system

Abstract

The system according to this embodiment aims to understand the daily behavioral patterns of elderly people, detect abnormalities, and take appropriate action. [Solution] The system according to the embodiment comprises a learning unit, a detection unit, a comprehension unit, and a coordination unit. The learning unit learns the daily behavioral patterns of elderly people. The detection unit detects abnormalities based on the behavioral patterns learned by the learning unit. The comprehension unit grasps the health and mental state based on the abnormalities detected by the detection unit. The coordination unit coordinates with family members, medical institutions, and care services based on the information grasped by the comprehension 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the daily behavior patterns of the elderly are not fully grasped, abnormalities are not detected, and appropriate actions are not taken, leaving room for improvement. ​​​​​​​​​The system according to this embodiment comprises a learning unit, a detection unit, a comprehension unit, and a coordination unit. The learning unit learns the daily behavioral patterns of elderly people. The detection unit detects abnormalities based on the behavioral patterns learned by the learning unit. The comprehension unit grasps the health and mental state based on the abnormalities detected by the detection unit. The coordination unit coordinates with family members, medical institutions, and care services based on the information grasped by the comprehension unit. [Effects of the Invention]

[0007] The system according to this embodiment can understand the daily behavioral patterns of elderly people, detect abnormalities, and take appropriate action. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are 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 AI ​​agent service for preventing lonely deaths according to an embodiment of the present invention is an AI-powered service that monitors the daily lives of elderly people and reduces the risk of lonely deaths. This service uses AI to learn the daily behavioral patterns of elderly people and take appropriate action when it detects abnormalities. The AI ​​agent understands the health and mental state of elderly people through communication. Through regular conversations and questions, it senses changes in the elderly person's daily rhythm and mood, and coordinates with family, medical institutions, and care services as needed. Furthermore, this service aims not only to monitor but also to improve the quality of life for elderly people. The AI ​​agent provides conversations tailored to the elderly person's interests and hobbies, offering emotional support. It also promotes social connections by providing information on local events and social activities. Privacy protection is paramount, and collected data is strictly managed and used only to the minimum extent necessary. We strive for highly transparent service operation so that elderly people can use the service with peace of mind. Through this service, we aim to support elderly people in living independent lives with peace of mind and reduce the burden on families and communities. The AI ​​agent service for preventing lonely deaths will be a powerful tool for realizing a safe and fulfilling later life while protecting the dignity of elderly people. The target audience includes elderly people aged 65 and over who live alone, elderly people who are alone during the day, elderly people with health concerns, elderly people whose families live far away, elderly people with weak ties to their community, elderly people who are unfamiliar with technology, and elderly people who do not use care services or wish to use them minimally. This service provides 24 / 7 monitoring and anomaly detection using AI, mental support and health status assessment through natural dialogue, seamless coordination with family, medical institutions and care services, customized support tailored to individual lifestyles, a non-invasive monitoring system that respects privacy, and information provision and activity support that promotes connections with the community. Specifically, it employs a conversational AI agent using natural language processing technology, behavioral pattern analysis and anomaly detection using machine learning, a hands-free interface utilizing speech recognition and speech synthesis technology, contactless health status monitoring using image recognition technology, assessment of mental state using emotion analysis technology, and risk assessment and preventive approaches using predictive analytics.Through this service, we aim to protect the dignity of the elderly, support safe and secure living, reduce the risk of lonely deaths and establish a system for early detection and response, create opportunities for social participation and purpose in life for the elderly, reduce the burden on families and communities and build a sustainable elderly support system, create new forms of "connections" using technology, realize personalized care tailored to the needs of each elderly person, and extend healthy life expectancy and control medical costs through the promotion of preventive medicine. In this way, the lonely death prevention AI agent service can monitor the daily lives of the elderly and reduce the risk of lonely deaths.

[0029] The AI ​​agent service for preventing lonely deaths according to this embodiment comprises a learning unit, a detection unit, an understanding unit, and a collaboration unit. The learning unit learns the daily behavioral patterns of elderly people. The learning unit learns behavioral patterns such as eating, exercising, and sleeping of elderly people using AI, for example. The learning unit can analyze behavioral patterns using machine learning algorithms, for example. The learning unit can also predict behavioral patterns based on past behavioral data, for example. The detection unit detects abnormalities based on the behavioral patterns learned by the learning unit. The detection unit detects deviations from normal behavioral patterns using AI, for example. The detection unit can detect abnormalities based on the frequency of abnormal behavior, for example. The detection unit can also detect the absence of a specific behavior as an abnormality, for example. The understanding unit grasps the health and mental state based on the abnormalities detected by the detection unit. The understanding unit grasps the health state by analyzing vital signs using AI, for example. The understanding unit can grasp the mental state based on the results of psychological tests, for example. The understanding unit can also grasp the mental state using emotion analysis technology, for example. The collaboration unit coordinates with families, medical institutions, and care services based on the information gathered by the information gathering unit. The collaboration unit provides means of information sharing, for example, using AI. The collaboration unit can share information in real time, for example. The collaboration unit can also share information using an integrated system, for example. As a result, the AI ​​agent service for preventing lonely deaths according to this embodiment can learn the daily behavior patterns of elderly people, detect abnormalities, understand their health and mental state, and coordinate with families, medical institutions, and care services.

[0030] The learning unit learns the daily behavioral patterns of elderly people. Specifically, the learning unit uses AI to learn in detail the behavioral patterns of elderly people, such as eating, exercise, and sleep. For example, it analyzes data collected from sensors and wearable devices, such as the timing and content of meals, the frequency and type of exercise, and the duration and quality of sleep. The learning unit uses machine learning algorithms to analyze this data and model the behavioral patterns of elderly people. For example, it can predict behavioral trends on specific days of the week or time of day based on past behavioral data. Furthermore, the learning unit continuously collects data and updates the model to detect changes and anomalies in behavioral patterns. As a result, the learning unit can accurately understand the behavioral patterns of elderly people and contribute to the early detection of anomalies.

[0031] The detection unit detects anomalies based on behavioral patterns learned by the learning unit. Specifically, the detection unit uses AI to detect deviations from normal behavioral patterns in real time. For example, it detects anomalies if meal times are significantly delayed or if the frequency of exercise decreases sharply. The detection unit can evaluate the severity of an anomaly based on the frequency and duration of the abnormal behavior. For example, it detects serious anomalies if meals are not eaten for several consecutive days or if exercise is not performed for a long period of time. It can also detect anomalies in the absence of specific behaviors, such as the sudden interruption of a regular walk. This allows the detection unit to quickly grasp changes in the behavioral patterns of elderly people, enabling early detection and response to anomalies.

[0032] The monitoring unit understands the health and mental state based on abnormalities detected by the detection unit. Specifically, the monitoring unit uses AI to analyze vital signs and understand the health state in detail. For example, it acquires vital signs such as heart rate, blood pressure, and body temperature from sensors and detects changes in health by analyzing this data. Furthermore, the monitoring unit can evaluate the mental state based on the results of psychological tests. For example, it analyzes the results of regularly conducted psychological tests to understand stress levels and signs of depression. It can also use emotion analysis technology to analyze changes in emotions from daily conversations and social media posts to understand the mental state. As a result, the monitoring unit can comprehensively evaluate the health and mental state of elderly people and take necessary actions quickly.

[0033] The Collaboration Department coordinates with families, medical institutions, and care services based on information gathered by the Information Gathering Department. Specifically, the Collaboration Department uses AI to provide a means of information sharing. For example, if an abnormality is detected, it can send real-time notifications to families and medical institutions to encourage a quick response. The Collaboration Department uses a cloud-based integrated system to centrally manage information and facilitate information sharing among stakeholders. For example, families can check the health status of elderly individuals through a smartphone app, and medical institutions can access detailed health data through a dedicated portal site. Furthermore, care services can develop and implement appropriate care plans based on the information provided by the Collaboration Department. In this way, the Collaboration Department can build an effective collaborative system to support the health management of the elderly and reduce the risk of dying alone.

[0034] The conversation unit can provide conversations tailored to the interests and hobbies of elderly individuals. For example, the conversation unit can use AI to collect information about the interests and hobbies of elderly individuals and generate conversation content. The conversation unit can provide topics such as reading, music, and sports. The conversation unit can also provide the latest information related to the hobbies of elderly individuals. By providing conversations tailored to the interests and hobbies of elderly individuals, it can provide emotional support. Some or all of the above processing in the conversation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversation unit can input information about the interests and hobbies of elderly individuals into a generative AI and have the generative AI generate conversation content.

[0035] The information provision department can provide information on local events and social activities. For example, the information provision department can use AI to collect information on local events and social activities and provide it to the elderly. For example, the information provision department can provide information on local festivals, volunteer activities, etc. For example, the information provision department can also provide information on events held at local community centers. In this way, providing information on local events and social activities promotes connections with society. Some or all of the above processing in the information provision department may be performed using, for example, generative AI, or without generative AI. For example, the information provision department can input information on local events and social activities into generative AI and have the generative AI execute the content of the information provision.

[0036] The protection unit can protect privacy. For example, the protection unit can encrypt collected data using AI and impose access restrictions. For example, the protection unit can strictly manage the location where data is stored. For example, the protection unit can limit the scope of data use to the minimum necessary. This ensures privacy and allows elderly people to use the system with peace of mind. Some or all of the above-described processes in the protection unit may be performed using, for example, generative AI, or without generative AI. For example, the protection unit can have generative AI perform the encryption of collected data.

[0037] The learning unit can perform behavioral pattern analysis using machine learning. For example, the learning unit can analyze behavioral patterns using a neural network. The learning unit can also classify behavioral patterns using a support vector machine. The learning unit can also predict behavioral patterns using a decision tree algorithm. This improves the accuracy of learning by performing behavioral pattern analysis using machine learning. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can have a generative AI perform the analysis of behavioral patterns.

[0038] The detection unit can perform predictive analysis to detect anomalies. For example, the detection unit can predict anomalies using time series analysis. The detection unit can also calculate the probability of anomaly occurrence using regression analysis. The detection unit can also predict the occurrence of anomalies using Bayesian estimation. By performing predictive analysis, the accuracy of anomaly detection is improved. Some or all of the above-described processes in the detection unit may be performed using, for example, generative AI, or without generative AI. For example, the detection unit can have generative AI perform anomaly prediction.

[0039] The comprehension unit can grasp a person's mental state using emotion analysis technology. For example, the comprehension unit can estimate emotions from the content of an elderly person's speech using text mining. For example, the comprehension unit can also estimate emotions from the tone and speed of an elderly person's voice using speech analysis. For example, the comprehension unit can estimate emotions from an elderly person's facial expressions using facial recognition technology. As a result, the accuracy of grasping a person's mental state is improved by using emotion analysis technology. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is 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 comprehension unit may be performed using a generative AI, for example, or without a generative AI. For example, the comprehension unit can have a generative AI perform emotion estimation.

[0040] The collaboration unit can facilitate seamless collaboration with families, medical institutions, and care services. The collaboration unit can, for example, share information in real time using AI. The collaboration unit can also share information using an integrated system. The collaboration unit can also provide means of information sharing. This enables rapid response by facilitating seamless collaboration with families, medical institutions, and care services. Some or all of the above-described processes in the collaboration unit may be performed using, for example, generative AI, or without generative AI. For example, the collaboration unit can have generative AI perform the means of information sharing.

[0041] The learning unit can optimize its learning algorithm by referring to the elderly person's past behavioral history during the learning process. For example, the learning unit adjusts the learning algorithm based on actions that the elderly person has frequently performed in the past. The learning unit can also prioritize learning actions performed during specific time periods based on the elderly person's past behavioral history. For example, the learning unit can analyze the elderly person's past behavioral history and reflect changes in behavioral patterns in the learning algorithm. This makes it possible to optimize the learning algorithm by referring to the elderly person's past behavioral history. Some or all of the above processing in the learning unit may be performed using, for example, generative AI, or without using generative AI. For example, the learning unit can have the generative AI perform the optimization of the learning algorithm by referring to past behavioral history.

[0042] The learning unit can customize the learning data during the learning process based on the elderly person's living environment and health condition. For example, the learning unit can learn indoor behavior patterns to match the elderly person's living environment. The learning unit can also learn exercise levels and eating patterns according to the elderly person's health condition. The learning unit can also learn daytime and nighttime behavior patterns to match the elderly person's daily rhythm. This allows for more appropriate learning by customizing the learning data based on the elderly person's living environment and health condition. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can have a generative AI perform the customization of the learning data based on the living environment and health condition.

[0043] The learning unit can collect learning data while considering the geographical location information of elderly individuals during the learning process. For example, the learning unit can learn region-specific behavioral patterns based on the characteristics of the area where the elderly person lives. The learning unit can also learn behavioral patterns of places that elderly individuals frequently visit. The learning unit can also customize behavioral patterns based on the elderly person's travel range. This allows for more appropriate learning by collecting learning data while considering the geographical location information of elderly individuals. Some or all of the above-described processes in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can have a generative AI perform the collection of learning data while considering geographical location information.

[0044] The learning unit can analyze the social media activities of elderly individuals and incorporate relevant data into its learning process. For example, the learning unit can learn behavioral patterns based on the activities that elderly individuals share on social media. The learning unit can also learn social behavioral patterns by considering the social media friendships of elderly individuals. For example, the learning unit can analyze the frequency and content of elderly individuals' social media posts and reflect this in their behavioral patterns. This allows for more appropriate learning by analyzing the social media activities of elderly individuals and incorporating relevant data into the learning process. Some or all of the above-described processes in the learning unit may be performed using, for example, generative AI, or without generative AI. For example, the learning unit can have a generative AI analyze social media activities and collect learning data.

[0045] The detection unit can optimize its detection algorithm by referring to the elderly person's past anomaly detection history when an anomaly is detected. For example, the detection unit adjusts the detection algorithm based on patterns of anomalies the elderly person has experienced in the past. The detection unit can also prioritize the detection of anomalies that occur during specific time periods based on the elderly person's past anomaly detection history. The detection unit can also analyze the elderly person's past anomaly detection history and optimize an algorithm to prevent the recurrence of anomalies. This makes it possible to optimize the detection algorithm by referring to the elderly person's past anomaly detection history. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can have a generative AI perform the optimization of the detection algorithm by referring to the past anomaly detection history.

[0046] The detection unit can improve the accuracy of anomaly detection based on the elderly person's lifestyle and health condition when an anomaly is detected. For example, the detection unit adjusts the timing of anomaly detection to match the elderly person's lifestyle. The detection unit can also customize the criteria for anomaly detection according to the elderly person's health condition. The detection unit can also improve the accuracy of anomaly detection by considering the elderly person's lifestyle and health condition. This makes it possible to perform more appropriate anomaly detection by improving the accuracy of anomaly detection based on the elderly person's lifestyle and health condition. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can have a generative AI perform the improvement of anomaly detection accuracy based on lifestyle and health condition.

[0047] The detection unit can perform anomaly detection while considering the geographical location information of the elderly person. For example, the detection unit can detect region-specific anomalies based on the characteristics of the area where the elderly person lives. The detection unit can also prioritize detecting anomalies in places that the elderly person frequently visits. The detection unit can also customize the range of anomaly detection based on the elderly person's range of movement. This makes it possible to perform more appropriate anomaly detection by considering the geographical location information of the elderly person. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can cause a generative AI to perform anomaly detection while considering geographical location information.

[0048] The detection unit can improve the accuracy of anomaly detection by analyzing the social media activities of elderly individuals when detection occurs. For example, the detection unit can detect anomalies based on the content of activities shared by elderly individuals on social media. The detection unit can also detect a decrease in social behavior as an anomaly by considering the social media friendships of elderly individuals. The detection unit can also improve the accuracy of anomaly detection by analyzing the frequency and content of posts made by elderly individuals on social media. By analyzing the social media activities of elderly individuals and improving the accuracy of anomaly detection, more appropriate anomaly detection becomes possible. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can have a generative AI perform the task of analyzing social media activities to improve the accuracy of anomaly detection.

[0049] The assessment unit can optimize its assessment algorithm by referring to the elderly person's past health data during assessment. For example, the assessment unit can understand changes in the elderly person's health status based on their past health data. For example, the assessment unit can also prioritize understanding changes in health status that occur during specific time periods from the elderly person's past health data. For example, the assessment unit can analyze the elderly person's past health data and optimize an algorithm to prevent the recurrence of health conditions. This makes it possible to optimize the assessment algorithm by referring to the elderly person's past health data. Some or all of the above processing in the assessment unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the assessment unit can have the generative AI perform the optimization of the assessment algorithm by referring to past health data.

[0050] The data acquisition unit can customize the data acquired based on the elderly person's living environment and health condition. For example, the data acquisition unit can acquire the health condition indoors, tailored to the elderly person's living environment. For example, the data acquisition unit can also acquire exercise levels and eating patterns according to the elderly person's health condition. For example, the data acquisition unit can acquire the health condition during the day and at night, tailored to the elderly person's daily rhythm. This allows for more accurate data acquisition by customizing the data acquired based on the elderly person's living environment and health condition. Some or all of the above processing in the data acquisition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the data acquisition unit can have the generation AI perform the customization of the data acquired based on the living environment and health condition.

[0051] The assessment unit can assess the health and mental state of elderly individuals while considering their geographical location. For example, the assessment unit can assess region-specific health conditions based on the characteristics of the area where the elderly person lives. For example, the assessment unit can prioritize assessing the health condition of elderly individuals in places they frequently visit. For example, the assessment unit can customize the range of health condition assessment based on the elderly person's travel range. This allows for more appropriate assessment by considering the elderly person's geographical location when assessing their health and mental state. Some or all of the above-described processes in the assessment unit may be performed using, for example, a generative AI, or without a generative AI. For example, the assessment unit can have a generative AI perform the assessment of health and mental state while considering geographical location information.

[0052] The assessment unit can analyze the social media activities of elderly individuals and incorporate relevant data into its assessment. For example, the assessment unit can assess the health status based on the activities shared by elderly individuals on social media. The assessment unit can also consider the social relationships of elderly individuals on social media and reflect a decrease in social activity in its assessment of health status. The assessment unit can also analyze the frequency and content of elderly individuals' social media posts and reflect this in its assessment of health status. By analyzing the social media activities of elderly individuals and incorporating relevant data into the assessment, a more accurate assessment becomes possible. Some or all of the above processing in the assessment unit may be performed using, for example, a generative AI, or without a generative AI. For example, the assessment unit can have a generative AI analyze social media activities and assess health status.

[0053] The collaboration unit can optimize the collaboration algorithm by referring to the elderly person's past collaboration history during collaboration. For example, the collaboration unit provides the optimal collaboration method based on the elderly person's past collaboration history. For example, the collaboration unit can also prioritize providing collaboration methods to be performed during specific time periods based on the elderly person's past collaboration history. For example, the collaboration unit can analyze the elderly person's past collaboration history and optimize the algorithm to prevent the recurrence of collaboration issues. This makes it possible to optimize the collaboration algorithm by referring to the elderly person's past collaboration history. Some or all of the above processing in the collaboration unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the collaboration unit can have a generative AI perform the optimization of the collaboration algorithm by referring to past collaboration history.

[0054] The collaboration unit can customize the collaboration data based on the elderly person's living environment and health condition during the collaboration process. For example, the collaboration unit can provide a method of collaboration within the home that is tailored to the elderly person's living environment. For example, the collaboration unit can also provide a method of collaboration related to health maintenance depending on the elderly person's health condition. For example, the collaboration unit can also provide a method of collaboration for daytime and nighttime that is tailored to the elderly person's daily rhythm. This allows for more appropriate collaboration by customizing the collaboration data based on the elderly person's living environment and health condition. Some or all of the above processing in the collaboration unit may be performed using, for example, a generative AI, or without a generative AI. For example, the collaboration unit can have a generative AI perform the customization of the collaboration data based on the living environment and health condition.

[0055] The collaboration unit can perform collaboration while considering the geographical location information of elderly individuals. For example, the collaboration unit can provide region-specific collaboration methods based on the characteristics of the area where the elderly person lives. For example, the collaboration unit can also prioritize providing collaboration methods for places that elderly individuals frequently visit. For example, the collaboration unit can customize collaboration methods based on the elderly person's range of movement. This makes it possible to perform collaboration more appropriately by considering the geographical location information of elderly individuals. Some or all of the above processing in the collaboration unit may be performed using, for example, a generative AI, or without a generative AI. For example, the collaboration unit can cause a generative AI to perform collaboration while considering geographical location information.

[0056] The collaboration unit can improve the accuracy of collaboration by analyzing the social media activities of elderly individuals during the collaboration process. For example, the collaboration unit can provide a collaboration method based on the activities shared by elderly individuals on social media. The collaboration unit can also provide a collaboration method that promotes social activities by considering the social media friendships of elderly individuals. The collaboration unit can also improve the accuracy of collaboration by analyzing the frequency and content of elderly individuals' social media posts. By analyzing the social media activities of elderly individuals and improving the accuracy of collaboration, more appropriate collaboration becomes possible. Some or all of the above processing in the collaboration unit may be performed using, for example, generative AI, or without generative AI. For example, the collaboration unit can have generative AI analyze social media activities to improve the accuracy of collaboration.

[0057] The conversation unit can optimize its conversation algorithm by referring to the elderly person's past conversation history during a conversation. For example, the conversation unit can provide optimal conversation content and tone based on the elderly person's past conversation history. For example, the conversation unit can also prioritize providing conversation content and tone for specific time periods based on the elderly person's past conversation history. For example, the conversation unit can analyze the elderly person's past conversation history and optimize an algorithm to prevent the recurrence of conversations. This makes it possible to optimize the conversation algorithm by referring to the elderly person's past conversation history. Some or all of the above processing in the conversation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversation unit can have a generative AI perform the optimization of the conversation algorithm by referring to past conversation history.

[0058] The conversation unit can customize the conversation content based on the elderly person's living environment and health condition. For example, the conversation unit can provide conversation content tailored to the elderly person's living environment. For example, the conversation unit can also provide conversation content related to maintaining health, depending on the elderly person's health condition. For example, the conversation unit can also provide conversation content for daytime and nighttime, according to the elderly person's daily rhythm. By customizing the conversation content based on the elderly person's living environment and health condition, more appropriate conversations become possible. Some or all of the above processing in the conversation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversation unit can have a generative AI perform the customization of conversation content based on the living environment and health condition.

[0059] The conversation unit can customize the conversation content by taking into account the geographical location information of the elderly person during a conversation. For example, the conversation unit can provide region-specific conversation content based on the characteristics of the area where the elderly person lives. For example, the conversation unit can also prioritize providing conversation content for places that the elderly person frequently visits. For example, the conversation unit can also customize the conversation content based on the elderly person's range of movement. This makes it possible to have more appropriate conversations by customizing the conversation content while taking into account the geographical location information of the elderly person. Some or all of the above processing in the conversation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversation unit can have a generative AI perform the customization of conversation content while taking into account geographical location information.

[0060] The information provision unit can optimize its information provision algorithm by referring to the elderly person's past information provision history when providing information. For example, the information provision unit can provide the most suitable information based on the elderly person's past information provision history. For example, the information provision unit can also prioritize providing information at specific time periods based on the elderly person's past information provision history. For example, the information provision unit can analyze the elderly person's past information provision history and optimize the algorithm to prevent the recurrence of information provision issues. This makes it possible to optimize the information provision algorithm by referring to the elderly person's past information provision history. Some or all of the above processing in the information provision unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the information provision unit can have a generative AI perform the optimization of the information provision algorithm by referring to the past information provision history.

[0061] The information provision unit can customize the information content based on the elderly person's living environment and health condition when providing information. For example, the information provision unit can provide information about indoor activities tailored to the elderly person's living environment. For example, the information provision unit can also provide information related to maintaining health according to the elderly person's health condition. For example, the information provision unit can provide information for daytime and nighttime, tailored to the elderly person's daily rhythm. By customizing the information content based on the elderly person's living environment and health condition, it becomes possible to provide more appropriate information. Some or all of the above processing in the information provision unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the information provision unit can have a generative AI perform the customization of information content based on the living environment and health condition.

[0062] The information provision unit can customize the content of information provided by elderly individuals by taking into account their geographical location. For example, the information provision unit can provide region-specific information based on the characteristics of the area where the elderly person lives. For example, the information provision unit can also prioritize providing information about places that elderly individuals frequently visit. For example, the information provision unit can also customize the content of information based on the elderly person's range of movement. By customizing the content of information while taking into account the geographical location of elderly individuals, it becomes possible to provide more appropriate information. Some or all of the above processing in the information provision unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the information provision unit can have a generative AI perform the customization of information content while taking into account geographical location information.

[0063] The protection unit can optimize the protection algorithm by referring to the elderly person's past privacy protection history during protection. For example, the protection unit provides the optimal protection method based on the elderly person's past privacy protection history. For example, the protection unit can also prioritize providing protection methods to be performed at specific times based on the elderly person's past privacy protection history. For example, the protection unit can analyze the elderly person's past privacy protection history and optimize the algorithm to prevent recurrence of protection issues. This makes it possible to optimize the protection algorithm by referring to the elderly person's past privacy protection history. Some or all of the above processing in the protection unit may be performed using, for example, generative AI, or without generative AI. For example, the protection unit can have the generative AI perform the optimization of the protection algorithm by referring to the past privacy protection history.

[0064] The protection unit can customize the protection data based on the elderly person's living environment and health condition during protection. For example, the protection unit can provide methods for protecting privacy indoors, tailored to the elderly person's living environment. For example, the protection unit can also provide methods for protecting privacy related to health maintenance, depending on the elderly person's health condition. For example, the protection unit can also provide methods for protecting privacy during the day and at night, tailored to the elderly person's daily rhythm. This allows for more appropriate privacy protection by customizing the protection data based on the elderly person's living environment and health condition. Some or all of the above processing in the protection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the protection unit can have a generative AI perform the customization of protection data based on the living environment and health condition.

[0065] The protection unit can customize the privacy protection method when protecting an elderly person, taking into account their geographical location information. For example, the protection unit can provide a region-specific privacy protection method based on the characteristics of the area where the elderly person lives. For example, the protection unit can also prioritize providing a privacy protection method in places that the elderly person frequently visits. For example, the protection unit can also customize the privacy protection method based on the elderly person's range of movement. This allows for more appropriate privacy protection by customizing the privacy protection method to take into account the elderly person's geographical location information. Some or all of the above processing in the protection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the protection unit can have a generative AI perform the customization of the privacy protection method taking into account geographical location information.

[0066] The protection unit can improve the accuracy of privacy protection by analyzing the social media activities of elderly individuals during the protection process. For example, the protection unit can provide privacy protection methods based on the content of activities shared by elderly individuals on social media. The protection unit can also provide privacy protection methods that promote social activities by considering the social media friendships of elderly individuals. For example, the protection unit can improve the accuracy of privacy protection by analyzing the frequency and content of elderly individuals' social media posts. This allows for more appropriate privacy protection by analyzing the social media activities of elderly individuals and improving the accuracy of privacy protection. Some or all of the above-described processes in the protection unit may be performed using, for example, generative AI, or without generative AI. For example, the protection unit can have generative AI analyze social media activities to improve the accuracy of privacy protection.

[0067] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0068] The AI ​​agent service for preventing lonely deaths may also include a "reminder unit." The reminder unit has the function of reminding elderly people of important tasks and appointments in their daily lives. For example, the reminder unit can notify users of medication times. The reminder unit can also send notifications to encourage users to make appointments at medical institutions or to participate in local events. The reminder unit can also provide reminders to encourage users to contact family and friends. This helps elderly people to remember and perform important tasks in their daily lives. Some or all of the above processing in the reminder unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reminder unit can have a generative AI execute the content of the reminder.

[0069] The AI ​​agent service for preventing lonely deaths may also include an "exercise unit." The exercise unit has the function of providing appropriate exercise programs for maintaining the health of the elderly. For example, the exercise unit can use AI to create exercise menus tailored to the physical strength and health condition of the elderly. The exercise unit can also provide guidance on simple stretches and exercises that can be done on a daily basis. The exercise unit can also record the progress of exercise and provide appropriate feedback. This helps the elderly to continue exercising to maintain their health without overexerting themselves. Some or all of the above-mentioned processes in the exercise unit may be performed using, for example, generative AI, or without generative AI. For example, the exercise unit can have generative AI create exercise menus.

[0070] The AI ​​agent service for preventing lonely deaths may also include a "Hobby Support Department." The Hobby Support Department has functions to support activities related to the hobbies and interests of the elderly. For example, the Hobby Support Department can use AI to collect information on the elderly's hobbies and suggest related activities and events. The Hobby Support Department can also encourage participation in online communities related to hobbies. The Hobby Support Department can also suggest new ideas and projects related to hobbies. This can help the elderly lead fulfilling lives through their hobbies. Some or all of the above-mentioned processes in the Hobby Support Department may be performed using, for example, generative AI, or not using generative AI. For example, the Hobby Support Department can have generative AI collect information on hobbies.

[0071] The AI ​​agent service for preventing lonely deaths may also include a "meal management department." The meal management department has the function of managing the nutritional balance of the elderly person's meals. For example, the meal management department can use AI to analyze the elderly person's diet and suggest a nutritionally balanced meal menu. The meal management department can also record meals and understand the status of nutrient intake. The meal management department can also provide dietary advice tailored to specific health conditions. This can help the elderly person maintain a healthy diet. Some or all of the above processes in the meal management department may be performed using, for example, generative AI, or without generative AI. For example, the meal management department can have generative AI suggest meal menus.

[0072] The AI ​​agent service for preventing lonely deaths may also include a "safety verification unit." The safety verification unit has the function of verifying the safety of the elderly person's living environment. For example, the safety verification unit can use AI to detect dangerous areas in the elderly person's living environment and propose improvement measures. The safety verification unit can also, for example, periodically check the safety of the living environment and take necessary measures. The safety verification unit can also, for example, provide a means of communication for a quick response in an emergency. This will help create an environment in which the elderly person can live safely. Some or all of the above-mentioned processes in the safety verification unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the safety verification unit can have a generative AI perform a safety check of the living environment.

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

[0074] Step 1: The learning unit learns the daily behavioral patterns of elderly people. The learning unit uses AI to learn the behavioral patterns of elderly people, such as eating, exercising, and sleeping, and analyzes these behavioral patterns using machine learning algorithms. Furthermore, it can also predict behavioral patterns based on past behavioral data. Step 2: The detection unit detects anomalies based on the behavior patterns learned by the learning unit. The detection unit can use AI to detect deviations from normal behavior patterns and detect anomalies based on the frequency of abnormal behavior or the absence of specific behaviors. Step 3: The sensing unit understands the health and mental state based on the abnormalities detected by the detection unit. The sensing unit uses AI to analyze vital signs and understand the health state. Furthermore, it can also understand the mental state using psychological test results and emotion analysis technology. Step 4: The Collaboration Department coordinates with families, medical institutions, and care services based on the information gathered by the Information Gathering Department. The Collaboration Department uses AI to provide a means of information sharing, enabling real-time information sharing. Furthermore, information can also be shared using an integrated system.

[0075] (Example of form 2)The AI ​​agent service for preventing lonely deaths according to an embodiment of the present invention is an AI-powered service that monitors the daily lives of elderly people and reduces the risk of lonely deaths. This service uses AI to learn the daily behavioral patterns of elderly people and take appropriate action when it detects abnormalities. The AI ​​agent understands the health and mental state of elderly people through communication. Through regular conversations and questions, it senses changes in the elderly person's daily rhythm and mood, and coordinates with family, medical institutions, and care services as needed. Furthermore, this service aims not only to monitor but also to improve the quality of life for elderly people. The AI ​​agent provides conversations tailored to the elderly person's interests and hobbies, offering emotional support. It also promotes social connections by providing information on local events and social activities. Privacy protection is paramount, and collected data is strictly managed and used only to the minimum extent necessary. We strive for highly transparent service operation so that elderly people can use the service with peace of mind. Through this service, we aim to support elderly people in living independent lives with peace of mind and reduce the burden on families and communities. The AI ​​agent service for preventing lonely deaths will be a powerful tool for realizing a safe and fulfilling later life while protecting the dignity of elderly people. The target audience includes elderly people aged 65 and over who live alone, elderly people who are alone during the day, elderly people with health concerns, elderly people whose families live far away, elderly people with weak ties to their community, elderly people who are unfamiliar with technology, and elderly people who do not use care services or wish to use them minimally. This service provides 24 / 7 monitoring and anomaly detection using AI, mental support and health status assessment through natural dialogue, seamless coordination with family, medical institutions and care services, customized support tailored to individual lifestyles, a non-invasive monitoring system that respects privacy, and information provision and activity support that promotes connections with the community. Specifically, it employs a conversational AI agent using natural language processing technology, behavioral pattern analysis and anomaly detection using machine learning, a hands-free interface utilizing speech recognition and speech synthesis technology, contactless health status monitoring using image recognition technology, assessment of mental state using emotion analysis technology, and risk assessment and preventive approaches using predictive analytics.Through this service, we aim to protect the dignity of the elderly, support safe and secure living, reduce the risk of lonely deaths and establish a system for early detection and response, create opportunities for social participation and purpose in life for the elderly, reduce the burden on families and communities and build a sustainable elderly support system, create new forms of "connections" using technology, realize personalized care tailored to the needs of each elderly person, and extend healthy life expectancy and control medical costs through the promotion of preventive medicine. In this way, the lonely death prevention AI agent service can monitor the daily lives of the elderly and reduce the risk of lonely deaths.

[0076] The AI ​​agent service for preventing lonely deaths according to this embodiment comprises a learning unit, a detection unit, an understanding unit, and a collaboration unit. The learning unit learns the daily behavioral patterns of elderly people. The learning unit learns behavioral patterns such as eating, exercising, and sleeping of elderly people using AI, for example. The learning unit can analyze behavioral patterns using machine learning algorithms, for example. The learning unit can also predict behavioral patterns based on past behavioral data, for example. The detection unit detects abnormalities based on the behavioral patterns learned by the learning unit. The detection unit detects deviations from normal behavioral patterns using AI, for example. The detection unit can detect abnormalities based on the frequency of abnormal behavior, for example. The detection unit can also detect the absence of a specific behavior as an abnormality, for example. The understanding unit grasps the health and mental state based on the abnormalities detected by the detection unit. The understanding unit grasps the health state by analyzing vital signs using AI, for example. The understanding unit can grasp the mental state based on the results of psychological tests, for example. The understanding unit can also grasp the mental state using emotion analysis technology, for example. The collaboration unit coordinates with families, medical institutions, and care services based on the information gathered by the information gathering unit. The collaboration unit provides means of information sharing, for example, using AI. The collaboration unit can share information in real time, for example. The collaboration unit can also share information using an integrated system, for example. As a result, the AI ​​agent service for preventing lonely deaths according to this embodiment can learn the daily behavior patterns of elderly people, detect abnormalities, understand their health and mental state, and coordinate with families, medical institutions, and care services.

[0077] The learning unit learns the daily behavioral patterns of elderly people. Specifically, the learning unit uses AI to learn in detail the behavioral patterns of elderly people, such as eating, exercise, and sleep. For example, it analyzes data collected from sensors and wearable devices, such as the timing and content of meals, the frequency and type of exercise, and the duration and quality of sleep. The learning unit uses machine learning algorithms to analyze this data and model the behavioral patterns of elderly people. For example, it can predict behavioral trends on specific days of the week or time of day based on past behavioral data. Furthermore, the learning unit continuously collects data and updates the model to detect changes and anomalies in behavioral patterns. As a result, the learning unit can accurately understand the behavioral patterns of elderly people and contribute to the early detection of anomalies.

[0078] The detection unit detects anomalies based on behavioral patterns learned by the learning unit. Specifically, the detection unit uses AI to detect deviations from normal behavioral patterns in real time. For example, it detects anomalies if meal times are significantly delayed or if the frequency of exercise decreases sharply. The detection unit can evaluate the severity of an anomaly based on the frequency and duration of the abnormal behavior. For example, it detects serious anomalies if meals are not eaten for several consecutive days or if exercise is not performed for a long period of time. It can also detect anomalies in the absence of specific behaviors, such as the sudden interruption of a regular walk. This allows the detection unit to quickly grasp changes in the behavioral patterns of elderly people, enabling early detection and response to anomalies.

[0079] The monitoring unit understands the health and mental state based on abnormalities detected by the detection unit. Specifically, the monitoring unit uses AI to analyze vital signs and understand the health state in detail. For example, it acquires vital signs such as heart rate, blood pressure, and body temperature from sensors and detects changes in health by analyzing this data. Furthermore, the monitoring unit can evaluate the mental state based on the results of psychological tests. For example, it analyzes the results of regularly conducted psychological tests to understand stress levels and signs of depression. It can also use emotion analysis technology to analyze changes in emotions from daily conversations and social media posts to understand the mental state. As a result, the monitoring unit can comprehensively evaluate the health and mental state of elderly people and take necessary actions quickly.

[0080] The Collaboration Department coordinates with families, medical institutions, and care services based on information gathered by the Information Gathering Department. Specifically, the Collaboration Department uses AI to provide a means of information sharing. For example, if an abnormality is detected, it can send real-time notifications to families and medical institutions to encourage a quick response. The Collaboration Department uses a cloud-based integrated system to centrally manage information and facilitate information sharing among stakeholders. For example, families can check the health status of elderly individuals through a smartphone app, and medical institutions can access detailed health data through a dedicated portal site. Furthermore, care services can develop and implement appropriate care plans based on the information provided by the Collaboration Department. In this way, the Collaboration Department can build an effective collaborative system to support the health management of the elderly and reduce the risk of dying alone.

[0081] The conversation unit can provide conversations tailored to the interests and hobbies of elderly individuals. For example, the conversation unit can use AI to collect information about the interests and hobbies of elderly individuals and generate conversation content. The conversation unit can provide topics such as reading, music, and sports. The conversation unit can also provide the latest information related to the hobbies of elderly individuals. By providing conversations tailored to the interests and hobbies of elderly individuals, it can provide emotional support. Some or all of the above processing in the conversation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversation unit can input information about the interests and hobbies of elderly individuals into a generative AI and have the generative AI generate conversation content.

[0082] The information provision department can provide information on local events and social activities. For example, the information provision department can use AI to collect information on local events and social activities and provide it to the elderly. For example, the information provision department can provide information on local festivals, volunteer activities, etc. For example, the information provision department can also provide information on events held at local community centers. In this way, providing information on local events and social activities promotes connections with society. Some or all of the above processing in the information provision department may be performed using, for example, generative AI, or without generative AI. For example, the information provision department can input information on local events and social activities into generative AI and have the generative AI execute the content of the information provision.

[0083] The protection unit can protect privacy. For example, the protection unit can encrypt collected data using AI and impose access restrictions. For example, the protection unit can strictly manage the location where data is stored. For example, the protection unit can limit the scope of data use to the minimum necessary. This ensures privacy and allows elderly people to use the system with peace of mind. Some or all of the above-described processes in the protection unit may be performed using, for example, generative AI, or without generative AI. For example, the protection unit can have generative AI perform the encryption of collected data.

[0084] The learning unit can perform behavioral pattern analysis using machine learning. For example, the learning unit can analyze behavioral patterns using a neural network. The learning unit can also classify behavioral patterns using a support vector machine. The learning unit can also predict behavioral patterns using a decision tree algorithm. This improves the accuracy of learning by performing behavioral pattern analysis using machine learning. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning unit can have a generative AI perform the analysis of behavioral patterns.

[0085] The detection unit can perform predictive analysis to detect anomalies. For example, the detection unit can predict anomalies using time series analysis. The detection unit can also calculate the probability of anomaly occurrence using regression analysis. The detection unit can also predict the occurrence of anomalies using Bayesian estimation. By performing predictive analysis, the accuracy of anomaly detection is improved. Some or all of the above-described processes in the detection unit may be performed using, for example, generative AI, or without generative AI. For example, the detection unit can have generative AI perform anomaly prediction.

[0086] The comprehension unit can grasp a person's mental state using emotion analysis technology. For example, the comprehension unit can estimate emotions from the content of an elderly person's speech using text mining. For example, the comprehension unit can also estimate emotions from the tone and speed of an elderly person's voice using speech analysis. For example, the comprehension unit can estimate emotions from an elderly person's facial expressions using facial recognition technology. As a result, the accuracy of grasping a person's mental state is improved by using emotion analysis technology. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is 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 comprehension unit may be performed using a generative AI, for example, or without a generative AI. For example, the comprehension unit can have a generative AI perform emotion estimation.

[0087] The collaboration unit can facilitate seamless collaboration with families, medical institutions, and care services. The collaboration unit can, for example, share information in real time using AI. The collaboration unit can also share information using an integrated system. The collaboration unit can also provide means of information sharing. This enables rapid response by facilitating seamless collaboration with families, medical institutions, and care services. Some or all of the above-described processes in the collaboration unit may be performed using, for example, generative AI, or without generative AI. For example, the collaboration unit can have generative AI perform the means of information sharing.

[0088] The learning unit can estimate the emotions of elderly individuals and adjust the learning method for behavioral patterns based on the estimated emotions. For example, if an elderly individual is feeling stressed, the learning unit will prioritize learning behavioral patterns in a relaxing environment. For example, if an elderly individual is feeling lonely, the learning unit can also learn behavioral patterns that include social activities. For example, if an elderly individual is anxious about their health, the learning unit can also learn behavioral patterns related to maintaining health. This allows for more appropriate learning by adjusting the learning method for behavioral patterns based on the emotions of elderly individuals. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can estimate the emotions of elderly individuals and have a generative AI perform the adjustment of the learning method for behavioral patterns.

[0089] The learning unit can optimize its learning algorithm by referring to the elderly person's past behavioral history during the learning process. For example, the learning unit adjusts the learning algorithm based on actions that the elderly person has frequently performed in the past. The learning unit can also prioritize learning actions performed during specific time periods based on the elderly person's past behavioral history. For example, the learning unit can analyze the elderly person's past behavioral history and reflect changes in behavioral patterns in the learning algorithm. This makes it possible to optimize the learning algorithm by referring to the elderly person's past behavioral history. Some or all of the above processing in the learning unit may be performed using, for example, generative AI, or without using generative AI. For example, the learning unit can have the generative AI perform the optimization of the learning algorithm by referring to past behavioral history.

[0090] The learning unit can customize the learning data during the learning process based on the elderly person's living environment and health condition. For example, the learning unit can learn indoor behavior patterns to match the elderly person's living environment. The learning unit can also learn exercise levels and eating patterns according to the elderly person's health condition. The learning unit can also learn daytime and nighttime behavior patterns to match the elderly person's daily rhythm. This allows for more appropriate learning by customizing the learning data based on the elderly person's living environment and health condition. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can have a generative AI perform the customization of the learning data based on the living environment and health condition.

[0091] The learning unit can estimate the emotions of elderly individuals and prioritize training data based on those estimated emotions. For example, if an elderly individual is feeling anxious, the learning unit will prioritize learning behavioral patterns that provide a sense of security. For example, if an elderly individual is enjoying themselves, the learning unit can also prioritize learning behavioral patterns related to hobbies and interests. For example, if an elderly individual is tired, the learning unit can also prioritize learning behavioral patterns related to rest and relaxation. This allows for more appropriate learning by prioritizing training data based on the emotions of elderly individuals. Some or all of the above processing in the learning unit may be performed using, for example, generative AI, or without generative AI. For example, the learning unit can estimate the emotions of elderly individuals and have the generative AI perform the task of prioritizing training data.

[0092] The learning unit can collect learning data while considering the geographical location information of elderly individuals during the learning process. For example, the learning unit can learn region-specific behavioral patterns based on the characteristics of the area where the elderly person lives. The learning unit can also learn behavioral patterns of places that elderly individuals frequently visit. The learning unit can also customize behavioral patterns based on the elderly person's travel range. This allows for more appropriate learning by collecting learning data while considering the geographical location information of elderly individuals. Some or all of the above-described processes in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can have a generative AI perform the collection of learning data while considering geographical location information.

[0093] The learning unit can analyze the social media activities of elderly individuals and incorporate relevant data into its learning process. For example, the learning unit can learn behavioral patterns based on the activities that elderly individuals share on social media. The learning unit can also learn social behavioral patterns by considering the social media friendships of elderly individuals. For example, the learning unit can analyze the frequency and content of elderly individuals' social media posts and reflect this in their behavioral patterns. This allows for more appropriate learning by analyzing the social media activities of elderly individuals and incorporating relevant data into the learning process. Some or all of the above-described processes in the learning unit may be performed using, for example, generative AI, or without generative AI. For example, the learning unit can have a generative AI analyze social media activities and collect learning data.

[0094] The detection unit can estimate the emotions of elderly individuals and adjust the anomaly detection criteria based on the estimated emotions. For example, if an elderly individual is experiencing stress, the detection unit may not consider stress-reducing behaviors as abnormal. For example, if an elderly individual is feeling lonely, the detection unit may also detect a decrease in social behavior as abnormal. For example, if an elderly individual is feeling anxious about their health, the detection unit may also detect changes in health-related behaviors as abnormal. By adjusting the anomaly detection criteria based on the emotions of elderly individuals, more appropriate anomaly detection becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, by using an emotion engine or generative AI. Generative 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 processing in the detection unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the detection unit can estimate the emotions of elderly individuals and have the generative AI perform the adjustment of the anomaly detection criteria.

[0095] The detection unit can optimize its detection algorithm by referring to the elderly person's past anomaly detection history when an anomaly is detected. For example, the detection unit adjusts the detection algorithm based on patterns of anomalies the elderly person has experienced in the past. The detection unit can also prioritize the detection of anomalies that occur during specific time periods based on the elderly person's past anomaly detection history. The detection unit can also analyze the elderly person's past anomaly detection history and optimize an algorithm to prevent the recurrence of anomalies. This makes it possible to optimize the detection algorithm by referring to the elderly person's past anomaly detection history. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can have a generative AI perform the optimization of the detection algorithm by referring to the past anomaly detection history.

[0096] The detection unit can improve the accuracy of anomaly detection based on the elderly person's lifestyle and health condition when an anomaly is detected. For example, the detection unit adjusts the timing of anomaly detection to match the elderly person's lifestyle. The detection unit can also customize the criteria for anomaly detection according to the elderly person's health condition. The detection unit can also improve the accuracy of anomaly detection by considering the elderly person's lifestyle and health condition. This makes it possible to perform more appropriate anomaly detection by improving the accuracy of anomaly detection based on the elderly person's lifestyle and health condition. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can have a generative AI perform the improvement of anomaly detection accuracy based on lifestyle and health condition.

[0097] The detection unit can estimate the emotions of elderly individuals and determine the priority of anomaly detection based on the estimated emotions. For example, if an elderly individual is feeling anxious, the detection unit may prioritize detecting a decrease in behaviors that provide a sense of security. For example, if an elderly individual is enjoying themselves, the detection unit may also prioritize detecting a decrease in behaviors related to hobbies or interests. For example, if an elderly individual is tired, the detection unit may also prioritize detecting a decrease in behaviors related to rest or relaxation. This allows for more appropriate anomaly detection by determining the priority of anomaly detection based on the emotions of elderly individuals. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can estimate the emotions of elderly individuals and have a generative AI perform the determination of the priority of anomaly detection.

[0098] The detection unit can perform anomaly detection while considering the geographical location information of the elderly person. For example, the detection unit can detect region-specific anomalies based on the characteristics of the area where the elderly person lives. The detection unit can also prioritize detecting anomalies in places that the elderly person frequently visits. The detection unit can also customize the range of anomaly detection based on the elderly person's range of movement. This makes it possible to perform more appropriate anomaly detection by considering the geographical location information of the elderly person. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the detection unit can cause a generative AI to perform anomaly detection while considering geographical location information.

[0099] The detection unit can improve the accuracy of anomaly detection by analyzing the social media activities of elderly individuals when detection occurs. For example, the detection unit can detect anomalies based on the content of activities shared by elderly individuals on social media. The detection unit can also detect a decrease in social behavior as an anomaly by considering the social media friendships of elderly individuals. The detection unit can also improve the accuracy of anomaly detection by analyzing the frequency and content of posts made by elderly individuals on social media. By analyzing the social media activities of elderly individuals and improving the accuracy of anomaly detection, more appropriate anomaly detection becomes possible. Some or all of the above processing in the detection unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the detection unit can have a generative AI perform the task of analyzing social media activities to improve the accuracy of anomaly detection.

[0100] The assessment unit can estimate the emotions of elderly individuals and adjust the method of assessing their health and mental state based on the estimated emotions. For example, if an elderly individual is experiencing stress, the assessment unit will prioritize assessing their health in order to reduce stress. For example, if an elderly individual is feeling lonely, the assessment unit can also reflect a decrease in social activities in assessing their mental state. For example, if an elderly individual is anxious about their health, the assessment unit can also reflect changes in health maintenance-related behaviors in assessing their mental state. This allows for a more accurate assessment by adjusting the method of assessing health and mental state based on the emotions of elderly individuals. Some or all of the above-described processes in the assessment unit may be performed using, for example, a generative AI, or without a generative AI. For example, the assessment unit can estimate the emotions of elderly individuals and have the generative AI perform the adjustment of the method of assessing their health and mental state.

[0101] The assessment unit can optimize its assessment algorithm by referring to the elderly person's past health data during assessment. For example, the assessment unit can understand changes in the elderly person's health status based on their past health data. For example, the assessment unit can also prioritize understanding changes in health status that occur during specific time periods from the elderly person's past health data. For example, the assessment unit can analyze the elderly person's past health data and optimize an algorithm to prevent the recurrence of health conditions. This makes it possible to optimize the assessment algorithm by referring to the elderly person's past health data. Some or all of the above processing in the assessment unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the assessment unit can have the generative AI perform the optimization of the assessment algorithm by referring to past health data.

[0102] The data acquisition unit can customize the data acquired based on the elderly person's living environment and health condition. For example, the data acquisition unit can acquire the health condition indoors, tailored to the elderly person's living environment. For example, the data acquisition unit can also acquire exercise levels and eating patterns according to the elderly person's health condition. For example, the data acquisition unit can acquire the health condition during the day and at night, tailored to the elderly person's daily rhythm. This allows for more accurate data acquisition by customizing the data acquired based on the elderly person's living environment and health condition. Some or all of the above processing in the data acquisition unit may be performed using, for example, a generation AI, or without a generation AI. For example, the data acquisition unit can have the generation AI perform the customization of the data acquired based on the living environment and health condition.

[0103] The assessment unit can estimate the emotions of elderly individuals and determine the priority of assessment data based on the estimated emotions. For example, if an elderly individual is feeling anxious, the assessment unit may prioritize assessment of health conditions that provide a sense of security. For example, if an elderly individual is enjoying themselves, the assessment unit may also prioritize assessment of health conditions related to hobbies and interests. For example, if an elderly individual is tired, the assessment unit may also prioritize assessment of health conditions related to rest and relaxation. This allows for more appropriate assessment by determining the priority of assessment data based on the emotions of elderly individuals. Some or all of the above processing in the assessment unit may be performed using, for example, a generative AI, or without a generative AI. For example, the assessment unit can estimate the emotions of elderly individuals and have the generative AI perform the determination of the priority of assessment data.

[0104] The assessment unit can assess the health and mental state of elderly individuals while considering their geographical location. For example, the assessment unit can assess region-specific health conditions based on the characteristics of the area where the elderly person lives. For example, the assessment unit can prioritize assessing the health condition of elderly individuals in places they frequently visit. For example, the assessment unit can customize the range of health condition assessment based on the elderly person's travel range. This allows for more appropriate assessment by considering the elderly person's geographical location when assessing their health and mental state. Some or all of the above-described processes in the assessment unit may be performed using, for example, a generative AI, or without a generative AI. For example, the assessment unit can have a generative AI perform the assessment of health and mental state while considering geographical location information.

[0105] The assessment unit can analyze the social media activities of elderly individuals and incorporate relevant data into its assessment. For example, the assessment unit can assess the health status based on the activities shared by elderly individuals on social media. The assessment unit can also consider the social relationships of elderly individuals on social media and reflect a decrease in social activity in its assessment of health status. The assessment unit can also analyze the frequency and content of elderly individuals' social media posts and reflect this in its assessment of health status. By analyzing the social media activities of elderly individuals and incorporating relevant data into the assessment, a more accurate assessment becomes possible. Some or all of the above processing in the assessment unit may be performed using, for example, a generative AI, or without a generative AI. For example, the assessment unit can have a generative AI analyze social media activities and assess health status.

[0106] The collaboration unit can estimate the emotions of elderly individuals and adjust the collaboration method based on the estimated emotions. For example, if an elderly individual is experiencing stress, the collaboration unit will prioritize providing collaboration methods to reduce stress. For example, if an elderly individual is feeling lonely, the collaboration unit may also provide collaboration methods that promote social activities. For example, if an elderly individual is feeling anxious about their health, the collaboration unit may also provide collaboration methods related to maintaining health. By adjusting the collaboration method based on the emotions of elderly individuals, more appropriate collaboration becomes possible. Some or all of the above processing in the collaboration unit may be performed using, for example, a generative AI, or without a generative AI. For example, the collaboration unit can estimate the emotions of elderly individuals and have a generative AI perform the adjustment of the collaboration method.

[0107] The collaboration unit can optimize the collaboration algorithm by referring to the elderly person's past collaboration history during collaboration. For example, the collaboration unit provides the optimal collaboration method based on the elderly person's past collaboration history. For example, the collaboration unit can also prioritize providing collaboration methods to be performed during specific time periods based on the elderly person's past collaboration history. For example, the collaboration unit can analyze the elderly person's past collaboration history and optimize the algorithm to prevent the recurrence of collaboration issues. This makes it possible to optimize the collaboration algorithm by referring to the elderly person's past collaboration history. Some or all of the above processing in the collaboration unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the collaboration unit can have a generative AI perform the optimization of the collaboration algorithm by referring to past collaboration history.

[0108] The collaboration unit can customize the collaboration data based on the elderly person's living environment and health condition during the collaboration process. For example, the collaboration unit can provide a method of collaboration within the home that is tailored to the elderly person's living environment. For example, the collaboration unit can also provide a method of collaboration related to health maintenance depending on the elderly person's health condition. For example, the collaboration unit can also provide a method of collaboration for daytime and nighttime that is tailored to the elderly person's daily rhythm. This allows for more appropriate collaboration by customizing the collaboration data based on the elderly person's living environment and health condition. Some or all of the above processing in the collaboration unit may be performed using, for example, a generative AI, or without a generative AI. For example, the collaboration unit can have a generative AI perform the customization of the collaboration data based on the living environment and health condition.

[0109] The collaboration unit can estimate the emotions of elderly individuals and determine the priority of collaborations based on those estimated emotions. For example, if an elderly individual is feeling anxious, the collaboration unit can prioritize providing a sense of security through collaboration methods. For example, if an elderly individual is enjoying themselves, the collaboration unit can prioritize providing collaboration methods related to their hobbies and interests. For example, if an elderly individual is tired, the collaboration unit can prioritize providing collaboration methods related to rest and relaxation. This allows for more appropriate collaborations by determining the priority of collaborations based on the emotions of elderly individuals. Some or all of the above processing in the collaboration unit may be performed using, for example, a generative AI, or without a generative AI. For example, the collaboration unit can estimate the emotions of elderly individuals and have a generative AI determine the priority of collaborations.

[0110] The collaboration unit can perform collaboration while considering the geographical location information of elderly individuals. For example, the collaboration unit can provide region-specific collaboration methods based on the characteristics of the area where the elderly person lives. For example, the collaboration unit can also prioritize providing collaboration methods for places that elderly individuals frequently visit. For example, the collaboration unit can customize collaboration methods based on the elderly person's range of movement. This makes it possible to perform collaboration more appropriately by considering the geographical location information of elderly individuals. Some or all of the above processing in the collaboration unit may be performed using, for example, a generative AI, or without a generative AI. For example, the collaboration unit can cause a generative AI to perform collaboration while considering geographical location information.

[0111] The collaboration unit can improve the accuracy of collaboration by analyzing the social media activities of elderly individuals during the collaboration process. For example, the collaboration unit can provide a collaboration method based on the activities shared by elderly individuals on social media. The collaboration unit can also provide a collaboration method that promotes social activities by considering the social media friendships of elderly individuals. The collaboration unit can also improve the accuracy of collaboration by analyzing the frequency and content of elderly individuals' social media posts. By analyzing the social media activities of elderly individuals and improving the accuracy of collaboration, more appropriate collaboration becomes possible. Some or all of the above processing in the collaboration unit may be performed using, for example, generative AI, or without generative AI. For example, the collaboration unit can have generative AI analyze social media activities to improve the accuracy of collaboration.

[0112] The conversation unit can estimate the emotions of elderly individuals and adjust the content and tone of the conversation based on the estimated emotions. For example, if an elderly individual is feeling stressed, the conversation unit can provide relaxing conversation content and tone. For example, if an elderly individual is feeling lonely, the conversation unit can also provide sociable conversation content and tone. For example, if an elderly individual is anxious about their health, the conversation unit can also provide conversation content and tone related to maintaining health. By adjusting the content and tone of the conversation based on the emotions of elderly individuals, more appropriate conversations become possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the conversation unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the conversation unit can estimate the emotions of elderly individuals and have the generative AI perform the adjustment of the content and tone of the conversation.

[0113] The conversation unit can optimize its conversation algorithm by referring to the elderly person's past conversation history during a conversation. For example, the conversation unit can provide optimal conversation content and tone based on the elderly person's past conversation history. For example, the conversation unit can also prioritize providing conversation content and tone for specific time periods based on the elderly person's past conversation history. For example, the conversation unit can analyze the elderly person's past conversation history and optimize an algorithm to prevent the recurrence of conversations. This makes it possible to optimize the conversation algorithm by referring to the elderly person's past conversation history. Some or all of the above processing in the conversation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversation unit can have a generative AI perform the optimization of the conversation algorithm by referring to past conversation history.

[0114] The conversation unit can customize the conversation content based on the elderly person's living environment and health condition. For example, the conversation unit can provide conversation content tailored to the elderly person's living environment. For example, the conversation unit can also provide conversation content related to maintaining health, depending on the elderly person's health condition. For example, the conversation unit can also provide conversation content for daytime and nighttime, according to the elderly person's daily rhythm. By customizing the conversation content based on the elderly person's living environment and health condition, more appropriate conversations become possible. Some or all of the above processing in the conversation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversation unit can have a generative AI perform the customization of conversation content based on the living environment and health condition.

[0115] The conversation unit can estimate the emotions of elderly individuals and determine conversation priorities based on those estimated emotions. For example, if an elderly person is feeling anxious, the conversation unit can prioritize providing reassuring conversation topics. For example, if an elderly person is enjoying themselves, the conversation unit can prioritize providing conversation topics related to their hobbies and interests. For example, if an elderly person is tired, the conversation unit can prioritize providing conversation topics related to rest and relaxation. This allows for more appropriate conversations by prioritizing conversations based on the elderly person's emotions. Some or all of the above processing in the conversation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversation unit can estimate the emotions of elderly individuals and have a generative AI perform the task of determining conversation priorities.

[0116] The conversation unit can customize the conversation content by taking into account the geographical location information of the elderly person during a conversation. For example, the conversation unit can provide region-specific conversation content based on the characteristics of the area where the elderly person lives. For example, the conversation unit can also prioritize providing conversation content for places that the elderly person frequently visits. For example, the conversation unit can also customize the conversation content based on the elderly person's range of movement. This makes it possible to have more appropriate conversations by customizing the conversation content while taking into account the geographical location information of the elderly person. Some or all of the above processing in the conversation unit may be performed using, for example, a generative AI, or without a generative AI. For example, the conversation unit can have a generative AI perform the customization of conversation content while taking into account geographical location information.

[0117] The information provision unit can estimate the emotions of elderly individuals and adjust the content and timing of the information provided based on those estimated emotions. For example, if an elderly person is feeling stressed, the information provision unit can prioritize providing information that promotes relaxation. For example, if an elderly person is feeling lonely, the information provision unit can prioritize providing information related to social activities. For example, if an elderly person is anxious about their health, the information provision unit can prioritize providing information related to maintaining health. By adjusting the content and timing of information provided based on the emotions of elderly individuals, more appropriate information can be provided. Some or all of the above processing in the information provision unit may be performed using, for example, a generative AI, or without a generative AI. For example, the information provision unit can estimate the emotions of elderly individuals and have a generative AI perform the adjustment of the content and timing of the information.

[0118] The information provision unit can optimize its information provision algorithm by referring to the elderly person's past information provision history when providing information. For example, the information provision unit can provide the most suitable information based on the elderly person's past information provision history. For example, the information provision unit can also prioritize providing information at specific time periods based on the elderly person's past information provision history. For example, the information provision unit can analyze the elderly person's past information provision history and optimize the algorithm to prevent the recurrence of information provision issues. This makes it possible to optimize the information provision algorithm by referring to the elderly person's past information provision history. Some or all of the above processing in the information provision unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the information provision unit can have a generative AI perform the optimization of the information provision algorithm by referring to the past information provision history.

[0119] The information provision unit can customize the information content based on the elderly person's living environment and health condition when providing information. For example, the information provision unit can provide information about indoor activities tailored to the elderly person's living environment. For example, the information provision unit can also provide information related to maintaining health according to the elderly person's health condition. For example, the information provision unit can provide information for daytime and nighttime, tailored to the elderly person's daily rhythm. By customizing the information content based on the elderly person's living environment and health condition, it becomes possible to provide more appropriate information. Some or all of the above processing in the information provision unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the information provision unit can have a generative AI perform the customization of information content based on the living environment and health condition.

[0120] The information provision unit can estimate the emotions of elderly individuals and determine the priority of information provision based on those estimated emotions. For example, if an elderly person is feeling anxious, the information provision unit can prioritize providing information that provides a sense of security. For example, if an elderly person is enjoying themselves, the information provision unit can also prioritize providing information related to their hobbies and interests. For example, if an elderly person is tired, the information provision unit can also prioritize providing information related to rest and relaxation. By determining the priority of information provision based on the emotions of elderly individuals, more appropriate information can be provided. Some or all of the above processing in the information provision unit may be performed using, for example, a generative AI, or without a generative AI. For example, the information provision unit can estimate the emotions of elderly individuals and have a generative AI perform the determination of the priority of information provision.

[0121] The information provision unit can customize the content of information provided by elderly individuals by taking into account their geographical location. For example, the information provision unit can provide region-specific information based on the characteristics of the area where the elderly person lives. For example, the information provision unit can also prioritize providing information about places that elderly individuals frequently visit. For example, the information provision unit can also customize the content of information based on the elderly person's range of movement. By customizing the content of information while taking into account the geographical location of elderly individuals, it becomes possible to provide more appropriate information. Some or all of the above processing in the information provision unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the information provision unit can have a generative AI perform the customization of information content while taking into account geographical location information.

[0122] The protection unit can estimate the emotions of elderly individuals and adjust privacy protection methods based on the estimated emotions. For example, if an elderly individual is experiencing stress, the protection unit may minimize privacy notifications. For example, if an elderly individual is experiencing loneliness, the protection unit may increase privacy notifications. For example, if an elderly individual is experiencing health concerns, the protection unit may limit privacy notifications to content related to health maintenance. This allows for more appropriate privacy protection by adjusting privacy protection methods based on the emotions of elderly individuals. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the protection unit may be performed using, for example, generative AI, or not using generative AI. For example, the protection unit can estimate the emotions of elderly individuals and have the generative AI perform the adjustment of privacy protection methods.

[0123] The protection unit can optimize the protection algorithm by referring to the elderly person's past privacy protection history during protection. For example, the protection unit provides the optimal protection method based on the elderly person's past privacy protection history. For example, the protection unit can also prioritize providing protection methods to be performed at specific times based on the elderly person's past privacy protection history. For example, the protection unit can analyze the elderly person's past privacy protection history and optimize the algorithm to prevent recurrence of protection issues. This makes it possible to optimize the protection algorithm by referring to the elderly person's past privacy protection history. Some or all of the above processing in the protection unit may be performed using, for example, generative AI, or without generative AI. For example, the protection unit can have the generative AI perform the optimization of the protection algorithm by referring to the past privacy protection history.

[0124] The protection unit can customize the protection data based on the elderly person's living environment and health condition during protection. For example, the protection unit can provide methods for protecting privacy indoors, tailored to the elderly person's living environment. For example, the protection unit can also provide methods for protecting privacy related to health maintenance, depending on the elderly person's health condition. For example, the protection unit can also provide methods for protecting privacy during the day and at night, tailored to the elderly person's daily rhythm. This allows for more appropriate privacy protection by customizing the protection data based on the elderly person's living environment and health condition. Some or all of the above processing in the protection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the protection unit can have a generative AI perform the customization of protection data based on the living environment and health condition.

[0125] The protection unit can estimate the emotions of elderly individuals and determine privacy protection priorities based on those estimated emotions. For example, if an elderly individual is feeling anxious, the protection unit can prioritize providing privacy protection methods that offer a sense of security. For example, if an elderly individual is enjoying themselves, the protection unit can prioritize providing privacy protection methods related to their hobbies and interests. For example, if an elderly individual is tired, the protection unit can prioritize providing privacy protection methods related to rest and relaxation. This allows for more appropriate privacy protection by determining privacy protection priorities based on the emotions of elderly individuals. Some or all of the above processing in the protection unit may be performed using, for example, generative AI, or without generative AI. For example, the protection unit can estimate the emotions of elderly individuals and have generative AI perform the determination of privacy protection priorities.

[0126] The protection unit can customize the privacy protection method when protecting an elderly person, taking into account their geographical location information. For example, the protection unit can provide a region-specific privacy protection method based on the characteristics of the area where the elderly person lives. For example, the protection unit can also prioritize providing a privacy protection method in places that the elderly person frequently visits. For example, the protection unit can also customize the privacy protection method based on the elderly person's range of movement. This allows for more appropriate privacy protection by customizing the privacy protection method to take into account the elderly person's geographical location information. Some or all of the above processing in the protection unit may be performed using, for example, a generative AI, or without a generative AI. For example, the protection unit can have a generative AI perform the customization of the privacy protection method taking into account geographical location information.

[0127] The protection unit can improve the accuracy of privacy protection by analyzing the social media activities of elderly individuals during the protection process. For example, the protection unit can provide privacy protection methods based on the content of activities shared by elderly individuals on social media. The protection unit can also provide privacy protection methods that promote social activities by considering the social media friendships of elderly individuals. For example, the protection unit can improve the accuracy of privacy protection by analyzing the frequency and content of elderly individuals' social media posts. This allows for more appropriate privacy protection by analyzing the social media activities of elderly individuals and improving the accuracy of privacy protection. Some or all of the above-described processes in the protection unit may be performed using, for example, generative AI, or without generative AI. For example, the protection unit can have generative AI analyze social media activities to improve the accuracy of privacy protection.

[0128] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0129] The AI ​​agent service for preventing lonely deaths may also include a "reminder unit." The reminder unit has the function of reminding elderly people of important tasks and appointments in their daily lives. For example, the reminder unit can notify users of medication times. The reminder unit can also send notifications to encourage users to make appointments at medical institutions or to participate in local events. The reminder unit can also provide reminders to encourage users to contact family and friends. This helps elderly people to remember and perform important tasks in their daily lives. Some or all of the above processing in the reminder unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the reminder unit can have a generative AI execute the content of the reminder.

[0130] The AI ​​agent service for preventing lonely deaths may also include an "exercise unit." The exercise unit has the function of providing appropriate exercise programs for maintaining the health of the elderly. For example, the exercise unit can use AI to create exercise menus tailored to the physical strength and health condition of the elderly. The exercise unit can also provide guidance on simple stretches and exercises that can be done on a daily basis. The exercise unit can also record the progress of exercise and provide appropriate feedback. This helps the elderly to continue exercising to maintain their health without overexerting themselves. Some or all of the above-mentioned processes in the exercise unit may be performed using, for example, generative AI, or without generative AI. For example, the exercise unit can have generative AI create exercise menus.

[0131] The AI ​​agent service for preventing lonely deaths may also include a "Hobby Support Department." The Hobby Support Department has functions to support activities related to the hobbies and interests of the elderly. For example, the Hobby Support Department can use AI to collect information on the elderly's hobbies and suggest related activities and events. The Hobby Support Department can also encourage participation in online communities related to hobbies. The Hobby Support Department can also suggest new ideas and projects related to hobbies. This can help the elderly lead fulfilling lives through their hobbies. Some or all of the above-mentioned processes in the Hobby Support Department may be performed using, for example, generative AI, or not using generative AI. For example, the Hobby Support Department can have generative AI collect information on hobbies.

[0132] The AI ​​agent service for preventing lonely deaths may also include a "meal management department." The meal management department has the function of managing the nutritional balance of the elderly person's meals. For example, the meal management department can use AI to analyze the elderly person's diet and suggest a nutritionally balanced meal menu. The meal management department can also record meals and understand the status of nutrient intake. The meal management department can also provide dietary advice tailored to specific health conditions. This can help the elderly person maintain a healthy diet. Some or all of the above processes in the meal management department may be performed using, for example, generative AI, or without generative AI. For example, the meal management department can have generative AI suggest meal menus.

[0133] The AI ​​agent service for preventing lonely deaths may also include a "safety verification unit." The safety verification unit has the function of verifying the safety of the elderly person's living environment. For example, the safety verification unit can use AI to detect dangerous areas in the elderly person's living environment and propose improvement measures. The safety verification unit can also, for example, periodically check the safety of the living environment and take necessary measures. The safety verification unit can also, for example, provide a means of communication for a quick response in an emergency. This will help create an environment in which the elderly person can live safely. Some or all of the above-mentioned processes in the safety verification unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the safety verification unit can have a generative AI perform a safety check of the living environment.

[0134] The AI ​​agent service for preventing lonely deaths may also include an "emotional support unit." The emotional support unit has the function of estimating the emotions of elderly people and providing appropriate support based on the estimated emotions. For example, if an elderly person is feeling stressed, the emotional support unit can provide relaxing music or videos. If an elderly person is feeling lonely, the emotional support unit can also suggest social activities. If an elderly person is feeling anxious about their health, the emotional support unit can also provide reassuring information. This allows for the provision of appropriate support tailored to the emotions of elderly people. Some or all of the above-described processes in the emotional support unit may be performed using, for example, generative AI, or without generative AI. For example, the emotional support unit can have generative AI perform emotion estimation and support content provision.

[0135] The AI ​​agent service for preventing lonely deaths may also include an "emotional feedback unit." The emotional feedback unit has the function of estimating the emotions of elderly people and providing feedback based on the estimated emotions. For example, if an elderly person is feeling stressed, the emotional feedback unit can provide advice to reduce stress. If an elderly person is feeling lonely, the emotional feedback unit can also provide feedback to encourage social activities. If an elderly person is feeling anxious about their health, the emotional feedback unit can also provide feedback to maintain their health. This allows for the provision of appropriate feedback tailored to the emotions of elderly people. Some or all of the above-described processes in the emotional feedback unit may be performed using, for example, generative AI, or without generative AI. For example, the emotional feedback unit can have generative AI perform emotion estimation and feedback provision.

[0136] The AI ​​agent service for preventing lonely deaths may also include an "emotional monitoring unit." The emotional monitoring unit has the function of continuously monitoring the emotions of elderly people and detecting abnormalities. For example, the emotional monitoring unit can use AI to estimate emotions from the elderly person's statements and actions and detect abnormalities. The emotional monitoring unit can also record changes in emotions and notify if an abnormality occurs. The emotional monitoring unit can also suggest appropriate actions if an emotional abnormality is detected. This allows for continuous monitoring of changes in the elderly person's emotions and early detection of abnormalities. Some or all of the above processing in the emotional monitoring unit may be performed using, for example, generative AI, or without generative AI. For example, the emotional monitoring unit can have generative AI perform emotion estimation and abnormality detection.

[0137] The AI ​​agent service for preventing lonely deaths may also include an "emotion prediction unit." The emotion prediction unit has the function of predicting the emotions of elderly people and taking appropriate action based on the predicted emotions. For example, the emotion prediction unit can use AI to analyze the past emotional data of elderly people and predict their future emotions. The emotion prediction unit can also provide appropriate support and advice based on the predicted emotions. The emotion prediction unit can also take preventative measures based on the predicted emotions. This allows for the prediction of changes in the emotions of elderly people in advance and the taking of appropriate action. Some or all of the above processing in the emotion prediction unit may be performed using, for example, generative AI, or without generative AI. For example, the emotion prediction unit can have generative AI perform the prediction of emotions and the provision of responses.

[0138] The AI ​​agent service for preventing lonely deaths may also be equipped with an "emotional recording unit." The emotional recording unit has the function of recording the emotions of elderly people and understanding long-term emotional changes. For example, the emotional recording unit can use AI to estimate and record emotions from the elderly person's statements and actions. The emotional recording unit can also visualize emotional changes in graphs or charts. The emotional recording unit can also analyze long-term emotional changes and provide appropriate feedback. This allows for a long-term understanding of the elderly person's emotional changes and appropriate responses to be taken. Some or all of the above processing in the emotional recording unit may be performed using, for example, generative AI, or without generative AI. For example, the emotional recording unit can have generative AI perform the recording and analysis of emotions.

[0139] The following briefly describes the processing flow for example form 2.

[0140] Step 1: The learning unit learns the daily behavioral patterns of elderly people. The learning unit uses AI to learn the behavioral patterns of elderly people, such as eating, exercising, and sleeping, and analyzes these behavioral patterns using machine learning algorithms. Furthermore, it can also predict behavioral patterns based on past behavioral data. Step 2: The detection unit detects anomalies based on the behavior patterns learned by the learning unit. The detection unit can use AI to detect deviations from normal behavior patterns and detect anomalies based on the frequency of abnormal behavior or the absence of specific behaviors. Step 3: The sensing unit understands the health and mental state based on the abnormalities detected by the detection unit. The sensing unit uses AI to analyze vital signs and understand the health state. Furthermore, it can also understand the mental state using psychological test results and emotion analysis technology. Step 4: The Collaboration Department coordinates with families, medical institutions, and care services based on the information gathered by the Information Gathering Department. The Collaboration Department uses AI to provide a means of information sharing, enabling real-time information sharing. Furthermore, information can also be shared using an integrated system.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] Each of the multiple elements described above, including the learning unit, detection unit, understanding unit, collaboration unit, conversation unit, information provision unit, and protection unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the smart device 14 and learns the daily behavior patterns of the elderly person. The detection unit is implemented by the specific processing unit 290 of the data processing unit 12 and detects abnormalities based on the learned behavior patterns. The understanding unit is implemented by the control unit 46A of the smart device 14 and grasps the health and mental state based on the detected abnormalities. The collaboration unit is implemented by the specific processing unit 290 of the data processing unit 12 and coordinates with family, medical institutions, and care services based on the grasped information. The conversation unit is implemented by the control unit 46A of the smart device 14 and provides conversations tailored to the elderly person's interests and hobbies. The information provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides information on local events and social activities. The protection unit is implemented, for example, by the control unit 46A of the smart device 14, which encrypts the collected data and restricts access. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0145] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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).

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.).

[0157] 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.

[0158] 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.

[0159] 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.

[0160] Each of the multiple elements described above, including the learning unit, detection unit, understanding unit, collaboration unit, conversation unit, information provision unit, and protection unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the smart glasses 214 and learns the daily behavior patterns of the elderly person. The detection unit is implemented by the specific processing unit 290 of the data processing unit 12 and detects abnormalities based on the learned behavior patterns. The understanding unit is implemented by the control unit 46A of the smart glasses 214 and grasps the health and mental state based on the detected abnormalities. The collaboration unit is implemented by the specific processing unit 290 of the data processing unit 12 and coordinates with family, medical institutions, and care services based on the grasped information. The conversation unit is implemented by the control unit 46A of the smart glasses 214 and provides conversations tailored to the elderly person's interests and hobbies. The information provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides information on local events and social activities. The protection unit is implemented, for example, by the control unit 46A of the smart glasses 214, which encrypts the collected data and restricts access. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0161] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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).

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.).

[0173] 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.

[0174] 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.

[0175] 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.

[0176] Each of the multiple elements described above, including the learning unit, detection unit, understanding unit, collaboration unit, conversation unit, information provision unit, and protection unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the headset terminal 314 and learns the daily behavior patterns of the elderly person. The detection unit is implemented by the specific processing unit 290 of the data processing unit 12 and detects abnormalities based on the learned behavior patterns. The understanding unit is implemented by the control unit 46A of the headset terminal 314 and grasps the health and mental state based on the detected abnormalities. The collaboration unit is implemented by the specific processing unit 290 of the data processing unit 12 and coordinates with family, medical institutions, and care services based on the grasped information. The conversation unit is implemented by the control unit 46A of the headset terminal 314 and provides conversations tailored to the elderly person's interests and hobbies. The information provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides information on local events and social activities. The protection unit is implemented, for example, by the control unit 46A of the headset-type terminal 314, which encrypts the collected data and restricts access. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0177] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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).

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.).

[0190] 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.

[0191] 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.

[0192] 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.

[0193] Each of the multiple elements described above, including the learning unit, detection unit, grasping unit, collaboration unit, conversation unit, information provision unit, and protection unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the learning unit is implemented by the control unit 46A of the robot 414 and learns the daily behavior patterns of the elderly person. The detection unit is implemented by the specific processing unit 290 of the data processing unit 12 and detects abnormalities based on the learned behavior patterns. The grasping unit is implemented by the control unit 46A of the robot 414 and grasps the health and mental state based on the detected abnormalities. The collaboration unit is implemented by the specific processing unit 290 of the data processing unit 12 and coordinates with family, medical institutions, and care services based on the grasped information. The conversation unit is implemented by the control unit 46A of the robot 414 and provides conversations tailored to the elderly person's interests and hobbies. The information provision unit is implemented by the specific processing unit 290 of the data processing unit 12 and provides information on local events and social activities. The protection unit is implemented, for example, by the control unit 46A of the robot 414, which encrypts the collected data and restricts access. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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."

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] (Note 1) A learning department that studies the daily behavioral patterns of the elderly, A detection unit that detects anomalies based on the behavioral patterns learned by the learning unit, A unit that grasps the health and mental state based on the abnormality detected by the aforementioned detection unit, The system includes a coordination unit that facilitates coordination with family members, medical institutions, and care services based on the information gathered by the aforementioned information gathering unit. A system characterized by the following features. (Note 2) The facility includes a conversation department that provides conversations tailored to the interests and hobbies of elderly people. The system described in Appendix 1, characterized by the features described herein. (Note 3) It has an information department that provides information on local events and social activities. The system described in Appendix 1, characterized by the features described herein. (Note 4) Equipped with a protective section to protect privacy. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned learning unit, Perform behavioral pattern analysis using machine learning. The system described in Appendix 1, characterized by the features described herein. (Note 6) The detection unit, Perform predictive analytics to detect anomalies. The system described in Appendix 1, characterized by the features described herein. (Note 7) The gripping part is, Using emotion analysis techniques to understand mental state The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned linkage unit is, To ensure seamless collaboration with family, medical institutions, and care services. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, This system estimates the emotions of older adults and adjusts the learning method of behavioral patterns based on the estimated emotions of older adults. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, During the learning process, the learning algorithm is optimized by referring to the past behavioral history of elderly individuals. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning unit, During learning, the learning data is customized based on the living environment and health status of elderly individuals. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned learning unit, This system estimates the emotions of elderly individuals and prioritizes training data based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned learning unit, During the learning process, the learning data is collected while taking into account the geographical location information of elderly individuals. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned learning unit, During the learning process, analyze the social media activity of older adults and incorporate relevant data into the learning process. The system described in Appendix 1, characterized by the features described herein. (Note 15) The detection unit, The system estimates the emotions of elderly individuals and adjusts the criteria for detecting anomalies based on these estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The detection unit, When detection occurs, the detection algorithm is optimized by referring to the elderly person's past abnormality detection history. The system described in Appendix 1, characterized by the features described herein. (Note 17) The detection unit, When detection occurs, the accuracy of anomaly detection is improved based on the elderly person's lifestyle and health condition. The system described in Appendix 1, characterized by the features described herein. (Note 18) The detection unit, The system estimates the emotions of elderly individuals and determines the priority of anomaly detection based on these estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The detection unit, When detecting an anomaly, the system takes into account the geographical location information of the elderly person. The system described in Appendix 1, characterized by the features described herein. (Note 20) The detection unit, When detection occurs, the accuracy of anomaly detection is improved by analyzing the social media activity of elderly individuals. The system described in Appendix 1, characterized by the features described herein. (Note 21) The gripping part is, We estimate the emotions of elderly people and adjust the methods for assessing their health and mental state based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The gripping part is, When assessing health status, the assessment algorithm is optimized by referring to the elderly person's past health data. The system described in Appendix 1, characterized by the features described herein. (Note 23) The gripping part is, When gathering data, customize the data based on the elderly person's living environment and health condition. The system described in Appendix 1, characterized by the features described herein. (Note 24) The gripping part is, The system estimates the emotions of elderly individuals and prioritizes the data to be collected based on these estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The gripping part is, When assessing the situation, the geographical location of the elderly person should be taken into consideration when assessing their health and mental state. The system described in Appendix 1, characterized by the features described herein. (Note 26) The gripping part is, When assessing the situation, we will analyze the social media activities of elderly people and incorporate relevant data into the assessment. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned linkage unit is, The system estimates the emotions of elderly individuals and adjusts the collaboration method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned linkage unit is, During integration, the integration algorithm is optimized by referring to the elderly user's past integration history. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned linkage unit is, During integration, the data is customized based on the elderly person's living environment and health condition. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned linkage unit is, The system estimates the emotions of elderly individuals and determines the priority of collaboration based on these estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned linkage unit is, When collaborating, the geographical location information of elderly individuals will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned linkage unit is, During collaboration, we analyze the social media activity of elderly individuals to improve the accuracy of the collaboration. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned conversation section is, The system estimates the emotions of elderly individuals and adjusts the content and tone of conversation based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 34) The aforementioned conversation section is, During conversations, the conversation algorithm is optimized by referring to the elderly person's past conversation history. The system described in Appendix 2, characterized by the features described herein. (Note 35) The aforementioned conversation section is, During conversations, the content of the conversation is customized based on the elderly person's living environment and health condition. The system described in Appendix 2, characterized by the features described herein. (Note 36) The aforementioned conversation section is, It estimates the emotions of elderly people and determines the priority of conversations based on the estimated emotions of the elderly people. The system described in Appendix 2, characterized by the features described herein. (Note 37) The aforementioned conversation section is, During conversations, the content of the conversation is customized to take into account the geographical location of the elderly person. The system described in Appendix 2, characterized by the features described herein. (Note 38) The aforementioned information provision unit, The system estimates the emotions of elderly individuals and adjusts the content and timing of the information provided based on those estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 39) The aforementioned information provision unit, When providing information, the information provision algorithm is optimized by referring to the elderly person's past information provision history. The system described in Appendix 3, characterized by the features described herein. (Note 40) The aforementioned information provision unit, When providing information, customize the content based on the elderly person's living environment and health condition. The system described in Appendix 3, characterized by the features described herein. (Note 41) The aforementioned information provision unit, The system estimates the emotions of elderly individuals and determines the priority of information provision based on these estimated emotions. The system described in Appendix 3, characterized by the features described herein. (Note 42) The aforementioned information provision unit, When providing information, customize the content of the information to take into account the geographical location of the elderly person. The system described in Appendix 3, characterized by the features described herein. (Note 43) The aforementioned protective part is We estimate the emotions of older adults and adjust privacy protection methods based on the estimated emotions of older adults. The system described in Appendix 4, characterized by the features described herein. (Note 44) The aforementioned protective part is During protection, the protection algorithm is optimized by referring to the elderly person's past privacy protection history. The system described in Appendix 4, characterized by the features described herein. (Note 45) The aforementioned protective part is During protection, protection data is customized based on the elderly person's living environment and health condition. The system described in Appendix 4, characterized by the features described herein. (Note 46) The aforementioned protective part is The system estimates the emotions of older adults and determines privacy protection priorities based on these estimated emotions. The system described in Appendix 4, characterized by the features described herein. (Note 47) The aforementioned protective part is When providing protection, the method of protecting privacy will be customized to take into account the geographical location of the elderly person. The system described in Appendix 4, characterized by the features described herein. (Note 48) The aforementioned protective part is During protection, we analyze the social media activity of elderly individuals to improve the accuracy of privacy protection. The system described in Appendix 4, characterized by the features described herein. [Explanation of Symbols]

[0213] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A learning department that studies the daily behavioral patterns of the elderly, A detection unit that detects anomalies based on the behavioral patterns learned by the learning unit, A unit that grasps the health and mental state based on the abnormality detected by the aforementioned detection unit, The system includes a coordination unit that facilitates coordination with family members, medical institutions, and care services based on the information gathered by the aforementioned information gathering unit. A system characterized by the following features.

2. The facility includes a conversation department that provides conversations tailored to the interests and hobbies of elderly people. The system according to feature 1.

3. It has an information department that provides information on local events and social activities. The system according to feature 1.

4. Equipped with a protective section to protect privacy. The system according to feature 1.

5. The aforementioned learning unit, Perform behavioral pattern analysis using machine learning. The system according to feature 1.

6. The detection unit, Perform predictive analytics to detect anomalies. The system according to feature 1.

7. The gripping part is, Using emotion analysis techniques to understand mental state The system according to feature 1.

8. The aforementioned linkage unit is, To ensure seamless collaboration with family, medical institutions, and care services. The system according to feature 1.

9. The aforementioned learning unit, This system estimates the emotions of elderly individuals and adjusts the learning method of behavioral patterns based on those estimated emotions. The system according to feature 1.

10. The aforementioned learning unit, During the learning process, the learning algorithm is optimized by referring to the past behavioral history of elderly individuals. The system according to feature 1.

Images