System

Abstract

An object of a system according to an embodiment is to reduce anxiety of a care receiver and to reduce a burden on a caregiver.SOLUTION: In general, according to one embodiment, a system includes a camera, generated AI, an avatar, and conversation information. The camera grasps the state of the care-receiver by using the camera. The generating AI analyzes the date acquired by the camera. The avatar talks based on the AI analyzed by the generator. The conversation data repeats the conversation between the caregiver and the person to be cared for.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem that care recipients with impaired cognitive function tend to feel anxious when their caregiver is away, placing a heavy burden on the caregiver.

[0005] The system according to the embodiment aims to reduce the anxiety of the care recipient and the burden on the caregiver. [Means for solving the problem]

[0006] The system according to the embodiment includes a camera, a generation AI, an avatar, and conversation data. The camera uses the camera to grasp the condition of the care recipient. The generation AI analyzes the data acquired by the camera. The avatar speaks to the care recipient based on the data analyzed by the generation AI. The conversation data repeats the conversation between the caregiver and the care recipient. [Effects of the Invention]

[0007] The system according to the embodiment can reduce the anxiety of the care recipient and the burden on the caregiver. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The care support system according to an embodiment of the present invention uses a camera to monitor the condition of the care recipient, analyzes the condition using a generation AI, and then uses an avatar to speak to the care recipient and repeat the conversation data. This allows the care support system to reduce the anxiety of the care recipient and the burden on the caregiver.

[0029] A care support system according to an embodiment includes a camera, a generation AI, an avatar, and conversation data. The camera monitors the condition of a care recipient. For example, the camera monitors the movements and facial expressions of the care recipient in real time. The camera can also record the behavioral patterns of the care recipient. The generation AI analyzes the data acquired by the camera. For example, the generation AI analyzes the condition of the care recipient using a text generation AI (e.g., LLM). The generation AI can also analyze the movements and facial expressions of the care recipient using a multimodal generation AI. The generation AI can also execute an algorithm to detect abnormal behavior. The avatar communicates with the care recipient based on the data analyzed by the generation AI. For example, the avatar communicates with the care recipient in the form of, for example, "Hello, what's wrong?" or "Are you okay?" The avatar can also provide words of encouragement or warnings depending on the condition of the care recipient. The conversation data repeats conversations between the caregiver and the care recipient. For example, the conversation data includes everyday conversations such as, "What did you do today?" or "What did you have for lunch?" Furthermore, conversation data can be generated based on conversation data input in advance. This allows the care support system according to the embodiment to reduce the anxiety of the care recipient and the burden on the caregiver. For example, the caregiver can have time to do laundry, cleaning, or have a quick chat at the entrance. Furthermore, the care recipient can feel secure knowing that someone is always watching over them.

[0030] The camera can simultaneously analyze not only the facial expressions of the care recipient, but also biometric data such as voice and heart rate. For example, the camera can combine camera footage with a microphone to simultaneously analyze the facial expressions and voice of the care recipient. For example, if the care recipient has an anxious expression and a rising tone of voice, it can be determined to be in a higher state of anxiety. The camera can also use a wearable device to acquire biometric data such as heart rate and body temperature in real time, which can be integrated with the camera footage for analysis. For example, a sudden increase in heart rate can be detected as a sign of abnormal behavior. The camera can also analyze the care recipient's movements to detect abnormal movements or the risk of falls. For example, it can analyze camera footage to detect changes in walking patterns or loss of balance and immediately issue an alert. This allows for a more detailed understanding of the care recipient's condition.

[0031] The camera can learn the past behavioral history of the care recipient and build a predictive model for abnormal behavior. For example, the camera collects the care recipient's past behavioral data and uses a machine learning algorithm to build a predictive model for abnormal behavior. For example, it learns the behavioral patterns of past falls and issues an alert if a similar pattern is detected. The camera also analyzes the care recipient's daily behavioral patterns to develop a system that can detect signs of abnormal behavior early. For example, not eating at normal mealtimes is detected as abnormal behavior. The camera also builds a model that predicts the probability of abnormal behavior occurring based on the care recipient's behavioral history. For example, an increase in frequent waking up at night is detected as a sign of a sleep disorder. This improves the accuracy of predicting abnormal behavior.

[0032] To understand the condition of the care recipient, the camera can collect data not only using the camera but also using wearable devices. For example, the camera has the care recipient wear a wearable device and collects data such as heart rate, body temperature, and activity level in real time. For example, a sudden increase in heart rate can be detected as a sign of abnormal behavior. The camera also integrates the data obtained from the wearable device with camera footage to create a system that comprehensively analyzes the condition of the care recipient. For example, it can simultaneously analyze fluctuations in heart rate and changes in facial expression. The camera also monitors the health condition of the care recipient based on the data from the wearable device and issues an alert if an abnormality is detected. For example, an abnormally high body temperature can be detected as a sign of fever. This allows for a more detailed understanding of the care recipient's condition.

[0033] The camera can be linked to IoT devices in the home to monitor the condition of the care recipient. For example, the camera uses a smart speaker to analyze the voice commands of the care recipient and monitor their condition. For example, if it detects an emergency voice such as "help me," it will immediately issue an alert. The camera also uses smart lights to detect the care recipient's movements and identify abnormal behavior. For example, frequent lighting in a room at night could be detected as a sign of a sleep disorder. The camera can also integrate with IoT devices in the home to create a system that comprehensively monitors the condition of the care recipient. For example, it can analyze the opening and closing history of a smart door lock to determine how often the care recipient goes out. In this way, by linking with IoT devices in the home, the condition of the care recipient can be monitored comprehensively.

[0034] The avatar can learn the care recipient's past reaction data and predict the optimal timing to speak to them. For example, the avatar collects the care recipient's past reaction data and uses a machine learning algorithm to build a system that predicts the optimal timing to speak to them. For example, if anxiety increases during a specific time period, the avatar will speak to them at that time. The avatar also evaluates the effectiveness of speaking to them based on the care recipient's reaction data and adjusts the optimal timing. For example, it analyzes behavioral changes after speaking to them and identifies the most effective timing. The avatar also analyzes the care recipient's daily rhythm and predicts the optimal timing to speak to them based on their daily behavioral patterns. For example, speaking to them before or after meals can reduce anxiety. This makes it possible to optimally speak to them based on the care recipient's reactions.

[0035] In addition to the caregiver's avatar, avatars for family and friends can also be prepared, allowing a variety of messages to be spoken to the care recipient. For example, avatars for family and friends can be created to build a system that provides a variety of messages to the care recipient. For example, the avatar can speak in the voice of a family member, saying, "How are you?" The avatar can also select the most appropriate avatar to speak to the care recipient depending on the emotional state of the care recipient. For example, if the care recipient is emotional, the avatar can use the avatar of a friend. The avatar can also use avatars of family and friends to increase the variety of messages that can be spoken to the care recipient. For example, a different avatar can speak to the care recipient on a different day. This provides a variety of messages to the care recipient, increasing their sense of security.

[0036] The avatar can suggest relaxing music and videos to the care recipient. For example, the avatar will build a system that analyzes the emotional state of the care recipient and suggests music to help them relax. For example, classical music will be played if anxiety increases. The avatar will also suggest relaxing videos to the care recipient. For example, videos of natural landscapes or animals will be played. The avatar will also develop a system that suggests the most appropriate relaxation method depending on the emotional state of the care recipient. For example, if the emotional score is high, the avatar will guide them through meditation. This will promote relaxation in the care recipient.

[0037] The generative AI can learn from the care recipient's past conversation data and generate more natural conversations. For example, the generative AI collects past conversation data between the care recipient and caregiver and uses natural language processing technology to learn. For example, it analyzes past conversation patterns and phrases to generate natural conversations. The generative AI also builds a system that generates individualized conversation scenarios based on the care recipient's past conversation data. For example, it reflects the topics and interests that the care recipient often talks about. The generative AI also uses past conversation data to learn the care recipient's speaking style and vocabulary and generates more natural conversations. For example, it incorporates the care recipient's catchphrases and unique expressions. This makes it possible to have natural conversations with the care recipient.

[0038] Generative AI can generate conversation content based on the interests and concerns of the care recipient, improving the quality of the conversation. For example, generative AI will analyze the interests and concerns of the care recipient and build a system that generates conversation content based on that. For example, conversations will be held about the care recipient's favorite hobbies and topics. Generative AI will also identify interests and concerns based on the care recipient's past conversation data and generate conversation scenarios accordingly. For example, topics that the care recipient often talks about will be incorporated. Generative AI will also develop a system that automatically generates conversation content based on the care recipient's interests and concerns. For example, topics related to the care recipient's favorite movies and music will be provided. This will enable conversations based on the care recipient's interests and concerns.

[0039] The generative AI can generate conversations that incorporate not only conversations between caregivers and care recipients, but also the content of television and radio programs that the care recipient likes. For example, the generative AI can analyze the content of television and radio programs that the care recipient likes and build a system that generates conversation content based on that. For example, it can incorporate topics and episodes from the programs. The generative AI can also incorporate the content of television and radio programs into conversations based on the interests of the care recipient. For example, it can talk about the story of a drama that the care recipient likes. The generative AI can also develop a system that generates conversation scenarios based on the content of programs that the care recipient often watches. For example, it can talk about the latest episode of a program. This makes it possible to have conversations based on the interests of the care recipient.

[0040] The generative AI can generate conversations based on the hobbies and activities that the care recipient has enjoyed in the past, thereby pique their interest. For example, the generative AI will analyze the care recipient's past hobbies and activities and build a system that generates conversation content based on that. For example, the care recipient will talk about their favorite sports or handicrafts. The generative AI will also generate conversation scenarios that pique interest based on the care recipient's past activity history. For example, the care recipient will talk about events or trips they have participated in in the past. The generative AI will also develop a system that automatically generates conversation content based on the care recipient's hobbies and activities. For example, the care recipient will talk about their favorite cooking or gardening. This will enable conversations that pique the care recipient's interest.

[0041] Generative AI can develop algorithms that optimize caregiver schedules while monitoring the condition of the care recipient. For example, generative AI monitors the condition of the care recipient in real time and develops an algorithm that optimizes the caregiver's schedule based on that data. For example, it allows the caregiver to perform other tasks during times when the care recipient is stable. Generative AI also analyzes the behavioral patterns of the care recipient and builds a system that dynamically adjusts the caregiver's schedule. For example, it allows the caregiver to take a break during times when the care recipient is taking a nap. Generative AI also develops a system that automatically generates caregiver schedules based on the condition data of the care recipient. For example, it allows the caregiver to go out during times when the care recipient's condition is stable. This optimizes the caregiver's schedule and enables more efficient care.

[0042] Generative AI can automatically generate reminders and notifications for caregivers based on the condition of the care recipient. For example, generative AI could monitor the condition of the care recipient in real time and build a system that automatically generates reminders and notifications for caregivers based on that data. For example, a notification could be sent when it is time for the care recipient to take their medicine. Generative AI could also analyze the behavioral patterns of the care recipient and develop a system that dynamically adjusts reminders for caregivers. For example, a reminder could be sent when it is time for the care recipient to eat. Generative AI could also build a system that automatically generates notifications for caregivers based on the condition data of the care recipient. For example, a notification could be sent immediately if the care recipient exhibits abnormal behavior. This would allow caregivers to take appropriate action according to the condition of the care recipient.

[0043] To ensure that caregivers have more time, generative AI can build a system that collaborates with other family and friends to share the responsibility of watching over the care recipient. For example, generative AI could build a system that collaborates with other family and friends to share the responsibility of watching over the care recipient. For example, it could automatically generate a schedule for family and friends to take turns watching over the care recipient. Generative AI could also develop a system that shares the care recipient's condition in real time and provides other family and friends with the information they need to watch over the care recipient. For example, it could share the care recipient's emotional state and behavioral patterns. Generative AI could also build a system that suggests countermeasures based on the care recipient's condition when family and friends are watching over the care recipient. For example, if the emotional score is high, it could provide advice on how to relax. This reduces the burden on caregivers and allows them to collaborate with other family and friends to share the responsibility of watching over the care recipient.

[0044] Generative AI can provide a function that allows caregivers to check the condition of the care recipient in real time through a smartphone app even when they are out. For example, generative AI can develop a smartphone app that provides a function that allows caregivers to check the condition of the care recipient in real time even when they are out. For example, camera footage and biometric data can be displayed on the app. Generative AI can also build a system that monitors the condition of the care recipient through a smartphone app and sends an immediate notification if an abnormality is detected. For example, an alert can be issued if a fall is detected. Generative AI can also develop a system that provides countermeasures according to the condition of the care recipient through a smartphone app. For example, if the emotional score is high, advice on how to relax can be displayed. This allows caregivers to check the condition of the care recipient in real time even when they are out.

[0045] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0046] To grasp the condition of the care recipient, the care support system can link not only cameras but also IoT devices in the home. For example, a smart speaker can be used to analyze the voice commands of the care recipient and grasp their condition. For example, if an emergency voice such as "help me" is detected, an alert can be issued immediately. Smart lights can also be used to detect the movements of the care recipient and identify abnormal behavior. For example, frequent lighting in a room at night can be detected as a sign of a sleep disorder. In addition, a system can be built that integrates IoT devices in the home to comprehensively monitor the condition of the care recipient. For example, the opening and closing history of a smart door lock can be analyzed to determine how often the care recipient goes out. In this way, by linking with IoT devices in the home, the condition of the care recipient can be grasped comprehensively.

[0047] To understand the condition of the care recipient, a care support system can collect data not only using cameras but also using wearable devices. For example, the care recipient can wear a wearable device to collect data such as heart rate, body temperature, and activity level in real time. For example, a sudden increase in heart rate can be detected as a sign of abnormal behavior. In addition, data obtained from the wearable device can be integrated with camera footage to create a system that comprehensively analyzes the condition of the care recipient. For example, fluctuations in heart rate and changes in facial expression can be analyzed simultaneously. The health condition of the care recipient can also be monitored based on data from the wearable device, and an alert can be issued if an abnormality is detected. For example, an abnormally high body temperature can be detected as a sign of fever. This allows for a more detailed understanding of the care recipient's condition.

[0048] Care support systems can learn the past behavioral history of care recipients and build a predictive model for abnormal behavior. For example, past behavioral data of care recipients can be collected and a machine learning algorithm can be used to build a predictive model for abnormal behavior. For example, the system can learn behavioral patterns from past falls and issue an alert if a similar pattern is detected. We will also develop a system that analyzes the daily behavioral patterns of care recipients and detects signs of abnormal behavior early on. For example, not eating at normal mealtimes can be detected as abnormal behavior. We will also build a model that predicts the probability of abnormal behavior occurring based on the behavioral history of care recipients. For example, an increase in frequent waking up at night can be detected as a sign of a sleep disorder. This will improve the accuracy of predicting abnormal behavior.

[0049] A care support system can learn the past reaction data of the care recipient and predict the optimal timing to speak to them. For example, a system can be built that collects the past reaction data of the care recipient and uses a machine learning algorithm to predict the optimal timing to speak to them. For example, if anxiety increases at a certain time of day, the system can speak to them at that time. The effectiveness of speaking to them can be evaluated based on the reaction data of the care recipient and the optimal timing can be adjusted. For example, behavioral changes after speaking to them can be analyzed to identify the most effective timing. The system can also analyze the daily rhythm of the care recipient and predict the optimal timing to speak to them based on their daily behavioral patterns. For example, speaking to them before or after meals can reduce anxiety. This makes it possible to optimally speak to them based on their reactions.

[0050] The care support system provides not only the avatar of the caregiver, but also avatars of family and friends, making it possible to provide a variety of messages to the care recipient. For example, a system can be constructed in which avatars of family and friends are created and a variety of messages can be provided to the care recipient. For example, the system could speak to the care recipient in the voice of a family member, saying, "How are you?". The system can also select the most appropriate avatar to speak to depending on the emotional state of the care recipient. For example, if the care recipient is feeling emotional, the avatar of a friend can be used. The avatars of family and friends can also be used to increase the variety of messages that can be spoken to the care recipient. For example, a different avatar could speak to the care recipient on a different day. This provides a variety of messages to the care recipient, increasing their sense of security.

[0051] A care support system can suggest relaxing music and videos to the care recipient. For example, we will build a system that analyzes the emotional state of the care recipient and suggests music to help them relax. For example, classical music can be played if anxiety increases. We will also suggest videos to help the care recipient relax. For example, videos of natural landscapes or animals can be played. We will also develop a system that suggests the most appropriate relaxation method depending on the emotional state of the care recipient. For example, if the emotional score is high, a meditation guide will be provided. This will promote relaxation in the care recipient.

[0052] The processing flow of the first embodiment will be briefly explained below.

[0053] Step 1: The camera monitors the care recipient's condition. For example, the camera can monitor the care recipient's movements and facial expressions in real time and record their behavioral patterns. Step 2: The generation AI analyzes the data captured by the camera. For example, the generation AI can analyze the care recipient's condition using text generation AI (e.g., LLM) or multimodal generation AI, and can also run algorithms to detect abnormal behavior. Step 3: The avatar speaks to the care recipient based on the data analyzed by the AI. For example, the avatar may say, "Hello, what's wrong?" or "Are you OK?" and may also offer words of encouragement or warnings depending on the care recipient's condition. Step 4: The conversation data is used to repeat conversations between the caregiver and the care recipient. For example, the conversation data can be everyday conversations such as "What did you do today?" or "What did you have for lunch?", and conversations with the care recipient can be generated based on previously input conversation data.

[0054] (Example 2) The care support system according to an embodiment of the present invention uses a camera to monitor the condition of the care recipient, analyzes the condition using a generation AI, and then uses an avatar to speak to the care recipient and repeat the conversation data. This allows the care support system to reduce the anxiety of the care recipient and the burden on the caregiver.

[0055] A care support system according to an embodiment includes a camera, a generation AI, an avatar, and conversation data. The camera monitors the condition of a care recipient. For example, the camera monitors the movements and facial expressions of the care recipient in real time. The camera can also record the behavioral patterns of the care recipient. The generation AI analyzes the data acquired by the camera. For example, the generation AI analyzes the condition of the care recipient using a text generation AI (e.g., LLM). The generation AI can also analyze the movements and facial expressions of the care recipient using a multimodal generation AI. The generation AI can also execute an algorithm to detect abnormal behavior. The avatar communicates with the care recipient based on the data analyzed by the generation AI. For example, the avatar communicates with the care recipient in the form of, for example, "Hello, what's wrong?" or "Are you okay?" The avatar can also provide words of encouragement or warnings depending on the condition of the care recipient. The conversation data repeats conversations between the caregiver and the care recipient. For example, the conversation data includes everyday conversations such as, "What did you do today?" or "What did you have for lunch?" Furthermore, conversation data can be generated based on conversation data input in advance. This allows the care support system according to the embodiment to reduce the anxiety of the care recipient and the burden on the caregiver. For example, the caregiver can have time to do laundry, cleaning, or have a quick chat at the entrance. Furthermore, the care recipient can feel secure knowing that someone is always watching over them.

[0056] The camera can simultaneously analyze not only the facial expressions of the care recipient, but also biometric data such as voice and heart rate. For example, the camera can combine camera footage with a microphone to simultaneously analyze the facial expressions and voice of the care recipient. For example, if the care recipient has an anxious expression and a rising tone of voice, it can be determined to be in a higher state of anxiety. The camera can also use a wearable device to acquire biometric data such as heart rate and body temperature in real time, which can be integrated with the camera footage for analysis. For example, a sudden increase in heart rate can be detected as a sign of abnormal behavior. The camera can also analyze the care recipient's movements to detect abnormal movements or the risk of falls. For example, it can analyze camera footage to detect changes in walking patterns or loss of balance and immediately issue an alert. This allows for a more detailed understanding of the care recipient's condition.

[0057] The camera can learn the past behavioral history of the care recipient and build a predictive model for abnormal behavior. For example, the camera collects the care recipient's past behavioral data and uses a machine learning algorithm to build a predictive model for abnormal behavior. For example, it learns the behavioral patterns of past falls and issues an alert if a similar pattern is detected. The camera also analyzes the care recipient's daily behavioral patterns to develop a system that can detect signs of abnormal behavior early. For example, not eating at normal mealtimes is detected as abnormal behavior. The camera also builds a model that predicts the probability of abnormal behavior occurring based on the care recipient's behavioral history. For example, an increase in frequent waking up at night is detected as a sign of a sleep disorder. This improves the accuracy of predicting abnormal behavior.

[0058] The camera uses its emotion estimation function to analyze the emotional state of the care recipient in real time and respond according to changes in emotion. For example, the camera analyzes the care recipient's facial expressions from camera footage and uses an emotion estimation algorithm to grasp their emotional state in real time. For example, it analyzes facial expressions such as smiling and crying and calculates an emotion score. The camera also analyzes the care recipient's voice data and estimates their emotional state from the tone and speed of their voice. For example, if the voice is trembling, it may be determined that the person is feeling strong anxiety or fear. The camera will also develop a system that automatically generates responses according to the care recipient's emotional state based on the emotion estimation data. For example, if anxiety increases, relaxing music may be played. This makes it possible to respond appropriately according to the care recipient's emotional state.

[0059] To understand the condition of the care recipient, the camera can collect data not only using the camera but also using wearable devices. For example, the camera has the care recipient wear a wearable device and collects data such as heart rate, body temperature, and activity level in real time. For example, a sudden increase in heart rate can be detected as a sign of abnormal behavior. The camera also integrates the data obtained from the wearable device with camera footage to create a system that comprehensively analyzes the condition of the care recipient. For example, it can simultaneously analyze fluctuations in heart rate and changes in facial expression. The camera also monitors the health condition of the care recipient based on the data from the wearable device and issues an alert if an abnormality is detected. For example, an abnormally high body temperature can be detected as a sign of fever. This allows for a more detailed understanding of the care recipient's condition.

[0060] The camera can be linked to IoT devices in the home to monitor the condition of the care recipient. For example, the camera uses a smart speaker to analyze the voice commands of the care recipient and monitor their condition. For example, if it detects an emergency voice such as "help me," it will immediately issue an alert. The camera also uses smart lights to detect the care recipient's movements and identify abnormal behavior. For example, frequent lighting in a room at night could be detected as a sign of a sleep disorder. The camera can also integrate with IoT devices in the home to create a system that comprehensively monitors the condition of the care recipient. For example, it can analyze the opening and closing history of a smart door lock to determine how often the care recipient goes out. In this way, by linking with IoT devices in the home, the condition of the care recipient can be monitored comprehensively.

[0061] Using its emotion estimation function, the camera can notify family members and medical staff of the emotional state of the care recipient and encourage appropriate responses. For example, the camera can analyze the emotional state of the care recipient from camera footage in real time and create a system that notifies family members and medical staff of the emotional score. For example, an alert can be issued if the anxiety score is high. The camera can also suggest countermeasures to family members and medical staff based on the emotion estimation data according to the care recipient's emotional state. For example, it can instruct the playing of relaxing music. The camera can also periodically report the emotional state of the care recipient so that family members and medical staff can understand the situation. For example, it can report fluctuations in the emotional score in a weekly report. This enables appropriate responses according to the care recipient's emotional state.

[0062] The avatar can communicate more effectively by changing the tone of voice and speaking style depending on the emotional state of the care recipient. For example, a system will be built in which the avatar analyzes the emotional state of the care recipient and generates a tone of voice and speaking style that corresponds to that emotion. For example, if the care recipient is highly anxious, the avatar will speak in a gentle tone. The avatar will also automatically generate speech content that corresponds to the emotional state of the care recipient based on emotion estimation data. For example, if the care recipient is very sad, the avatar will speak encouraging words. The avatar will also develop a system that adjusts the speed and volume of the voice depending on the emotional state of the care recipient. For example, if the care recipient is excited, the avatar will speak more slowly. This will enable the avatar to communicate appropriately according to the emotional state of the care recipient.

[0063] The avatar can learn the care recipient's past reaction data and predict the optimal timing to speak to them. For example, the avatar collects the care recipient's past reaction data and uses a machine learning algorithm to build a system that predicts the optimal timing to speak to them. For example, if anxiety increases during a specific time period, the avatar will speak to them at that time. The avatar also evaluates the effectiveness of speaking to them based on the care recipient's reaction data and adjusts the optimal timing. For example, it analyzes behavioral changes after speaking to them and identifies the most effective timing. The avatar also analyzes the care recipient's daily rhythm and predicts the optimal timing to speak to them based on their daily behavioral patterns. For example, speaking to them before or after meals can reduce anxiety. This makes it possible to optimally speak to them based on the care recipient's reactions.

[0064] The avatar can use the emotion estimation function to analyze the emotional state of the care recipient and generate words of encouragement based on the emotion. For example, the avatar uses an emotion estimation algorithm to analyze the emotional state of the care recipient in real time and automatically generate words of encouragement based on the results. For example, if the emotion score is high, the avatar may offer words of encouragement. We have also developed a system for generating words of encouragement based on the emotional state of the care recipient. For example, if anxiety increases, the avatar may offer advice on how to relax. We have also developed a system for generating words of encouragement based on the emotion estimation data, creating a words of encouragement scenario based on the emotional state of the care recipient and speaking to the care recipient according to that scenario. For example, the scenario may be dynamically adjusted according to changes in emotion. This allows appropriate words of encouragement to be generated based on the emotional state of the care recipient.

[0065] In addition to the caregiver's avatar, avatars for family and friends can also be prepared, allowing a variety of messages to be spoken to the care recipient. For example, avatars for family and friends can be created to build a system that provides a variety of messages to the care recipient. For example, the avatar can speak in the voice of a family member, saying, "How are you?" The avatar can also select the most appropriate avatar to speak to the care recipient depending on the emotional state of the care recipient. For example, if the care recipient is emotional, the avatar can use the avatar of a friend. The avatar can also use avatars of family and friends to increase the variety of messages that can be spoken to the care recipient. For example, a different avatar can speak to the care recipient on a different day. This provides a variety of messages to the care recipient, increasing their sense of security.

[0066] The avatar can suggest relaxing music and videos to the care recipient. For example, the avatar will build a system that analyzes the emotional state of the care recipient and suggests music to help them relax. For example, classical music will be played if anxiety increases. The avatar will also suggest relaxing videos to the care recipient. For example, videos of natural landscapes or animals will be played. The avatar will also develop a system that suggests the most appropriate relaxation method depending on the emotional state of the care recipient. For example, if the emotional score is high, the avatar will guide them through meditation. This will promote relaxation in the care recipient.

[0067] The avatar can use the emotion estimation function to suggest relaxation methods according to the emotional state of the care recipient. For example, the avatar uses an emotion estimation algorithm to analyze the emotional state of the care recipient in real time and build a system that suggests relaxation methods based on the results. For example, if anxiety increases, the avatar can guide deep breathing. The avatar can also develop a system that suggests relaxation methods according to the emotional state of the care recipient. For example, if the emotion score is high, the avatar can suggest yoga poses. The avatar can also build a system that automatically generates relaxation methods according to the emotional state of the care recipient based on the emotion estimation data. For example, the relaxation method can be dynamically adjusted according to changes in emotion. This allows appropriate relaxation methods to be suggested according to the emotional state of the care recipient.

[0068] The generative AI can learn from the care recipient's past conversation data and generate more natural conversations. For example, the generative AI collects past conversation data between the care recipient and caregiver and uses natural language processing technology to learn. For example, it analyzes past conversation patterns and phrases to generate natural conversations. The generative AI also builds a system that generates individualized conversation scenarios based on the care recipient's past conversation data. For example, it reflects the topics and interests that the care recipient often talks about. The generative AI also uses past conversation data to learn the care recipient's speaking style and vocabulary and generates more natural conversations. For example, it incorporates the care recipient's catchphrases and unique expressions. This makes it possible to have natural conversations with the care recipient.

[0069] Generative AI can generate conversation content based on the interests and concerns of the care recipient, improving the quality of the conversation. For example, generative AI will analyze the interests and concerns of the care recipient and build a system that generates conversation content based on that. For example, conversations will be held about the care recipient's favorite hobbies and topics. Generative AI will also identify interests and concerns based on the care recipient's past conversation data and generate conversation scenarios accordingly. For example, topics that the care recipient often talks about will be incorporated. Generative AI will also develop a system that automatically generates conversation content based on the care recipient's interests and concerns. For example, topics related to the care recipient's favorite movies and music will be provided. This will enable conversations based on the care recipient's interests and concerns.

[0070] The generation AI can use the emotion estimation function to generate conversation content according to the emotional state of the care recipient. For example, the generation AI uses an emotion estimation algorithm to analyze the emotional state of the care recipient in real time and automatically generate conversation content based on the results. For example, if the emotion score is high, it will offer words of encouragement. The generation AI will also develop a system that generates conversation content according to the emotional state of the care recipient. For example, if anxiety increases, it will provide advice on how to relax. The generation AI will also create a conversation scenario according to the emotional state of the care recipient based on the emotion estimation data, and the avatar will conduct the conversation according to that scenario. For example, it will dynamically adjust the scenario according to changes in emotions. This will allow appropriate conversation content to be generated according to the emotional state of the care recipient.

[0071] The generative AI can generate conversations that incorporate not only conversations between caregivers and care recipients, but also the content of television and radio programs that the care recipient likes. For example, the generative AI can analyze the content of television and radio programs that the care recipient likes and build a system that generates conversation content based on that. For example, it can incorporate topics and episodes from the programs. The generative AI can also incorporate the content of television and radio programs into conversations based on the interests of the care recipient. For example, it can talk about the story of a drama that the care recipient likes. The generative AI can also develop a system that generates conversation scenarios based on the content of programs that the care recipient often watches. For example, it can talk about the latest episode of a program. This makes it possible to have conversations based on the interests of the care recipient.

[0072] The generative AI can generate conversations based on the hobbies and activities that the care recipient has enjoyed in the past, thereby pique their interest. For example, the generative AI will analyze the care recipient's past hobbies and activities and build a system that generates conversation content based on that. For example, the care recipient will talk about their favorite sports or handicrafts. The generative AI will also generate conversation scenarios that pique interest based on the care recipient's past activity history. For example, the care recipient will talk about events or trips they have participated in in the past. The generative AI will also develop a system that automatically generates conversation content based on the care recipient's hobbies and activities. For example, the care recipient will talk about their favorite cooking or gardening. This will enable conversations that pique the care recipient's interest.

[0073] The generative AI can use its emotion estimation function to suggest hobbies and activities that correspond to the emotional state of the care recipient. For example, the generative AI uses an emotion estimation algorithm to analyze the emotional state of the care recipient in real time and build a system that suggests hobbies and activities based on the results. For example, if anxiety increases, it will suggest a hobby for relaxation. The generative AI will also develop a system that suggests hobbies and activities that correspond to the emotional state of the care recipient. For example, if the emotion score is high, it will suggest an active activity. The generative AI will also build a system that automatically generates hobbies and activities that correspond to the emotional state of the care recipient based on the emotion estimation data. For example, it will dynamically adjust hobbies and activities according to changes in emotions. This will suggest appropriate hobbies and activities that correspond to the emotional state of the care recipient.

[0074] Generative AI can develop algorithms that optimize caregiver schedules while monitoring the condition of the care recipient. For example, generative AI monitors the condition of the care recipient in real time and develops an algorithm that optimizes the caregiver's schedule based on that data. For example, it allows the caregiver to perform other tasks during times when the care recipient is stable. Generative AI also analyzes the behavioral patterns of the care recipient and builds a system that dynamically adjusts the caregiver's schedule. For example, it allows the caregiver to take a break during times when the care recipient is taking a nap. Generative AI also develops a system that automatically generates caregiver schedules based on the condition data of the care recipient. For example, it allows the caregiver to go out during times when the care recipient's condition is stable. This optimizes the caregiver's schedule and enables more efficient care.

[0075] Generative AI can automatically generate reminders and notifications for caregivers based on the condition of the care recipient. For example, generative AI could monitor the condition of the care recipient in real time and build a system that automatically generates reminders and notifications for caregivers based on that data. For example, a notification could be sent when it is time for the care recipient to take their medicine. Generative AI could also analyze the behavioral patterns of the care recipient and develop a system that dynamically adjusts reminders for caregivers. For example, a reminder could be sent when it is time for the care recipient to eat. Generative AI could also build a system that automatically generates notifications for caregivers based on the condition data of the care recipient. For example, a notification could be sent immediately if the care recipient exhibits abnormal behavior. This would allow caregivers to take appropriate action according to the condition of the care recipient.

[0076] Using emotion estimation functions, the generative AI can adjust the caregiver's schedule according to the emotional state of the care recipient. For example, the generative AI uses an emotion estimation algorithm to analyze the emotional state of the care recipient in real time and build a system to adjust the caregiver's schedule based on the results. For example, if anxiety increases, the caregiver can respond immediately. The generative AI also develops a system to adjust the caregiver's schedule according to the emotional state of the care recipient. For example, if the emotion score is high, the caregiver can spend more time nearby. The generative AI also builds a system that automatically generates a caregiver's schedule according to the emotional state of the care recipient based on emotion estimation data. For example, the schedule can be dynamically adjusted according to changes in emotions. This makes it possible to adjust the schedule appropriately according to the emotional state of the care recipient.

[0077] To ensure that caregivers have more time, generative AI can build a system that collaborates with other family and friends to share the responsibility of watching over the care recipient. For example, generative AI could build a system that collaborates with other family and friends to share the responsibility of watching over the care recipient. For example, it could automatically generate a schedule for family and friends to take turns watching over the care recipient. Generative AI could also develop a system that shares the care recipient's condition in real time and provides other family and friends with the information they need to watch over the care recipient. For example, it could share the care recipient's emotional state and behavioral patterns. Generative AI could also build a system that suggests countermeasures based on the care recipient's condition when family and friends are watching over the care recipient. For example, if the emotional score is high, it could provide advice on how to relax. This reduces the burden on caregivers and allows them to collaborate with other family and friends to share the responsibility of watching over the care recipient.

[0078] Generative AI can provide a function that allows caregivers to check the condition of the care recipient in real time through a smartphone app even when they are out. For example, generative AI can develop a smartphone app that provides a function that allows caregivers to check the condition of the care recipient in real time even when they are out. For example, camera footage and biometric data can be displayed on the app. Generative AI can also build a system that monitors the condition of the care recipient through a smartphone app and sends an immediate notification if an abnormality is detected. For example, an alert can be issued if a fall is detected. Generative AI can also develop a system that provides countermeasures according to the condition of the care recipient through a smartphone app. For example, if the emotional score is high, advice on how to relax can be displayed. This allows caregivers to check the condition of the care recipient in real time even when they are out.

[0079] The generation AI can use its emotion estimation function to suggest rest times for caregivers based on the emotional state of the care recipient. For example, the generation AI uses an emotion estimation algorithm to analyze the emotional state of the care recipient in real time and build a system that suggests rest times for caregivers based on the results. For example, the caregiver takes rest during times when the care recipient is stable. The generation AI also develops a system that suggests rest times for caregivers based on the emotional state of the care recipient. For example, if the emotion score is low, the caregiver's rest time is increased. The generation AI also builds a system that automatically generates rest times for caregivers based on the emotional state of the care recipient based on the emotion estimation data. For example, the rest time is dynamically adjusted according to changes in emotions. This allows appropriate rest times to be suggested based on the emotional state of the care recipient.

[0080] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0081] To grasp the condition of the care recipient, the care support system can link not only cameras but also IoT devices in the home. For example, a smart speaker can be used to analyze the voice commands of the care recipient and grasp their condition. For example, if an emergency voice such as "help me" is detected, an alert can be issued immediately. Smart lights can also be used to detect the movements of the care recipient and identify abnormal behavior. For example, frequent lighting in a room at night can be detected as a sign of a sleep disorder. In addition, a system can be built that integrates IoT devices in the home to comprehensively monitor the condition of the care recipient. For example, the opening and closing history of a smart door lock can be analyzed to determine how often the care recipient goes out. In this way, by linking with IoT devices in the home, the condition of the care recipient can be grasped comprehensively.

[0082] To understand the condition of the care recipient, a care support system can collect data not only using cameras but also using wearable devices. For example, the care recipient can wear a wearable device to collect data such as heart rate, body temperature, and activity level in real time. For example, a sudden increase in heart rate can be detected as a sign of abnormal behavior. In addition, data obtained from the wearable device can be integrated with camera footage to create a system that comprehensively analyzes the condition of the care recipient. For example, fluctuations in heart rate and changes in facial expression can be analyzed simultaneously. The health condition of the care recipient can also be monitored based on data from the wearable device, and an alert can be issued if an abnormality is detected. For example, an abnormally high body temperature can be detected as a sign of fever. This allows for a more detailed understanding of the care recipient's condition.

[0083] Care support systems can learn the past behavioral history of care recipients and build a predictive model for abnormal behavior. For example, past behavioral data of care recipients can be collected and a machine learning algorithm can be used to build a predictive model for abnormal behavior. For example, the system can learn behavioral patterns from past falls and issue an alert if a similar pattern is detected. We will also develop a system that analyzes the daily behavioral patterns of care recipients and detects signs of abnormal behavior early on. For example, not eating at normal mealtimes can be detected as abnormal behavior. We will also build a model that predicts the probability of abnormal behavior occurring based on the behavioral history of care recipients. For example, an increase in frequent waking up at night can be detected as a sign of a sleep disorder. This will improve the accuracy of predicting abnormal behavior.

[0084] The care support system can analyze the emotional state of the care recipient in real time and respond according to changes in emotion. For example, it analyzes the facial expressions of the care recipient from camera footage and uses an emotion estimation algorithm to grasp their emotional state in real time. For example, it analyzes facial expressions such as smiling and crying and calculates an emotion score. It also analyzes the care recipient's voice data and estimates their emotional state from the tone and speed of their voice. For example, if the voice is trembling, it is determined that they are feeling strong anxiety or fear. We will also develop a system that automatically generates responses according to the emotional state of the care recipient based on the emotion estimation data. For example, if anxiety increases, it can play relaxing music. This makes it possible to respond appropriately according to the emotional state of the care recipient.

[0085] A care support system can notify family members and medical staff of the emotional state of the care recipient and encourage appropriate responses. For example, a system can be built that analyzes the emotional state of the care recipient from camera footage in real time and notifies family members and medical staff of the emotional score. For example, an alert can be issued if the anxiety score is high. Furthermore, based on the emotion estimation data, the system can suggest countermeasures to the family members and medical staff according to the emotional state of the care recipient. For example, it can instruct the family members and medical staff to play relaxing music. The emotional state of the care recipient can also be reported periodically so that the family members and medical staff can understand the situation. For example, fluctuations in the emotional score can be reported in a weekly report. This makes it possible to respond appropriately according to the emotional state of the care recipient.

[0086] Care support systems can speak more effectively by changing the tone of voice and speaking style depending on the emotional state of the care recipient. For example, we will build a system that analyzes the emotional state of the care recipient and generates a tone of voice and speaking style that matches that emotion. For example, if the care recipient is highly anxious, the system will speak in a gentler tone. We will also automatically generate speech content that matches the emotional state of the care recipient based on emotion estimation data. For example, if the care recipient is very sad, the system will speak encouraging words. We will also develop a system that adjusts the speed and volume of the voice depending on the emotional state of the care recipient. For example, if the care recipient is excited, the system will speak more slowly. This will make it possible to speak appropriately to the care recipient according to their emotional state.

[0087] A care support system can learn the past reaction data of the care recipient and predict the optimal timing to speak to them. For example, a system can be built that collects the past reaction data of the care recipient and uses a machine learning algorithm to predict the optimal timing to speak to them. For example, if anxiety increases at a certain time of day, the system can speak to them at that time. The effectiveness of speaking to them can be evaluated based on the reaction data of the care recipient and the optimal timing can be adjusted. For example, behavioral changes after speaking to them can be analyzed to identify the most effective timing. The system can also analyze the daily rhythm of the care recipient and predict the optimal timing to speak to them based on their daily behavioral patterns. For example, speaking to them before or after meals can reduce anxiety. This makes it possible to optimally speak to them based on their reactions.

[0088] The care support system can analyze the emotional state of the care recipient and generate words of encouragement that correspond to that emotion. For example, an emotion estimation algorithm can be used to analyze the emotional state of the care recipient in real time, and words of encouragement can be automatically generated based on the results. For example, if the emotional score is high, words of encouragement can be given. We will also develop a system that generates words of encouragement that correspond to the emotional state of the care recipient. For example, if anxiety increases, advice on how to relax can be given. Furthermore, based on the emotion estimation data, a dialogue scenario that corresponds to the emotional state of the care recipient is created, and an avatar will communicate according to that scenario. For example, the scenario can be dynamically adjusted according to changes in emotion. This allows appropriate dialogue to be generated that corresponds to the emotional state of the care recipient.

[0089] The care support system provides not only the avatar of the caregiver, but also avatars of family and friends, making it possible to provide a variety of messages to the care recipient. For example, a system can be constructed in which avatars of family and friends are created and a variety of messages can be provided to the care recipient. For example, the system could speak to the care recipient in the voice of a family member, saying, "How are you?". The system can also select the most appropriate avatar to speak to depending on the emotional state of the care recipient. For example, if the care recipient is feeling emotional, the avatar of a friend can be used. The avatars of family and friends can also be used to increase the variety of messages that can be spoken to the care recipient. For example, a different avatar could speak to the care recipient on a different day. This provides a variety of messages to the care recipient, increasing their sense of security.

[0090] A care support system can suggest relaxing music and videos to the care recipient. For example, we will build a system that analyzes the emotional state of the care recipient and suggests music to help them relax. For example, classical music can be played if anxiety increases. We will also suggest videos to help the care recipient relax. For example, videos of natural landscapes or animals can be played. We will also develop a system that suggests the most appropriate relaxation method depending on the emotional state of the care recipient. For example, if the emotional score is high, a meditation guide will be provided. This will promote relaxation in the care recipient.

[0091] The processing flow of the second embodiment will be briefly explained below.

[0092] Step 1: The camera monitors the care recipient's condition. For example, the camera can monitor the care recipient's movements and facial expressions in real time and record their behavioral patterns. Step 2: The generation AI analyzes the data captured by the camera. For example, the generation AI can analyze the care recipient's condition using text generation AI (e.g., LLM) or multimodal generation AI, and can also run algorithms to detect abnormal behavior. Step 3: The avatar speaks to the care recipient based on the data analyzed by the AI. For example, the avatar may say, "Hello, what's wrong?" or "Are you OK?" and may also offer words of encouragement or warnings depending on the care recipient's condition. Step 4: The conversation data is used to repeat conversations between the caregiver and the care recipient. For example, the conversation data can be everyday conversations such as "What did you do today?" or "What did you have for lunch?", and conversations with the care recipient can be generated based on previously input conversation data.

[0093] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0094] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0095] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0096] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0097] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0098] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0099] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0100] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0101] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0102] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0103] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0104] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0105] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0106] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0107] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0108] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0109] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0110] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0111] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0112] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0113] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0114] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0115] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0118] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0119] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0120] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0121] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0122] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0123] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0125] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0126] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0127] 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.

[0128] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0134] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0135] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0137] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0138] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0139] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0140] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0141] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0142] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0143] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0144] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0145] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0146] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0147] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0148] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0149] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0150] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0151] 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.

[0152] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0153] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0154] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0155] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0156] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0157] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0158] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0159] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0160] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A camera that uses a camera to grasp the condition of the care recipient; A generation AI that analyzes data acquired by the camera; an avatar that speaks out based on the data analyzed by the generating AI; Conversation data that repeats conversations between a caregiver and a care recipient. A system characterized by:

2. The camera is Analyzes not only the facial expressions of the care recipient, but also voice, heart rate, and other biometric data simultaneously 2. The system of claim 1.

3. The camera is Learning the past behavioral history of care recipients and building a predictive model for abnormal behavior 2. The system of claim 1.

4. The camera is Analyze the emotional state of the care recipient in real time and respond accordingly to changes in their emotions 2. The system of claim 1.

5. The camera is To understand the condition of the care recipient, data is collected not only using cameras but also using wearable devices.

2. The system of claim 1.

6. The camera is Linking with IoT devices in the home to monitor the condition of the care recipient 2. The system of claim 1.

7. The camera is Notifying family members and medical staff of the emotional state of the care recipient and encouraging appropriate responses 2. The system of claim 1.

8. The avatar is By changing the tone and manner of speaking depending on the emotional state of the person you are caring for, you can communicate more effectively.

2. The system of claim 1.

Images