System

Abstract

An object of the system according to the embodiment is to reduce a sense of loneliness of an elderly person who lives separately or an elderly person who lives alone and to check a health condition or survival.SOLUTION: A system according to an embodiment includes a generation AI, a speech recognition tool, a health condition grasping unit, a survival checking unit, and a notifying unit. The generated AI reduces loneliness through conversation with the senior citizen. The AI recognition tool analyzes the generated speech and the conversation content of the elderly person. The health condition grasping unit grasps a health condition of the elderly person on the basis of the conversation content. The existence confirmation unit periodically makes a conversation with the elderly person to confirm the existence. The notification unit notifies a family member or a medical institution when an abnormality is detected from the conversation content.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 technologies have had the problem of not being able to adequately alleviate the sense of loneliness felt by elderly people who live far away or alone, or to check their health and well-being.

[0005] The system according to the embodiment aims to reduce the sense of loneliness felt by elderly people who live far away or alone, and to check their health and survival status. [Means for solving the problem]

[0006] The system according to the embodiment comprises a generation AI, a voice recognition tool, a health condition understanding unit, a survival confirmation unit, and a notification unit. The generation AI reduces feelings of loneliness through conversation with the elderly. The voice recognition tool analyzes the content of the conversation between the generation AI and the elderly. The health condition understanding unit understands the health condition of the elderly based on the content of the conversation. The survival confirmation unit periodically talks with the elderly to confirm their survival. The notification unit notifies family members or a medical institution if an abnormality is detected from the content of the conversation. [Effects of the Invention]

[0007] The system according to the embodiment can reduce the sense of loneliness felt by elderly people who live far away or alone, and can check their health and survival status. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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 conversation support system according to an embodiment of the present invention combines a generation AI and a voice recognition tool to provide elderly people with a conversation partner, and also ascertains their health status and confirms their survival based on the content of the conversation. As a result, the conversation support system can reduce the elderly's sense of loneliness and ascertain their health status and confirm their survival.

[0029] A conversation support system according to an embodiment includes a generation AI, a voice recognition tool, a health status monitoring unit, a survival confirmation unit, and a notification unit. The generation AI reduces feelings of loneliness through conversation with the elderly. For example, when an elderly person says, "The weather is nice today," the generation AI responds, "Yes, it's very nice today. Maybe we should go for a walk." The generation AI provides mental care for the elderly through natural conversation. The voice recognition tool analyzes the content of the conversation between the generation AI and the elderly. For example, when an elderly person says, "I haven't had much of an appetite lately," the voice recognition tool analyzes the content and causes the generation AI to generate a response such as, "I see you have no appetite. Is there anything you're worried about?" The health status monitoring unit monitors the elderly's health status based on the content of the conversation. For example, when an elderly person says, "I haven't been sleeping well lately," the health status monitoring unit records that information and monitors changes in their health status. The survival confirmation unit periodically converses with the elderly to check their survival. For example, every morning, it greets them with, "Good morning. How are you today?" and checks their response. The notification unit notifies a family member or a medical institution when an abnormality is detected from the conversation content. For example, if an elderly person says, "I have chest pain," the notification unit notifies the family member or a medical institution of that information and prompts them to take action. As a result, the conversation support system according to the embodiment can reduce the elderly person's sense of loneliness and provide an environment in which they can live with peace of mind by understanding their health condition and confirming their survival.

[0030] The generation AI can learn the elderly person's past conversation history and provide conversations tailored to each individual. The generation AI can, for example, learn the elderly person's past conversation history and provide personalized conversations tailored to each individual. For example, based on the hobbies and family topics that the elderly person has talked about in the past, the generation AI can ask specific questions such as "How are your grandchildren doing these days?" The generation AI can understand the elderly person's interests and concerns based on past conversation history and provide conversations based on that. This allows for more intimate communication by responding to the elderly individually.

[0031] Generative AI can provide topics based on the hobbies and interests of elderly people, increasing the diversity of conversations. For example, generative AI can provide topics based on the hobbies and interests of elderly people. For example, it can ask a question such as, "What kind of flowers have you been growing recently?" to an elderly person whose hobby is gardening. Generative AI can understand the hobbies and interests of elderly people and provide topics based on them. By providing topics based on the hobbies and interests of elderly people, it is possible to increase the diversity of conversations and enrich communication.

[0032] Generative AI can suggest relevant music and videos based on what the elderly person is saying, making conversations more fulfilling. For example, generative AI can suggest relevant music based on what the elderly person is saying. For example, if an elderly person says, "I like old music," the generative AI can suggest, "Shall we play some Showa-era hit songs?" Based on what the elderly person is saying, generative AI can suggest relevant videos. For example, if an elderly person says, "I like traveling," the generative AI can suggest, "Shall we watch a travel documentary?" In this way, conversations can be enriched by suggesting relevant music and videos based on what the elderly person is saying.

[0033] A voice recognition tool can analyze the speaking rate and strength of an elderly person's voice to detect changes in their health condition. For example, a voice recognition tool can analyze the speaking rate of an elderly person to detect changes in their health condition. For example, if their speaking rate slows down, the tool can ask a question such as, "How are you feeling these days?" A voice recognition tool can analyze the strength of an elderly person's voice to detect changes in their health condition. For example, if their voice gets quieter, the tool can ask a question such as, "You seem a little down these days. Are you okay?" In this way, by analyzing the speaking rate and strength of an elderly person's voice, changes in their health condition can be detected early.

[0034] The speech recognition tool allows the generation AI to provide appropriate advice or reminders to the elderly based on the analysis of the conversation content. For example, if an elderly person says, "I haven't had much of an appetite lately," the generation AI can provide advice such as, "Try to eat a well-balanced diet." The speech recognition tool allows the generation AI to provide reminders to the elderly based on the analysis of the conversation content. For example, the generation AI can provide a reminder such as, "Make sure you don't forget to take your medicine." This allows the elderly to receive appropriate advice and reminders, thereby supporting their health management.

[0035] The speech recognition tool can analyze the dialects and accents of the elderly and respond to expressions specific to the region. For example, the speech recognition tool can analyze the dialects and respond to expressions specific to the region. For example, to an elderly person speaking Kansai dialect, it can respond with, "It's a nice day today." The speech recognition tool can analyze the accents of the elderly and respond to expressions specific to the region. For example, to an elderly person speaking Tohoku dialect, it can respond with, "It's cold today." This allows for more natural communication by responding to the dialects and accents of the elderly.

[0036] Based on the analysis of the conversation content, the speech recognition tool's generation AI provides health-related quizzes or games to the elderly, allowing them to manage their health while having fun. Based on the analysis of the conversation content, the speech recognition tool's generation AI provides health-related quizzes to the elderly. For example, it might ask a question such as, "How many minutes of walking per day is ideal?" Based on the analysis of the conversation content, the speech recognition tool's generation AI provides health-related games to the elderly. For example, it might suggest, "Let's play a brain training game together." This allows the elderly to manage their health while having fun.

[0037] Generative AI can monitor the conversation content of elderly people over the long term and analyze trends in their health condition. Generative AI can, for example, monitor the conversation content of elderly people over the long term and analyze trends in their health condition. For example, it can analyze the conversation content from the past few months to identify changes in their physical condition. Generative AI can analyze trends in the elderly's health condition based on the conversation content and notify them if an abnormality is detected. In this way, by analyzing trends in the elderly's health condition, it can support long-term health management.

[0038] The generating AI can provide health advice or reminders to the elderly based on the content of the conversation. For example, the generating AI can provide health advice to the elderly based on the content of the conversation. For example, if an elderly person says, "I haven't been getting enough exercise lately," the generating AI can provide advice such as, "Try to walk a little bit every day." The generating AI can provide reminders to the elderly based on the content of the conversation. For example, it can provide a reminder such as, "Don't forget to take your medicine." In this way, by providing health advice and reminders to the elderly, it can assist in health management.

[0039] Generative AI can analyze the content of conversations of elderly people and automatically generate reports on their health status to provide to their families or medical institutions. Generative AI can, for example, analyze the content of conversations of elderly people and automatically generate reports on their health status. For example, it can create a report summarizing changes in their health status based on their daily conversations. Generative AI can provide the reports on their health status to their families and medical institutions. For example, it can send the reports via email or a dedicated app. This allows for the automatic generation of reports on the elderly person's health status and the provision of these reports to their families and medical institutions, thereby supporting appropriate responses.

[0040] The generation AI can suggest health-related exercises or stretches to the elderly based on the content of the conversation. The generation AI can suggest health-related exercises to the elderly based on the content of the conversation. For example, if an elderly person says, "I haven't been getting enough exercise lately," the generation AI can suggest an exercise such as, "Try walking a little bit every day." The generation AI can suggest stretches to the elderly based on the content of the conversation. For example, if an elderly person says, "I have severe shoulder stiffness," the generation AI can suggest, "Try some simple stretches." In this way, by suggesting health-related exercises and stretches to the elderly, it can support health management.

[0041] The generative AI can learn the response patterns of the elderly and respond quickly if an abnormality is detected. The generative AI can, for example, learn the response patterns of the elderly and respond quickly if an abnormality is detected. For example, if the response is different from the usual one, it will ask a question such as "Is there a problem?" The generative AI can detect abnormalities based on the response patterns of the elderly and respond quickly. In this way, safety can be ensured by learning the response patterns of the elderly and responding quickly if an abnormality is detected.

[0042] When checking whether an elderly person is alive, the generation AI can ask simple questions to the elderly person and analyze their responses to check their health condition. For example, when checking whether an elderly person is alive, the generation AI can ask simple questions to the elderly person and analyze their responses to check their health condition. For example, it might ask, "How are you feeling lately?" The generation AI checks the elderly person's health condition through simple questions and notifies them if any abnormalities are detected. This makes it possible to support a quick response by checking the elderly person's health condition through simple questions.

[0043] The generating AI can learn the lifestyle rhythms of the elderly and check whether they are alive at the optimal time. The generating AI can, for example, learn the lifestyle rhythms of the elderly and check whether they are alive at the optimal time. For example, every morning when they wake up, it could say, "Good morning. How are you today?" The generating AI checks whether they are alive at the optimal time based on the elderly's lifestyle rhythm. This allows for more effective support by checking whether they are alive at the optimal time based on the elderly's lifestyle rhythm.

[0044] When checking whether an elderly person is alive, the generation AI can ask questions about everyday events to confirm their survival through conversation. For example, when checking whether an elderly person is alive, the generation AI can ask questions about everyday events to confirm their survival through conversation. For example, it can ask questions such as, "What did you do today?" The generation AI can ask questions about everyday events to confirm the elderly person's survival through conversation. This can support a quick response by asking questions about everyday events to confirm the elderly person's survival through conversation.

[0045] The generation AI can analyze the content of conversations between elderly people and provide a detailed report to family members or medical institutions if an abnormality is detected. For example, the generation AI can analyze the content of conversations between elderly people and provide a detailed report to family members or medical institutions if an abnormality is detected. For example, if an elderly person says, "I've been having chest pains lately," the information can be compiled into a report and notified. The generation AI can provide a detailed report to family members or medical institutions if an abnormality is detected. This allows the generation AI to analyze the content of conversations between elderly people and provide a detailed report if an abnormality is detected, thereby supporting a rapid response.

[0046] When notifying, the generative AI can comprehensively evaluate the health and emotional state of the elderly person and suggest an appropriate response. For example, when notifying, the generative AI can comprehensively evaluate the health and emotional state of the elderly person and suggest an appropriate response. For example, if an elderly person says, "I've been feeling unwell lately," the generative AI could suggest, "I recommend that you see a doctor." The generative AI comprehensively evaluates the health and emotional state of the elderly person and suggests an appropriate response based on that. This makes it possible to comprehensively evaluate the health and emotional state of the elderly person and suggest an appropriate response, thereby supporting rapid response.

[0047] The generative AI can analyze the content of conversations between elderly people and notify family members or medical institutions in real time if an abnormality is detected. The generative AI can, for example, analyze the content of conversations between elderly people and notify family members or medical institutions in real time if an abnormality is detected. For example, it can notify family members or medical institutions in real time if an elderly person says, "I've been having chest pains lately." The generative AI supports a rapid response by notifying in real time if an abnormality is detected. This allows the generative AI to support a rapid response by analyzing the content of conversations between elderly people and notifying in real time if an abnormality is detected.

[0048] When notifying, the generating AI can visualize the health and emotional state of the elderly person and provide it to their family or medical institution. For example, when notifying, the generating AI can visualize the health and emotional state of the elderly person and provide it to their family or medical institution. For example, it can notify them by graphing changes in their health state. The generating AI can visualize the health and emotional state and provide it to their family or medical institution. This can help provide information that is easier to understand by visualizing the health and emotional state of the elderly person.

[0049] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0050] The conversation support system can also provide event information based on the hobbies and interests of elderly people. For example, an elderly person who enjoys gardening can be provided with information about nearby flower exhibitions and gardening workshops. An elderly person who enjoys music can be provided with information about local concerts and music events. This will make it easier for elderly people to participate in social activities and contribute to reducing feelings of loneliness.

[0051] The conversation support system can also record the elderly person's diet and provide advice on nutritional balance. For example, it can record daily meals and suggest balanced meals under the supervision of a nutritionist. If a specific nutrient is lacking, it can suggest ingredients and recipes to supplement that nutrient. This can provide more effective support for the elderly's health management.

[0052] The conversation support system can also record the elderly's exercise habits and suggest appropriate exercise programs. For example, it can record the number of steps taken each day and the amount of exercise time, and if a lack of exercise is detected, it can suggest simple exercises and stretches. It can also provide exercise programs to strengthen specific muscle groups. This can support the elderly's exercise habits and contribute to maintaining their health.

[0053] The conversation support system can also record the elderly's sleep patterns and provide advice to improve sleep quality. For example, it can record the daily sleep duration and quality, and if sleep deprivation is detected, it can suggest relaxing music or meditation. It can also provide advice on improving bedtime routines. This can improve the quality of sleep for the elderly and support their overall health.

[0054] The conversation support system can also provide information on online communities and support groups to further strengthen social connections among seniors. For example, it can provide information on online forums where people with similar interests gather, or local support groups. It can also provide information on regularly scheduled online events and workshops. This can help seniors build social connections and reduce feelings of loneliness.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The generative AI reduces feelings of loneliness through conversation with the elderly. For example, if an elderly person says, "The weather is nice today," the generative AI will respond, "Yes, it's very nice today. Maybe it would be nice to go for a walk." The generative AI provides mental care for the elderly through natural conversation. Step 2: The voice recognition tool analyzes the conversation between the generation AI and the elderly person. For example, if an elderly person says, "I haven't had much of an appetite lately," the voice recognition tool analyzes the content and has the generation AI generate a response such as, "I see you have no appetite. Is there anything you're worried about?" Step 3: The health condition monitoring unit monitors the health condition of the elderly person based on the content of the conversation. For example, if an elderly person says, "I haven't been sleeping well lately," the health condition monitoring unit records that information and monitors any changes in their health condition. Step 4: The survival confirmation unit periodically talks with the elderly person to confirm their survival. For example, every morning it greets them with a greeting such as "Good morning. How are you today?" and checks for a response from the elderly person. Step 5: If the notification unit detects any abnormalities in the conversation, it notifies the family or a medical institution. For example, if an elderly person says, "I have chest pain," the notification unit notifies the family or a medical institution of that information and promptly takes action.

[0057] (Example 2) The conversation support system according to an embodiment of the present invention combines a generation AI and a voice recognition tool to provide elderly people with a conversation partner, and also ascertains their health status and confirms their survival based on the content of the conversation. As a result, the conversation support system can reduce the elderly's sense of loneliness and ascertain their health status and confirm their survival.

[0058] A conversation support system according to an embodiment includes a generation AI, a voice recognition tool, a health status monitoring unit, a survival confirmation unit, and a notification unit. The generation AI reduces feelings of loneliness through conversation with the elderly. For example, when an elderly person says, "The weather is nice today," the generation AI responds, "Yes, it's very nice today. Maybe we should go for a walk." The generation AI provides mental care for the elderly through natural conversation. The voice recognition tool analyzes the content of the conversation between the generation AI and the elderly. For example, when an elderly person says, "I haven't had much of an appetite lately," the voice recognition tool analyzes the content and causes the generation AI to generate a response such as, "I see you have no appetite. Is there anything you're worried about?" The health status monitoring unit monitors the elderly's health status based on the content of the conversation. For example, when an elderly person says, "I haven't been sleeping well lately," the health status monitoring unit records that information and monitors changes in their health status. The survival confirmation unit periodically converses with the elderly to check their survival. For example, every morning, it greets them with, "Good morning. How are you today?" and checks their response. The notification unit notifies a family member or a medical institution when an abnormality is detected from the conversation content. For example, if an elderly person says, "I have chest pain," the notification unit notifies the family member or a medical institution of that information and prompts them to take action. As a result, the conversation support system according to the embodiment can reduce the elderly person's sense of loneliness and provide an environment in which they can live with peace of mind by understanding their health condition and confirming their survival.

[0059] The generation AI can learn the elderly person's past conversation history and provide conversations tailored to each individual. The generation AI can, for example, learn the elderly person's past conversation history and provide personalized conversations tailored to each individual. For example, based on the hobbies and family topics that the elderly person has talked about in the past, the generation AI can ask specific questions such as "How are your grandchildren doing these days?" The generation AI can understand the elderly person's interests and concerns based on past conversation history and provide conversations based on that. This allows for more intimate communication by responding to the elderly individually.

[0060] The generation AI can analyze changes in the elderly person's tone of voice and speaking style, detect changes in their emotions, and adjust the response accordingly. For example, the generation AI can analyze changes in the elderly person's tone of voice and speaking style to detect changes in their emotions. For example, if the elderly person's voice is low, the generation AI can respond with something like, "Is there anything you're worried about?" The generation AI can estimate the elderly person's emotions based on changes in tone of voice and speaking style, and generate a response accordingly. This makes it possible to provide a response that is appropriate to the elderly person's emotions, thereby achieving more appropriate communication.

[0061] The generative AI can use its emotion estimation function to estimate the emotional state of an elderly person in real time and generate conversations that elicit positive emotions. For example, the generative AI can use its emotion estimation function to estimate the emotional state of an elderly person in real time and generate conversations that elicit positive emotions. For example, if the elderly person is feeling down, it can ask questions such as, "Did anything fun happen today?" The generative AI uses its emotion estimation function to analyze the elderly person's emotions and provide positive conversations accordingly. This can support the mental health of the elderly by keeping their emotions positive.

[0062] Generative AI can provide topics based on the hobbies and interests of elderly people, increasing the diversity of conversations. For example, generative AI can provide topics based on the hobbies and interests of elderly people. For example, it can ask a question such as, "What kind of flowers have you been growing recently?" to an elderly person whose hobby is gardening. Generative AI can understand the hobbies and interests of elderly people and provide topics based on them. By providing topics based on the hobbies and interests of elderly people, it is possible to increase the diversity of conversations and enrich communication.

[0063] Generative AI can suggest relevant music and videos based on what the elderly person is saying, making conversations more fulfilling. For example, generative AI can suggest relevant music based on what the elderly person is saying. For example, if an elderly person says, "I like old music," the generative AI can suggest, "Shall we play some Showa-era hit songs?" Based on what the elderly person is saying, generative AI can suggest relevant videos. For example, if an elderly person says, "I like traveling," the generative AI can suggest, "Shall we watch a travel documentary?" In this way, conversations can be enriched by suggesting relevant music and videos based on what the elderly person is saying.

[0064] The generative AI can use its emotion estimation function to analyze the emotions expressed when an elderly person speaks and suggest music or videos that match the emotion. For example, the generative AI can use its emotion estimation function to analyze the emotions expressed when an elderly person speaks and suggest music that matches the emotion. For example, if the elderly person is feeling depressed, it can suggest, "Shall I play some relaxing music?" The generative AI can use its emotion estimation function to analyze the emotions expressed when an elderly person speaks and suggest videos that match the emotion. For example, if the elderly person is feeling excited, it can suggest, "Shall we watch a fun movie?" In this way, by suggesting music or videos that match the elderly person's emotions, it is possible to stabilize their emotions.

[0065] A voice recognition tool can analyze the speaking rate and strength of an elderly person's voice to detect changes in their health condition. For example, a voice recognition tool can analyze the speaking rate of an elderly person to detect changes in their health condition. For example, if their speaking rate slows down, the tool can ask a question such as, "How are you feeling these days?" A voice recognition tool can analyze the strength of an elderly person's voice to detect changes in their health condition. For example, if their voice gets quieter, the tool can ask a question such as, "You seem a little down these days. Are you okay?" In this way, by analyzing the speaking rate and strength of an elderly person's voice, changes in their health condition can be detected early.

[0066] The speech recognition tool allows the generation AI to provide appropriate advice or reminders to the elderly based on the analysis of the conversation content. For example, if an elderly person says, "I haven't had much of an appetite lately," the generation AI can provide advice such as, "Try to eat a well-balanced diet." The speech recognition tool allows the generation AI to provide reminders to the elderly based on the analysis of the conversation content. For example, the generation AI can provide a reminder such as, "Make sure you don't forget to take your medicine." This allows the elderly to receive appropriate advice and reminders, thereby supporting their health management.

[0067] The voice recognition tool can use an emotion estimation function to analyze the emotional state of the elderly person from the content of the conversation and generate a response that corresponds to the emotion. For example, the voice recognition tool can use the emotion estimation function to analyze the emotional state of the elderly person from the content of the conversation and generate a response that corresponds to the emotion. For example, if the elderly person is feeling depressed, the voice recognition tool can respond with, "Is there anything you're worried about?" The voice recognition tool can use the emotion estimation function to analyze the emotional state of the elderly person from the content of the conversation and generate a response that corresponds to the emotion. For example, if the elderly person is feeling excited, the voice recognition tool can respond with, "You seem to be in good spirits today." In this way, by generating a response that corresponds to the elderly person's emotional state, more appropriate communication can be achieved.

[0068] The speech recognition tool can analyze the dialects and accents of the elderly and respond to expressions specific to the region. For example, the speech recognition tool can analyze the dialects and respond to expressions specific to the region. For example, to an elderly person speaking Kansai dialect, it can respond with, "It's a nice day today." The speech recognition tool can analyze the accents of the elderly and respond to expressions specific to the region. For example, to an elderly person speaking Tohoku dialect, it can respond with, "It's cold today." This allows for more natural communication by responding to the dialects and accents of the elderly.

[0069] Based on the analysis of the conversation content, the speech recognition tool's generation AI provides health-related quizzes or games to the elderly, allowing them to manage their health while having fun. Based on the analysis of the conversation content, the speech recognition tool's generation AI provides health-related quizzes to the elderly. For example, it might ask a question such as, "How many minutes of walking per day is ideal?" Based on the analysis of the conversation content, the speech recognition tool's generation AI provides health-related games to the elderly. For example, it might suggest, "Let's play a brain training game together." This allows the elderly to manage their health while having fun.

[0070] The voice recognition tool can use an emotion estimation function to analyze the emotions of the elderly person from the content of the conversation and provide a quiz or game that corresponds to the emotion. The voice recognition tool, for example, uses the emotion estimation function to analyze the emotions of the elderly person from the content of the conversation and provide a quiz that corresponds to the emotion. For example, if the elderly person is feeling depressed, it can suggest a "relaxing quiz." The voice recognition tool uses the emotion estimation function to analyze the emotions of the elderly person from the content of the conversation and provide a game that corresponds to the emotion. For example, if the elderly person is feeling excited, it can suggest, "Let's play a fun game together." In this way, by providing quizzes and games that correspond to the emotions of the elderly person, it is possible to stabilize their emotions while having fun.

[0071] Generative AI can monitor the conversation content of elderly people over the long term and analyze trends in their health condition. Generative AI can, for example, monitor the conversation content of elderly people over the long term and analyze trends in their health condition. For example, it can analyze the conversation content from the past few months to identify changes in their physical condition. Generative AI can analyze trends in the elderly's health condition based on the conversation content and notify them if an abnormality is detected. In this way, by analyzing trends in the elderly's health condition, it can support long-term health management.

[0072] The generating AI can provide health advice or reminders to the elderly based on the content of the conversation. For example, the generating AI can provide health advice to the elderly based on the content of the conversation. For example, if an elderly person says, "I haven't been getting enough exercise lately," the generating AI can provide advice such as, "Try to walk a little bit every day." The generating AI can provide reminders to the elderly based on the content of the conversation. For example, it can provide a reminder such as, "Don't forget to take your medicine." In this way, by providing health advice and reminders to the elderly, it can assist in health management.

[0073] The generation AI can use the emotion estimation function to analyze the emotional state of the elderly and provide health advice that corresponds to the emotion. For example, the generation AI can use the emotion estimation function to analyze the emotional state of the elderly and provide health advice that corresponds to the emotion. For example, if the elderly is feeling depressed, the generation AI can provide advice such as "Try doing something to relax." The generation AI can use the emotion estimation function to analyze the emotions of the elderly and provide health advice that corresponds to the emotion. This can support more appropriate health management by providing health advice that corresponds to the elderly's emotional state.

[0074] Generative AI can analyze the content of conversations of elderly people and automatically generate reports on their health status to provide to their families or medical institutions. Generative AI can, for example, analyze the content of conversations of elderly people and automatically generate reports on their health status. For example, it can create a report summarizing changes in their health status based on their daily conversations. Generative AI can provide the reports on their health status to their families and medical institutions. For example, it can send the reports via email or a dedicated app. This allows for the automatic generation of reports on the elderly person's health status and the provision of these reports to their families and medical institutions, thereby supporting appropriate responses.

[0075] The generation AI can suggest health-related exercises or stretches to the elderly based on the content of the conversation. The generation AI can suggest health-related exercises to the elderly based on the content of the conversation. For example, if an elderly person says, "I haven't been getting enough exercise lately," the generation AI can suggest an exercise such as, "Try walking a little bit every day." The generation AI can suggest stretches to the elderly based on the content of the conversation. For example, if an elderly person says, "I have severe shoulder stiffness," the generation AI can suggest, "Try some simple stretches." In this way, by suggesting health-related exercises and stretches to the elderly, it can support health management.

[0076] The generation AI can use the emotion estimation function to analyze the emotional state of the elderly person and suggest exercises or stretches that correspond to the emotion. For example, the generation AI can use the emotion estimation function to analyze the emotional state of the elderly person and suggest exercises that correspond to the emotion. For example, if the elderly person is feeling depressed, it can suggest, "Try some relaxing yoga." The generation AI can use the emotion estimation function to analyze the emotional state of the elderly person and suggest stretches that correspond to the emotion. For example, if the elderly person is feeling excited, it can suggest, "Try some energetic stretches." This can support more appropriate health management by suggesting exercises and stretches that correspond to the elderly person's emotional state.

[0077] The generative AI can learn the response patterns of the elderly and respond quickly if an abnormality is detected. The generative AI can, for example, learn the response patterns of the elderly and respond quickly if an abnormality is detected. For example, if the response is different from the usual one, it will ask a question such as "Is there a problem?" The generative AI can detect abnormalities based on the response patterns of the elderly and respond quickly. In this way, safety can be ensured by learning the response patterns of the elderly and responding quickly if an abnormality is detected.

[0078] When checking whether an elderly person is alive, the generation AI can ask simple questions to the elderly person and analyze their responses to check their health condition. For example, when checking whether an elderly person is alive, the generation AI can ask simple questions to the elderly person and analyze their responses to check their health condition. For example, it might ask, "How are you feeling lately?" The generation AI checks the elderly person's health condition through simple questions and notifies them if any abnormalities are detected. This makes it possible to support a quick response by checking the elderly person's health condition through simple questions.

[0079] The generation AI can use the emotion estimation function to analyze the emotional state of the elderly person and adjust the method of confirming their survival according to their emotions. For example, the generation AI can use the emotion estimation function to analyze the emotional state of the elderly person and adjust the method of confirming their survival according to their emotions. For example, if the elderly person is feeling depressed, it can ask a question such as "Is there anything you are worried about?" The generation AI can use the emotion estimation function to analyze the elderly person's emotions and adjust the method of confirming their survival accordingly. This can support more appropriate responses by adjusting the method of confirming their survival according to the elderly person's emotional state.

[0080] The generating AI can learn the lifestyle rhythms of the elderly and check whether they are alive at the optimal time. The generating AI can, for example, learn the lifestyle rhythms of the elderly and check whether they are alive at the optimal time. For example, every morning when they wake up, it could say, "Good morning. How are you today?" The generating AI checks whether they are alive at the optimal time based on the elderly's lifestyle rhythm. This allows for more effective support by checking whether they are alive at the optimal time based on the elderly's lifestyle rhythm.

[0081] When checking whether an elderly person is alive, the generation AI can ask questions about everyday events to confirm their survival through conversation. For example, when checking whether an elderly person is alive, the generation AI can ask questions about everyday events to confirm their survival through conversation. For example, it can ask questions such as, "What did you do today?" The generation AI can ask questions about everyday events to confirm the elderly person's survival through conversation. This can support a quick response by asking questions about everyday events to confirm the elderly person's survival through conversation.

[0082] The generation AI can use the emotion estimation function to analyze the emotional state of the elderly person and ask questions about daily events that correspond to their emotions. For example, the generation AI can use the emotion estimation function to analyze the emotional state of the elderly person and ask questions about daily events that correspond to their emotions. For example, if the elderly person is feeling depressed, it can ask questions such as, "Did anything fun happen today?" The generation AI can use the emotion estimation function to analyze the elderly person's emotions and ask questions about daily events that correspond to their emotions. This allows for more appropriate responses by asking questions about daily events that correspond to the elderly person's emotional state.

[0083] The generation AI can analyze the content of conversations between elderly people and provide a detailed report to family members or medical institutions if an abnormality is detected. For example, the generation AI can analyze the content of conversations between elderly people and provide a detailed report to family members or medical institutions if an abnormality is detected. For example, if an elderly person says, "I've been having chest pains lately," the information can be compiled into a report and notified. The generation AI can provide a detailed report to family members or medical institutions if an abnormality is detected. This allows the generation AI to analyze the content of conversations between elderly people and provide a detailed report if an abnormality is detected, thereby supporting a rapid response.

[0084] When notifying, the generative AI can comprehensively evaluate the health and emotional state of the elderly person and suggest an appropriate response. For example, when notifying, the generative AI can comprehensively evaluate the health and emotional state of the elderly person and suggest an appropriate response. For example, if an elderly person says, "I've been feeling unwell lately," the generative AI could suggest, "I recommend that you see a doctor." The generative AI comprehensively evaluates the health and emotional state of the elderly person and suggests an appropriate response based on that. This makes it possible to comprehensively evaluate the health and emotional state of the elderly person and suggest an appropriate response, thereby supporting rapid response.

[0085] The generation AI can use the emotion estimation function to analyze the emotional state of the elderly person and adjust the notification content according to their emotions. For example, the generation AI can use the emotion estimation function to analyze the emotional state of the elderly person and adjust the notification content according to their emotions. For example, if the elderly person is feeling depressed, the generation AI can send a notification such as "You have been feeling emotionally unstable recently." The generation AI can use the emotion estimation function to analyze the elderly person's emotions and adjust the notification content accordingly. This allows the generation AI to support more appropriate responses by adjusting the notification content according to the elderly person's emotional state.

[0086] The generative AI can analyze the content of conversations between elderly people and notify family members or medical institutions in real time if an abnormality is detected. The generative AI can, for example, analyze the content of conversations between elderly people and notify family members or medical institutions in real time if an abnormality is detected. For example, it can notify family members or medical institutions in real time if an elderly person says, "I've been having chest pains lately." The generative AI supports a rapid response by notifying in real time if an abnormality is detected. This allows the generative AI to support a rapid response by analyzing the content of conversations between elderly people and notifying in real time if an abnormality is detected.

[0087] When notifying, the generating AI can visualize the health and emotional state of the elderly person and provide it to their family or medical institution. For example, when notifying, the generating AI can visualize the health and emotional state of the elderly person and provide it to their family or medical institution. For example, it can notify them by graphing changes in their health state. The generating AI can visualize the health and emotional state and provide it to their family or medical institution. This can help provide information that is easier to understand by visualizing the health and emotional state of the elderly person.

[0088] The generation AI can use the emotion estimation function to analyze the emotional state of the elderly person and provide visualized notification content according to the emotion. For example, the generation AI can use the emotion estimation function to analyze the emotional state of the elderly person and provide visualized notification content according to the emotion. For example, if the elderly person is feeling depressed, the generation AI can send a notification such as "You have been feeling emotionally unstable recently." The generation AI can use the emotion estimation function to analyze the elderly person's emotions and provide visualized notification content according to the emotion. This can support more appropriate responses by providing visualized notification content according to the elderly person's emotional state.

[0089] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0090] The conversation support system can also provide event information based on the hobbies and interests of elderly people. For example, an elderly person who enjoys gardening can be provided with information about nearby flower exhibitions and gardening workshops. An elderly person who enjoys music can be provided with information about local concerts and music events. This will make it easier for elderly people to participate in social activities and contribute to reducing feelings of loneliness.

[0091] The conversation support system can also record the elderly person's diet and provide advice on nutritional balance. For example, it can record daily meals and suggest balanced meals under the supervision of a nutritionist. If a specific nutrient is lacking, it can suggest ingredients and recipes to supplement that nutrient. This can provide more effective support for the elderly's health management.

[0092] The conversation support system can also record the elderly's exercise habits and suggest appropriate exercise programs. For example, it can record the number of steps taken each day and the amount of exercise time, and if a lack of exercise is detected, it can suggest simple exercises and stretches. It can also provide exercise programs to strengthen specific muscle groups. This can support the elderly's exercise habits and contribute to maintaining their health.

[0093] The conversation support system can also record the elderly's sleep patterns and provide advice to improve sleep quality. For example, it can record the daily sleep duration and quality, and if sleep deprivation is detected, it can suggest relaxing music or meditation. It can also provide advice on improving bedtime routines. This can improve the quality of sleep for the elderly and support their overall health.

[0094] The conversation support system can also provide information on online communities and support groups to further strengthen social connections among seniors. For example, it can provide information on online forums where people with similar interests gather, or local support groups. It can also provide information on regularly scheduled online events and workshops. This can help seniors build social connections and reduce feelings of loneliness.

[0095] The conversation support system can use its emotion estimation function to analyze the emotional state of the elderly person and suggest relaxation methods according to their emotions. For example, if the elderly person is feeling depressed, the system can suggest, "Take a deep breath and relax." If the elderly person is feeling excited, the system can suggest, "Listen to relaxing music." In this way, by providing relaxation methods according to the elderly person's emotional state, it is possible to support their mental health.

[0096] The conversation support system uses its emotion estimation function to analyze the emotional state of the elderly person and suggest hobbies and activities that correspond to their emotions. For example, if the elderly person is feeling down, the system may suggest "Let's try drawing a picture." If the elderly person is feeling excited, the system may suggest "Let's go for a walk." This allows the system to support the elderly person's mental health by offering hobbies and activities that correspond to their emotional state.

[0097] The conversation support system uses its emotion estimation function to analyze the emotional state of the elderly person and make meal suggestions based on that emotion. For example, if the person is feeling down, the system can suggest, "Drink some relaxing herbal tea." If the person is feeling excited, the system can suggest, "Eat an energizing meal." This makes it possible to support the mental health of the elderly by making meal suggestions based on their emotional state.

[0098] The conversation support system can use its emotion estimation function to analyze the emotional state of the elderly person and suggest an exercise program that matches their emotions. For example, if the elderly person is feeling down, the system can suggest, "Try some relaxing yoga." If the elderly person is feeling excited, the system can suggest, "Try some energetic exercise." This allows the system to support the elderly person's mental health by providing an exercise program that matches their emotional state.

[0099] The conversation support system can use its emotion estimation function to analyze the emotional state of the elderly person and provide sleep advice according to their emotions. For example, if the person is feeling depressed, it can suggest, "Try listening to some relaxing music." If the person is feeling excited, it can also suggest, "Take a deep breath and relax." In this way, by providing sleep advice according to the elderly person's emotional state, it is possible to support their mental health.

[0100] The processing flow of the second embodiment will be briefly explained below.

[0101] Step 1: The generative AI reduces feelings of loneliness through conversation with the elderly. For example, if an elderly person says, "The weather is nice today," the generative AI will respond, "Yes, it's very nice today. Maybe it would be nice to go for a walk." The generative AI provides mental care for the elderly through natural conversation. Step 2: The voice recognition tool analyzes the conversation between the generation AI and the elderly person. For example, if an elderly person says, "I haven't had much of an appetite lately," the voice recognition tool analyzes the content and has the generation AI generate a response such as, "I see you have no appetite. Is there anything you're worried about?" Step 3: The health condition monitoring unit monitors the health condition of the elderly person based on the content of the conversation. For example, if an elderly person says, "I haven't been sleeping well lately," the health condition monitoring unit records that information and monitors any changes in their health condition. Step 4: The survival confirmation unit periodically talks with the elderly person to confirm their survival. For example, every morning it greets them with a greeting such as "Good morning. How are you today?" and checks for a response from the elderly person. Step 5: If the notification unit detects any abnormalities in the conversation, it notifies the family or a medical institution. For example, if an elderly person says, "I have chest pain," the notification unit notifies the family or a medical institution of that information and promptly takes action.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0115] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0121] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0130] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0136] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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).

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0146] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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."

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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]

[0169] 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. Generative AI and Voice recognition tools and A health status assessment unit; A survival confirmation unit; a notification unit, The AI ​​generative technology will help reduce loneliness through conversations with elderly people. The voice recognition tool analyzes the content of the conversation between the generation AI and the elderly person, the health condition assessment unit assesses the health condition of the elderly person based on the content of the conversation; the existence confirmation unit periodically talks with the elderly person to confirm their existence, The notification unit notifies a family member or a medical institution when an abnormality is detected from the content of the conversation. A system characterized by:

2. The generated AI is Analyzing changes in the elderly person's tone of voice and speaking style, detecting changes in emotions, and adjusting responses accordingly 2. The system of claim 1.

3. The generated AI is Based on what the elderly person is saying, relevant music and videos are suggested to enrich the conversation.

2. The system of claim 1.

4. The speech recognition tool Analyzing the elderly person's speaking speed and voice strength to detect changes in their health condition 2. The system of claim 1.

5. The generated AI is Long-term monitoring of the elderly person's conversation content and analysis of health status trends.

2. The system of claim 1.

6. The generated AI is Learning the response patterns of the elderly person and responding quickly when abnormalities are detected 2. The system of claim 1.

7. The generated AI is Analyzing the elderly person's conversation content and providing a detailed report to the family or medical institution if an abnormality is detected 2. The system of claim 1.

8. The generated AI is Analyzing the emotional state of the elderly person and adjusting the notification content according to the emotional state.

2. The system of claim 1.

Images