI and have the generating AI perform anomaly detection.

[0065] The location management unit can provide the optimal alert method by considering the user's geographical location information during location management. For example, the location management unit can acquire the user's geographical location information and provide the optimal alert method based on that data. For example, if the user is at high altitude, the location management unit can provide an alert regarding oxygen supply. The location management unit can also provide an alert regarding air quality if the user is in an urban area. Furthermore, if the user is at the beach, the location management unit can provide an alert regarding sun protection. For example, if the user is at high altitude, the location management unit can provide an alert regarding oxygen supply. The location management unit can also provide an alert regarding air quality if the user is in an urban area. The location management unit can also provide an alert regarding sun protection if the user is at the beach. In this way, the location management unit can provide the optimal alert method by considering the user's geographical location information. Some or all of the above processing in the location management unit may be performed using AI, for example, or without AI. For example, the location management unit can input the user's geographical location information into a generating AI and have the generating AI generate the optimal alert method.

[0066] The conversation unit can suggest the optimal flow of conversation by referring to past conversation history during a conversation. For example, the conversation unit can record past conversation history and suggest the optimal flow of conversation based on that data. For example, the conversation unit can recreate conversation flows that were well received in the past. The conversation unit can also avoid conversation flows that caused anxiety in the past. Furthermore, the conversation unit can analyze past conversation history and facilitate conversation at the optimal timing. For example, the conversation unit can recreate conversation flows that were well received in the past. The conversation unit can also avoid conversation flows that caused anxiety in the past. The conversation unit can also analyze past conversation history and facilitate conversation at the optimal timing. As a result, the conversation unit can suggest the optimal flow of conversation by referring to past conversation history. Some or all of the above processing in the conversation unit may be performed using AI, for example, or without AI. For example, the conversation unit can input past conversation history data into a generating AI and have the generating AI suggest the optimal flow of conversation.

[0067] The conversation unit can provide optimal conversation topics while considering the user's geographical location. For example, the conversation unit can acquire the user's geographical location and provide optimal conversation topics based on that data. For example, if the user is at high altitude, the conversation unit can provide conversation topics related to high altitude. Also, if the user is in an urban area, the conversation unit can provide conversation topics related to urban life. Furthermore, if the user is by the sea, the conversation unit can provide conversation topics related to the sea. For example, if the user is at high altitude, the conversation unit can provide conversation topics related to high altitude. If the user is in an urban area, the conversation unit can provide conversation topics related to urban life. If the user is by the sea, the conversation unit can provide conversation topics related to the sea. In this way, the conversation unit can provide optimal conversation topics while considering the user's geographical location. Some or all of the above processing in the conversation unit may be performed using AI, for example, or without AI. For example, the conversation unit can input the user's geographical location into a generating AI and have the generating AI generate optimal conversation topics.

[0068] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0069] The monitoring system can also be equipped with an environmental sensor unit. This unit can monitor the user's living environment and detect factors that affect their health. For example, it can measure indoor temperature and humidity and provide advice for maintaining a suitable environment. It can also monitor indoor air quality using an air quality sensor and prompt ventilation as needed. Furthermore, it can monitor indoor lighting conditions using an illuminance sensor and suggest an appropriate lighting environment. In this way, the monitoring system can optimize the user's living environment and support their health.

[0070] The monitoring system can also be equipped with an exercise recording unit. This unit can record the user's exercise data and analyze their exercise habits. For example, it can record the user's steps and exercise time, allowing for a grasp of their daily exercise volume. Furthermore, it can analyze the user's exercise patterns and suggest appropriate exercise plans. Additionally, the unit can monitor the user's exercise data over the long term, enabling early detection of signs of insufficient or excessive exercise. This allows the monitoring system to support the user's exercise habits and provide advice for maintaining good health.

[0071] The monitoring system can also be equipped with an emergency response unit. This unit can detect abnormalities in the user's health or environment and respond quickly. For example, it can detect abnormalities in the user's heart rate or blood pressure and notify emergency contacts. It can also detect abnormalities in indoor temperature or humidity and prompt appropriate action. Furthermore, the emergency response unit can track the user's location and respond quickly in emergencies. This allows the monitoring system to ensure user safety and provide a rapid response in emergencies.

[0072] The monitoring system can also be equipped with a learning support unit. This unit can support the user's intellectual activities and help maintain and improve cognitive function. For example, the learning support unit can provide the user with intellectual games such as quizzes and puzzles. It can also suggest learning content based on the user's interests. Furthermore, the learning support unit can record the user's learning progress and provide appropriate feedback. In this way, the monitoring system can support the user's intellectual activities and help maintain and improve cognitive function.

[0073] The following briefly describes the processing flow for example form 1.

[0074] Step 1: The health check unit performs a health check. Specifically, it can perform health checks using methods such as measuring body temperature, measuring blood pressure, and conducting interviews. For example, it can measure body temperature to detect abnormalities, measure blood pressure to detect abnormalities, and conduct interviews to confirm the user's health status. Step 2: The sharing unit shares the information confirmed by the health verification unit with the family. Specifically, information can be shared via email, messaging apps, or phone. For example, health information can be sent to family members via email, messaging apps, or phone. Step 3: The conversation facilitator facilitates conversation among family members based on the information shared by the sharing unit. Specifically, it can facilitate conversation by suggesting topics, presenting questions, etc. For example, it can facilitate conversation among family members by suggesting topics, presenting questions, or suggesting activities to stimulate conversation among family members.

[0075] (Example of form 2) The monitoring system according to an embodiment of the present invention is a system targeted at elderly parents, particularly elderly people living alone, and their families. This monitoring system is designed to mitigate the risks associated with elderly parents living alone, especially the risk of mental illness such as dementia. Preventing dementia requires intellectual activity, a balanced diet, moderate exercise, and sufficient sleep, but providing detailed and close support is difficult when living apart. The monitoring system utilizes an AI character and group chat to perform timely health checks, provide health support, and share this information with family members. This creates opportunities for conversation among family members and revitalizes communication. The AI ​​character also provides comprehensive support for the parent's life, including alleviating loneliness, intellectual conversation, meal management, medication management, physical condition management, exercise promotion, sleep management, schedule management, and stress relief. For example, the monitoring system can analyze and record the amount of calories and nutrients from video of meals. Furthermore, the monitoring system can determine the type of medication and intake status from video of medications. The monitoring system can record and analyze vital signs such as heart rate, calories burned, and steps taken, and provide health advice and encourage exercise. It can record sleep quality and duration, and provide advice to promote proper sleep. It can record the timing of events through daily activity logs and conversations, and provide reminders at appropriate times. It can track location information using GPS and issue alerts for unusual movement. It can learn from conversations with the user and family, and provide automated conversations optimized for the user. It can detect signs of mental illnesses such as dementia and depression from conversation content. This allows family members living separately to monitor and support their elderly parents. This improves the quality of life for parents and increases the family's sense of security.

[0076] The monitoring system according to the embodiment comprises a health confirmation unit, a sharing unit, and a conversation facilitating unit. The health confirmation unit performs health checks. The health confirmation unit can perform health checks by methods such as measuring body temperature, measuring blood pressure, and conducting interviews. For example, the health confirmation unit can measure body temperature and detect abnormal body temperature. The health confirmation unit can also measure blood pressure and detect abnormal blood pressure. Furthermore, the health confirmation unit can conduct interviews to confirm the user's health status. The sharing unit shares the information confirmed by the health confirmation unit with family members. The sharing unit can share information by methods such as email, messaging apps, and telephone. For example, the sharing unit can send health information to family members using email. The sharing unit can also send health information to family members using messaging apps. Furthermore, the sharing unit can also convey health information to family members by telephone. The conversation facilitating unit facilitates conversations among family members based on the information shared by the sharing unit. The conversation facilitating unit can facilitate conversations by methods such as suggesting topics and presenting questions. For example, the conversation facilitating unit can facilitate conversations among family members by suggesting topics. Furthermore, the conversation facilitator can also facilitate conversations among family members by presenting questions. In addition, the conversation facilitator can suggest activities to stimulate conversations among family members. As a result, the monitoring system according to the embodiment enables health checks, information sharing, and conversation facilitation.

[0077] The health check unit performs health checks. Specifically, it can perform health checks using methods such as temperature measurement, blood pressure measurement, and medical interviews. Temperature measurement can be performed using non-contact infrared thermometers or ear thermometers, allowing for quick and accurate temperature measurement. When detecting abnormal temperatures, it has a function to issue an alert if the temperature exceeds a pre-set normal range. Blood pressure measurement is performed using upper arm or wrist blood pressure monitors, measuring both systolic and diastolic blood pressure. This allows for early detection of abnormal blood pressure and the taking of necessary measures. Medical interviews involve asking users questions about their health status and evaluating their health status based on their answers. The content of the interviews is wide-ranging, such as recent changes in physical condition, appetite, and sleep quality. This allows for an understanding of the user's overall health status. Furthermore, the health check unit records these measurement and medical interview results as digital data for later reference. This allows for tracking changes in health status by comparing them with past data. The health check unit can also use AI to analyze measurement data and medical interview results to perform early detection of abnormalities and predict health status. For example, AI can learn patterns of anomalies based on past data and predict future risks. AI can also provide personalized health advice based on user responses. This allows the health monitoring unit to comprehensively manage the user's health status and facilitate early detection and prevention of anomalies.

[0078] The sharing unit shares information verified by the health monitoring unit with family members. Specifically, information can be shared via email, messaging apps, or telephone. When using email, data collected by the health monitoring unit is automatically formatted and sent to family members periodically. Emails include temperature and blood pressure measurement results, questionnaire responses, etc., and any detected abnormalities are highlighted. When using messaging apps, health information can be notified to family members in real time. For example, if an abnormality is detected, a notification is sent immediately, allowing family members to respond quickly. When using telephone, health information can be conveyed verbally using speech synthesis technology. This allows visually impaired family members and the elderly to receive the information. Furthermore, the sharing unit can customize how information is received according to the family's preferences. For example, it is possible to set notifications to be received only at specific times or to only receive important information. The sharing unit also takes information security into consideration and is equipped with data encryption and authentication functions. This minimizes the risk of personal information being leaked to third parties. The sharing unit can also provide a dedicated web portal or application to allow family members to easily access health information. This allows family members to check health information and take necessary actions anytime, anywhere.

[0079] The conversation facilitator facilitates conversations among family members based on information shared by the sharing unit. Specifically, it can facilitate conversations by suggesting topics and presenting questions. Topic suggestions are made, for example, by providing the latest health news or topics related to shared health information. This fosters natural conversations among family members and increases their interest in health. Questions are made by asking family members specific questions such as, "How have you been feeling lately?" or "Are you eating properly?" This activates communication among family members and allows for a deeper understanding of the user's health status. Furthermore, the conversation facilitator can also suggest activities to stimulate conversations among family members. For example, it can suggest activities such as cooking healthy meals together, going for walks, or participating in online health seminars. This increases the time families spend together and raises their awareness of health. The conversation facilitator can also use AI to analyze the content of conversations among family members and suggest more effective topics and questions. For example, it can identify topics that family members are likely to be interested in based on past conversation history and suggest topics based on that. The AI ​​can also analyze the tone and emotions of conversations and present questions at the appropriate time. This allows the conversation facilitator to facilitate communication among family members and provide support for a deeper understanding of the user's health condition.

[0080] The meal management unit can analyze and record the amount of calories and nutrients from video footage of meals. For example, the meal management unit can acquire video footage of meals using a camera, analyze the footage, and calculate the amount of calories and nutrients. For example, the meal management unit can set up a camera to film meals, analyze the footage, and calculate the amount of calories and nutrients. Furthermore, the meal management unit can perform more accurate analysis by setting a higher resolution for the video footage. In addition, the meal management unit can also calculate the amount of calories and nutrients of meals using a food database. For example, the meal management unit can calculate the amount of calories and nutrients of meals by referring to a food database. This allows the meal management unit to analyze and record the amount of calories and nutrients of meals. Some or all of the above processing in the meal management unit may be performed using AI, for example, or without AI. For example, the meal management unit can input video footage of meals into a generating AI and have the generating AI perform the analysis of the amount of calories and nutrients.

[0081] The drug management department can determine the type of drug and its intake status from images of the drug. For example, the drug management department can acquire images of the drug using a camera and analyze those images to determine the type of drug and its intake status. For example, the drug management department can install a camera to photograph the drug and analyze those images to determine the type of drug and its intake status. Furthermore, the drug management department can perform a more accurate analysis by setting a higher resolution for the images. In addition, the drug management department can also determine the type of drug and its intake status using drug shape recognition technology. For example, the drug management department can use drug shape recognition technology to identify the type of drug and determine its intake status. This allows the drug management department to determine the type of drug and its intake status. Some or all of the above processes in the drug management department may be performed using AI, for example, or without AI. For example, the drug management department can input images of the drug into a generating AI and have the generating AI perform the determination of the type of drug and its intake status.

[0082] The health management unit can record and analyze vital signs such as heart rate, calories burned, and steps taken. The health management unit can record vital signs using devices such as heart rate sensors, calorie calculators, and pedometers. For example, the health management unit can record heart rate using a heart rate sensor and analyze the data. It can also record calories burned using a calorie calculator and analyze the data. Furthermore, it can record steps taken using a pedometer and analyze the data. For example, the health management unit can record heart rate in real time using a heart rate sensor and issue an alert if there are abnormal fluctuations. The health management unit can also calculate calories burned and issue a warning if there is excessive calorie consumption. The health management unit can record steps using a pedometer and prompt exercise if the target number of steps has not been reached. This allows the health management unit to record and analyze vital signs. Some or all of the above-described processes in the health management unit may be performed using AI, for example, or without AI. For example, the health management department can input vital sign data into a generating AI and have the AI ​​generate health advice.

[0083] The sleep management department can record sleep quality and duration and provide advice to promote proper sleep. For example, the sleep management department can record sleep quality and duration using a sleep tracker. The sleep management department can also record sleep duration using a sleep tracker and analyze that data. Furthermore, the sleep management department can analyze sleep stages and provide advice to promote proper sleep. For example, the sleep management department can record sleep quality in real time using a sleep tracker and issue an alert if quality declines. The sleep management department can also measure sleep duration and suggest appropriate sleep durations. The sleep management department can analyze sleep stages and suggest improvements if deep sleep is insufficient. This allows the sleep management department to record sleep quality and duration and provide advice to promote proper sleep. Some or all of the above processes in the sleep management department may be performed using AI, or not. For example, the sleep management department can input sleep data into a generating AI and have the generating AI generate sleep advice.

[0084] The schedule management unit can record the timing of events through daily activity logs and conversations, and provide reminders at appropriate times. For example, the schedule management unit can analyze conversations using speech recognition technology to record the timing of events. The schedule management unit can also record activity logs, analyze that data, and record the timing of events. Furthermore, the schedule management unit can use a calendar to record the timing of events and set reminders. For example, the schedule management unit can register events in the calendar and provide reminders at appropriate times. This allows the schedule management unit to record the timing of events and provide reminders at appropriate times. Some or all of the above processes in the schedule management unit may be performed using AI, or not. For example, the schedule management unit can input activity log data into a generating AI and have the generating AI execute reminder timings.

[0085] The location management unit can grasp location information using GPS and issue alerts when movement deviates from the norm. For example, the location management unit can acquire location information using a GPS device and analyze that data to detect abnormal movement. For example, the location management unit can acquire location information in real time using a GPS device and issue an alert if there is movement deviating from the norm. The location management unit can also analyze movement patterns and detect abnormal movement. Furthermore, the location management unit can use an anomaly detection algorithm to detect abnormal movement at an early stage. For example, the location management unit analyzes movement patterns and issues an alert if there is movement deviating from the norm. In this way, the location management unit can grasp location information and issue alerts when movement deviates from the norm. Some or all of the above processing in the location management unit may be performed using AI, for example, or without using AI. For example, the location management unit can input location information data into a generating AI and have the generating AI perform the detection of abnormal movement.

[0086] The conversational unit can learn from conversations with the user and their family and conduct automated conversations optimized for the user. For example, the conversational unit can learn from conversation history and generate responses optimized for the user. For example, the conversational unit can analyze conversation history and generate responses based on the user's interests. The conversational unit can also learn from conversation history to generate personalized responses. Furthermore, the conversational unit can learn the user's conversation patterns and generate optimal responses. For example, the conversational unit can learn from conversation history and advance the conversation based on the user's interests. This allows the conversational unit to conduct automated conversations optimized for the user. Some or all of the above processes in the conversational unit may be performed using AI, for example, or without AI. For example, the conversational unit can input conversation history data into a generating AI and have the generating AI perform the generation of optimal responses.

[0087] The health monitoring unit can estimate the user's emotions and adjust the frequency of health checks based on those estimated emotions. For example, the health monitoring unit can use facial recognition technology to estimate the user's emotions and adjust the frequency of health checks based on those emotions. Alternatively, it can analyze the user's facial expressions using facial recognition technology to estimate emotions. Furthermore, the health monitoring unit can analyze the user's voice using voice analysis technology to estimate emotions. In addition, it can analyze the user's text data using text analysis technology to estimate emotions. For example, if the user is stressed, the health monitoring unit can reduce the frequency of health checks and increase the time the user can relax. If the user is relaxed, the health monitoring unit can increase the frequency of health checks and provide more detailed health information. If the user is anxious, the health monitoring unit can appropriately adjust the frequency of health checks to provide a sense of security. Thus, the health monitoring unit can adjust the frequency of health checks based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generating AI may be a text generating AI (e.g., LLM) or a multimodal generating AI, but is not limited to such examples. Some or all of the processing described above in the health check unit may be performed using AI, or not using AI. For example, the health check unit can input user emotion data into the generating AI and have the generating AI adjust the frequency of health checks.

[0088] The health monitoring unit can detect abnormalities early by referring to past health data during health checks. For example, the health monitoring unit can refer to past heart rate data and issue an alert if there are abnormal fluctuations. For example, the health monitoring unit can analyze past heart rate data and issue an alert if there are abnormal fluctuations. The health monitoring unit can also refer to past step count data and detect abnormalities if there is a sudden decrease. Furthermore, the health monitoring unit can refer to past sleep data and detect abnormalities if the quality of sleep has deteriorated. For example, the health monitoring unit can refer to past heart rate data and issue an alert if there are abnormal fluctuations. The health monitoring unit can also analyze past step count data and detect abnormalities if there is a sudden decrease. The health monitoring unit can also refer to past sleep data and detect abnormalities if the quality of sleep has deteriorated. As a result, the health monitoring unit can detect abnormalities early by referring to past health data. Some or all of the above processing in the health monitoring unit may be performed using AI, for example, or without using AI. For example, the health verification unit can input past health data into a generating AI and have the generating AI perform abnormality detection.

[0089] The health check unit can provide customized health advice based on the user's lifestyle habits during health checks. For example, the health check unit can suggest a balanced diet based on the user's eating habits. For example, the health check unit can record the user's eating habits and suggest a balanced diet based on that data. The health check unit can also provide appropriate exercise advice based on the user's exercise habits. Furthermore, the health check unit can provide advice to promote quality sleep based on the user's sleep habits. For example, the health check unit can record the user's eating habits and suggest a balanced diet based on that data. The health check unit can also record the user's exercise habits and provide appropriate exercise advice based on that data. The health check unit can also record the user's sleep habits and provide advice to promote quality sleep based on that data. In this way, the health check unit can provide customized health advice based on the user's lifestyle habits. Some or all of the above processing in the health check unit may be performed using AI, for example, or without using AI. For example, the health monitoring unit can input the user's lifestyle data into a generating AI, which can then generate customized health advice.

[0090] The health check unit can estimate the user's emotions and adjust the content of the health check based on the estimated emotions. For example, the health check unit can estimate the user's emotions using facial recognition technology and adjust the content of the health check based on those emotions. For example, the health check unit can analyze the user's facial expressions using facial recognition technology and estimate their emotions. Furthermore, the health check unit can analyze the user's voice using voice analysis technology and estimate their emotions. In addition, the health check unit can analyze the user's text data using text analysis technology and estimate their emotions. For example, if the user is feeling stressed, the health check unit can provide relaxing advice. If the user is relaxed, the health check unit can also provide detailed health information. If the user is feeling anxious, the health check unit can also provide reassuring health information. This allows the health check unit to adjust the content of the health check based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the health verification unit may be performed using AI, for example, or without AI. For example, the health verification unit can input user emotion data into a generating AI and have the generating AI adjust the content of the health verification.

[0091] The health verification unit can provide environmentally appropriate health advice based on the user's geographical location information during health verification. For example, the health verification unit can provide environmentally appropriate health advice considering the user's geographical location information. For example, if the user is at high altitude, the health verification unit can provide advice regarding oxygen supply. The health verification unit can also provide advice regarding air quality if the user is in an urban area. Furthermore, if the user is at the beach, the health verification unit can provide advice regarding sun protection. For example, if the user is at high altitude, the health verification unit can provide advice regarding oxygen supply. The health verification unit can also provide advice regarding air quality if the user is in an urban area. The health verification unit can also provide advice regarding sun protection if the user is at the beach. In this way, the health verification unit can provide environmentally appropriate health advice based on the user's geographical location information. Some or all of the above processing in the health verification unit may be performed using AI, for example, or without AI. For example, the health verification unit can input the user's geographical location information into a generating AI and have the generating AI generate environmentally appropriate health advice.

[0092] The health verification unit can analyze the user's social media activity and provide relevant health information during health verification. For example, the health verification unit can analyze the user's social media activity and provide relevant health information. For example, if the user is experiencing stress on social media, the health verification unit can suggest ways to relax. The health verification unit can also provide relevant advice if the user is sharing health-related information on social media. Furthermore, if the user is sharing exercise-related information on social media, the health verification unit can suggest appropriate exercise methods. For example, if the user is experiencing stress on social media, the health verification unit can suggest ways to relax. The health verification unit can also provide relevant advice if the user is sharing health-related information on social media. The health verification unit can also suggest appropriate exercise methods if the user is sharing exercise-related information on social media. This allows the health verification unit to analyze the user's social media activity and provide relevant health information. Some or all of the above processing in the health verification unit may be performed using AI, for example, or without AI. For example, the health verification unit can input the user's social media data into a generating AI and have the generating AI generate relevant health information.

[0093] The sharing unit can estimate the user's emotions and determine the priority of information to share based on those estimated emotions. For example, the sharing unit can use facial recognition technology to estimate the user's emotions and determine the priority of information to share based on those emotions. For example, the sharing unit can analyze the user's facial expressions using facial recognition technology and estimate their emotions. The sharing unit can also analyze the user's voice using voice analysis technology and estimate their emotions. Furthermore, the sharing unit can analyze the user's text data using text analysis technology and estimate their emotions. For example, if the user is stressed, the sharing unit will prioritize sharing information that helps them relax. If the user is relaxed, the sharing unit can also prioritize sharing detailed health information. If the user is anxious, the sharing unit can also prioritize sharing information that provides reassurance. This allows the sharing unit to determine the priority of information to share based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the shared section may be performed using AI, for example, or without AI. For example, the shared section can input user emotion data into a generating AI and have the generating AI determine the priority of the information.

[0094] The sharing unit can analyze the family's past reactions and select the optimal sharing method when sharing information. For example, the sharing unit can record the family's past reactions and analyze that data to select the optimal sharing method. For example, the sharing unit can prioritize sharing information that the family has received favorably in the past. The sharing unit can also avoid sharing information that the family has felt anxious about in the past. Furthermore, the sharing unit can analyze the family's past reactions and share information at the optimal timing. For example, the sharing unit can prioritize sharing information that the family has received favorably in the past. The sharing unit can also avoid sharing information that the family has felt anxious about in the past. The sharing unit can also analyze the family's past reactions and share information at the optimal timing. As a result, the sharing unit can analyze the family's past reactions and select the optimal sharing method. Some or all of the above processing in the sharing unit may be performed using AI, for example, or without AI. For example, the sharing unit can input data on the family's past reactions into a generating AI and have the generating AI select the optimal sharing method.

[0095] The sharing unit can adjust the level of detail of information shared based on its importance. For example, the sharing unit can evaluate the importance of information and adjust the level of detail based on that evaluation. For example, the sharing unit can share important health information in detail. It can also share general health information concisely. Furthermore, it can share urgent information quickly. For example, the sharing unit can share important health information in detail. It can also share general health information concisely. It can also share urgent information quickly. This allows the sharing unit to adjust the level of detail of information shared based on its importance. Some or all of the above processing in the sharing unit may be performed using AI, for example, or without AI. For example, the sharing unit can input information importance data into a generating AI and have the generating AI perform the adjustment of the level of detail of sharing.

[0096] The sharing unit can estimate the user's emotions and adjust the format of the information it shares based on those emotions. For example, the sharing unit can use facial recognition technology to estimate the user's emotions and adjust the format of the information it shares based on those emotions. For example, the sharing unit can analyze the user's facial expressions using facial recognition technology and estimate their emotions. The sharing unit can also analyze the user's voice using speech analysis technology and estimate their emotions. Furthermore, the sharing unit can analyze the user's text data using text analysis technology and estimate their emotions. For example, if the user is stressed, the sharing unit can share information in a visually relaxing format. If the user is relaxed, the sharing unit can also share information in a detailed text format. If the user is anxious, the sharing unit can also share information in a reassuring format. This allows the sharing unit to adjust the format of the information it shares based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the shared section may be performed using AI, for example, or without AI. For example, the shared section can input user emotion data into a generating AI and have the generating AI adjust the format of the information.

[0097] The sharing unit can select the optimal sharing method by considering the geographical location information of family members when sharing information. For example, the sharing unit can acquire the geographical location information of family members and select the optimal sharing method based on that data. For example, if family members are nearby, the sharing unit can share information through direct conversation. The sharing unit can also share information via video call if family members are far away. Furthermore, if family members are on the move, the sharing unit can share information via text message. For example, if family members are nearby, the sharing unit can share information through direct conversation. The sharing unit can also share information via video call if family members are far away. The sharing unit can also share information via text message if family members are on the move. This allows the sharing unit to select the optimal sharing method by considering the geographical location information of family members. Some or all of the above processing in the sharing unit may be performed using AI, for example, or without AI. For example, the sharing unit can input the geographical location information of family members into a generating AI and have the generating AI select the optimal sharing method.

[0098] The sharing unit can analyze the family's social media activity and share relevant information when sharing. For example, the sharing unit can analyze the family's social media activity and share relevant information based on that data. For example, if the family shares health-related information on social media, the sharing unit can provide relevant information. The sharing unit can also suggest relaxation methods if the family is feeling stressed on social media. Furthermore, if the family shares exercise-related information on social media, the sharing unit can suggest appropriate exercise methods. For example, if the family shares health-related information on social media, the sharing unit can provide relevant information. The sharing unit can also suggest relaxation methods if the family is feeling stressed on social media. The sharing unit can also suggest appropriate exercise methods if the family shares exercise-related information on social media. In this way, the sharing unit can analyze the family's social media activity and share relevant information. Some or all of the above processing in the sharing unit may be performed using AI, for example, or not. For example, the sharing unit can input the family's social media data into a generating AI and have the generating AI generate relevant information.

[0099] The conversation facilitator can estimate the user's emotions and select conversation topics based on those estimated emotions. For example, the conversation facilitator can use facial recognition technology to estimate the user's emotions and select conversation topics based on those emotions. Alternatively, it can analyze the user's facial expressions using facial recognition technology to estimate emotions. Furthermore, it can analyze the user's voice using voice analysis technology to estimate emotions. In addition, it can analyze the user's text data using text analysis technology to estimate emotions. For example, if the user is stressed, the conversation facilitator can select a relaxing topic. If the user is relaxed, it can also select a topic about detailed health information. If the user is anxious, it can also select a topic that provides reassurance. Thus, the conversation facilitator can select conversation topics based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. The generative AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the processing described above in the conversation facilitation unit may be performed using AI, for example, or not using AI. For example, the conversation facilitation unit may input user sentiment data into the generative AI and have the generative AI select conversation topics.

[0100] The conversation facilitator can, when facilitating a conversation, refer to past conversation history to suggest the optimal flow of conversation. For example, the conversation facilitator can record past conversation history and suggest the optimal flow of conversation based on that data. For example, the conversation facilitator can recreate conversation flows that were well-received in the past. The conversation facilitator can also avoid conversation flows that caused anxiety in the past. Furthermore, the conversation facilitator can analyze past conversation history and facilitate conversation at the optimal timing. For example, the conversation facilitator can recreate conversation flows that were well-received in the past. The conversation facilitator can also avoid conversation flows that caused anxiety in the past. The conversation facilitator can analyze past conversation history and facilitate conversation at the optimal timing. As a result, the conversation facilitator can refer to past conversation history to suggest the optimal flow of conversation. Some or all of the above processing in the conversation facilitator may be performed using AI, for example, or without AI. For example, the conversation facilitator can input past conversation history data into a generating AI and have the generating AI propose the optimal flow of conversation.

[0101] The conversation facilitator can customize the content of conversations based on the family's interests when facilitating a conversation. For example, the conversation facilitator can record the family's interests and customize the content of conversations based on that data. For example, if the family is interested in health, the conversation facilitator can facilitate conversations about health. The conversation facilitator can also facilitate conversations about hobbies if the family is interested in those hobbies. Furthermore, if the family is interested in travel, the conversation facilitator can also facilitate conversations about travel. For example, if the family is interested in health, the conversation facilitator can facilitate conversations about health. The conversation facilitator can also facilitate conversations about hobbies if the family is interested in those hobbies. The conversation facilitator can also facilitate conversations about travel if the family is interested in travel. In this way, the conversation facilitator can customize the content of conversations based on the family's interests. Some or all of the above processing in the conversation facilitator may be performed using AI, for example, or without AI. For example, the conversation facilitator can input family interest data into a generating AI and have the generating AI perform the customization of the conversation content.

[0102] The conversation facilitator can estimate the user's emotions and adjust the timing of the conversation based on those emotions. For example, the conversation facilitator can use facial recognition technology to estimate the user's emotions and adjust the timing of the conversation based on those emotions. For example, the conversation facilitator can analyze the user's facial expressions using facial recognition technology and estimate their emotions. Furthermore, the conversation facilitator can analyze the user's voice using voice analysis technology and estimate their emotions. In addition, the conversation facilitator can analyze the user's text data using text analysis technology and estimate their emotions. For example, if the user is stressed, the conversation facilitator can facilitate the conversation at a time when the user can relax. If the user is relaxed, the conversation facilitator can also facilitate the conversation at a time when the user can provide detailed health information. If the user is anxious, the conversation facilitator can also facilitate the conversation at a time when the user can provide reassurance. This allows the conversation facilitator to adjust the timing of the conversation based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generating AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the conversation facilitator may be performed using AI, or not using AI. For example, the conversation facilitator may input user emotion data into the generating AI and have the generating AI adjust the timing of the conversation.

[0103] The conversation facilitator can select the optimal timing for a conversation by considering the geographical location information of the family members when facilitating a conversation. For example, the conversation facilitator can acquire the geographical location information of the family members and select the optimal timing for a conversation based on that data. For example, if the family members are nearby, the conversation facilitator can facilitate the conversation through direct conversation. The conversation facilitator can also facilitate the conversation through video calls if the family members are far away. Furthermore, if the family members are on the move, the conversation facilitator can facilitate the conversation through text messages. For example, if the family members are nearby, the conversation facilitator can facilitate the conversation through direct conversation. The conversation facilitator can also facilitate the conversation through video calls if the family members are far away. The conversation facilitator can also facilitate the conversation through text messages if the family members are on the move. This allows the conversation facilitator to select the optimal timing for a conversation by considering the geographical location information of the family members. Some or all of the above processing in the conversation facilitator may be performed using AI, for example, or without AI. For example, the conversation facilitator can input the geographical location information of the family members into a generating AI and have the generating AI select the optimal timing for a conversation.

[0104] The conversation facilitator can analyze the family's social media activity and provide relevant conversation topics when facilitating a conversation. For example, the conversation facilitator can analyze the family's social media activity and provide relevant conversation topics based on that data. For example, if the family is sharing health-related information on social media, the conversation facilitator can provide relevant conversation topics. The conversation facilitator can also suggest ways to relax if the family is feeling stressed by social media. Furthermore, if the family is sharing exercise-related information on social media, the conversation facilitator can suggest appropriate exercise methods. For example, if the family is sharing health-related information on social media, the conversation facilitator can provide relevant conversation topics. The conversation facilitator can also suggest ways to relax if the family is feeling stressed by social media. The conversation facilitator can also suggest appropriate exercise methods if the family is sharing exercise-related information on social media. This allows the conversation facilitator to analyze the family's social media activity and provide relevant conversation topics. Some or all of the above processing in the conversation facilitator may be performed using AI, for example, or without AI. For example, the conversation facilitator can input family social media data into a generating AI and have the AI ​​generate relevant conversation topics.

[0105] The meal management department can estimate the user's emotions and adjust meal suggestions based on those emotions. For example, the meal management department can use facial recognition technology to estimate the user's emotions and adjust meal suggestions based on those emotions. Alternatively, it can analyze the user's facial expressions using facial recognition technology to estimate emotions. Furthermore, the meal management department can analyze the user's voice using voice analysis technology to estimate emotions. In addition, it can analyze the user's text data using text analysis technology to estimate emotions. For example, if the user is stressed, the meal management department can suggest a relaxing meal. If the user is relaxed, the meal management department can suggest a well-balanced meal. If the user is anxious, the meal management department can suggest a reassuring meal. This allows the meal management department to adjust meal suggestions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the meal management department may be performed using AI, for example, or without AI. For example, the meal management department can input user emotion data into a generating AI and have the generating AI adjust meal suggestions.

[0106] The meal management department can optimize nutritional balance by referring to past meal data during meal management. For example, the meal management department can record past meal data and optimize nutritional balance based on that data. For example, the meal management department can analyze past meal data and propose meals that compensate for nutrient deficiencies. The meal management department can also refer to past meal data and propose meals that prevent calorie overload. Furthermore, the meal management department can propose well-balanced meal menus based on past meal data. For example, the meal management department can analyze past meal data and propose meals that compensate for nutrient deficiencies. The meal management department can also refer to past meal data and propose meals that prevent calorie overload. The meal management department can also propose well-balanced meal menus based on past meal data. In this way, the meal management department can optimize nutritional balance by referring to past meal data. Some or all of the above processes in the meal management department may be performed using AI, for example, or without AI. For example, the meal management department can input past meal data into a generating AI and have the generating AI perform the optimization of nutritional balance.

[0107] The meal management unit can customize meal content based on the user's health condition during meal management. For example, the meal management unit can record the user's health condition and customize meal content based on that data. For example, the meal management unit can suggest a low-sodium meal considering the user's health condition. The meal management unit can also suggest a low-calorie meal based on the user's health condition. Furthermore, the meal management unit can suggest a meal rich in specific nutrients considering the user's health condition. For example, the meal management unit can suggest a low-sodium meal considering the user's health condition. The meal management unit can also suggest a low-calorie meal based on the user's health condition. The meal management unit can also suggest a meal rich in specific nutrients considering the user's health condition. In this way, the meal management unit can customize meal content based on the user's health condition. Some or all of the above processing in the meal management unit may be performed using AI, for example, or without AI. For example, the meal management unit can input the user's health condition data into a generating AI and have the generating AI perform the customization of meal content.

[0108] The meal management system can estimate the user's emotions and adjust meal timing based on those emotions. For example, the system can use facial recognition technology to estimate the user's emotions and adjust meal timing accordingly. Alternatively, it can analyze the user's facial expressions using facial recognition technology to estimate emotions. Furthermore, it can analyze the user's voice using voice analysis technology to estimate emotions. In addition, it can analyze the user's text data using text analysis technology to estimate emotions. For example, if the user is stressed, the system can suggest a meal at a time that promotes relaxation. If the user is relaxed, the system can suggest a meal at an appropriate time. If the user is anxious, the system can suggest a meal at a time that provides reassurance. This allows the system to adjust meal timing based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the meal management department may be performed using AI, for example, or without AI. For example, the meal management department can input user emotional data into a generating AI and have the generating AI adjust the timing of meals.

[0109] The meal management unit can suggest the optimal meal while considering the user's geographical location. For example, the meal management unit can acquire the user's geographical location and suggest the optimal meal based on that data. For example, if the user is at high altitude, the meal management unit can suggest a high-calorie meal. Also, if the user is in an urban area, the meal management unit can suggest a well-balanced meal. Furthermore, if the user is by the sea, the meal management unit can suggest a meal that includes a lot of seafood. For example, if the user is at high altitude, the meal management unit can suggest a high-calorie meal. If the user is in an urban area, the meal management unit can suggest a well-balanced meal. If the user is by the sea, the meal management unit can suggest a meal that includes a lot of seafood. In this way, the meal management unit can suggest the optimal meal while considering the user's geographical location. Some or all of the above processing in the meal management unit may be performed using AI, for example, or without AI. For example, the meal management unit can input the user's geographical location information into a generating AI and have the generating AI suggest the optimal meal.

[0110] The diet management department can analyze a user's social media activity and provide relevant dietary information during dietary management. For example, the diet management department can analyze a user's social media activity and provide relevant dietary information based on that data. For example, if a user shares health-related information on social media, the diet management department can provide relevant dietary information. The diet management department can also suggest relaxing meals if a user is experiencing stress on social media. Furthermore, if a user shares exercise-related information on social media, the diet management department can provide appropriate dietary information. For example, if a user shares health-related information on social media, the diet management department can provide relevant dietary information. The diet management department can also suggest relaxing meals if a user is experiencing stress on social media. The diet management department can also provide appropriate dietary information if a user shares exercise-related information on social media. This allows the diet management department to analyze a user's social media activity and provide relevant dietary information. Some or all of the above processing in the diet management department may be performed using AI, for example, or without AI. For example, the diet management department can input the user's social media data into a generating AI and have the generating AI generate relevant dietary information.

[0111] The medication management department can estimate the user's emotions and adjust the timing of medication intake based on those emotions. For example, the medication management department can use facial recognition technology to estimate the user's emotions and adjust the timing of medication intake based on those emotions. For example, the medication management department can use facial recognition technology to analyze the user's facial expressions and estimate their emotions. The medication management department can also use voice analysis technology to analyze the user's voice and estimate their emotions. Furthermore, the medication management department can use text analysis technology to analyze the user's text data and estimate their emotions. For example, if the user is feeling stressed, the medication management department can suggest taking medication at a time when they can relax. If the user is relaxed, the medication management department can also suggest taking medication at an appropriate time. If the user is feeling anxious, the medication management department can also suggest taking medication at a time that will provide reassurance. In this way, the medication management department can adjust the timing of medication intake based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the above-described processes in the drug management department may be performed using AI, for example, or not using AI. For example, the drug management department may input user emotion data into the generative AI and have the generative AI adjust the timing of drug intake.

[0112] The medication management department can propose the optimal method of medication intake by referring to past medication intake data during medication management. For example, the medication management department can record past medication intake data and propose the optimal method of intake based on that data. For example, the medication management department can analyze past medication intake data and propose the optimal timing of intake. The medication management department can also refer to past medication intake data and propose the appropriate dosage of medication. Furthermore, the medication management department can customize the method of medication intake based on past medication intake data. For example, the medication management department can analyze past medication intake data and propose the optimal timing of intake. The medication management department can also refer to past medication intake data and propose the appropriate dosage of medication. The medication management department can also customize the method of medication intake based on past medication intake data. As a result, the medication management department can propose the optimal method of medication intake by referring to past medication intake data. Some or all of the above processes in the medication management department may be performed using AI, for example, or not using AI. For example, the medication management department can input past medication intake data into a generating AI and have the generating AI propose the optimal method of intake.

[0113] The drug management department can estimate the user's emotions and adjust the method of medication intake based on those estimated emotions. For example, the drug management department can use facial recognition technology to estimate the user's emotions and adjust the method of medication intake based on those emotions. For example, the drug management department can analyze the user's facial expressions using facial recognition technology to estimate emotions. Furthermore, the drug management department can analyze the user's voice using voice analysis technology to estimate emotions. In addition, the drug management department can analyze the user's text data using text analysis technology to estimate emotions. For example, if the user is feeling stressed, the drug management department can suggest a relaxing way to take the medication. If the user is relaxed, the drug management department can also suggest an appropriate way to take the medication. If the user is feeling anxious, the drug management department can also suggest a reassuring way to take the medication. This allows the drug management department to adjust the method of medication intake based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generative AI may be, but is not limited to, text-generating AI (e.g., LLM) or multimodal generative AI. Some or all of the above-described processes in the drug management department may be performed using AI, or not using AI. For example, the drug management department may input user emotion data into the generative AI and have the generative AI adjust the method of drug intake.

[0114] The drug management department can propose the optimal method of drug intake when managing medication, taking into account the user's geographical location. For example, the drug management department can acquire the user's geographical location and propose the optimal method of drug intake based on that data. For example, if the user is at high altitude, the drug management department can propose taking the medication with a high-calorie meal. Also, if the user is in an urban area, the drug management department can propose taking the medication with a balanced meal. Furthermore, if the user is by the sea, the drug management department can propose taking the medication with a meal rich in seafood. For example, if the user is at high altitude, the drug management department can propose taking the medication with a high-calorie meal. If the user is in an urban area, the drug management department can propose taking the medication with a balanced meal. If the user is by the sea, the drug management department can propose taking the medication with a meal rich in seafood. In this way, the drug management department can propose the optimal method of drug intake, taking into account the user's geographical location. Some or all of the above processing in the drug management department may be performed using AI, for example, or not using AI. For example, the drug management department can input the user's geographical location information into a generating AI and have the AI ​​suggest the optimal way to take the medication.

[0115] The health management unit can estimate the user's emotions and adjust health management advice based on those emotions. For example, the health management unit can use facial recognition technology to estimate the user's emotions and adjust health management advice based on those emotions. For example, the health management unit can analyze the user's facial expressions using facial recognition technology and estimate their emotions. Furthermore, the health management unit can analyze the user's voice using voice analysis technology and estimate their emotions. In addition, the health management unit can analyze the user's text data using text analysis technology and estimate their emotions. For example, if the user is feeling stressed, the health management unit can provide advice to help them relax. If the user is relaxed, the health management unit can also provide detailed health information. If the user is feeling anxious, the health management unit can also provide advice to reassure them. This allows the health management unit to adjust health management advice based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the health management department may be performed using AI, for example, or without AI. For example, the health management department can input user emotional data into a generating AI and have the generating AI adjust health management advice.

[0116] The health management department can provide optimal health advice by referring to past vital sign data during health management. For example, the health management department can record past vital sign data and provide optimal health advice based on that data. For example, the health management department can analyze past heart rate data and suggest the optimal exercise method. The health management department can also refer to past calorie expenditure data and suggest appropriate meals. Furthermore, the health management department can suggest the optimal amount of exercise based on past step count data. For example, the health management department can analyze past heart rate data and suggest the optimal exercise method. The health management department can also refer to past calorie expenditure data and suggest appropriate meals. The health management department can also suggest the optimal amount of exercise based on past step count data. As a result, the health management department can provide optimal health advice by referring to past vital sign data. Some or all of the above processing in the health management department may be performed using AI, for example, or without AI. For example, the health management department can input past vital sign data into a generating AI and have the generating AI generate optimal health advice.

[0117] The health management unit can estimate the user's emotions and adjust the frequency of health management based on those estimated emotions. For example, the health management unit can use facial recognition technology to estimate the user's emotions and adjust the frequency of health management based on those emotions. For example, the health management unit can analyze the user's facial expressions using facial recognition technology and estimate their emotions. Furthermore, the health management unit can analyze the user's voice using voice analysis technology and estimate their emotions. In addition, the health management unit can analyze the user's text data using text analysis technology and estimate their emotions. For example, if the user is stressed, the health management unit can reduce the frequency of health management and increase the time the user can relax. If the user is relaxed, the health management unit can increase the frequency of health management and provide more detailed health information. If the user is anxious, the health management unit can appropriately adjust the frequency of health management to provide a sense of security. In this way, the health management unit can adjust the frequency of health management based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processes in the health management unit may be performed using AI, or not using AI. For example, the health management unit can input user emotion data into the generation AI and have the generation AI adjust the frequency of health management.

[0118] The health management unit can provide optimal health advice by taking into account the user's geographical location information during health management. For example, the health management unit can acquire the user's geographical location information and provide optimal health advice based on that data. For example, if the user is at high altitude, the health management unit can provide advice regarding oxygen supply. The health management unit can also provide advice regarding air quality if the user is in an urban area. Furthermore, if the user is at the beach, the health management unit can provide advice regarding sun protection. For example, if the user is at high altitude, the health management unit can provide advice regarding oxygen supply. The health management unit can also provide advice regarding air quality if the user is in an urban area. The health management unit can also provide advice regarding sun protection if the user is at the beach. In this way, the health management unit can provide optimal health advice by taking into account the user's geographical location information. Some or all of the above processing in the health management unit may be performed using AI, for example, or without AI. For example, the health management unit can input the user's geographical location information into a generating AI and have the generating AI generate optimal health advice.

[0119] The sleep management unit can estimate the user's emotions and adjust sleep management advice based on those emotions. For example, the sleep management unit can use facial recognition technology to estimate the user's emotions and adjust sleep management advice based on those emotions. Alternatively, the sleep management unit can analyze the user's facial expressions using facial recognition technology to estimate emotions. Furthermore, the sleep management unit can analyze the user's voice using voice analysis technology to estimate emotions. In addition, the sleep management unit can analyze the user's text data using text analysis technology to estimate emotions. For example, if the user is feeling stressed, the sleep management unit can suggest a relaxing sleep environment. If the user is relaxed, the sleep management unit can also provide detailed sleep information. If the user is feeling anxious, the sleep management unit can provide reassuring sleep advice. This allows the sleep management unit to adjust sleep management advice based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the sleep management unit may be performed using AI, for example, or without AI. For example, the sleep management unit can input user emotional data into a generating AI and have the generating AI adjust the sleep management advice.

[0120] The sleep management unit can provide optimal sleep advice by referring to past sleep data during sleep management. For example, the sleep management unit can record past sleep data and provide optimal sleep advice based on that data. For example, the sleep management unit can analyze past sleep data and propose an optimal sleep duration. Furthermore, the sleep management unit can refer to past sleep data and propose an appropriate sleep environment. In addition, the sleep management unit can provide advice to promote quality sleep based on past sleep data. For example, the sleep management unit can analyze past sleep data and propose an optimal sleep duration. The sleep management unit can also refer to past sleep data and propose an appropriate sleep environment. The sleep management unit can also provide advice to promote quality sleep based on past sleep data. Thus, the sleep management unit can provide optimal sleep advice by referring to past sleep data. Some or all of the above processes in the sleep management unit may be performed using AI, for example, or without AI. For example, the sleep management unit can input past sleep data into a generating AI and have the generating AI generate optimal sleep advice.

[0121] The sleep management unit can estimate the user's emotions and adjust the frequency of sleep management based on those emotions. For example, the sleep management unit can use facial recognition technology to estimate the user's emotions and adjust the frequency of sleep management based on those emotions. Alternatively, the sleep management unit can analyze the user's facial expressions using facial recognition technology to estimate emotions. Furthermore, the sleep management unit can analyze the user's voice using voice analysis technology to estimate emotions. In addition, the sleep management unit can analyze the user's text data using text analysis technology to estimate emotions. For example, if the user is stressed, the sleep management unit can reduce the frequency of sleep management and increase the time for relaxation. If the user is relaxed, the sleep management unit can increase the frequency of sleep management and provide more detailed sleep information. If the user is anxious, the sleep management unit can appropriately adjust the frequency of sleep management to provide a sense of security. Thus, the sleep management unit can adjust the frequency of sleep management based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processes in the sleep management unit may be performed using AI, or not using AI. For example, the sleep management unit can input user emotion data into the generation AI and have the generation AI adjust the frequency of sleep management.

[0122] The sleep management unit can provide optimal sleep advice while considering the user's geographical location information. For example, the sleep management unit can acquire the user's geographical location information and provide optimal sleep advice based on that data. For example, if the user is at high altitude, the sleep management unit can provide advice regarding oxygen supply. The sleep management unit can also provide advice regarding air quality if the user is in an urban area. Furthermore, if the user is at the beach, the sleep management unit can provide advice regarding sun protection. For example, if the user is at high altitude, the sleep management unit can provide advice regarding oxygen supply. The sleep management unit can also provide advice regarding air quality if the user is in an urban area. The sleep management unit can also provide advice regarding sun protection if the user is at the beach. In this way, the sleep management unit can provide optimal sleep advice while considering the user's geographical location information. Some or all of the above processing in the sleep management unit may be performed using AI, for example, or without AI. For example, the sleep management unit can input the user's geographical location information into a generating AI and have the generating AI generate optimal sleep advice.

[0123] The schedule management unit can estimate the user's emotions and adjust schedule management advice based on those emotions. For example, the schedule management unit can use facial recognition technology to estimate the user's emotions and adjust schedule management advice based on those emotions. Alternatively, the schedule management unit can analyze the user's facial expressions using facial recognition technology to estimate emotions. Furthermore, the schedule management unit can analyze the user's voice using voice analysis technology to estimate emotions. In addition, the schedule management unit can analyze the user's text data using text analysis technology to estimate emotions. For example, if the user is feeling stressed, the schedule management unit can suggest relaxing activities. If the user is relaxed, the schedule management unit can also provide detailed activity information. If the user is feeling anxious, the schedule management unit can provide reassuring activity advice. This allows the schedule management unit to adjust schedule management advice based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processes described above in the schedule management unit may be performed using AI, for example, or without AI. For example, the schedule management unit can input user emotion data into a generating AI and have the generating AI adjust the schedule management advice.

[0124] The schedule management unit can provide the optimal reminder method by referring to past activity records when managing schedules. For example, the schedule management unit can record past activity records and provide the optimal reminder method based on that data. For example, the schedule management unit can analyze past activity records and propose the optimal reminder timing. The schedule management unit can also refer to past activity records and propose an appropriate reminder method (voice, text, etc.). Furthermore, the schedule management unit can adjust the frequency of reminders based on past activity records. For example, the schedule management unit can analyze past activity records and propose the optimal reminder timing. The schedule management unit can also refer to past activity records and propose an appropriate reminder method (voice, text, etc.). The schedule management unit can also adjust the frequency of reminders based on past activity records. This allows the schedule management unit to provide the optimal reminder method by referring to past activity records. Some or all of the above processes in the schedule management unit may be performed using AI, for example, or not. For example, the schedule management unit can input past activity record data into a generating AI and have the generating AI propose an optimal reminder method.

[0125] The schedule management unit can estimate the user's emotions and adjust the frequency of schedule management based on those estimated emotions. For example, the schedule management unit can use facial recognition technology to estimate the user's emotions and adjust the frequency of schedule management based on those emotions. Alternatively, the schedule management unit can analyze the user's facial expressions using facial recognition technology to estimate emotions. Furthermore, the schedule management unit can analyze the user's voice using voice analysis technology to estimate emotions. In addition, the schedule management unit can analyze the user's text data using text analysis technology to estimate emotions. For example, if the user is stressed, the schedule management unit can reduce the frequency of schedule management and increase the time the user can relax. If the user is relaxed, the schedule management unit can increase the frequency of schedule management and provide more detailed schedule information. If the user is anxious, the schedule management unit can appropriately adjust the frequency of schedule management to provide a sense of security. In this way, the schedule management unit can adjust the frequency of schedule management based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processes in the schedule management unit may be performed using AI, or not using AI. For example, the schedule management unit may input user sentiment data into the generation AI and have the generation AI adjust the frequency of schedule management.

[0126] The schedule management unit can provide the optimal reminder method when managing schedules, taking into account the user's geographical location information. For example, the schedule management unit can acquire the user's geographical location information and provide the optimal reminder method based on that data. For example, if the user is at high altitude, the schedule management unit can provide a reminder regarding oxygen supply. Also, if the user is in an urban area, the schedule management unit can provide a reminder regarding air quality. Furthermore, if the user is at the beach, the schedule management unit can provide a reminder regarding sun protection. For example, if the user is at high altitude, the schedule management unit can provide a reminder regarding oxygen supply. If the user is in an urban area, the schedule management unit can provide a reminder regarding air quality. If the user is at the beach, the schedule management unit can provide a reminder regarding sun protection. In this way, the schedule management unit can provide the optimal reminder method, taking into account the user's geographical location information. Some or all of the above processing in the schedule management unit may be performed using AI, for example, or without using AI. For example, the schedule management department can input the user's geographical location information into a generation AI and have the AI ​​generate the optimal reminder method.

[0127] The location management unit can estimate the user's emotions and adjust location management alerts based on the estimated emotions. For example, the location management unit can estimate the user's emotions using facial recognition technology and adjust location management alerts based on those emotions. For example, the location management unit can analyze the user's facial expressions using facial recognition technology and estimate their emotions. Furthermore, the location management unit can analyze the user's voice using voice analysis technology and estimate their emotions. In addition, the location management unit can analyze the user's text data using text analysis technology and estimate their emotions. For example, if the user is feeling stressed, the location management unit can provide a relaxing alert. If the user is relaxed, the location management unit can also set an alert providing detailed location information. If the user is feeling anxious, the location management unit can also provide a reassuring alert. This allows the location management unit to adjust location management alerts based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the location management unit may be performed using AI, for example, or without AI. For example, the location management unit can input user emotion data into a generating AI and have the generating AI adjust location management alerts.

[0128] The location management unit can detect anomalies early by referring to past movement data during location management. For example, the location management unit can record past movement data and detect anomalies early based on that data. For example, the location management unit can analyze past movement data and detect abnormal movement patterns. The location management unit can also refer to past movement data and issue an alert if there is movement that is different from the normal. Furthermore, the location management unit can also detect abnormal movement early based on past movement data. For example, the location management unit can analyze past movement data and detect abnormal movement patterns. The location management unit can refer to past movement data and issue an alert if there is movement that is different from the normal. The location management unit can also detect abnormal movement early based on past movement data. As a result, the location management unit can detect anomalies early by referring to past movement data. Some or all of the above processing in the location management unit may be performed using AI, for example, or without using AI. For example, the location management unit can input past movement data into a generating AI and have the generating AI perform anomaly detection.

[0129] The location management unit can estimate the user's emotions and adjust the frequency of location management based on the estimated emotions. For example, the location management unit can estimate the user's emotions using facial recognition technology and adjust the frequency of location management based on those emotions. For example, the location management unit can analyze the user's facial expressions using facial recognition technology and estimate their emotions. Furthermore, the location management unit can analyze the user's voice using voice analysis technology and estimate their emotions. In addition, the location management unit can analyze the user's text data using text analysis technology and estimate their emotions. For example, if the user is feeling stressed, the location management unit can reduce the frequency of location management and increase the time the user can relax. If the user is relaxed, the location management unit can increase the frequency of location management and provide more detailed location information. If the user is feeling anxious, the location management unit can appropriately adjust the frequency of location management to provide a sense of security. In this way, the location management unit can adjust the frequency of location management based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the location management unit may be performed using AI, or not using AI. For example, the location management unit may input user emotion data into the generation AI and have the generation AI adjust the frequency of location management.

[0130] The location management unit can provide the optimal alert method by considering the user's geographical location information during location management. For example, the location management unit can acquire the user's geographical location information and provide the optimal alert method based on that data. For example, if the user is at high altitude, the location management unit can provide an alert regarding oxygen supply. The location management unit can also provide an alert regarding air quality if the user is in an urban area. Furthermore, if the user is at the beach, the location management unit can provide an alert regarding sun protection. For example, if the user is at high altitude, the location management unit can provide an alert regarding oxygen supply. The location management unit can also provide an alert regarding air quality if the user is in an urban area. The location management unit can also provide an alert regarding sun protection if the user is at the beach. In this way, the location management unit can provide the optimal alert method by considering the user's geographical location information. Some or all of the above processing in the location management unit may be performed using AI, for example, or without AI. For example, the location management unit can input the user's geographical location information into a generating AI and have the generating AI generate the optimal alert method.

[0131] The conversation unit can estimate the user's emotions and adjust the conversation content based on those estimated emotions. For example, the conversation unit can use facial recognition technology to estimate the user's emotions and adjust the conversation content based on those emotions. For example, the conversation unit can analyze the user's facial expressions using facial recognition technology and estimate their emotions. The conversation unit can also analyze the user's voice using speech analysis technology and estimate their emotions. Furthermore, the conversation unit can analyze the user's text data using text analysis technology and estimate their emotions. For example, if the user is stressed, the conversation unit can provide relaxing conversation content. If the user is relaxed, the conversation unit can also include detailed health information in the conversation content. If the user is anxious, the conversation unit can provide reassuring conversation content. This allows the conversation unit to adjust the conversation content based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the conversation unit may be performed using AI, for example, or without AI. For example, the conversation unit can input user emotion data into a generating AI and have the generating AI adjust the content of the conversation.

[0132] The conversation unit can suggest the optimal flow of conversation by referring to past conversation history during a conversation. For example, the conversation unit can record past conversation history and suggest the optimal flow of conversation based on that data. For example, the conversation unit can recreate conversation flows that were well received in the past. The conversation unit can also avoid conversation flows that caused anxiety in the past. Furthermore, the conversation unit can analyze past conversation history and facilitate conversation at the optimal timing. For example, the conversation unit can recreate conversation flows that were well received in the past. The conversation unit can also avoid conversation flows that caused anxiety in the past. The conversation unit can also analyze past conversation history and facilitate conversation at the optimal timing. As a result, the conversation unit can suggest the optimal flow of conversation by referring to past conversation history. Some or all of the above processing in the conversation unit may be performed using AI, for example, or without AI. For example, the conversation unit can input past conversation history data into a generating AI and have the generating AI suggest the optimal flow of conversation.

[0133] The conversation unit can estimate the user's emotions and adjust the timing of the conversation based on those emotions. For example, the conversation unit can use facial recognition technology to estimate the user's emotions and adjust the timing of the conversation based on those emotions. For example, the conversation unit can analyze the user's facial expressions using facial recognition technology and estimate their emotions. The conversation unit can also analyze the user's voice using speech analysis technology and estimate their emotions. Furthermore, the conversation unit can analyze the user's text data using text analysis technology and estimate their emotions. For example, if the user is stressed, the conversation unit can facilitate the conversation at a time that promotes relaxation. If the user is relaxed, the conversation unit can also facilitate the conversation at a time that provides detailed health information. If the user is anxious, the conversation unit can also facilitate the conversation at a time that provides reassurance. This allows the conversation unit to adjust the timing of the conversation based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the conversation unit may be performed using AI, for example, or without AI. For example, the conversation unit can input user emotion data into a generating AI and have the generating AI adjust the timing of the conversation.

[0134] The conversation unit can provide optimal conversation topics while considering the user's geographical location. For example, the conversation unit can acquire the user's geographical location and provide optimal conversation topics based on that data. For example, if the user is at high altitude, the conversation unit can provide conversation topics related to high altitude. Also, if the user is in an urban area, the conversation unit can provide conversation topics related to urban life. Furthermore, if the user is by the sea, the conversation unit can provide conversation topics related to the sea. For example, if the user is at high altitude, the conversation unit can provide conversation topics related to high altitude. If the user is in an urban area, the conversation unit can provide conversation topics related to urban life. If the user is by the sea, the conversation unit can provide conversation topics related to the sea. In this way, the conversation unit can provide optimal conversation topics while considering the user's geographical location. Some or all of the above processing in the conversation unit may be performed using AI, for example, or without AI. For example, the conversation unit can input the user's geographical location into a generating AI and have the generating AI generate optimal conversation topics.

[0135] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0136] The monitoring system can also be equipped with a voice recognition unit. This unit can analyze the user's voice and estimate their health status and emotions. For example, it can detect changes in the user's tone of voice and speaking style to estimate signs of stress or fatigue. It can also analyze the content of the user's conversations and provide health advice. Furthermore, it can monitor changes in the user's voice over the long term and detect abnormalities early. This allows the monitoring system to understand the user's health status and emotions through their voice and provide appropriate support.

[0137] The monitoring system can also be equipped with an environmental sensor unit. This unit can monitor the user's living environment and detect factors that affect their health. For example, it can measure indoor temperature and humidity and provide advice for maintaining a suitable environment. It can also monitor indoor air quality using an air quality sensor and prompt ventilation as needed. Furthermore, it can monitor indoor lighting conditions using an illuminance sensor and suggest an appropriate lighting environment. In this way, the monitoring system can optimize the user's living environment and support their health.

[0138] The monitoring system can also be equipped with an exercise recording unit. This unit can record the user's exercise data and analyze their exercise habits. For example, it can record the user's steps and exercise time, allowing for a grasp of their daily exercise volume. Furthermore, it can analyze the user's exercise patterns and suggest appropriate exercise plans. Additionally, the unit can monitor the user's exercise data over the long term, enabling early detection of signs of insufficient or excessive exercise. This allows the monitoring system to support the user's exercise habits and provide advice for maintaining good health.

[0139] The monitoring system can also be equipped with an emotion analysis unit. This unit can analyze the user's facial expressions, voice, and text data to estimate their emotions. For example, it can analyze the user's facial expressions to estimate emotions such as joy, sadness, and anger. It can also analyze the user's voice to estimate their stress and relaxation levels. Furthermore, it can analyze the user's text data to understand changes in their emotions. This allows the monitoring system to understand the user's emotional state in real time and provide appropriate support.

[0140] The monitoring system can also be equipped with a reminder function. This reminder function can provide timely reminders based on the user's schedule and health status. For example, it can remind the user to take their medication. It can also remind the user to exercise or eat. Furthermore, the reminder function can adjust the content and timing of reminders based on the user's emotional state. This allows the monitoring system to support the user's daily routine and provide reminders to maintain their health.

[0141] The monitoring system can also be equipped with a communication unit. This unit can support communication between the user and family and friends. For example, it can provide video call and messaging functions, allowing users to easily stay in touch with family and friends. Furthermore, the communication unit can consider the user's emotional state and encourage communication at the appropriate time. It can also analyze the user's conversations and suggest conversation topics. In this way, the monitoring system can help reduce feelings of loneliness and provide support for maintaining social connections.

[0142] The monitoring system can also be equipped with an emergency response unit. This unit can detect abnormalities in the user's health or environment and respond quickly. For example, it can detect abnormalities in the user's heart rate or blood pressure and notify emergency contacts. It can also detect abnormalities in indoor temperature or humidity and prompt appropriate action. Furthermore, the emergency response unit can track the user's location and respond quickly in emergencies. This allows the monitoring system to ensure user safety and provide a rapid response in emergencies.

[0143] The monitoring system can also be equipped with a learning support unit. This unit can support the user's intellectual activities and help maintain and improve cognitive function. For example, the learning support unit can provide the user with intellectual games such as quizzes and puzzles. It can also suggest learning content based on the user's interests. Furthermore, the learning support unit can record the user's learning progress and provide appropriate feedback. In this way, the monitoring system can support the user's intellectual activities and help maintain and improve cognitive function.

[0144] The monitoring system can also be equipped with a hobby support unit. This unit can support the user's hobby activities and improve their quality of life. For example, it can provide information about the user's hobbies and help them discover new ones. It can also record the user's hobby activities and manage their progress. Furthermore, it can suggest appropriate hobby activities, taking into account the user's emotional state. In this way, the monitoring system can support the user's hobby activities and improve their quality of life.

[0145] The monitoring system can also be equipped with a feedback unit. This feedback unit can provide feedback on the user's health status and lifestyle habits, encouraging improvement. For example, it can analyze data on the user's diet, exercise, and sleep, and provide health advice. It can also provide appropriate feedback, taking into account the user's emotional state. Furthermore, the feedback unit can set goals and manage progress to support improvements in the user's lifestyle habits. In this way, the monitoring system can support improvements in the user's health status and lifestyle habits, thereby improving their quality of life.

[0146] The following briefly describes the processing flow for example form 2.

[0147] Step 1: The health check unit performs a health check. Specifically, it can perform health checks using methods such as measuring body temperature, measuring blood pressure, and conducting interviews. For example, it can measure body temperature to detect abnormalities, measure blood pressure to detect abnormalities, and conduct interviews to confirm the user's health status. Step 2: The sharing unit shares the information confirmed by the health verification unit with the family. Specifically, information can be shared via email, messaging apps, or phone. For example, health information can be sent to family members via email, messaging apps, or phone. Step 3: The conversation facilitator facilitates conversation among family members based on the information shared by the sharing unit. Specifically, it can facilitate conversation by suggesting topics, presenting questions, etc. For example, it can facilitate conversation among family members by suggesting topics, presenting questions, or suggesting activities to stimulate conversation among family members.

[0148] 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.

[0149] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0150] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0151] Each of the multiple elements described above, including the health confirmation unit, sharing unit, conversation promotion unit, meal management unit, medication management unit, physical condition management unit, sleep management unit, schedule management unit, location management unit, and conversation unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the health confirmation unit measures body temperature and blood pressure using the camera 42 and sensors of the smart device 14 and confirms the health status with the control unit 46A. The sharing unit transmits health information to family members with the specific processing unit 290 of the data processing unit 12. The conversation promotion unit facilitates conversations among family members with the control unit 46A of the smart device 14. The meal management unit acquires images of meals using the camera 42 of the smart device 14 and analyzes the amount of calories and nutrients with the specific processing unit 290 of the data processing unit 12. The medication management unit acquires images of medications using the camera 42 of the smart device 14 and determines the type of medication and intake status with the specific processing unit 290 of the data processing unit 12. The health management unit records heart rate and steps using the sensors of the smart device 14 and analyzes them using the specific processing unit 290 of the data processing unit 12. The sleep management unit records sleep quality and duration using the sensors of the smart device 14 and provides advice to promote appropriate sleep using the specific processing unit 290 of the data processing unit 12. The schedule management unit analyzes conversations using the voice recognition technology of the smart device 14 and provides reminders using the specific processing unit 290 of the data processing unit 12. The location management unit acquires location information using the GPS device of the smart device 14 and detects abnormal movement using the specific processing unit 290 of the data processing unit 12. The conversation unit learns the conversation history of the smart device 14 and generates the optimal response using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be changed in various ways.

[0152] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0153] 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.

[0154] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0155] 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.

[0156] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0157] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0158] 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.

[0159] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0160] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0161] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0162] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0163] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0164] 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.

[0165] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0166] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0167] Each of the multiple elements described above, including the health confirmation unit, sharing unit, conversation promotion unit, meal management unit, medication management unit, physical condition management unit, sleep management unit, schedule management unit, location management unit, and conversation unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing unit 12. For example, the health confirmation unit measures body temperature and blood pressure using the camera 42 and sensors of the smart glasses 214 and confirms the health status with the control unit 46A. The sharing unit transmits health information to family members using the identification processing unit 290 of the data processing unit 12. The conversation promotion unit facilitates conversations between family members using the control unit 46A of the smart glasses 214. The meal management unit acquires images of meals using the camera 42 of the smart glasses 214 and analyzes the amount of calories and nutrients with the identification processing unit 290 of the data processing unit 12. The medication management unit acquires images of medications using the camera 42 of the smart glasses 214 and determines the type of medication and intake status with the identification processing unit 290 of the data processing unit 12. The health management unit records heart rate and steps using the sensors of the smart glasses 214 and analyzes them using the specific processing unit 290 of the data processing unit 12. The sleep management unit records sleep quality and duration using the sensors of the smart glasses 214 and provides advice to promote appropriate sleep using the specific processing unit 290 of the data processing unit 12. The schedule management unit analyzes conversations using the voice recognition technology of the smart glasses 214 and provides reminders using the specific processing unit 290 of the data processing unit 12. The location management unit acquires location information using the GPS device of the smart glasses 214 and detects abnormal movement using the specific processing unit 290 of the data processing unit 12. The conversation unit learns the conversation history of the smart glasses 214 and generates the optimal response using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be changed in various ways.

[0168] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0169] 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.

[0170] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0171] 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.

[0172] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0173] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0174] 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.

[0175] 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.

[0176] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0177] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0178] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0179] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0180] 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.

[0181] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0182] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0183] Each of the multiple elements described above, including the health confirmation unit, sharing unit, conversation promotion unit, meal management unit, medication management unit, physical condition management unit, sleep management unit, schedule management unit, location management unit, and conversation unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the health confirmation unit measures body temperature and blood pressure using the camera 42 and sensors of the headset terminal 314 and confirms the health status using the control unit 46A. The sharing unit transmits health information to family members using the specific processing unit 290 of the data processing unit 12. The conversation promotion unit facilitates conversations between family members using the control unit 46A of the headset terminal 314. The meal management unit acquires images of meals using the camera 42 of the headset terminal 314 and analyzes the amount of calories and nutrients using the specific processing unit 290 of the data processing unit 12. The medication management unit acquires images of medications using the camera 42 of the headset terminal 314 and determines the type of medication and intake status using the specific processing unit 290 of the data processing unit 12. The health management unit records heart rate and steps using the sensors of the headset terminal 314 and analyzes them using the specific processing unit 290 of the data processing unit 12. The sleep management unit records sleep quality and duration using the sensors of the headset terminal 314 and provides advice to promote appropriate sleep using the specific processing unit 290 of the data processing unit 12. The schedule management unit analyzes conversations using the voice recognition technology of the headset terminal 314 and provides reminders using the specific processing unit 290 of the data processing unit 12. The location management unit acquires location information using the GPS device of the headset terminal 314 and detects abnormal movement using the specific processing unit 290 of the data processing unit 12. The conversation unit learns the conversation history of the headset terminal 314 and generates the optimal response using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be modified in various ways.

[0184] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0185] 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.

[0186] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0187] 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.

[0188] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0189] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0190] 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.

[0191] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0192] 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.

[0193] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0194] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0195] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0196] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0197] 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.

[0198] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0199] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0200] Each of the multiple elements mentioned above, including the health confirmation unit, sharing unit, conversation promotion unit, meal management unit, medication management unit, physical condition management unit, sleep management unit, schedule management unit, location management unit, and conversation unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the health confirmation unit measures body temperature and blood pressure using the camera 42 and sensors of the robot 414 and confirms the health status with the control unit 46A. The sharing unit transmits health information to the family using the specific processing unit 290 of the data processing unit 12. The conversation promotion unit facilitates conversations between family members using the control unit 46A of the robot 414. The meal management unit acquires images of meals using the camera 42 of the robot 414 and analyzes the amount of calories and nutrients with the specific processing unit 290 of the data processing unit 12. The medication management unit acquires images of medications using the camera 42 of the robot 414 and determines the type of medication and intake status with the specific processing unit 290 of the data processing unit 12. The health management unit records heart rate and steps using the robot 414's sensors and analyzes them using the specific processing unit 290 of the data processing unit 12. The sleep management unit records sleep quality and duration using the robot 414's sensors and provides advice to promote appropriate sleep using the specific processing unit 290 of the data processing unit 12. The schedule management unit analyzes conversations using the robot 414's voice recognition technology and provides reminders using the specific processing unit 290 of the data processing unit 12. The location management unit acquires location information using the robot 414's GPS device and detects abnormal movement using the specific processing unit 290 of the data processing unit 12. The conversation unit learns the robot 414's conversation history and generates the optimal response using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be modified in various ways.

[0201] 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.

[0202] Figure 9 shows the 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.

[0203] 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.

[0204] 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.

[0205] 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, and motorcycles, 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 based, for example, 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.

[0206] 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."

[0207] 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.

[0208] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0217] 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 other things 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.

[0218] 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 to be incorporated by reference.

[0219] (Note 1) The health check department conducts health checks, A sharing unit that shares the information confirmed by the aforementioned health confirmation unit with the family, The system includes a conversation facilitator that facilitates conversations among family members based on information shared by the aforementioned shared unit. A system characterized by the following features. (Note 2) It is equipped with a meal management department that analyzes and records the amount of calories and nutrients from video footage of meals. The system described in Appendix 1, characterized by the features described herein. (Note 3) The facility includes a medication management department that can determine the type of medication and the patient's intake status from images of the medication. The system described in Appendix 1, characterized by the features described herein. (Note 4) It is equipped with a health management department that records and analyzes vital signs such as heart rate, calories burned, and steps taken. The system described in Appendix 1, characterized by the features described herein. (Note 5) The facility includes a sleep management department that records sleep quality and duration and provides advice to promote proper sleep. The system described in Appendix 1, characterized by the features described herein. (Note 6) The system includes a scheduling department that records the timing of events through daily activity logs and conversations, and sends reminders at the appropriate time. The system described in Appendix 1, characterized by the features described herein. (Note 7) It features a location management unit that uses GPS to determine location information and issues alerts when movement deviates from the normal pattern. The system described in Appendix 1, characterized by the features described herein. (Note 8) It features a conversational unit that learns from interactions with the user and their family, and performs automated conversations optimized for the user. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned health verification unit, The system estimates the user's emotions and adjusts the frequency of health checks based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned health verification unit, During health checks, past health data is referenced to detect abnormalities early. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned health verification unit, During health checks, the system provides customized health advice based on the user's lifestyle. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned health verification unit, The system estimates the user's emotions and adjusts the content of the health check based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned health verification unit, During health checks, the system provides environment-appropriate health advice based on the user's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned health verification unit, During health checks, the system analyzes the user's social media activity and provides relevant health information. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned shared portion is, It estimates the user's emotions and prioritizes the information to share based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned shared portion is, When sharing information, analyze past reactions from family members to select the most suitable sharing method. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned shared portion is, When sharing information, adjust the level of detail based on the importance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned shared portion is, It estimates the user's emotions and adjusts the format of the information shared based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned shared portion is, When sharing information, the optimal sharing method is selected considering the geographical location of family members. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned shared portion is, When sharing, analyze family members' social media activity and share relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned conversation facilitator unit, It estimates the user's emotions and selects conversation topics based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned conversation facilitator unit, When facilitating a conversation, it refers to past conversation history to suggest the optimal flow of conversation. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned conversation facilitator unit, When facilitating conversation, customize the content of the conversation based on the family's interests. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned conversation facilitator unit, It estimates the user's emotions and adjusts the timing of the conversation based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned conversation facilitator unit, When facilitating conversation, the optimal timing for the conversation is selected by considering the geographical location information of family members. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned conversation facilitator unit, When facilitating conversation, analyze family members' social media activity and provide relevant conversation topics. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned Food Management Department, It estimates the user's emotions and adjusts meal suggestions based on those emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned Food Management Department, When managing your diet, refer to past meal data to optimize nutritional balance. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned Food Management Department, When managing meals, the content of meals is customized based on the user's health condition. The system described in Appendix 2, characterized by the features described herein. (Note 30) The aforementioned Food Management Department, It estimates the user's emotions and adjusts meal timing based on those emotions. The system described in Appendix 2, characterized by the features described herein. (Note 31) The aforementioned Food Management Department, When managing meals, the system suggests the optimal meal plan considering the user's geographical location. The system described in Appendix 2, characterized by the features described herein. (Note 32) The aforementioned Food Management Department, During meal management, the system analyzes the user's social media activity and provides relevant dietary information. The system described in Appendix 2, characterized by the features described herein. (Note 33) The aforementioned drug management department, The system estimates the user's emotions and adjusts the timing of medication intake based on those emotions. The system described in Appendix 3, characterized by the features described herein. (Note 34) The aforementioned drug management department, When managing medication, we refer to past medication intake data to suggest the optimal dosage method. The system described in Appendix 3, characterized by the features described herein. (Note 35) The aforementioned drug management department, It estimates the user's emotions and adjusts the medication administration method based on the estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 36) The aforementioned drug management department, When managing medication, the system suggests the optimal method of medication intake, taking into account the user's geographical location. The system described in Appendix 3, characterized by the features described herein. (Note 37) The aforementioned health management department, It estimates the user's emotions and adjusts health management advice based on those estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 38) The aforementioned health management department, When managing your health, we provide optimal health advice by referring to past vital sign data. The system described in Appendix 4, characterized by the features described herein. (Note 39) The aforementioned health management department, It estimates the user's emotions and adjusts the frequency of health checks based on the estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 40) The aforementioned health management department, When managing your health, the system provides optimal health advice while taking into account the user's geographical location. The system described in Appendix 4, characterized by the features described herein. (Note 41) The aforementioned sleep management department, It estimates the user's emotions and adjusts sleep management advice based on those emotions. The system described in Appendix 5, characterized by the features described herein. (Note 42) The aforementioned sleep management department, When performing sleep management, refer to past sleep data to provide optimal sleep advice The system according to appended note 5, characterized in that it does so (Appended note 43) The sleep management unit Estimates the user's emotion and adjusts the frequency of sleep management based on the estimated user emotion The system according to appended note 5, characterized in that it does so (Appended note 44) The sleep management unit When performing sleep management, consider the user's geographical location information to provide optimal sleep advice The system according to appended note 5, characterized in that it does so (Appended note 45) The schedule management unit Estimates the user's emotion and adjusts the schedule management advice based on the estimated user emotion The system according to appended note 6, characterized in that it does so (Appended note 46) The schedule management unit When performing schedule management, refer to past action records to provide an optimal reminder method The system according to appended note 6, characterized in that it does so (Appended note 47) The schedule management unit Estimates the user's emotion and adjusts the frequency of schedule management based on the estimated user emotion The system according to appended note 6, characterized in that it does so (Appended note 48) The schedule management unit When performing schedule management, consider the user's geographical location information to provide an optimal reminder method The system according to appended note 6, characterized in that it does so (Appended note 49) The location management unit Estimates the user's emotion and adjusts the location management alert based on the estimated user emotion The system according to appended note 7, characterized in that it does so (Appended note 50) The location management unit When performing location management, early detection of abnormalities by referring to past movement data The system according to appended note 7, characterized in that (Appended note 51) The location management unit Estimates the user's emotion and adjusts the frequency of location management based on the estimated user emotion The system according to appended note 7, characterized in that (Appended note 52) The location management unit When performing location management, provides an optimal alert method in consideration of the user's geographical location information The system according to appended note 7, characterized in that (Appended note 53) The conversation unit Estimates the user's emotion and adjusts the content of the conversation based on the estimated user emotion The system according to appended note 8, characterized in that (Appended note 54) The conversation unit When having a conversation, proposes an optimal conversation flow by referring to past conversation histories The system according to appended note 8, characterized in that (Appended note 55) The conversation unit Estimates the user's emotion and adjusts the timing of the conversation based on the estimated user emotion The system according to appended note 8, characterized in that (Appended note 56) The conversation unit When having a conversation, provides an optimal conversation topic in consideration of the user's geographical location information The system according to appended note 8, characterized in that

Explanation of reference numerals

[0220] 10, 210, 310, 410 Data processing system 12 Data processing device 14 Smart device 214 Smart glasses 314 Headset-type terminal 414 Robots

Claims

1. The health check department conducts health checks, A sharing unit that shares the information confirmed by the aforementioned health confirmation unit with the family, The system includes a conversation facilitator that facilitates conversations among family members based on information shared by the aforementioned shared unit. A system characterized by the following features.

2. It is equipped with a meal management department that analyzes and records the amount of calories and nutrients from video footage of meals. The system according to feature 1.

3. The facility includes a medication management department that can determine the type of medication and the patient's intake status from images of the medication. The system according to feature 1.

4. It has a health management department that records and analyzes vital signs such as heart rate, calories burned, and steps taken. The system according to feature 1.

5. The facility includes a sleep management department that records sleep quality and duration and provides advice to promote proper sleep. The system according to feature 1.

6. The system includes a scheduling department that records the timing of events through daily activity logs and conversations, and sends reminders at the appropriate time. The system according to feature 1.

7. It features a location management unit that uses GPS to determine location information and issues alerts when movement deviates from the normal pattern. The system according to feature 1.

8. It features a conversational unit that learns from interactions with the user and their family, and performs automated conversations optimized for the user. The system according to feature 1.

9. The aforementioned health verification unit, The system estimates the user's emotions and adjusts the frequency of health checks based on those emotions. The system according to feature 1.

10. The aforementioned health verification unit, During health checks, past health data is referenced to detect abnormalities early. The system according to feature 1.

Images