system

Abstract

The system of the embodiment aims to remotely monitor the health status of elderly people living alone and detect the risk of dementia and depression at an early stage. [Solution] A system according to an embodiment includes a voice recognition unit, a conversation recording unit, a health monitoring unit, and an alert unit. The voice recognition unit recognizes voices. The conversation recording unit records conversations based on the voices recognized by the voice recognition unit. The health monitoring unit monitors health conditions based on the conversations recorded by the conversation recording unit. The alert unit sends an alert for dementia or depression based on information monitored by the health monitoring unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the drawback of making it difficult to remotely monitor the health of elderly people living alone and to detect the risk of dementia or depression at an early stage.

[0005] The system of the embodiment aims to remotely monitor the health status of elderly people living alone and detect the risk of dementia and depression at an early stage. [Means for solving the problem]

[0006] A system according to an embodiment includes a voice recognition unit, a conversation recording unit, a health monitoring unit, and an alert unit. The voice recognition unit recognizes a voice. The conversation recording unit records a conversation based on the voice recognized by the voice recognition unit. The health monitoring unit monitors a health condition based on the conversation recorded by the conversation recording unit. The alert unit sends an alert for dementia or depression based on information monitored by the health monitoring unit. [Effects of the Invention]

[0007] The system according to the embodiment can remotely monitor the health of elderly people living alone and detect the risk of dementia or depression at an early stage. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention is designed to address the challenges faced by families living far from elderly people who live alone. This system recognizes the elderly's voice and speaks to them as if they were a family member. The system records the conversation and provides information to family members who are far away. Furthermore, the system records the conversation and sends an alert if it detects signs of dementia or depression. The system also assists with reminders to take medication, providing regular meals, and creating shopping lists. Finally, the system works in conjunction with a camera to immediately contact family members and hospitals if the elderly falls. This system protects the health and safety of elderly people living alone and provides peace of mind to family members who are far away. For example, the system can recognize the elderly's voice and speak to them as if they were a family member. This reduces the elderly's sense of loneliness and gives them a sense of security. Next, the system records the conversation and provides information to family members who are far away. For example, information about the elderly's recent preferences and health status can be sent to family members, allowing the family members to send gifts tailored to the elderly's current preferences. Furthermore, the system records the conversation and sends an alert if it detects signs of dementia or depression. This allows early and appropriate interventions to be taken. The system also assists with reminders to take medication, providing regular meals, and creating shopping lists. For example, the system can set reminders to prevent forgetting to take medication and support regular meal provision. Finally, the system works in conjunction with a camera to immediately contact family members and the hospital if an elderly person falls. This allows for a quick response and ensures the safety of the elderly. This system can protect the health and safety of elderly people living alone and provide peace of mind to family members who live far away. This system can protect the health and safety of elderly people living alone and provide peace of mind to family members who live far away.

[0029] The system according to the embodiment includes a voice recognition unit, a conversation recording unit, a health monitoring unit, and an alert unit. The voice recognition unit recognizes the elderly person's voice. For example, the voice recognition unit recognizes the elderly person's voice using a voice recognition algorithm. The voice recognition unit can support multiple languages. For example, the voice recognition unit can recognize languages ​​such as Japanese, English, and French. The voice recognition unit can filter background sounds to improve the accuracy of the voice recognition. For example, the voice recognition unit can remove background sounds using noise canceling technology to accurately recognize the elderly person's voice. The conversation recording unit records a conversation based on the voice recognized by the voice recognition unit. For example, the conversation recording unit converts audio data into text data and records it. The conversation recording unit can automatically classify and save the content of the conversation. For example, the conversation recording unit can save health-related conversations in a health folder and family-related conversations in a family folder. The conversation recording unit can automatically extract and tag important keywords. For example, the conversation recording unit extracts and tags health-related keywords. The health monitoring unit monitors the health condition based on the conversation recorded by the conversation recording unit. For example, the health monitoring unit analyzes the content of the conversation and evaluates the health condition. The health monitoring unit can also detect abnormalities by referring to past health data. For example, the health monitoring unit can refer to past blood pressure data and detect abnormal fluctuations. The health monitoring unit can automatically perform detailed examinations when an abnormality is detected. For example, the health monitoring unit performs detailed blood pressure examinations when blood pressure is abnormally high. The alert unit sends an alert for dementia or depression based on the information monitored by the health monitoring unit. For example, the alert unit sends an alert when it detects signs of dementia. The alert unit can also send an alert when it detects signs of depression. The alert unit can also apply different notification methods depending on the importance of the alert. For example, the alert unit uses a phone call or emergency notification for a high-importance alert and an email or app notification for a medium-importance alert.As a result, the system according to the embodiment can protect the health and safety of elderly people living alone and provide peace of mind to family members who live far away.

[0030] The alert unit can send an alert when it detects signs of dementia. The alert unit sends an alert when it detects signs of dementia, for example. For example, the alert unit detects specific behavioral patterns or changes in language to determine signs of dementia. The alert unit can also refer to past conversation data to detect signs of dementia early. For example, the alert unit analyzes past conversation data to detect signs of dementia. Furthermore, the alert unit can send an alert to family members or medical institutions when signs of dementia are detected. For example, the alert unit sends an email or an app notification to family members to notify them of the signs of dementia. This allows signs of dementia to be detected early and appropriate measures to be taken.

[0031] The alert unit can send an alert when it detects signs of depression. For example, the alert unit can detect changes in the frequency of use of specific words or in tone of voice to determine signs of depression. The alert unit can also refer to past conversation data to detect signs of depression early. For example, the alert unit can analyze past conversation data to detect signs of depression. Furthermore, the alert unit can send an alert to family members or medical institutions when signs of depression are detected. For example, the alert unit can send an email or an app notification to family members to notify them of the signs of depression. This allows signs of depression to be detected early and appropriate measures to be taken.

[0032] The system includes a medicine reminder unit that sets a reminder to prevent forgetting to take medicine. The medicine reminder unit sets a reminder to prevent forgetting to take medicine, for example. For example, the medicine reminder unit sounds an alarm at a specific time to notify the user to take the medicine. The medicine reminder unit can also set reminders based on the type of medicine and the medication schedule. For example, the medicine reminder unit can set reminders for different time periods, such as for medicine to be taken after breakfast, after lunch, and after dinner. Furthermore, the medicine reminder unit can adjust the reminder notification method. For example, the medicine reminder unit can notify reminders in different ways, such as voice notification, text notification, and app notification. This can prevent users from forgetting to take their medicine and support health management.

[0033] The system includes a meal provision support unit that supports the provision of regular meals. The meal provision support unit supports, for example, the provision of regular meals. For example, the meal provision support unit sets meals to be provided at specific times. The meal provision support unit can also select meal menus and provide nutritionally balanced meals. For example, the meal provision support unit selects menus for breakfast, lunch, and dinner and provides nutritious meals. Furthermore, the meal provision support unit can adjust the method of providing meals. For example, the meal provision support unit provides meals in different ways, such as by delivering meals, cooking meals, or heating meals. This supports the provision of regular meals and enables nutritional management.

[0034] The system includes a fall detection unit that detects falls in conjunction with a camera and notifies family members and hospitals. The fall detection unit, for example, detects falls in conjunction with a camera. For example, the fall detection unit analyzes camera footage to detect falling motions. The fall detection unit can also use multiple sensors to improve fall detection accuracy. For example, the fall detection unit detects falls using an acceleration sensor or a gyro sensor. Furthermore, the fall detection unit can contact family members and hospitals when a fall is detected. For example, the fall detection unit notifies family members by phone or email and makes emergency contact with a hospital. This allows falls to be detected quickly and appropriate measures to be taken.

[0035] The voice recognition unit can analyze the tone and speed of the elderly person's voice and select an optimal recognition algorithm. The voice recognition unit, for example, analyzes the tone and speed of the elderly person's voice and selects an optimal recognition algorithm. For example, if the elderly person has a low voice, the voice recognition unit applies a recognition algorithm specialized for low-pitched sounds. Furthermore, if the elderly person speaks slowly, the voice recognition unit can select an algorithm that corresponds to a slow speaking style. Furthermore, if the elderly person has a high-pitched voice, the voice recognition unit can apply a recognition algorithm specialized for high-pitched sounds. This allows the optimal recognition algorithm to be selected according to the characteristics of the elderly person's voice and improves recognition accuracy. The analysis of the voice tone and speed is performed, for example, using a method of analyzing a voice waveform or measuring the speed. For example, the voice recognition unit analyzes a voice waveform and evaluates the voice tone. Furthermore, the voice recognition unit can measure the voice speed and evaluate the speaking speed. This allows the voice recognition unit to grasp the voice tone and speed of the elderly person in detail and select an optimal recognition algorithm.

[0036] The voice recognition unit can improve recognition accuracy by filtering background sounds during voice recognition. For example, the voice recognition unit can improve recognition accuracy by filtering background sounds during voice recognition. For example, when there is television sound, the voice recognition unit can filter the sound to recognize only the voice of an elderly person. Furthermore, when there is external noise, the voice recognition unit can filter the noise to recognize only the voice of an elderly person. Furthermore, when there is sound from home appliances, the voice recognition unit can filter the noise to recognize only the voice of an elderly person. In this way, by filtering background sounds, recognition accuracy can be improved. Filtering background sounds is performed using, for example, noise canceling technology or a filtering algorithm. For example, the voice recognition unit can remove background sounds using noise canceling technology to accurately recognize the voice of an elderly person. Furthermore, the voice recognition unit can remove specific sounds using a filtering algorithm to recognize the voice of an elderly person. In this way, the voice recognition unit can improve recognition accuracy by understanding background sounds in detail and filtering them.

[0037] The conversation recording unit can automatically extract and tag important keywords when recording a conversation. The conversation recording unit, for example, automatically extracts and tags important keywords when recording a conversation. For example, the conversation recording unit automatically extracts and tags health-related keywords that appear in a conversation. The conversation recording unit can also automatically extract and tag family-related keywords that appear in a conversation. The conversation recording unit can also automatically extract and tag hobbies that appear in a conversation. This allows the content of a conversation to be efficiently organized by extracting and tagging important keywords. The extraction of important keywords is performed using techniques such as appearance frequency and context analysis. For example, the conversation recording unit extracts and tags keywords that appear frequently in a conversation. The conversation recording unit can also extract and tag important keywords using context analysis. This allows the conversation recording unit to grasp the content of a conversation in detail and extract and tag important keywords.

[0038] The conversation recording unit can automatically classify and save the content of a conversation when recording the conversation. The conversation recording unit, for example, automatically classifies and saves the content of a conversation when recording the conversation. For example, the conversation recording unit can automatically classify conversations related to health and save them in a health folder. The conversation recording unit can also automatically classify conversations related to family and save them in a family folder. The conversation recording unit can also automatically classify conversations related to hobbies and save them in a hobby folder. This automatically classifying and saving the content of a conversation makes it easier to manage information. The content of a conversation is classified using techniques such as topic classification and keyword-based classification. For example, the conversation recording unit analyzes the topic of the conversation and classifies it by topic. The conversation recording unit can also classify the content of a conversation based on keywords. This allows the conversation recording unit to grasp the content of a conversation in detail and automatically classify and save it.

[0039] The health monitoring unit can detect abnormalities by referring to past health data during health monitoring. The health monitoring unit can, for example, detect abnormalities by referring to past health data during health monitoring. For example, the health monitoring unit can refer to past blood pressure data of an elderly person to detect abnormal fluctuations. The health monitoring unit can also refer to past heart rate data of an elderly person to detect abnormal fluctuations. The health monitoring unit can also refer to past body temperature data of an elderly person to detect abnormal fluctuations. By referring to past health data, abnormalities can be detected early. The reference to past health data is performed using, for example, a data storage format or a reference method. For example, the health monitoring unit stores past health data in a digital format and references it as needed. The health monitoring unit can also store past health data on the cloud and reference it in real time. This allows the health monitoring unit to grasp past health data in detail and detect abnormalities.

[0040] The health monitoring unit can automatically conduct a detailed examination if an abnormality is detected during health monitoring. The health monitoring unit can automatically conduct a detailed examination if an abnormality is detected during health monitoring, for example. For example, the health monitoring unit can automatically conduct a detailed blood pressure examination if blood pressure is abnormally high. The health monitoring unit can also automatically conduct a detailed heart rate examination if heart rate is abnormally high. The health monitoring unit can also automatically conduct a detailed body temperature examination if body temperature is abnormally high. As a result, by conducting a detailed examination when an abnormality is detected, appropriate measures can be taken. The content of the detailed examination can include, for example, additional health checks or a diagnosis by a specialist. For example, the health monitoring unit can conduct an additional blood test or an electrocardiogram test if an abnormality is detected. The health monitoring unit can also automatically make an appointment for a diagnosis by a specialist. As a result, the health monitoring unit can take prompt and appropriate measures when an abnormality is detected.

[0041] The alert unit can select the optimal timing for sending an alert by referring to past alert history. For example, the alert unit can select the optimal timing for sending an alert by referring to past alert history. For example, the alert unit can select the optimal timing for sending an alert based on the response time when sending alerts in the past. The alert unit can also select an effective timing for sending an alert during a specific time period based on past alert history. Furthermore, the alert unit can analyze past alert history and select the timing that resulted in the quickest response. This allows the optimal timing for sending an alert to be selected by referring to past alert history. The alert history is referenced, for example, using the recording format and reference method of past alerts. For example, the alert unit stores past alert history in a digital format and references it as needed. The alert unit can also store past alert history on the cloud and reference it in real time. This allows the alert unit to have a detailed understanding of past alert history and select the optimal timing for sending an alert.

[0042] The alert unit can apply different notification methods depending on the importance of the alert when sending an alert. For example, the alert unit can apply different notification methods depending on the importance of the alert when sending an alert. For example, the alert unit can use a phone call or emergency notification for a high-importance alert. The alert unit can also use email or app notification for a medium-importance alert. Furthermore, the alert unit can use periodic reminder notifications for a low-importance alert. This allows an appropriate notification method to be selected depending on the importance of the alert, enabling a prompt response. The importance of the alert is evaluated using, for example, an urgency evaluation criterion or a notification method selection criterion. For example, the alert unit evaluates the importance based on the content and situation of the alert and selects an appropriate notification method. The alert unit can also adjust the importance evaluation criterion by referring to past alert history. This allows the alert unit to grasp the importance of the alert in detail and select an appropriate notification method.

[0043] The medicine reminder unit can select the optimal notification timing by referring to the past medication history when issuing a medicine reminder. For example, the medicine reminder unit can select the optimal notification timing by referring to the past medication history when issuing a medicine reminder. For example, the medicine reminder unit issues a notification while avoiding a time period in which the patient has forgotten to take their medicine in the past. The medicine reminder unit can also issue a notification at the most effective time period based on the past medication history. Furthermore, the medicine reminder unit can analyze the past medication history and select the optimal notification timing. As a result, the optimal notification timing can be selected by referring to the past medication history. The medication history is referenced, for example, using a past medication record or a reference method. For example, the medicine reminder unit stores the past medication history in a digital format and references it as needed. The medicine reminder unit can also store the past medication history on the cloud and reference it in real time. As a result, the medicine reminder unit can grasp the past medication history in detail and select the optimal notification timing.

[0044] The medicine reminder unit can apply different notification methods depending on the importance of taking a medication when issuing a medicine reminder. For example, the medicine reminder unit can apply different notification methods depending on the importance of taking a medication when issuing a medicine reminder. For example, the medicine reminder unit can use a phone call or emergency notification for a highly important medicine. The medicine reminder unit can also use email or app notifications for a medium-important medicine. Furthermore, the medicine reminder unit can use periodic reminder notifications for a low-important medicine. This allows an appropriate notification method to be selected depending on the importance of taking a medication, enabling a prompt response. The importance of taking a medication is evaluated using criteria such as the type of medication and the urgency of taking the medication. For example, the medicine reminder unit evaluates the importance based on the type of medication and the urgency of taking the medication, and selects an appropriate notification method. The medicine reminder unit can also adjust the importance evaluation criteria by referring to past medication history. This allows the medicine reminder unit to grasp the importance of taking the medicine in detail and select an appropriate notification method.

[0045] The medicine reminder unit can adjust the frequency of notifications during medicine reminders, taking into account the elderly person's lifestyle rhythm. For example, the medicine reminder unit adjusts the frequency of notifications during medicine reminders, taking into account the elderly person's lifestyle rhythm. For example, if the elderly person has an early-to-bed, early-to-rise lifestyle rhythm, the medicine reminder unit can provide notifications based on that rhythm. Furthermore, if the elderly person has a nocturnal lifestyle rhythm, the medicine reminder unit can provide notifications based on that rhythm. Furthermore, if the elderly person has an irregular lifestyle rhythm, the medicine reminder unit can provide notifications based on that rhythm. This allows the frequency of notifications to be adjusted according to the elderly person's lifestyle rhythm, making it possible to provide appropriate notifications. Consideration of lifestyle rhythms is performed, for example, using data such as daily activity patterns and sleep duration. For example, the medicine reminder unit can analyze the elderly person's daily activity patterns and evaluate their lifestyle rhythm. Furthermore, the medicine reminder unit can monitor the elderly person's sleep duration and evaluate their lifestyle rhythm. This allows the medicine reminder unit to gain a detailed understanding of the elderly person's daily routine and adjust the frequency of notifications.

[0046] The medicine reminder unit can adjust the content of the notification taking into account the health condition of the elderly person when issuing a medicine reminder. For example, the medicine reminder unit adjusts the content of the notification taking into account the health condition of the elderly person when issuing a medicine reminder. For example, if the elderly person is in poor health, the medicine reminder unit sends a notification emphasizing the importance of taking medication. The medicine reminder unit can also send a regular notification if the elderly person is healthy. Furthermore, if the elderly person has a specific illness, the medicine reminder unit can preferentially send notifications about medicines related to that illness. This allows the content of the notification to be adjusted according to the elderly person's health condition and provide appropriate notifications. The health condition can be taken into account using, for example, current health indicators and past health data. For example, the medicine reminder unit monitors the elderly person's current health indicators and evaluates their health condition. The medicine reminder unit can also refer to past health data to evaluate their health condition. This allows the medicine reminder unit to grasp the elderly person's health condition in detail and adjust the content of the notification.

[0047] The meal provision support unit can suggest an optimal menu by referring to past meal history when providing a meal. The meal provision support unit, for example, can suggest an optimal menu by referring to past meal history when providing a meal. For example, the meal provision support unit can suggest an optimal menu based on the elderly person's past favorite menu items. The meal provision support unit can also suggest a nutritionally balanced menu based on the elderly person's past meal history. Furthermore, the meal provision support unit can analyze the elderly person's past meal history and suggest the healthiest menu. This makes it possible to suggest an optimal menu by referring to the past meal history. The meal history can be referenced, for example, using a past meal record or a reference method. For example, the meal provision support unit can store the past meal history in a digital format and reference it as needed. The meal provision support unit can also store the past meal history on the cloud and reference it in real time. This allows the meal provision support unit to grasp the past meal history in detail and suggest an optimal menu.

[0048] The meal provision support unit can optimize the menu by taking real-time health data into consideration when providing a meal. The meal provision support unit, for example, optimizes the menu by taking real-time health data into consideration when providing a meal. For example, the meal provision support unit proposes an optimal menu based on the elderly person's current blood pressure data. Furthermore, the meal provision support unit can propose an optimal menu based on the elderly person's current blood glucose level data. Furthermore, the meal provision support unit can propose an optimal menu based on the elderly person's current body temperature data. In this way, an optimal menu can be provided by taking real-time health data into consideration. The real-time health data is referenced using, for example, current health indicators and a data acquisition method. For example, the meal provision support unit monitors the elderly person's current health indicators and evaluates their health condition. Furthermore, the meal provision support unit can optimize the menu based on the health data acquired in real time. In this way, the meal provision support unit can grasp the real-time health data in detail and provide an optimal menu.

[0049] The meal provision support unit can adjust the menu taking into account the nutritional state of the elderly person when providing a meal. The meal provision support unit, for example, adjusts the menu taking into account the nutritional state of the elderly person when providing a meal. For example, the meal provision support unit can suggest a nutritious menu when the elderly person's nutritional state is poor. Furthermore, the meal provision support unit can suggest a regular menu when the elderly person's nutritional state is good. Furthermore, the meal provision support unit can suggest a menu that supplements a specific nutrient when the elderly person is deficient in that nutrient. This allows the menu to be adjusted according to the elderly person's nutritional state and an appropriate meal to be provided. The nutritional state is taken into account, for example, using current nutritional indicators and past nutritional data. For example, the meal provision support unit monitors the elderly person's current nutritional indicators and evaluates the nutritional state. Furthermore, the meal provision support unit can refer to past nutritional data to evaluate the nutritional state. This allows the meal provision support unit to grasp the elderly person's nutritional state in detail and adjust the menu.

[0050] The meal provision support unit can adjust the menu by referring to the elderly person's past meal history when providing a meal. The meal provision support unit, for example, adjusts the menu by referring to the elderly person's past meal history when providing a meal. For example, the meal provision support unit suggests an optimal menu based on the elderly person's past favorite menu items. The meal provision support unit can also suggest a nutritionally balanced menu based on the elderly person's past meal history. Furthermore, the meal provision support unit can analyze the elderly person's past meal history and suggest the healthiest menu. This makes it possible to provide an optimal menu by referring to the past meal history. The past meal history is referenced, for example, using a past meal record or a reference method. For example, the meal provision support unit stores the past meal history in a digital format and references it as needed. The meal provision support unit can also store the past meal history on the cloud and reference it in real time. This allows the meal provision support unit to understand the past meal history in detail and adjust the menu.

[0051] The fall detection unit can select the optimal detection algorithm by referring to past fall history when detecting a fall. For example, the fall detection unit can select the optimal detection algorithm by referring to past fall history when detecting a fall. For example, the fall detection unit can strengthen the detection algorithm for a specific location based on the location where the elderly person has fallen in the past. The fall detection unit can also select an algorithm that detects a specific movement pattern from the elderly person's past fall history. Furthermore, the fall detection unit can analyze the elderly person's past fall history and select the most effective detection algorithm. Thus, by referring to the past fall history, the optimal detection algorithm can be selected. The fall history can be referenced, for example, using a past fall record or a reference method. For example, the fall detection unit can store the past fall history in digital format and reference it as needed. Furthermore, the fall detection unit can store the past fall history on the cloud and reference it in real time. This allows the fall detection unit to grasp the past fall history in detail and select the optimal detection algorithm.

[0052] The fall detection unit can improve the accuracy of detection by taking real-time health data into consideration when detecting a fall. The fall detection unit can improve the accuracy of detection by taking real-time health data into consideration when detecting a fall, for example. For example, the fall detection unit can improve the accuracy of fall detection based on the elderly person's current blood pressure data. The fall detection unit can also improve the accuracy of fall detection based on the elderly person's current heart rate data. The fall detection unit can also improve the accuracy of fall detection based on the elderly person's current body temperature data. In this way, the detection accuracy can be improved by taking real-time health data into consideration. The real-time health data can be referenced using, for example, current health indicators or a data acquisition method. For example, the fall detection unit monitors the elderly person's current health indicators and evaluates their health condition. In addition, the fall detection unit can improve the accuracy of detection based on the health data acquired in real time. In this way, the fall detection unit can grasp the real-time health data in detail and improve the detection accuracy.

[0053] The fall detection unit can adjust the detection method when detecting a fall by taking into account the elderly person's living environment. For example, the fall detection unit adjusts the detection method when detecting a fall by taking into account the elderly person's living environment. For example, when the elderly person is at home, the fall detection unit uses a detection method optimized for the specific environment of the home. Furthermore, when the elderly person is out, the fall detection unit can use a detection method optimized for the external environment. Furthermore, when the elderly person is in a hospital, the fall detection unit can use a detection method optimized for the specific environment inside the hospital. This allows the detection method to be adjusted according to the elderly person's living environment and perform appropriate detection. The living environment is taken into account using, for example, data such as the structure of the residence and daily activity patterns. For example, the fall detection unit analyzes the structure of the elderly person's residence and evaluates the living environment. Furthermore, the fall detection unit can monitor the elderly person's daily activity patterns and evaluate the living environment. This allows the fall detection unit to grasp the elderly person's living environment in detail and adjust the detection method.

[0054] The fall detection unit can improve detection accuracy by referring to the elderly person's past fall history when detecting a fall. The fall detection unit can improve detection accuracy by, for example, referring to the elderly person's past fall history when detecting a fall. For example, the fall detection unit can improve detection accuracy at specific locations based on locations where the elderly person has fallen in the past. The fall detection unit can also improve the accuracy of detecting specific movement patterns from the elderly person's past fall history. Furthermore, the fall detection unit can analyze the elderly person's past fall history and improve the most effective detection accuracy. Thus, by referring to the past fall history, detection accuracy can be improved. Referencing the past fall history is performed, for example, using a past fall record or a reference method. For example, the fall detection unit stores the past fall history in digital format and references it as needed. Furthermore, the fall detection unit can store the past fall history on the cloud and reference it in real time. This allows the fall detection unit to grasp the past fall history in detail and improve detection accuracy.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The system may further include an activity monitoring unit that monitors the elderly person's activity level. The activity monitoring unit measures the elderly person's daily activity amount and evaluates their health condition. For example, the activity monitoring unit may measure the elderly person's walking distance and exercise amount using a pedometer or an acceleration sensor. The activity monitoring unit may also analyze daily activity patterns and detect abnormal decreases or increases in activity. Furthermore, the activity monitoring unit may provide health advice based on the activity level. This allows for a detailed understanding of the elderly person's activity level and supports health management.

[0057] The alert unit can further adjust the timing of sending an alert taking into account the elderly person's lifestyle rhythm. For example, if the elderly person has a lifestyle rhythm of going to bed early and rising early, the alert unit can send an alert in accordance with that rhythm. Also, if the elderly person has a nocturnal lifestyle rhythm, the alert unit can send an alert in accordance with that rhythm. Furthermore, if the elderly person has an irregular lifestyle rhythm, the alert unit can send an alert in accordance with that rhythm. This allows the timing of sending an alert to be adjusted according to the elderly person's lifestyle rhythm, making it possible to provide appropriate notifications.

[0058] The fall detection unit can further adjust the fall detection method taking into account the elderly person's living environment. For example, when the elderly person is at home, the fall detection unit uses a detection method optimized for the specific environment of the home. When the elderly person is out, the fall detection unit can use a detection method optimized for the external environment. When the elderly person is in a hospital, the fall detection unit can use a detection method optimized for the specific environment within the hospital. This allows the fall detection method to be adjusted according to the elderly person's living environment, making it possible to perform appropriate detection.

[0059] The system may further include a social connection support unit for supporting the elderly's social connections. The social connection support unit supports the elderly to keep in contact with friends and family. For example, the social connection support unit may periodically set up video calls with friends and family. The social connection support unit may also support messaging with friends and family. Furthermore, the social connection support unit may provide information on participating in local events and activities. This may strengthen the elderly's social connections and reduce feelings of loneliness.

[0060] The system may further include a hobby support unit for supporting the hobbies and interests of the elderly. The hobby support unit supports the elderly in maintaining their hobbies and interests. For example, the hobby support unit provides information on areas that interest the elderly. The hobby support unit may also support participation in online communities related to hobbies. Furthermore, the hobby support unit may provide information on events and workshops related to hobbies. This supports the hobbies and interests of the elderly, enabling them to live fulfilling lives.

[0061] The system may further include a sleep monitoring unit that monitors the sleep state of the elderly person. The sleep monitoring unit measures the elderly person's sleep patterns and evaluates their health condition. For example, the sleep monitoring unit may monitor their movements and breathing during sleep. The sleep monitoring unit may also evaluate the quality of their sleep and provide advice for improvement. Furthermore, the sleep monitoring unit may detect abnormal sleep patterns and send an alert. This allows for detailed understanding of the elderly person's sleep state and supports health management.

[0062] The processing flow of the first embodiment will be briefly explained below.

[0063] Step 1: The voice recognition unit recognizes the elderly person's voice. For example, a voice recognition algorithm is used to recognize the elderly person's voice and can support multiple languages ​​(Japanese, English, French, etc.). Additionally, noise cancellation technology is used to remove background noise and improve the accuracy of voice recognition. Step 2: The conversation recording unit records the conversation based on the voice recognized by the voice recognition unit. For example, it converts the voice data into text data, automatically classifies and saves the content of the conversation, and automatically extracts and tags important keywords. Step 3: The health monitoring unit monitors the health status based on the conversation recorded by the conversation recording unit. For example, it analyzes the content of the conversation and refers to past health data to detect abnormalities. If an abnormality is detected, detailed examinations are automatically performed. Step 4: The alert unit sends an alert for dementia or depression based on the information monitored by the health monitoring unit. For example, if it detects signs of dementia or depression, it sends an alert and applies different notification methods (such as phone call, emergency notification, email, or app notification) depending on the importance of the alert.

[0064] (Example 2) A system according to an embodiment of the present invention is designed to address the challenges faced by families living far from elderly people who live alone. This system recognizes the elderly's voice and speaks to them as if they were a family member. The system records the conversation and provides information to family members who are far away. Furthermore, the system records the conversation and sends an alert if it detects signs of dementia or depression. The system also assists with reminders to take medication, providing regular meals, and creating shopping lists. Finally, the system works in conjunction with a camera to immediately contact family members and hospitals if the elderly falls. This system protects the health and safety of elderly people living alone and provides peace of mind to family members who are far away. For example, the system can recognize the elderly's voice and speak to them as if they were a family member. This reduces the elderly's sense of loneliness and gives them a sense of security. Next, the system records the conversation and provides information to family members who are far away. For example, information about the elderly's recent preferences and health status can be sent to family members, allowing the family members to send gifts tailored to the elderly's current preferences. Furthermore, the system records the conversation and sends an alert if it detects signs of dementia or depression. This allows early and appropriate interventions to be taken. The system also assists with reminders to take medication, providing regular meals, and creating shopping lists. For example, the system can set reminders to prevent forgetting to take medication and support regular meal provision. Finally, the system works in conjunction with a camera to immediately contact family members and the hospital if an elderly person falls. This allows for a quick response and ensures the safety of the elderly. This system can protect the health and safety of elderly people living alone and provide peace of mind to family members who live far away. This system can protect the health and safety of elderly people living alone and provide peace of mind to family members who live far away.

[0065] The system according to the embodiment includes a voice recognition unit, a conversation recording unit, a health monitoring unit, and an alert unit. The voice recognition unit recognizes the elderly person's voice. For example, the voice recognition unit recognizes the elderly person's voice using a voice recognition algorithm. The voice recognition unit can support multiple languages. For example, the voice recognition unit can recognize languages ​​such as Japanese, English, and French. The voice recognition unit can filter background sounds to improve the accuracy of the voice recognition. For example, the voice recognition unit can remove background sounds using noise canceling technology to accurately recognize the elderly person's voice. The conversation recording unit records a conversation based on the voice recognized by the voice recognition unit. For example, the conversation recording unit converts audio data into text data and records it. The conversation recording unit can automatically classify and save the content of the conversation. For example, the conversation recording unit can save health-related conversations in a health folder and family-related conversations in a family folder. The conversation recording unit can automatically extract and tag important keywords. For example, the conversation recording unit extracts and tags health-related keywords. The health monitoring unit monitors the health condition based on the conversation recorded by the conversation recording unit. For example, the health monitoring unit analyzes the content of the conversation and evaluates the health condition. The health monitoring unit can also detect abnormalities by referring to past health data. For example, the health monitoring unit can refer to past blood pressure data and detect abnormal fluctuations. The health monitoring unit can automatically perform detailed examinations when an abnormality is detected. For example, the health monitoring unit performs detailed blood pressure examinations when blood pressure is abnormally high. The alert unit sends an alert for dementia or depression based on the information monitored by the health monitoring unit. For example, the alert unit sends an alert when it detects signs of dementia. The alert unit can also send an alert when it detects signs of depression. The alert unit can also apply different notification methods depending on the importance of the alert. For example, the alert unit uses a phone call or emergency notification for a high-importance alert and an email or app notification for a medium-importance alert.As a result, the system according to the embodiment can protect the health and safety of elderly people living alone and provide peace of mind to family members who live far away.

[0066] The alert unit can send an alert when it detects signs of dementia. The alert unit sends an alert when it detects signs of dementia, for example. For example, the alert unit detects specific behavioral patterns or changes in language to determine signs of dementia. The alert unit can also refer to past conversation data to detect signs of dementia early. For example, the alert unit analyzes past conversation data to detect signs of dementia. Furthermore, the alert unit can send an alert to family members or medical institutions when signs of dementia are detected. For example, the alert unit sends an email or an app notification to family members to notify them of the signs of dementia. This allows signs of dementia to be detected early and appropriate measures to be taken.

[0067] The alert unit can send an alert when it detects signs of depression. For example, the alert unit can detect changes in the frequency of use of specific words or in tone of voice to determine signs of depression. The alert unit can also refer to past conversation data to detect signs of depression early. For example, the alert unit can analyze past conversation data to detect signs of depression. Furthermore, the alert unit can send an alert to family members or medical institutions when signs of depression are detected. For example, the alert unit can send an email or an app notification to family members to notify them of the signs of depression. This allows signs of depression to be detected early and appropriate measures to be taken.

[0068] The system includes a medicine reminder unit that sets a reminder to prevent forgetting to take medicine. The medicine reminder unit sets a reminder to prevent forgetting to take medicine, for example. For example, the medicine reminder unit sounds an alarm at a specific time to notify the user to take the medicine. The medicine reminder unit can also set reminders based on the type of medicine and the medication schedule. For example, the medicine reminder unit can set reminders for different time periods, such as for medicine to be taken after breakfast, after lunch, and after dinner. Furthermore, the medicine reminder unit can adjust the reminder notification method. For example, the medicine reminder unit can notify reminders in different ways, such as voice notification, text notification, and app notification. This can prevent users from forgetting to take their medicine and support health management.

[0069] The system includes a meal provision support unit that supports the provision of regular meals. The meal provision support unit supports, for example, the provision of regular meals. For example, the meal provision support unit sets meals to be provided at specific times. The meal provision support unit can also select meal menus and provide nutritionally balanced meals. For example, the meal provision support unit selects menus for breakfast, lunch, and dinner and provides nutritious meals. Furthermore, the meal provision support unit can adjust the method of providing meals. For example, the meal provision support unit provides meals in different ways, such as by delivering meals, cooking meals, or heating meals. This supports the provision of regular meals and enables nutritional management.

[0070] The system includes a fall detection unit that detects falls in conjunction with a camera and notifies family members and hospitals. The fall detection unit, for example, detects falls in conjunction with a camera. For example, the fall detection unit analyzes camera footage to detect falling motions. The fall detection unit can also use multiple sensors to improve fall detection accuracy. For example, the fall detection unit detects falls using an acceleration sensor or a gyro sensor. Furthermore, the fall detection unit can contact family members and hospitals when a fall is detected. For example, the fall detection unit notifies family members by phone or email and makes emergency contact with a hospital. This allows falls to be detected quickly and appropriate measures to be taken.

[0071] The voice recognition unit can estimate the emotion of the elderly person and adjust the accuracy of voice recognition based on the estimated emotion. The voice recognition unit, for example, estimates the emotion of the elderly person and adjusts the accuracy of voice recognition based on the estimated emotion. For example, the voice recognition unit increases the sensitivity of voice recognition when the elderly person is stressed to achieve more accurate recognition. Furthermore, the voice recognition unit can return the sensitivity of voice recognition to normal when the elderly person is relaxed to promote natural conversation. Furthermore, the voice recognition unit can adjust the sensitivity of voice recognition when the elderly person is tired to reduce false recognition. This allows the accuracy of voice recognition to be adjusted according to the emotion of the elderly person and improve recognition accuracy. Emotion estimation is performed using techniques such as voice analysis and facial expression analysis. For example, the voice recognition unit analyzes the tone and speed of the elderly person's voice to estimate the emotion. Furthermore, the voice recognition unit can capture the facial expression of the elderly person with a camera and estimate the emotion using a facial expression analysis algorithm. This allows the voice recognition unit to grasp the emotions of the elderly person in detail and adjust the accuracy of voice recognition.

[0072] The voice recognition unit can analyze the tone and speed of the elderly person's voice and select an optimal recognition algorithm. The voice recognition unit, for example, analyzes the tone and speed of the elderly person's voice and selects an optimal recognition algorithm. For example, if the elderly person has a low voice, the voice recognition unit applies a recognition algorithm specialized for low-pitched sounds. Furthermore, if the elderly person speaks slowly, the voice recognition unit can select an algorithm that corresponds to a slow speaking style. Furthermore, if the elderly person has a high-pitched voice, the voice recognition unit can apply a recognition algorithm specialized for high-pitched sounds. This allows the optimal recognition algorithm to be selected according to the characteristics of the elderly person's voice and improves recognition accuracy. The analysis of the voice tone and speed is performed, for example, using a method of analyzing a voice waveform or measuring the speed. For example, the voice recognition unit analyzes a voice waveform and evaluates the voice tone. Furthermore, the voice recognition unit can measure the voice speed and evaluate the speaking speed. This allows the voice recognition unit to grasp the voice tone and speed of the elderly person in detail and select an optimal recognition algorithm.

[0073] The voice recognition unit can improve recognition accuracy by filtering background sounds during voice recognition. For example, the voice recognition unit can improve recognition accuracy by filtering background sounds during voice recognition. For example, when there is television sound, the voice recognition unit can filter the sound to recognize only the voice of an elderly person. Furthermore, when there is external noise, the voice recognition unit can filter the noise to recognize only the voice of an elderly person. Furthermore, when there is sound from home appliances, the voice recognition unit can filter the noise to recognize only the voice of an elderly person. In this way, by filtering background sounds, recognition accuracy can be improved. Filtering background sounds is performed using, for example, noise canceling technology or a filtering algorithm. For example, the voice recognition unit can remove background sounds using noise canceling technology to accurately recognize the voice of an elderly person. Furthermore, the voice recognition unit can remove specific sounds using a filtering algorithm to recognize the voice of an elderly person. In this way, the voice recognition unit can improve recognition accuracy by understanding background sounds in detail and filtering them.

[0074] The conversation recording unit can estimate the elderly person's emotions and adjust the level of detail of the conversation record based on the estimated emotions. For example, the conversation recording unit can estimate the elderly person's emotions and adjust the level of detail of the conversation record based on the estimated emotions. For example, the conversation recording unit can record a detailed conversation when the elderly person is relaxed. Furthermore, the conversation recording unit can record a concise conversation when the elderly person is nervous. Furthermore, the conversation recording unit can record only the important points when the elderly person is tired. This allows the level of detail of the conversation record to be adjusted according to the elderly person's emotions and appropriate recording. Emotion estimation is performed using techniques such as voice analysis and facial expression analysis. For example, the conversation recording unit can analyze the tone and speed of the elderly person's voice to estimate their emotions. Furthermore, the conversation recording unit can capture the elderly person's facial expressions with a camera and estimate their emotions using a facial expression analysis algorithm. This allows the conversation recording unit to grasp the elderly person's emotions in detail and adjust the level of detail of the conversation record.

[0075] The conversation recording unit can automatically extract and tag important keywords when recording a conversation. The conversation recording unit, for example, automatically extracts and tags important keywords when recording a conversation. For example, the conversation recording unit automatically extracts and tags health-related keywords that appear in a conversation. The conversation recording unit can also automatically extract and tag family-related keywords that appear in a conversation. The conversation recording unit can also automatically extract and tag hobbies that appear in a conversation. This allows the content of a conversation to be efficiently organized by extracting and tagging important keywords. The extraction of important keywords is performed using techniques such as appearance frequency and context analysis. For example, the conversation recording unit extracts and tags keywords that appear frequently in a conversation. The conversation recording unit can also extract and tag important keywords using context analysis. This allows the conversation recording unit to grasp the content of a conversation in detail and extract and tag important keywords.

[0076] The conversation recording unit can automatically classify and save the content of a conversation when recording the conversation. The conversation recording unit, for example, automatically classifies and saves the content of a conversation when recording the conversation. For example, the conversation recording unit can automatically classify conversations related to health and save them in a health folder. The conversation recording unit can also automatically classify conversations related to family and save them in a family folder. The conversation recording unit can also automatically classify conversations related to hobbies and save them in a hobby folder. This automatically classifying and saving the content of a conversation makes it easier to manage information. The content of a conversation is classified using techniques such as topic classification and keyword-based classification. For example, the conversation recording unit analyzes the topic of the conversation and classifies it by topic. The conversation recording unit can also classify the content of a conversation based on keywords. This allows the conversation recording unit to grasp the content of a conversation in detail and automatically classify and save it.

[0077] The health monitoring unit can estimate the elderly person's emotions and adjust the frequency of health monitoring based on the estimated emotions. For example, the health monitoring unit estimates the elderly person's emotions and adjusts the frequency of health monitoring based on the estimated emotions. For example, the health monitoring unit can increase the frequency of health monitoring when the elderly person is stressed. Furthermore, the health monitoring unit can return the frequency of health monitoring to normal when the elderly person is relaxed. Furthermore, the health monitoring unit can adjust the frequency of health monitoring when the elderly person is tired to reduce false recognition. This allows the frequency of health monitoring to be adjusted according to the elderly person's emotions and perform appropriate monitoring. Emotion estimation is performed using techniques such as voice analysis and facial expression analysis. For example, the health monitoring unit can analyze the tone and speed of the elderly person's voice to estimate their emotions. Furthermore, the health monitoring unit can capture the elderly person's facial expressions with a camera and estimate their emotions using a facial expression analysis algorithm. This allows the health monitoring unit to grasp the elderly person's emotions in detail and adjust the frequency of health monitoring.

[0078] The health monitoring unit can detect abnormalities by referring to past health data during health monitoring. The health monitoring unit can, for example, detect abnormalities by referring to past health data during health monitoring. For example, the health monitoring unit can refer to past blood pressure data of an elderly person to detect abnormal fluctuations. The health monitoring unit can also refer to past heart rate data of an elderly person to detect abnormal fluctuations. The health monitoring unit can also refer to past body temperature data of an elderly person to detect abnormal fluctuations. By referring to past health data, abnormalities can be detected early. The reference to past health data is performed using, for example, a data storage format or a reference method. For example, the health monitoring unit stores past health data in a digital format and references it as needed. The health monitoring unit can also store past health data on the cloud and reference it in real time. This allows the health monitoring unit to grasp past health data in detail and detect abnormalities.

[0079] The health monitoring unit can automatically conduct a detailed examination if an abnormality is detected during health monitoring. The health monitoring unit can automatically conduct a detailed examination if an abnormality is detected during health monitoring, for example. For example, the health monitoring unit can automatically conduct a detailed blood pressure examination if blood pressure is abnormally high. The health monitoring unit can also automatically conduct a detailed heart rate examination if heart rate is abnormally high. The health monitoring unit can also automatically conduct a detailed body temperature examination if body temperature is abnormally high. As a result, by conducting a detailed examination when an abnormality is detected, appropriate measures can be taken. The content of the detailed examination can include, for example, additional health checks or a diagnosis by a specialist. For example, the health monitoring unit can conduct an additional blood test or an electrocardiogram test if an abnormality is detected. The health monitoring unit can also automatically make an appointment for a diagnosis by a specialist. As a result, the health monitoring unit can take prompt and appropriate measures when an abnormality is detected.

[0080] The alert unit can estimate the elderly person's emotions and adjust the alert transmission method based on the estimated emotions. The alert unit, for example, estimates the elderly person's emotions and adjusts the alert transmission method based on the estimated emotions. For example, the alert unit can send an alert in a calm tone if the elderly person is nervous. Furthermore, the alert unit can send an alert in a normal tone if the elderly person is relaxed. Furthermore, the alert unit can send a concise and easy-to-understand alert if the elderly person is tired. This allows the alert transmission method to be adjusted according to the elderly person's emotions and appropriate notification to be provided. Emotion estimation is performed using techniques such as voice analysis and facial expression analysis. For example, the alert unit can analyze the tone and speed of the elderly person's voice to estimate their emotions. Furthermore, the alert unit can capture the elderly person's facial expressions with a camera and estimate their emotions using a facial expression analysis algorithm. This allows the alert unit to grasp the elderly person's emotions in detail and adjust the alert transmission method.

[0081] The alert unit can select the optimal timing for sending an alert by referring to past alert history. For example, the alert unit can select the optimal timing for sending an alert by referring to past alert history. For example, the alert unit can select the optimal timing for sending an alert based on the response time when sending alerts in the past. The alert unit can also select an effective timing for sending an alert during a specific time period based on past alert history. Furthermore, the alert unit can analyze past alert history and select the timing that resulted in the quickest response. This allows the optimal timing for sending an alert to be selected by referring to past alert history. The alert history is referenced, for example, using the recording format and reference method of past alerts. For example, the alert unit stores past alert history in a digital format and references it as needed. The alert unit can also store past alert history on the cloud and reference it in real time. This allows the alert unit to have a detailed understanding of past alert history and select the optimal timing for sending an alert.

[0082] The alert unit can apply different notification methods depending on the importance of the alert when sending an alert. For example, the alert unit can apply different notification methods depending on the importance of the alert when sending an alert. For example, the alert unit can use a phone call or emergency notification for a high-importance alert. The alert unit can also use email or app notification for a medium-importance alert. Furthermore, the alert unit can use periodic reminder notifications for a low-importance alert. This allows an appropriate notification method to be selected depending on the importance of the alert, enabling a prompt response. The importance of the alert is evaluated using, for example, an urgency evaluation criterion or a notification method selection criterion. For example, the alert unit evaluates the importance based on the content and situation of the alert and selects an appropriate notification method. The alert unit can also adjust the importance evaluation criterion by referring to past alert history. This allows the alert unit to grasp the importance of the alert in detail and select an appropriate notification method.

[0083] The medicine reminder unit can estimate the elderly person's emotions and adjust the reminder notification method based on the estimated emotions. For example, the medicine reminder unit can estimate the elderly person's emotions and adjust the reminder notification method based on the estimated emotions. For example, if the elderly person is nervous, the medicine reminder unit can notify the elderly person of the reminder in a calm tone. Also, if the elderly person is relaxed, the medicine reminder unit can notify the elderly person of the reminder in a normal tone. Furthermore, if the elderly person is tired, the medicine reminder unit can notify the elderly person of the reminder in a concise and easy-to-understand tone. This allows the reminder notification method to be adjusted according to the elderly person's emotions and appropriate notifications to be provided. Emotion estimation is performed using technologies such as voice analysis and facial expression analysis. For example, the medicine reminder unit can analyze the tone and speed of the elderly person's voice to estimate the emotion. The medicine reminder unit can also capture the facial expressions of the elderly person with a camera and estimate their emotions using a facial expression analysis algorithm, allowing the unit to understand the elderly person's emotions in detail and adjust the reminder notification method accordingly.

[0084] The medicine reminder unit can select the optimal notification timing by referring to the past medication history when issuing a medicine reminder. For example, the medicine reminder unit can select the optimal notification timing by referring to the past medication history when issuing a medicine reminder. For example, the medicine reminder unit issues a notification while avoiding a time period in which the patient has forgotten to take their medicine in the past. The medicine reminder unit can also issue a notification at the most effective time period based on the past medication history. Furthermore, the medicine reminder unit can analyze the past medication history and select the optimal notification timing. As a result, the optimal notification timing can be selected by referring to the past medication history. The medication history is referenced, for example, using a past medication record or a reference method. For example, the medicine reminder unit stores the past medication history in a digital format and references it as needed. The medicine reminder unit can also store the past medication history on the cloud and reference it in real time. As a result, the medicine reminder unit can grasp the past medication history in detail and select the optimal notification timing.

[0085] The medicine reminder unit can apply different notification methods depending on the importance of taking a medication when issuing a medicine reminder. For example, the medicine reminder unit can apply different notification methods depending on the importance of taking a medication when issuing a medicine reminder. For example, the medicine reminder unit can use a phone call or emergency notification for a highly important medicine. The medicine reminder unit can also use email or app notifications for a medium-important medicine. Furthermore, the medicine reminder unit can use periodic reminder notifications for a low-important medicine. This allows an appropriate notification method to be selected depending on the importance of taking a medication, enabling a prompt response. The importance of taking a medication is evaluated using criteria such as the type of medication and the urgency of taking the medication. For example, the medicine reminder unit evaluates the importance based on the type of medication and the urgency of taking the medication, and selects an appropriate notification method. The medicine reminder unit can also adjust the importance evaluation criteria by referring to past medication history. This allows the medicine reminder unit to grasp the importance of taking the medicine in detail and select an appropriate notification method.

[0086] The medicine reminder unit can estimate the elderly person's emotions and determine the priority of reminders based on the estimated emotions. For example, the medicine reminder unit can estimate the elderly person's emotions and determine the priority of reminders based on the estimated emotions. For example, if the elderly person is feeling stressed, the medicine reminder unit can prioritize notifying the elderly person of a reminder. Furthermore, if the elderly person is relaxed, the medicine reminder unit can prioritize notifying the elderly person of a reminder with normal priority. Furthermore, if the elderly person is tired, the medicine reminder unit can prioritize notifying the elderly person of an important reminder. This allows the reminder priority to be determined according to the elderly person's emotions and appropriate notifications to be made. Emotion estimation is performed using, for example, technologies such as voice analysis and facial expression analysis. For example, the medicine reminder unit can analyze the tone and speed of the elderly person's voice to estimate their emotions. Furthermore, the medicine reminder unit can capture the elderly person's facial expressions with a camera and estimate their emotions using a facial expression analysis algorithm. This allows the medicine reminder unit to understand the elderly person's emotions in detail and determine the priority of reminders.

[0087] The medicine reminder unit can adjust the frequency of notifications during medicine reminders, taking into account the elderly person's lifestyle rhythm. For example, the medicine reminder unit adjusts the frequency of notifications during medicine reminders, taking into account the elderly person's lifestyle rhythm. For example, if the elderly person has an early-to-bed, early-to-rise lifestyle rhythm, the medicine reminder unit can provide notifications based on that rhythm. Furthermore, if the elderly person has a nocturnal lifestyle rhythm, the medicine reminder unit can provide notifications based on that rhythm. Furthermore, if the elderly person has an irregular lifestyle rhythm, the medicine reminder unit can provide notifications based on that rhythm. This allows the frequency of notifications to be adjusted according to the elderly person's lifestyle rhythm, making it possible to provide appropriate notifications. Consideration of lifestyle rhythms is performed, for example, using data such as daily activity patterns and sleep duration. For example, the medicine reminder unit can analyze the elderly person's daily activity patterns and evaluate their lifestyle rhythm. Furthermore, the medicine reminder unit can monitor the elderly person's sleep duration and evaluate their lifestyle rhythm. This allows the medicine reminder unit to gain a detailed understanding of the elderly person's daily routine and adjust the frequency of notifications.

[0088] The medicine reminder unit can adjust the content of the notification taking into account the health condition of the elderly person when issuing a medicine reminder. For example, the medicine reminder unit adjusts the content of the notification taking into account the health condition of the elderly person when issuing a medicine reminder. For example, if the elderly person is in poor health, the medicine reminder unit sends a notification emphasizing the importance of taking medication. The medicine reminder unit can also send a regular notification if the elderly person is healthy. Furthermore, if the elderly person has a specific illness, the medicine reminder unit can preferentially send notifications about medicines related to that illness. This allows the content of the notification to be adjusted according to the elderly person's health condition and provide appropriate notifications. The health condition can be taken into account using, for example, current health indicators and past health data. For example, the medicine reminder unit monitors the elderly person's current health indicators and evaluates their health condition. The medicine reminder unit can also refer to past health data to evaluate their health condition. This allows the medicine reminder unit to grasp the elderly person's health condition in detail and adjust the content of the notification.

[0089] The meal provision support unit can estimate the emotions of the elderly and adjust the meal provision method based on the estimated emotions. The meal provision support unit, for example, estimates the emotions of the elderly and adjusts the meal provision method based on the estimated emotions. For example, the meal provision support unit can suggest a relaxing meal menu when the elderly is feeling stressed. Furthermore, the meal provision support unit can suggest a regular meal menu when the elderly is relaxed. Furthermore, the meal provision support unit can suggest a nutritious meal menu when the elderly is tired. This makes it possible to adjust the meal provision method according to the elderly's emotions and provide an appropriate meal. Emotions are estimated using techniques such as voice analysis and facial expression analysis. For example, the meal provision support unit can analyze the tone and speed of the elderly's voice to estimate their emotions. Furthermore, the meal provision support unit can capture the elderly's facial expressions with a camera and estimate their emotions using a facial expression analysis algorithm. This allows the meal provision support unit to grasp the elderly's emotions in detail and adjust the meal provision method.

[0090] The meal provision support unit can suggest an optimal menu by referring to past meal history when providing a meal. The meal provision support unit, for example, can suggest an optimal menu by referring to past meal history when providing a meal. For example, the meal provision support unit can suggest an optimal menu based on the elderly person's past favorite menu items. The meal provision support unit can also suggest a nutritionally balanced menu based on the elderly person's past meal history. Furthermore, the meal provision support unit can analyze the elderly person's past meal history and suggest the healthiest menu. This makes it possible to suggest an optimal menu by referring to the past meal history. The meal history can be referenced, for example, using a past meal record or a reference method. For example, the meal provision support unit can store the past meal history in a digital format and reference it as needed. The meal provision support unit can also store the past meal history on the cloud and reference it in real time. This allows the meal provision support unit to grasp the past meal history in detail and suggest an optimal menu.

[0091] The meal provision support unit can optimize the menu by taking real-time health data into consideration when providing a meal. The meal provision support unit, for example, optimizes the menu by taking real-time health data into consideration when providing a meal. For example, the meal provision support unit proposes an optimal menu based on the elderly person's current blood pressure data. Furthermore, the meal provision support unit can propose an optimal menu based on the elderly person's current blood glucose level data. Furthermore, the meal provision support unit can propose an optimal menu based on the elderly person's current body temperature data. In this way, an optimal menu can be provided by taking real-time health data into consideration. The real-time health data is referenced using, for example, current health indicators and a data acquisition method. For example, the meal provision support unit monitors the elderly person's current health indicators and evaluates their health condition. Furthermore, the meal provision support unit can optimize the menu based on the health data acquired in real time. In this way, the meal provision support unit can grasp the real-time health data in detail and provide an optimal menu.

[0092] The meal provision support unit can estimate the emotions of the elderly and determine the priority of meal provision based on the estimated emotions. The meal provision support unit, for example, estimates the emotions of the elderly and determines the priority of meal provision based on the estimated emotions. For example, if the elderly is feeling stressed, the meal provision support unit can prioritize providing that meal. Furthermore, if the elderly is relaxed, the meal provision support unit can prioritize providing meals with normal priority. Furthermore, if the elderly is tired, the meal provision support unit can prioritize providing nutritious meals. This makes it possible to determine the priority of meal provision according to the elderly's emotions and provide appropriate meals. Emotions are estimated using techniques such as voice analysis and facial expression analysis. For example, the meal provision support unit can analyze the tone and speed of the elderly's voice to estimate their emotions. Furthermore, the meal provision support unit can capture the elderly's facial expressions with a camera and estimate their emotions using a facial expression analysis algorithm. This allows the meal provision support unit to grasp the elderly's emotions in detail and determine the priority of meal provision.

[0093] The meal provision support unit can adjust the menu taking into account the nutritional state of the elderly person when providing a meal. The meal provision support unit, for example, adjusts the menu taking into account the nutritional state of the elderly person when providing a meal. For example, the meal provision support unit can suggest a nutritious menu when the elderly person's nutritional state is poor. Furthermore, the meal provision support unit can suggest a regular menu when the elderly person's nutritional state is good. Furthermore, the meal provision support unit can suggest a menu that supplements a specific nutrient when the elderly person is deficient in that nutrient. This allows the menu to be adjusted according to the elderly person's nutritional state and an appropriate meal to be provided. The nutritional state is taken into account, for example, using current nutritional indicators and past nutritional data. For example, the meal provision support unit monitors the elderly person's current nutritional indicators and evaluates the nutritional state. Furthermore, the meal provision support unit can refer to past nutritional data to evaluate the nutritional state. This allows the meal provision support unit to grasp the elderly person's nutritional state in detail and adjust the menu.

[0094] The meal provision support unit can adjust the menu by referring to the elderly person's past meal history when providing a meal. The meal provision support unit, for example, adjusts the menu by referring to the elderly person's past meal history when providing a meal. For example, the meal provision support unit suggests an optimal menu based on the elderly person's past favorite menu items. The meal provision support unit can also suggest a nutritionally balanced menu based on the elderly person's past meal history. Furthermore, the meal provision support unit can analyze the elderly person's past meal history and suggest the healthiest menu. This makes it possible to provide an optimal menu by referring to the past meal history. The past meal history is referenced, for example, using a past meal record or a reference method. For example, the meal provision support unit stores the past meal history in a digital format and references it as needed. The meal provision support unit can also store the past meal history on the cloud and reference it in real time. This allows the meal provision support unit to understand the past meal history in detail and adjust the menu.

[0095] The fall detection unit can estimate the elderly person's emotions and adjust the accuracy of fall detection based on the estimated emotions. The fall detection unit, for example, estimates the elderly person's emotions and adjusts the accuracy of fall detection based on the estimated emotions. For example, the fall detection unit increases the sensitivity of fall detection when the elderly person is stressed to detect the elderly person more accurately. Furthermore, the fall detection unit can return the sensitivity of fall detection to normal when the elderly person is relaxed to detect natural movements. Furthermore, the fall detection unit can adjust the sensitivity of fall detection when the elderly person is tired to reduce false positives. This allows the accuracy of fall detection to be adjusted according to the elderly person's emotions and reduce false positives. Emotion estimation is performed using techniques such as voice analysis and facial expression analysis. For example, the fall detection unit can analyze the tone and speed of the elderly person's voice to estimate their emotions. Furthermore, the fall detection unit can capture the elderly person's facial expressions with a camera and estimate their emotions using a facial expression analysis algorithm. This allows the fall detection unit to grasp the elderly person's emotions in detail and adjust the accuracy of fall detection.

[0096] The fall detection unit can select the optimal detection algorithm by referring to past fall history when detecting a fall. For example, the fall detection unit can select the optimal detection algorithm by referring to past fall history when detecting a fall. For example, the fall detection unit can strengthen the detection algorithm for a specific location based on the location where the elderly person has fallen in the past. The fall detection unit can also select an algorithm that detects a specific movement pattern from the elderly person's past fall history. Furthermore, the fall detection unit can analyze the elderly person's past fall history and select the most effective detection algorithm. Thus, by referring to the past fall history, the optimal detection algorithm can be selected. The fall history can be referenced, for example, using a past fall record or a reference method. For example, the fall detection unit can store the past fall history in digital format and reference it as needed. Furthermore, the fall detection unit can store the past fall history on the cloud and reference it in real time. This allows the fall detection unit to grasp the past fall history in detail and select the optimal detection algorithm.

[0097] The fall detection unit can improve the accuracy of detection by taking real-time health data into consideration when detecting a fall. The fall detection unit can improve the accuracy of detection by taking real-time health data into consideration when detecting a fall, for example. For example, the fall detection unit can improve the accuracy of fall detection based on the elderly person's current blood pressure data. The fall detection unit can also improve the accuracy of fall detection based on the elderly person's current heart rate data. The fall detection unit can also improve the accuracy of fall detection based on the elderly person's current body temperature data. In this way, the detection accuracy can be improved by taking real-time health data into consideration. The real-time health data can be referenced using, for example, current health indicators or a data acquisition method. For example, the fall detection unit monitors the elderly person's current health indicators and evaluates their health condition. In addition, the fall detection unit can improve the accuracy of detection based on the health data acquired in real time. In this way, the fall detection unit can grasp the real-time health data in detail and improve the detection accuracy.

[0098] The fall detection unit can estimate the elderly person's emotions and determine the priority of fall detection based on the estimated emotions. The fall detection unit can, for example, estimate the elderly person's emotions and determine the priority of fall detection based on the estimated emotions. For example, the fall detection unit can prioritize fall detection when the elderly person is feeling stressed. Furthermore, the fall detection unit can perform fall detection with normal priority when the elderly person is relaxed. Furthermore, the fall detection unit can prioritize important fall detection when the elderly person is tired. This allows the priority of fall detection to be determined according to the elderly person's emotions, allowing appropriate detection. Emotion estimation is performed using techniques such as voice analysis and facial expression analysis. For example, the fall detection unit can analyze the tone and speed of the elderly person's voice to estimate their emotions. Furthermore, the fall detection unit can capture the elderly person's facial expressions with a camera and estimate their emotions using a facial expression analysis algorithm. This allows the fall detection unit to grasp the emotions of the elderly person in detail and determine the priority of fall detection.

[0099] The fall detection unit can adjust the detection method when detecting a fall by taking into account the elderly person's living environment. For example, the fall detection unit adjusts the detection method when detecting a fall by taking into account the elderly person's living environment. For example, when the elderly person is at home, the fall detection unit uses a detection method optimized for the specific environment of the home. Furthermore, when the elderly person is out, the fall detection unit can use a detection method optimized for the external environment. Furthermore, when the elderly person is in a hospital, the fall detection unit can use a detection method optimized for the specific environment inside the hospital. This allows the detection method to be adjusted according to the elderly person's living environment and perform appropriate detection. The living environment is taken into account using, for example, data such as the structure of the residence and daily activity patterns. For example, the fall detection unit analyzes the structure of the elderly person's residence and evaluates the living environment. Furthermore, the fall detection unit can monitor the elderly person's daily activity patterns and evaluate the living environment. This allows the fall detection unit to grasp the elderly person's living environment in detail and adjust the detection method.

[0100] The fall detection unit can improve detection accuracy by referring to the elderly person's past fall history when detecting a fall. The fall detection unit can improve detection accuracy by, for example, referring to the elderly person's past fall history when detecting a fall. For example, the fall detection unit can improve detection accuracy at specific locations based on locations where the elderly person has fallen in the past. The fall detection unit can also improve the accuracy of detecting specific movement patterns from the elderly person's past fall history. Furthermore, the fall detection unit can analyze the elderly person's past fall history and improve the most effective detection accuracy. Thus, by referring to the past fall history, detection accuracy can be improved. Referencing the past fall history is performed, for example, using a past fall record or a reference method. For example, the fall detection unit stores the past fall history in digital format and references it as needed. Furthermore, the fall detection unit can store the past fall history on the cloud and reference it in real time. This allows the fall detection unit to grasp the past fall history in detail and improve detection accuracy. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned voice recognition unit, conversation recording unit, health monitoring unit, alert unit, medicine reminder unit, meal provision support unit, and fall detection unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the voice recognition unit is realized by the microphone 38B and control unit 46A of the smart device 14. The conversation recording unit is realized by the specific processing unit 290 of the data processing device 12. The health monitoring unit is realized by the specific processing unit 290 of the data processing device 12. The alert unit is realized by the specific processing unit 290 of the data processing device 12. The medicine reminder unit is realized by the control unit 46A of the smart device 14. The meal provision support unit is realized by the control unit 46A of the smart device 14. The fall detection unit is realized by the camera 42 and control unit 46A of the smart device 14. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned voice recognition unit, conversation recording unit, health monitoring unit, alert unit, medicine reminder unit, meal provision assistance unit, and fall detection unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the voice recognition unit is realized by the microphone 238 and control unit 46A of the smart glasses 214. The conversation recording unit is realized by the specific processing unit 290 of the data processing device 12. The health monitoring unit is realized by the specific processing unit 290 of the data processing device 12. The alert unit is realized by the specific processing unit 290 of the data processing device 12. The medicine reminder unit is realized by the control unit 46A of the smart glasses 214. The meal provision assistance unit is realized by the control unit 46A of the smart glasses 214. The fall detection unit is realized by the camera 42 and control unit 46A of the smart glasses 214. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned voice recognition unit, conversation recording unit, health monitoring unit, alert unit, medicine reminder unit, meal provision support unit, and fall detection unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the voice recognition unit is realized by the microphone 238 and control unit 46A of the headset type terminal 314. The conversation recording unit is realized by the specific processing unit 290 of the data processing device 12. The health monitoring unit is realized by the specific processing unit 290 of the data processing device 12. The alert unit is realized by the specific processing unit 290 of the data processing device 12. The medicine reminder unit is realized by the control unit 46A of the headset type terminal 314. The meal provision support unit is realized by the control unit 46A of the headset type terminal 314. The fall detection unit is realized by the camera 42 and control unit 46A of the headset type terminal 314. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned voice recognition unit, conversation recording unit, health monitoring unit, alert unit, medicine reminder unit, meal provision assistance unit, and fall detection unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the voice recognition unit is realized by the microphone 238 and control unit 46A of the robot 414. The conversation recording unit is realized by the specific processing unit 290 of the data processing device 12. The health monitoring unit is realized by the specific processing unit 290 of the data processing device 12. The alert unit is realized by the specific processing unit 290 of the data processing device 12. The medicine reminder unit is realized by the control unit 46A of the robot 414. The meal provision assistance unit is realized by the control unit 46A of the robot 414. The fall detection unit is realized by the camera 42 and control unit 46A of the robot 414.

[0101] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0102] The system may further include an activity monitoring unit that monitors the elderly person's activity level. The activity monitoring unit measures the elderly person's daily activity amount and evaluates their health condition. For example, the activity monitoring unit may measure the elderly person's walking distance and exercise amount using a pedometer or an acceleration sensor. The activity monitoring unit may also analyze daily activity patterns and detect abnormal decreases or increases in activity. Furthermore, the activity monitoring unit may provide health advice based on the activity level. This allows for a detailed understanding of the elderly person's activity level and supports health management.

[0103] The alert unit can further estimate the emotion of the elderly person and adjust the content of the alert based on the estimated emotion. For example, if the elderly person is feeling stressed, the alert unit can send an alert in a calm tone. If the elderly person is relaxed, the alert unit can send an alert in a normal tone. Furthermore, if the elderly person is tired, the alert unit can send a concise and easy-to-understand alert. This allows the content of the alert to be adjusted according to the emotion of the elderly person, and appropriate notification to be provided.

[0104] The alert unit can further adjust the timing of sending an alert taking into account the elderly person's lifestyle rhythm. For example, if the elderly person has a lifestyle rhythm of going to bed early and rising early, the alert unit can send an alert in accordance with that rhythm. Also, if the elderly person has a nocturnal lifestyle rhythm, the alert unit can send an alert in accordance with that rhythm. Furthermore, if the elderly person has an irregular lifestyle rhythm, the alert unit can send an alert in accordance with that rhythm. This allows the timing of sending an alert to be adjusted according to the elderly person's lifestyle rhythm, making it possible to provide appropriate notifications.

[0105] The medicine reminder unit can further estimate the elderly person's emotions and adjust the reminder notification method based on the estimated emotions. For example, if the elderly person is nervous, the medicine reminder unit can notify the reminder in a calm tone. If the elderly person is relaxed, the medicine reminder unit can notify the reminder in a normal tone. Furthermore, if the elderly person is tired, the medicine reminder unit can notify the reminder in a concise and easy-to-understand manner. This allows the reminder notification method to be adjusted according to the elderly person's emotions, and appropriate notifications can be provided.

[0106] The meal provision support unit can further estimate the emotions of the elderly person and adjust the method of providing the meal based on the estimated emotions. For example, if the elderly person is feeling stressed, the meal provision support unit can suggest a meal menu that will help them relax. Also, if the elderly person is relaxed, the meal provision support unit can suggest a regular meal menu. Furthermore, if the elderly person is tired, the meal provision support unit can suggest a nutritious meal menu. In this way, the method of providing the meal can be adjusted according to the emotions of the elderly person, and an appropriate meal can be provided.

[0107] The fall detection unit can further adjust the fall detection method taking into account the elderly person's living environment. For example, when the elderly person is at home, the fall detection unit uses a detection method optimized for the specific environment of the home. When the elderly person is out, the fall detection unit can use a detection method optimized for the external environment. When the elderly person is in a hospital, the fall detection unit can use a detection method optimized for the specific environment within the hospital. This allows the fall detection method to be adjusted according to the elderly person's living environment, making it possible to perform appropriate detection.

[0108] The system may further include a social connection support unit for supporting the elderly's social connections. The social connection support unit supports the elderly to keep in contact with friends and family. For example, the social connection support unit may periodically set up video calls with friends and family. The social connection support unit may also support messaging with friends and family. Furthermore, the social connection support unit may provide information on participating in local events and activities. This may strengthen the elderly's social connections and reduce feelings of loneliness.

[0109] The system may further include a hobby support unit for supporting the hobbies and interests of the elderly. The hobby support unit supports the elderly in maintaining their hobbies and interests. For example, the hobby support unit provides information on areas that interest the elderly. The hobby support unit may also support participation in online communities related to hobbies. Furthermore, the hobby support unit may provide information on events and workshops related to hobbies. This supports the hobbies and interests of the elderly, enabling them to live fulfilling lives.

[0110] The system may further include a sleep monitoring unit that monitors the sleep state of the elderly person. The sleep monitoring unit measures the elderly person's sleep patterns and evaluates their health condition. For example, the sleep monitoring unit may monitor their movements and breathing during sleep. The sleep monitoring unit may also evaluate the quality of their sleep and provide advice for improvement. Furthermore, the sleep monitoring unit may detect abnormal sleep patterns and send an alert. This allows for detailed understanding of the elderly person's sleep state and supports health management.

[0111] The system can further estimate the emotions of the elderly person and adjust the overall system operation based on the estimated emotions. For example, if the elderly person feels stressed, the system can play relaxing music. If the elderly person feels relaxed, the system can perform normal operations. Furthermore, if the elderly person feels tired, the system can reduce system notifications. In this way, the system can adjust the overall system operation according to the emotions of the elderly person and provide a comfortable environment.

[0112] The processing flow of the second embodiment will be briefly explained below.

[0113] Step 1: The voice recognition unit recognizes the elderly person's voice. For example, a voice recognition algorithm is used to recognize the elderly person's voice and can support multiple languages ​​(Japanese, English, French, etc.). Additionally, noise cancellation technology is used to remove background noise and improve the accuracy of voice recognition. Step 2: The conversation recording unit records the conversation based on the voice recognized by the voice recognition unit. For example, it converts the voice data into text data, automatically classifies and saves the content of the conversation, and automatically extracts and tags important keywords. Step 3: The health monitoring unit monitors the health status based on the conversation recorded by the conversation recording unit. For example, it analyzes the content of the conversation and refers to past health data to detect abnormalities. If an abnormality is detected, detailed examinations are automatically performed. Step 4: The alert unit sends an alert for dementia or depression based on the information monitored by the health monitoring unit. For example, if it detects signs of dementia or depression, it sends an alert and applies different notification methods (such as phone call, emergency notification, email, or app notification) depending on the importance of the alert.

[0114] 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.

[0115] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0116] 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.

[0117] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0118] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0119] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0128] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0129] 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.

[0130] 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.

[0131] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0132] 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.

[0133] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0134] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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).

[0140] 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.

[0141] 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.

[0142] 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.

[0143] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0144] 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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0145] 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.

[0146] 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.

[0147] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0148] 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.

[0149] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0150] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0161] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. 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 the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0162] 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.

[0163] 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.

[0164] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0165] 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.

[0166] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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).

[0171] 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.

[0172] 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."

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] [Explanation of symbols]

[0186] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A voice recognition unit that recognizes voices, a conversation recording unit that records a conversation based on the voice recognized by the voice recognition unit; a health monitoring unit that monitors a health state based on the conversation recorded by the conversation recording unit; an alert unit that transmits an alert for dementia or depression based on the information monitored by the health monitoring unit. A system characterized by:

2. The alert unit is, Sends alerts if signs of dementia are detected The system of claim 1 .

3. The alert unit is, Sends alerts if it detects signs of depression The system of claim 1 .

4. Equipped with a medicine reminder function that allows you to set reminders to prevent forgetting to take your medicine. The system of claim 1 .

5. Equipping a meal provision support department to help provide regular meals The system of claim 1 .

6. The device is equipped with a fall detection unit that works in conjunction with a camera to detect falls and notify family members and hospitals. The system of claim 1 .

7. The aforementioned voice recognition unit, Estimate the emotions of elderly people and adjust the accuracy of voice recognition based on the estimated emotions. The system of claim 1 .

8. The aforementioned voice recognition unit, Analyze the tone and speed of the elderly person's voice to select the optimal recognition algorithm The system of claim 1 .

9. The aforementioned voice recognition unit, Improve voice recognition accuracy by filtering background noise The system of claim 1 .

Images