System

Abstract

To support the daily life of a dementia patient to make smooth the communication with their family members and a caregiver.SOLUTION: A system according to an embodiment comprises a reminding unit, an identification unit, a notification unit, a detection unit, and a warning unit. The reminding unit reminds a dementia patient of the daily schedule or time to take medicine. The identification unit identifies family members or a caregiver by using face recognition. The notification unit notifies the dementia patient of a result of the identification made by the identification unit. The detection unit detects a change in the behavior or emotion of the dementia patient. The warning unit issues a warning to the family members or a doctor on the basis of a result of the detection performed by the detection unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Current technologies do not adequately support dementia patients in managing their daily lives or communicating with their families and caregivers, leaving room for improvement.

[0005] The system according to the embodiment aims to support the daily lives of dementia patients and facilitate communication with their families and caregivers. [Means for solving the problem]

[0006] The system according to the embodiment includes a reminding unit, an identification unit, a notification unit, a detection unit, and a warning unit. The reminding unit reminds the dementia patient of their daily schedule or the time to take their medicine. The identification unit identifies a family member or a caregiver using face recognition. The notification unit notifies the dementia patient of the identification result by the identification unit. The detection unit detects changes in the behavior or emotions of the dementia patient. The warning unit warns a family member or a doctor based on the detection result by the detection unit. Effect of the Invention

[0007] The system according to the embodiment can support the daily life of dementia patients and facilitate communication between them and their families and caregivers. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

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

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The AI ​​assistant for supporting dementia patients according to the embodiment of the present invention is a system that has a function of reminding the patient of daily schedules and time to take medicine, a function of identifying family members and caregivers using face recognition and notifying the patient, and a function of detecting changes in the patient's behavior and emotions and warning the family and doctor as necessary. This system has five main functions, a reminder unit, an identification unit, a notification unit, a detection unit, and a warning unit, which work together to support the daily life of dementia patients. For example, the reminder unit performs multimodal notifications combining vision, hearing, and touch, and personalizes the reminder method based on the patient's preferences and past behavior history. In addition, the reminder unit dynamically adjusts the reminder content based on the patient's activity level and weather information, and adaptively changes the effective reminder method by learning the patient's reaction to the reminder. The identification unit uses face recognition technology to identify family members and caregivers, and improves the identification accuracy by using location information and specific scents. The notification unit notifies the patient of the identification result, and the detection unit detects changes in the patient's behavior and emotions. The warning unit warns family members and doctors based on the detection result, and warns at the optimal timing taking into account the schedules of the family and doctors. The warning unit also adjusts the urgency of the warning based on the patient's location information, allowing the AI ​​assistant to support dementia patients in their daily lives and warn family members and doctors at the appropriate time.

[0029] An AI assistant for supporting a dementia patient according to an embodiment includes a reminder unit, an identification unit, a notification unit, a detection unit, and a warning unit. The reminder unit reminds the dementia patient of a daily schedule or a time to take medicine. The reminder unit performs a multimodal notification, for example, combining vision, hearing, and touch. The reminder unit can also personalize a reminder method based on the patient's preferences and past behavior history. The reminder unit can also dynamically adjust reminder content based on the patient's activity level and weather information. The reminder unit can learn the patient's response to the reminder and adaptively change an effective reminder method. The identification unit identifies a family member or caregiver using face recognition. The identification unit can also improve the identification accuracy by using location information of the family member or caregiver. The identification unit can also identify a family member or caregiver by identifying a specific scent of the family member or caregiver. The notification unit notifies the dementia patient of the identification result by the identification unit. The detection unit detects a change in the behavior or emotion of the dementia patient. The detection unit can also estimate the patient's emotions and improve the accuracy of detecting changes in behavior and emotions based on the estimated patient's emotions. The detection unit can also improve the detection accuracy by referring to the patient's past behavior history. The detection unit can also detect changes in behavior and emotions using the patient's biological information. The detection unit can also detect changes in behavior and emotions by considering the patient's geographic location information. The detection unit can also detect changes in behavior and emotions by analyzing the patient's social media activities. The warning unit issues a warning to the family and the doctor based on the detection result by the detection unit. The warning unit issues a warning at an optimal timing taking into account the schedules of the family and the doctor. The warning unit adjusts the urgency of the warning based on the location information of the dementia patient. The warning unit can also estimate the patient's emotions and adjust the timing of the warning based on the estimated patient's emotions. The warning unit can also select an optimal warning method by referring to the past reaction history of the family and the doctor. The warning unit can dynamically adjust the warning content based on the patient's current health condition and activity level. The warning unit can also prioritize highly relevant warnings by taking into account the geographic location information of the family and the doctor.The warning unit can also analyze the patient's social media activities and issue relevant warnings, allowing the AI ​​assistant for dementia patient support according to the embodiment to support the daily life of the dementia patient and issue warnings to family members and doctors at appropriate times.

[0030] The reminder unit reminds the dementia patient of their daily schedule or when to take their medicine. The reminder unit, for example, performs multimodal notifications that combine vision, hearing, and touch. Specifically, visual notifications are given using displays and LED lights, auditory notifications are given using audio alarms and music, and tactile notifications are given using vibration devices. This makes it easier for the patient to respond to any of the senses. The reminder unit can also personalize the reminder method based on the patient's preferences and past behavioral history. For example, if the patient has responded best to audio alarms in the past, audio alarms will be used preferentially. The reminder unit can also dynamically adjust the reminder content based on the patient's activity level and weather information. For example, if the weather is bad, it will suggest indoor activities. The reminder unit can learn the patient's response to reminders and adaptively change the effective reminder method. For example, AI analyzes the patient's response data and selects the most effective reminder method. This allows the reminder unit to provide optimal reminders according to the patient's individual needs and enhance support for daily life.

[0031] The identification unit uses facial recognition to identify family members or caregivers. Specifically, a camera is used to capture facial images, and the AI ​​uses a facial recognition algorithm to identify family members or caregivers. The identification unit can also improve the accuracy of identification by using the location information of the family members or caregivers. For example, if a family member is in a specific room, the camera footage of that room is preferentially analyzed. The identification unit can also identify family members or caregivers by identifying their specific scent. A scent sensor is used to detect a specific scent, and the AI ​​identifies the scent. This makes it possible to improve the accuracy of identification by utilizing not only visual information but also olfactory information. The identification unit integrates these diverse information to identify family members and caregivers with high accuracy and provide appropriate information to dementia patients.

[0032] The notification unit notifies the dementia patient of the identification result by the identification unit. Specifically, the name and relationship of the identified family member or caregiver are notified by voice or text. For example, the notification is made in the form of "Your mother has come" or "Tanaka, the caregiver, has come." The notification unit can also customize the notification method according to the patient's preferences. For example, text notification is given priority for patients who do not like voice notifications. The notification unit can also adjust the timing and frequency of notifications. For example, by notifying the patient during a time period when the patient is relaxed, stress is reduced. In this way, the notification unit can provide information to the patient at an appropriate time and give them a sense of security.

[0033] The detection unit detects changes in the behavior or emotions of the dementia patient. Specifically, it analyzes the patient's facial expressions, tone of voice, and movement patterns to estimate changes in emotions. The AI ​​uses image recognition and voice analysis technology to estimate emotions from the patient's facial expressions and tone of voice. It also analyzes the patient's movement patterns to detect abnormal behavior. For example, it detects walking patterns that are different from normal and behavior of staying in the same place for a long time. The detection unit can also estimate the patient's emotions and improve the accuracy of detecting changes in behavior and emotions based on the estimated patient's emotions. Furthermore, the detection unit can improve the detection accuracy by referring to the patient's past behavior history. For example, if a similar behavior was observed in the past, it will detect the behavior reoccurring early. The detection unit can also detect changes in behavior and emotions using the patient's biometric information. For example, it monitors changes in heart rate and body temperature to detect abnormalities. The detection unit can also detect changes in behavior and emotions by taking into account the patient's geographic location information. For example, it analyzes behavioral patterns in a specific place to detect abnormalities. The detection unit can also analyze the patient's social media activity to detect changes in behavior and emotions. This enables the detection unit to integrate a variety of information to detect changes in behavior or emotions with high accuracy and respond quickly.

[0034] The warning unit issues a warning to the family and the doctor based on the detection result by the detection unit. Specifically, when abnormal behavior or changes in emotion are detected, the warning is issued to the family and the doctor by voice call, SMS, email, etc. The warning unit issues a warning at the optimal timing taking into account the schedules of the family and the doctor. For example, when the family is at work, only a warning with a high level of urgency is sent. The warning unit adjusts the urgency of the warning based on the location information of the dementia patient. For example, the content of the warning is changed depending on whether the patient is at home or out. The warning unit can also estimate the patient's emotions and adjust the timing of the warning based on the estimated patient's emotions. For example, by issuing a warning during a time period when the patient is relaxed, stress is reduced. The warning unit can also select the optimal warning method by referring to the past reaction history of the family and the doctor. For example, a warning method that was effective in the past is preferentially used. The warning unit can also dynamically adjust the content of the warning based on the patient's current health condition and activity level. For example, when the patient is in poor health, detailed health information is provided to the doctor. The warning unit can also prioritize highly relevant warnings by taking into account the geographic location information of the family and the doctor. For example, if a family member is nearby, an alert will be sent so that they can respond quickly. The alerting unit can also analyze the patient's social media activity and provide relevant alerts. This allows the alerting unit to provide prompt and appropriate alerts to family members and doctors to ensure the safety of the dementia patient.

[0035] The reminder unit can perform multimodal notification by combining vision, hearing, and touch. For example, the reminder unit can use a message displayed on a screen or a flashing light as a visual notification. In addition, the reminder unit can use a voice message or an alarm sound as an auditory notification. In addition, the reminder unit can use vibration or haptic feedback as a haptic notification. For example, the reminder unit can perform notification by combining the three senses of vision, hearing, and touch by playing a voice message while displaying a message on a screen and vibrating the device at the same time. This allows for effective reminding of the patient.

[0036] The reminding unit can personalize the reminding method based on the preferences and past behavioral history of the dementia patient. For example, the reminding unit can preferentially use the reminding method to which the patient responded favorably in the past. For example, if the patient responded well to a voice message, the reminding unit can use the voice message to remind the patient. In addition, the timing and content of the reminding can be adjusted based on the patient's past behavioral history. For example, if the patient has a habit of taking medicine at a specific time of day, the reminding unit can remind the patient at that time of day. This makes it possible to provide the patient with the most suitable reminding method.

[0037] The warning unit can issue a warning at an appropriate timing based on the schedule of the family member or the doctor. The warning unit can adjust the timing of the warning, for example, taking into account the working hours and break times of the family member or the doctor. For example, when the family member is at work, the warning unit can delay a warning with a low level of urgency and issue the warning during the break time or after the end of work. Furthermore, issuing a warning in accordance with the doctor's consultation hours allows for a quick response. This allows the warning to be issued at an appropriate timing to the family member or the doctor.

[0038] The reminder unit can dynamically adjust the reminder content based on the activity level of the dementia patient and weather information. For example, when the activity level of the patient is high, the reminder unit can simplify the reminder content to reduce the burden on the patient. In addition, based on the weather information, the reminder unit can provide advice according to the weather when reminding the patient to go out. For example, it can remind the patient to take an umbrella on a rainy day. This makes it possible to provide reminder content according to the patient's situation.

[0039] The identification unit can improve the identification accuracy by using location information of the family member or caregiver. The identification unit can improve the identification accuracy by using, for example, GPS data or Wi-Fi location information of the family member or caregiver. For example, when a family member is in a specific location, the identification accuracy can be improved based on the location information. Furthermore, when a family member or caregiver is nearby, the identification accuracy is improved, enabling more accurate identification. This can improve the identification accuracy of the family member or caregiver.

[0040] The warning unit can adjust the urgency of the warning based on the location information of the dementia patient. The warning unit can adjust the urgency of the warning, for example, between when the patient is at home and when the patient is out. For example, when the patient is at home, a low-urgency warning can be issued, but when the patient is out, a high-urgency warning can be issued. Also, when the patient is in a specific location, a warning related to that location can be issued. This makes it possible to adjust the urgency of the warning based on the location information of the patient.

[0041] The reminding unit can learn the dementia patient's response to the reminder and adaptively change the effective reminding method. The reminding unit can, for example, learn how the patient responds to the reminder and change the reminding method based on the response. For example, if the patient responds well to a voice message, the reminding unit can use the voice message to remind the patient. Also, if the patient responds poorly to a specific reminding method, the reminding unit can avoid that method. This makes it possible to optimize the reminding method based on the patient's response.

[0042] The identification unit can identify a family member or a caregiver by identifying a specific scent of the family member or the caregiver. The identification unit can identify a family member or a caregiver by, for example, identifying a perfume of the family member or a specific smell of the caregiver. For example, the identification unit can detect a specific scent with a sensor and perform identification based on the scent. The identification unit can also identify a specific scent by using a scent database. This can improve the accuracy of identifying family members and caregivers.

[0043] The reminding unit can analyze the patient's past reminder history and select the optimal reminder method. For example, the reminding unit can preferentially select a reminder method to which the patient has responded well in the past. For example, if the patient responded well to a voice message, the reminding unit can use the voice message to remind the patient. It can also avoid reminder methods that the patient has ignored in the past and try new methods. Furthermore, it can also select a reminder method that is effective at a specific time period from the patient's past reminder history. This makes it possible to provide the patient with the optimal reminder method.

[0044] The reminder unit can dynamically adjust the reminder content based on the patient's current health condition and activity level at the time of reminding. For example, if the patient is tired, the reminder unit can simplify the reminder content to reduce the burden on the patient. Also, if the patient is active, the reminder unit can provide detailed reminder content. Furthermore, if the patient's health condition is deteriorating, important reminders can be given priority. In this way, reminder content according to the patient's situation can be provided.

[0045] When providing a reminder, the reminder unit can prioritize highly relevant reminders by taking into account the geographic location information of the patient. For example, when the patient is at home, the reminder unit can prioritize reminders related to daily schedules. Also, when the patient is out, the reminder unit can prioritize reminders related to the time to take medicine. Furthermore, when the patient is in a specific location, the reminder unit can provide reminders related to that location. This allows appropriate reminders to be provided based on the patient's location information.

[0046] The reminder unit can analyze the social media activity of the patient at the time of reminding and can provide a relevant reminder. For example, if the patient posts on social media that he / she plans to attend a specific event, the reminder unit can provide a reminder related to the event. Also, if the patient shares information about a specific medication on social media, the reminder unit can provide a reminder for the time to take the medication. Furthermore, if the patient posts on social media that he / she plans to go to a specific place, the reminder unit can provide a reminder related to the place. This makes it possible to provide appropriate reminders based on the patient's social media activity.

[0047] The identification unit can improve the identification accuracy by referring to the past visit history of the family member or caregiver at the time of identification. The identification unit can improve the identification accuracy by taking into account, for example, the time period when the family member or caregiver frequently visits. In addition, the identification unit can improve the identification accuracy by extracting a specific pattern from the past visit history of the family member or caregiver. Furthermore, the identification algorithm can be adjusted based on the visit frequency of the family member or caregiver. This makes it possible to improve the identification accuracy based on the past visit history of the family member or caregiver.

[0048] The identification unit can improve the accuracy of identification by utilizing the voice characteristics of the family member or caregiver during identification. For example, the identification unit can analyze the tone and pitch of the voice of the family member or caregiver to improve the accuracy of identification. Also, the voice characteristics of the family member or caregiver can be registered in a database and referenced during identification. Furthermore, the voice patterns of the family member or caregiver can be learned to strengthen the identification algorithm. This makes it possible to improve the accuracy of identification based on the voice characteristics of the family member or caregiver.

[0049] The identification unit can improve the accuracy of identification by using the clothes and belongings of the family member or caregiver during identification. For example, the identification unit can analyze the color and design of the clothes of the family member or caregiver to improve the accuracy of identification. The identification unit can also incorporate the belongings of the family member or caregiver (bag, hat, etc.) into the identification algorithm. Furthermore, the characteristics of the clothes and belongings of the family member or caregiver can be registered in a database and referenced during identification. This makes it possible to improve the accuracy of identification based on the clothes and belongings of the family member or caregiver.

[0050] The identification unit can improve the identification accuracy by utilizing the walking patterns of the family member or caregiver during identification. The identification unit can, for example, analyze the walking speed and rhythm of the family member or caregiver to improve the identification accuracy. Also, the walking patterns of the family member or caregiver can be registered in a database and referenced during identification. Furthermore, the identification algorithm can be strengthened by learning the walking patterns of the family member or caregiver. This makes it possible to improve the identification accuracy based on the walking patterns of the family member or caregiver.

[0051] At the time of notification, the notification unit can select the optimal notification method by referring to the patient's past reaction history. For example, the notification unit can preferentially select a notification method to which the patient responded well in the past. The notification unit can also try a new method, avoiding notification methods that the patient has ignored in the past. Furthermore, the notification unit can select a notification method that is effective in a specific time period from the patient's past reaction history. This makes it possible to provide the optimal notification method based on the patient's past reaction history.

[0052] The notification unit can dynamically adjust the notification content based on the current activity status of the patient at the time of notification. For example, when the patient is resting, the notification unit can provide detailed notification content. Also, when the patient is active, the notification unit can provide concise notification content. Furthermore, the notification timing can be adjusted according to the activity status of the patient. This makes it possible to provide appropriate notification content according to the activity status of the patient.

[0053] When sending a notification, the notification unit can prioritize notifications that are highly relevant, taking into consideration the geographical location information of the patient. For example, when the patient is at home, the notification unit can prioritize notifications related to the patient's daily schedule. Also, when the patient is out, the notification unit can prioritize notifications related to the time to take medicine. Furthermore, when the patient is in a specific location, notifications related to that location can be sent. This allows appropriate notifications to be sent based on the patient's location information.

[0054] The notification unit can analyze the patient's social media activity at the time of notification and provide a related notification. For example, if a patient posts on social media that he or she plans to attend a specific event, the notification unit can provide a notification related to the event. Also, if a patient shares information about a specific medication on social media, the notification unit can provide a notification of the time to take the medication. Furthermore, if a patient posts on social media that he or she plans to go to a specific place, the notification unit can provide a notification related to the place. In this way, it is possible to provide an appropriate notification based on the patient's social media activity.

[0055] The detection unit can improve detection accuracy by referring to the patient's past behavioral history at the time of detection. The detection unit can, for example, analyze the patient's past behavioral patterns and detect abnormal behavior. In addition, the detection unit can predict behavior that will occur during a specific time period from the patient's past behavioral history, thereby improving detection accuracy. Furthermore, the patient's past behavioral history can be registered in a database and referred to at the time of detection. This makes it possible to improve detection accuracy based on the patient's past behavioral history.

[0056] The detection unit can detect changes in behavior and emotions using the patient's biological information at the time of detection. The detection unit can, for example, monitor the patient's heart rate and blood pressure to detect abnormal changes. It can also monitor the patient's body temperature and respiratory rate to detect abnormal changes. Furthermore, the patient's biological information can be registered in a database and referenced at the time of detection. This allows appropriate detection to be performed based on the patient's biological information.

[0057] The detection unit can detect changes in behavior and emotions by taking into account the geographic location information of the patient at the time of detection. For example, when the patient is at home, the detection unit can detect based on normal behavior patterns. Also, when the patient is out, the detection unit can detect abnormal behavior. Furthermore, when the patient is in a specific location, the detection unit can detect behavior related to that location. This allows appropriate detection to be performed based on the patient's location information.

[0058] The detection unit can analyze the patient's social media activity at the time of detection and detect changes in behavior and emotion. For example, if the patient expresses a specific emotion on social media, the detection unit can detect a change in that emotion. Also, if the patient posts a specific behavior on social media, the detection unit can detect a change in behavior. Furthermore, the patient's social media activity can be registered in a database and referenced at the time of detection. This makes it possible to perform appropriate detection based on the patient's social media activity.

[0059] When issuing a warning, the warning unit can select the optimal warning method by referring to the past reaction history of the family member or doctor. For example, the warning unit can preferentially select a warning method to which the family member or doctor responded well in the past. The warning unit can also try a new method, avoiding warning methods that the family member or doctor ignored in the past. Furthermore, the warning unit can select a warning method that is effective in a specific time period from the past reaction history of the family member or doctor. This makes it possible to provide the optimal warning method based on the past reaction history of the family member or doctor.

[0060] The warning unit can dynamically adjust the warning content based on the patient's current health condition and activity level when issuing a warning. For example, when the patient is tired, the warning unit can simplify the warning content to reduce the burden on the patient. Also, when the patient is active, the warning unit can provide detailed warning content. Furthermore, when the patient's health condition is deteriorating, important warnings can be given priority. In this way, appropriate warning content can be provided according to the patient's health condition and activity level.

[0061] When issuing a warning, the warning unit can prioritize highly relevant warnings by taking into consideration the geographic location information of family members and doctors. For example, when a family member or doctor is nearby, the warning unit can prioritize warnings with high urgency. Also, when a family member or doctor is far away, the warning unit can follow a normal warning schedule. Furthermore, the optimal warning method can be selected based on the geographic location information of family members and doctors. This makes it possible to issue appropriate warnings based on the location information of family members and doctors.

[0062] The warning unit can analyze the social media activity of the patient and issue a related warning when issuing a warning. For example, if the patient expresses a specific emotion on social media, the warning unit can issue a warning based on the emotion. Also, if the patient posts a specific behavior on social media, the warning unit can issue a warning based on the behavior. Furthermore, the patient's social media activity can be registered in a database and referenced at the time of issuing a warning. This makes it possible to issue an appropriate warning based on the patient's social media activity.

[0063] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0064] The reminder unit can recognize the patient's voice commands and adjust the reminder content based on the voice commands. For example, if the patient says, "Tell me when to take my medicine," the reminder unit can recognize the voice command and remind the patient when to take the medicine. Also, if the patient asks, "What's my next appointment?" the reminder unit can notify the patient of the next appointment. Furthermore, if the patient says, "Stop the reminder," the reminder unit can pause the reminder. This makes it possible to flexibly adjust the reminder content based on the patient's voice commands.

[0065] The identification unit can analyze the walking pattern of the patient and detect an abnormal walking pattern. For example, if the patient is walking in a different way from a normal walking pattern, the identification unit can detect the abnormality and notify the notification unit. Also, if the patient falls, the identification unit can detect the fall and issue an emergency warning to the warning unit. Furthermore, the identification unit can learn the walking pattern of the patient and issue a warning if the walking pattern differs from the normal walking pattern. This makes it possible to detect abnormalities early on based on the walking pattern of the patient.

[0066] The detection unit can detect changes in behavior and emotions by using the patient's biological information. For example, it can monitor the patient's heart rate and blood pressure to detect abnormal changes. It can also monitor the patient's body temperature and respiratory rate to detect abnormal changes. Furthermore, it can register the patient's biological information in a database and refer to it at the time of detection. This allows appropriate detection to be performed based on the patient's biological information.

[0067] The reminder section can prioritize relevant reminders by taking into account the geographic location information of the patient. For example, if the patient is at home, reminders about daily schedules can be prioritized. Also, if the patient is out, reminders about the time to take medicine can be prioritized. Furthermore, if the patient is in a specific location, reminders related to that location can be sent. This allows appropriate reminders to be sent based on the patient's location information.

[0068] The identification unit can improve the identification accuracy by utilizing the voice characteristics of the family member or caregiver. For example, the identification accuracy can be improved by analyzing the tone and pitch of the family member or caregiver's voice. In addition, the voice characteristics of the family member or caregiver can be registered in a database and referenced during identification. Furthermore, the identification algorithm can be strengthened by learning the voice patterns of the family member or caregiver. This makes it possible to improve the identification accuracy based on the voice characteristics of the family member or caregiver.

[0069] The notification unit can analyze the patient's social media activity and provide relevant notifications. For example, if a patient posts on social media that he or she plans to attend a specific event, a notification related to the event can be provided. Also, if a patient shares information about a specific medication on social media, a notification can be provided of the time to take the medication. Furthermore, if a patient posts on social media that he or she plans to go to a specific place, a notification related to the place can be provided. In this way, appropriate notifications can be provided based on the patient's social media activity.

[0070] The warning unit can prioritize highly relevant warnings by taking into account the geographic location information of family members and doctors. For example, if a family member or doctor is nearby, a warning with high urgency can be prioritized. If a family member or doctor is far away, a normal warning schedule can be followed. Furthermore, the optimal warning method can be selected based on the geographic location information of family members and doctors. This makes it possible to issue appropriate warnings based on the location information of family members and doctors.

[0071] The process flow of the first embodiment will be briefly described below.

[0072] Step 1: The reminder unit reminds the dementia patient about their daily schedule or when to take their medicine. The reminder unit can provide multimodal notifications that combine visual, auditory, and tactile sensations, and can personalize the reminder method based on the patient's preferences and past behavioral history. It can also dynamically adjust the reminder content based on the patient's activity level and weather information, and adaptively change the effective reminder method by learning the patient's response to reminders. Step 2: The identification unit identifies the family member or caregiver using face recognition. The identification unit can improve the identification accuracy by using the location information of the family member or caregiver, and can also identify the family member or caregiver by identifying a specific scent. Step 3: The notification unit notifies the dementia patient of the identification result by the identification unit. Step 4: The detection unit detects changes in the behavior or emotions of the dementia patient. The detection unit can estimate the patient's emotions and improve the accuracy of detecting changes in behavior and emotions based on the estimated patient's emotions. It can also improve the detection accuracy by referring to the patient's past behavioral history, biometric information, geographic location information, and social media activity. Step 5: The warning unit issues a warning to the family and the doctor based on the detection result by the detection unit. The warning unit issues a warning at the optimal timing taking into account the schedules of the family and the doctor, and adjusts the urgency of the warning based on the location information of the dementia patient. In addition, the warning unit can estimate the patient's emotions, adjust the timing of the warning based on the estimated patient's emotions, and select the optimal warning method by referring to the past reaction history of the family and the doctor. The warning unit can dynamically adjust the warning content based on the patient's current health condition and activity level, and prioritize highly relevant warnings taking into account the geographic location information of the family and the doctor. It can also analyze the patient's social media activity and issue relevant warnings.

[0073] (Example 2) The AI ​​assistant for supporting dementia patients according to the embodiment of the present invention is a system that has a function of reminding the patient of daily schedules and time to take medicine, a function of identifying family members and caregivers using face recognition and notifying the patient, and a function of detecting changes in the patient's behavior and emotions and warning the family and doctor as necessary. This system has five main functions, a reminder unit, an identification unit, a notification unit, a detection unit, and a warning unit, which work together to support the daily life of dementia patients. For example, the reminder unit performs multimodal notifications that combine vision, hearing, and touch, and personalizes the reminder method based on the patient's preferences and past behavioral history. In addition, the reminder unit dynamically adjusts the reminder content based on the patient's activity level and weather information, and adaptively changes the effective reminder method by learning the patient's reaction to the reminder. The identification unit uses face recognition technology to identify family members and caregivers, and improves the identification accuracy by using location information and specific scents. The notification unit notifies the patient of the identification result, and the detection unit detects changes in the patient's behavior and emotions. The warning unit warns family members and doctors based on the detection result, and warns at the optimal timing taking into account the schedules of the family and doctors. The warning unit also adjusts the urgency of the warning based on the patient's location information, allowing the AI ​​assistant to support dementia patients in their daily lives and warn family members and doctors at the appropriate time.

[0074] An AI assistant for supporting a dementia patient according to an embodiment includes a reminder unit, an identification unit, a notification unit, a detection unit, and a warning unit. The reminder unit reminds the dementia patient of a daily schedule or a time to take medicine. The reminder unit performs a multimodal notification, for example, combining vision, hearing, and touch. The reminder unit can also personalize a reminder method based on the patient's preferences and past behavior history. The reminder unit can also dynamically adjust reminder content based on the patient's activity level and weather information. The reminder unit can learn the patient's response to the reminder and adaptively change an effective reminder method. The identification unit identifies a family member or caregiver using face recognition. The identification unit can also improve the identification accuracy by using location information of the family member or caregiver. The identification unit can also identify a family member or caregiver by identifying a specific scent of the family member or caregiver. The notification unit notifies the dementia patient of the identification result by the identification unit. The detection unit detects a change in the behavior or emotion of the dementia patient. The detection unit can also estimate the patient's emotions and improve the accuracy of detecting changes in behavior and emotions based on the estimated patient's emotions. The detection unit can also improve the detection accuracy by referring to the patient's past behavior history. The detection unit can also detect changes in behavior and emotions using the patient's biological information. The detection unit can also detect changes in behavior and emotions by considering the patient's geographic location information. The detection unit can also detect changes in behavior and emotions by analyzing the patient's social media activities. The warning unit issues a warning to the family and the doctor based on the detection result by the detection unit. The warning unit issues a warning at an optimal timing taking into account the schedules of the family and the doctor. The warning unit adjusts the urgency of the warning based on the location information of the dementia patient. The warning unit can also estimate the patient's emotions and adjust the timing of the warning based on the estimated patient's emotions. The warning unit can also select an optimal warning method by referring to the past reaction history of the family and the doctor. The warning unit can dynamically adjust the warning content based on the patient's current health condition and activity level. The warning unit can also prioritize highly relevant warnings by taking into account the geographic location information of the family and the doctor.The warning unit can also analyze the patient's social media activities and issue relevant warnings, allowing the AI ​​assistant for dementia patient support according to the embodiment to support the daily life of the dementia patient and issue warnings to family members and doctors at appropriate times.

[0075] The reminder unit reminds the dementia patient of their daily schedule or when to take their medicine. The reminder unit, for example, performs multimodal notifications that combine vision, hearing, and touch. Specifically, visual notifications are given using displays and LED lights, auditory notifications are given using audio alarms and music, and tactile notifications are given using vibration devices. This makes it easier for the patient to respond to any of the senses. The reminder unit can also personalize the reminder method based on the patient's preferences and past behavioral history. For example, if the patient has responded best to audio alarms in the past, audio alarms will be used preferentially. The reminder unit can also dynamically adjust the reminder content based on the patient's activity level and weather information. For example, if the weather is bad, it will suggest indoor activities. The reminder unit can learn the patient's response to reminders and adaptively change the effective reminder method. For example, AI analyzes the patient's response data and selects the most effective reminder method. This allows the reminder unit to provide optimal reminders according to the patient's individual needs and enhance support for daily life.

[0076] The identification unit uses facial recognition to identify family members or caregivers. Specifically, a camera is used to capture facial images, and the AI ​​uses a facial recognition algorithm to identify family members or caregivers. The identification unit can also improve the accuracy of identification by using the location information of the family members or caregivers. For example, if a family member is in a specific room, the camera footage of that room is preferentially analyzed. The identification unit can also identify family members or caregivers by identifying their specific scent. A scent sensor is used to detect a specific scent, and the AI ​​identifies the scent. This makes it possible to improve the accuracy of identification by utilizing not only visual information but also olfactory information. The identification unit integrates these diverse information to identify family members and caregivers with high accuracy and provide appropriate information to dementia patients.

[0077] The notification unit notifies the dementia patient of the identification result by the identification unit. Specifically, the name and relationship of the identified family member or caregiver are notified by voice or text. For example, the notification is made in the form of "Your mother has come" or "Tanaka, the caregiver, has come." The notification unit can also customize the notification method according to the patient's preferences. For example, text notification is given priority for patients who do not like voice notifications. The notification unit can also adjust the timing and frequency of notifications. For example, by notifying the patient during a time period when the patient is relaxed, stress is reduced. In this way, the notification unit can provide information to the patient at an appropriate time and give them a sense of security.

[0078] The detection unit detects changes in the behavior or emotions of the dementia patient. Specifically, it analyzes the patient's facial expressions, tone of voice, and movement patterns to estimate changes in emotions. The AI ​​uses image recognition and voice analysis technology to estimate emotions from the patient's facial expressions and tone of voice. It also analyzes the patient's movement patterns to detect abnormal behavior. For example, it detects walking patterns that are different from normal and behavior of staying in the same place for a long time. The detection unit can also estimate the patient's emotions and improve the accuracy of detecting changes in behavior and emotions based on the estimated patient's emotions. Furthermore, the detection unit can improve the detection accuracy by referring to the patient's past behavior history. For example, if a similar behavior was observed in the past, it will detect the behavior reoccurring early. The detection unit can also detect changes in behavior and emotions using the patient's biometric information. For example, it monitors changes in heart rate and body temperature to detect abnormalities. The detection unit can also detect changes in behavior and emotions by taking into account the patient's geographic location information. For example, it analyzes behavioral patterns in a specific place to detect abnormalities. The detection unit can also analyze the patient's social media activity to detect changes in behavior and emotions. This enables the detection unit to integrate a variety of information to detect changes in behavior or emotions with high accuracy and respond quickly.

[0079] The warning unit issues a warning to the family and the doctor based on the detection result by the detection unit. Specifically, when abnormal behavior or changes in emotion are detected, the warning is issued to the family and the doctor by voice call, SMS, email, etc. The warning unit issues a warning at the optimal timing taking into account the schedules of the family and the doctor. For example, when the family is at work, only a warning with a high level of urgency is sent. The warning unit adjusts the urgency of the warning based on the location information of the dementia patient. For example, the content of the warning is changed depending on whether the patient is at home or out. The warning unit can also estimate the patient's emotions and adjust the timing of the warning based on the estimated patient's emotions. For example, by issuing a warning during a time period when the patient is relaxed, stress is reduced. The warning unit can also select the optimal warning method by referring to the past reaction history of the family and the doctor. For example, a warning method that was effective in the past is preferentially used. The warning unit can also dynamically adjust the content of the warning based on the patient's current health condition and activity level. For example, when the patient is in poor health, detailed health information is provided to the doctor. The warning unit can also prioritize highly relevant warnings by taking into account the geographic location information of the family and the doctor. For example, if a family member is nearby, an alert will be sent so that they can respond quickly. The alerting unit can also analyze the patient's social media activity and provide relevant alerts. This allows the alerting unit to provide prompt and appropriate alerts to family members and doctors to ensure the safety of the dementia patient.

[0080] The reminder unit can perform multimodal notification by combining vision, hearing, and touch. For example, the reminder unit can use a message displayed on a screen or a flashing light as a visual notification. In addition, the reminder unit can use a voice message or an alarm sound as an auditory notification. In addition, the reminder unit can use vibration or haptic feedback as a haptic notification. For example, the reminder unit can perform notification by combining the three senses of vision, hearing, and touch by playing a voice message while displaying a message on a screen and vibrating the device at the same time. This allows for effective reminding of the patient.

[0081] The reminding unit can personalize the reminding method based on the preferences and past behavioral history of the dementia patient. For example, the reminding unit can preferentially use the reminding method to which the patient responded favorably in the past. For example, if the patient responded well to a voice message, the reminding unit can use the voice message to remind the patient. In addition, the timing and content of the reminding can be adjusted based on the patient's past behavioral history. For example, if the patient has a habit of taking medicine at a specific time of day, the reminding unit can remind the patient at that time of day. This makes it possible to provide the patient with the most suitable reminding method.

[0082] The warning unit can issue a warning at an appropriate timing based on the schedule of the family member or the doctor. The warning unit can adjust the timing of the warning, for example, taking into account the working hours and break times of the family member or the doctor. For example, when the family member is at work, the warning unit can delay a warning with a low level of urgency and issue the warning during the break time or after the end of work. Furthermore, issuing a warning in accordance with the doctor's consultation hours allows for a quick response. This allows the warning to be issued at an appropriate timing to the family member or the doctor.

[0083] The reminder unit can dynamically adjust the reminder content based on the activity level of the dementia patient and weather information. For example, when the activity level of the patient is high, the reminder unit can simplify the reminder content to reduce the burden on the patient. In addition, based on the weather information, the reminder unit can provide advice according to the weather when reminding the patient to go out. For example, it can remind the patient to take an umbrella on a rainy day. This makes it possible to provide reminder content according to the patient's situation.

[0084] The identification unit can improve the identification accuracy by using location information of the family member or caregiver. The identification unit can improve the identification accuracy by using, for example, GPS data or Wi-Fi location information of the family member or caregiver. For example, when a family member is in a specific location, the identification accuracy can be improved based on the location information. Furthermore, when a family member or caregiver is nearby, the identification accuracy is improved, enabling more accurate identification. This can improve the identification accuracy of the family member or caregiver.

[0085] The warning unit can adjust the urgency of the warning based on the location information of the dementia patient. The warning unit can adjust the urgency of the warning, for example, between when the patient is at home and when the patient is out. For example, when the patient is at home, a low-urgency warning can be issued, but when the patient is out, a high-urgency warning can be issued. Also, when the patient is in a specific location, a warning related to that location can be issued. This makes it possible to adjust the urgency of the warning based on the location information of the patient.

[0086] The reminding unit can learn the dementia patient's response to the reminder and adaptively change the effective reminding method. The reminding unit can, for example, learn how the patient responds to the reminder and change the reminding method based on the response. For example, if the patient responds well to a voice message, the reminding unit can use the voice message to remind the patient. Also, if the patient responds poorly to a specific reminding method, the reminding unit can avoid that method. This makes it possible to optimize the reminding method based on the patient's response.

[0087] The identification unit can identify a family member or a caregiver by identifying a specific scent of the family member or the caregiver. The identification unit can identify a family member or a caregiver by, for example, identifying a perfume of the family member or a specific smell of the caregiver. For example, the identification unit can detect a specific scent with a sensor and perform identification based on the scent. The identification unit can also identify a specific scent by using a scent database. This can improve the accuracy of identifying family members and caregivers.

[0088] The reminder unit can estimate the patient's emotions and adjust the timing of reminders based on the estimated patient's emotions. For example, when the patient is stressed, the reminder unit can reduce the frequency of reminders and perform reminders during times when the patient is relaxed. Also, when the patient is relaxed, the reminder unit can perform reminders according to a normal reminder schedule. Furthermore, when the patient is excited, the reminder unit can delay the timing of reminders and perform reminders after the patient has calmed down. This allows reminders to be performed at appropriate times according to the patient's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0089] The reminding unit can analyze the patient's past reminder history and select the optimal reminder method. For example, the reminding unit can preferentially select a reminder method to which the patient has responded well in the past. For example, if the patient responded well to a voice message, the reminding unit can use the voice message to remind the patient. It can also avoid reminder methods that the patient has ignored in the past and try new methods. Furthermore, it can also select a reminder method that is effective at a specific time period from the patient's past reminder history. This makes it possible to provide the patient with the optimal reminder method.

[0090] The reminder unit can dynamically adjust the reminder content based on the patient's current health condition and activity level at the time of reminding. For example, if the patient is tired, the reminder unit can simplify the reminder content to reduce the burden on the patient. Also, if the patient is active, the reminder unit can provide detailed reminder content. Furthermore, if the patient's health condition is deteriorating, important reminders can be given priority. In this way, reminder content according to the patient's situation can be provided.

[0091] The reminder unit can estimate the patient's emotions and determine the priority of reminders based on the estimated patient's emotions. For example, when the patient is stressed, the reminder unit can postpone reminders with low importance. Also, when the patient is relaxed, the reminder unit can follow a normal reminder schedule. Furthermore, when the patient is excited, reminders with high urgency can be given priority. This allows reminders to be given with appropriate priorities according to the patient's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0092] When providing a reminder, the reminder unit can prioritize highly relevant reminders by taking into account the geographic location information of the patient. For example, when the patient is at home, the reminder unit can prioritize reminders related to daily schedules. Also, when the patient is out, the reminder unit can prioritize reminders related to the time to take medicine. Furthermore, when the patient is in a specific location, the reminder unit can provide reminders related to that location. This allows appropriate reminders to be provided based on the patient's location information.

[0093] The reminder unit can analyze the social media activity of the patient at the time of reminding and can provide a relevant reminder. For example, if the patient posts on social media that he / she plans to attend a specific event, the reminder unit can provide a reminder related to the event. Also, if the patient shares information about a specific medication on social media, the reminder unit can provide a reminder for the time to take the medication. Furthermore, if the patient posts on social media that he / she plans to go to a specific place, the reminder unit can provide a reminder related to the place. This makes it possible to provide appropriate reminders based on the patient's social media activity.

[0094] The identification unit can estimate the patient's emotion and improve the accuracy of the identification based on the estimated emotion of the patient. For example, when the patient is relaxed, the identification unit can use a normal identification algorithm. Also, when the patient is stressed, the identification unit can strengthen the identification algorithm and improve the accuracy. Furthermore, when the patient is excited, the identification algorithm can be adjusted to reduce erroneous recognition. This makes it possible to provide an appropriate identification accuracy according to the emotion of the patient. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0095] The identification unit can improve the identification accuracy by referring to the past visit history of the family member or caregiver at the time of identification. The identification unit can improve the identification accuracy by taking into account, for example, the time period when the family member or caregiver frequently visits. In addition, the identification unit can improve the identification accuracy by extracting a specific pattern from the past visit history of the family member or caregiver. Furthermore, the identification algorithm can be adjusted based on the visit frequency of the family member or caregiver. This makes it possible to improve the identification accuracy based on the past visit history of the family member or caregiver.

[0096] The identification unit can improve the accuracy of identification by utilizing the voice characteristics of the family member or caregiver during identification. For example, the identification unit can analyze the tone and pitch of the voice of the family member or caregiver to improve the accuracy of identification. Also, the voice characteristics of the family member or caregiver can be registered in a database and referenced during identification. Furthermore, the voice patterns of the family member or caregiver can be learned to strengthen the identification algorithm. This makes it possible to improve the accuracy of identification based on the voice characteristics of the family member or caregiver.

[0097] The identification unit can estimate the patient's emotion and adjust the display method of the identification result based on the estimated emotion of the patient. For example, when the patient is relaxed, the identification unit can use a normal display method. Also, when the patient is stressed, the identification unit can provide a simple and highly visible display method. Furthermore, when the patient is excited, the identification unit can provide a calm display method. This makes it possible to provide an appropriate display method according to the emotion of the patient. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0098] The identification unit can improve the accuracy of identification by using the clothes and belongings of the family member or caregiver during identification. For example, the identification unit can analyze the color and design of the clothes of the family member or caregiver to improve the accuracy of identification. The identification unit can also incorporate the belongings of the family member or caregiver (bag, hat, etc.) into the identification algorithm. Furthermore, the characteristics of the clothes and belongings of the family member or caregiver can be registered in a database and referenced during identification. This makes it possible to improve the accuracy of identification based on the clothes and belongings of the family member or caregiver.

[0099] The identification unit can improve the identification accuracy by utilizing the walking patterns of the family member or caregiver during identification. The identification unit can, for example, analyze the walking speed and rhythm of the family member or caregiver to improve the identification accuracy. Also, the walking patterns of the family member or caregiver can be registered in a database and referenced during identification. Furthermore, the identification algorithm can be strengthened by learning the walking patterns of the family member or caregiver. This makes it possible to improve the identification accuracy based on the walking patterns of the family member or caregiver.

[0100] The notification unit can estimate the patient's emotion and adjust the notification expression method based on the estimated emotion of the patient. For example, when the patient is relaxed, the notification unit can use a normal notification method. Also, when the patient is stressed, the notification unit can provide a simple and highly visible notification method. Furthermore, when the patient is excited, the notification unit can provide a calm notification method. This makes it possible to provide an appropriate notification method according to the emotion of the patient. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0101] At the time of notification, the notification unit can select the optimal notification method by referring to the patient's past reaction history. For example, the notification unit can preferentially select a notification method to which the patient responded well in the past. The notification unit can also try a new method, avoiding notification methods that the patient has ignored in the past. Furthermore, the notification unit can select a notification method that is effective in a specific time period from the patient's past reaction history. This makes it possible to provide the optimal notification method based on the patient's past reaction history.

[0102] The notification unit can dynamically adjust the notification content based on the current activity status of the patient at the time of notification. For example, when the patient is resting, the notification unit can provide detailed notification content. Also, when the patient is active, the notification unit can provide concise notification content. Furthermore, the notification timing can be adjusted according to the activity status of the patient. This makes it possible to provide appropriate notification content according to the activity status of the patient.

[0103] The notification unit can estimate the patient's emotion and determine the priority of notifications based on the estimated emotion of the patient. For example, when the patient is stressed, the notification unit can postpone notifications of low importance. Also, when the patient is relaxed, the notification unit can follow a normal notification schedule. Furthermore, when the patient is excited, notifications of high urgency can be prioritized. This allows notifications to be made with appropriate priority according to the emotion of the patient. The emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0104] When sending a notification, the notification unit can prioritize notifications that are highly relevant, taking into consideration the geographical location information of the patient. For example, when the patient is at home, the notification unit can prioritize notifications related to the patient's daily schedule. Also, when the patient is out, the notification unit can prioritize notifications related to the time to take medicine. Furthermore, when the patient is in a specific location, notifications related to that location can be sent. This allows appropriate notifications to be sent based on the patient's location information.

[0105] The notification unit can analyze the patient's social media activity at the time of notification and provide a related notification. For example, if a patient posts on social media that he or she plans to attend a specific event, the notification unit can provide a notification related to the event. Also, if a patient shares information about a specific medication on social media, the notification unit can provide a notification of the time to take the medication. Furthermore, if a patient posts on social media that he or she plans to go to a specific place, the notification unit can provide a notification related to the place. In this way, it is possible to provide an appropriate notification based on the patient's social media activity.

[0106] The detection unit can estimate the patient's emotions and improve the accuracy of detecting changes in behavior and emotions based on the estimated patient's emotions. For example, when the patient is relaxed, the detection unit can use a normal detection algorithm. Also, when the patient is stressed, the detection algorithm can be strengthened to improve accuracy. Furthermore, when the patient is excited, the detection algorithm can be adjusted to reduce false positives. This makes it possible to provide appropriate detection accuracy according to the patient's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0107] The detection unit can improve detection accuracy by referring to the patient's past behavioral history at the time of detection. The detection unit can, for example, analyze the patient's past behavioral patterns and detect abnormal behavior. In addition, the detection unit can predict behavior that will occur during a specific time period from the patient's past behavioral history, thereby improving detection accuracy. Furthermore, the patient's past behavioral history can be registered in a database and referred to at the time of detection. This makes it possible to improve detection accuracy based on the patient's past behavioral history.

[0108] The detection unit can detect changes in behavior and emotions using the patient's biological information at the time of detection. The detection unit can, for example, monitor the patient's heart rate and blood pressure to detect abnormal changes. It can also monitor the patient's body temperature and respiratory rate to detect abnormal changes. Furthermore, the patient's biological information can be registered in a database and referenced at the time of detection. This allows appropriate detection to be performed based on the patient's biological information.

[0109] The detection unit can estimate the patient's emotion and adjust the display method of the detection result based on the estimated emotion of the patient. For example, when the patient is relaxed, the detection unit can use a normal display method. Also, when the patient is stressed, the detection unit can provide a simple and highly visible display method. Furthermore, when the patient is excited, the detection unit can provide a calm display method. This makes it possible to provide an appropriate display method according to the emotion of the patient. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0110] The detection unit can detect changes in behavior and emotions by taking into account the geographic location information of the patient at the time of detection. For example, when the patient is at home, the detection unit can detect based on normal behavior patterns. Also, when the patient is out, the detection unit can detect abnormal behavior. Furthermore, when the patient is in a specific location, the detection unit can detect behavior related to that location. This allows appropriate detection to be performed based on the patient's location information.

[0111] The detection unit can analyze the patient's social media activity at the time of detection and detect changes in behavior and emotion. For example, if the patient expresses a specific emotion on social media, the detection unit can detect a change in that emotion. Also, if the patient posts a specific behavior on social media, the detection unit can detect a change in behavior. Furthermore, the patient's social media activity can be registered in a database and referenced at the time of detection. This makes it possible to perform appropriate detection based on the patient's social media activity.

[0112] The warning unit can estimate the patient's emotion and adjust the timing of the warning based on the estimated emotion of the patient. For example, when the patient is relaxed, the warning unit can follow a normal warning schedule. Also, when the patient is stressed, the warning timing can be delayed. Furthermore, when the patient is excited, the warning timing can be adjusted and the warning can be issued after the patient has calmed down. This allows the warning to be issued at an appropriate timing according to the emotion of the patient. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0113] When issuing a warning, the warning unit can select the optimal warning method by referring to the past reaction history of the family member or doctor. For example, the warning unit can preferentially select a warning method to which the family member or doctor responded well in the past. The warning unit can also try a new method, avoiding warning methods that the family member or doctor ignored in the past. Furthermore, the warning unit can select a warning method that is effective in a specific time period from the past reaction history of the family member or doctor. This makes it possible to provide the optimal warning method based on the past reaction history of the family member or doctor.

[0114] The warning unit can dynamically adjust the warning content based on the patient's current health condition and activity level when issuing a warning. For example, when the patient is tired, the warning unit can simplify the warning content to reduce the burden on the patient. Also, when the patient is active, the warning unit can provide detailed warning content. Furthermore, when the patient's health condition is deteriorating, important warnings can be given priority. In this way, appropriate warning content can be provided according to the patient's health condition and activity level.

[0115] The warning unit can estimate the patient's emotion and determine the priority of warnings based on the estimated emotion of the patient. For example, when the patient is stressed, the warning unit can postpone warnings of low importance. Also, when the patient is relaxed, the warning unit can follow a normal warning schedule. Furthermore, when the patient is excited, a warning with high urgency can be given priority. This allows warnings to be issued with appropriate priority according to the emotion of the patient. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0116] When issuing a warning, the warning unit can prioritize highly relevant warnings by taking into consideration the geographic location information of family members and doctors. For example, when a family member or doctor is nearby, the warning unit can prioritize warnings with high urgency. Also, when a family member or doctor is far away, the warning unit can follow a normal warning schedule. Furthermore, the optimal warning method can be selected based on the geographic location information of family members and doctors. This makes it possible to issue appropriate warnings based on the location information of family members and doctors.

[0117] The warning unit can analyze the social media activity of the patient and issue a related warning when issuing a warning. For example, if the patient expresses a specific emotion on social media, the warning unit can issue a warning based on the emotion. Also, if the patient posts a specific behavior on social media, the warning unit can issue a warning based on the behavior. Furthermore, the patient's social media activity can be registered in a database and referenced at the time of issuing a warning. This makes it possible to issue an appropriate warning based on the patient's social media activity.

[0118] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0119] The reminder unit can recognize the patient's voice commands and adjust the reminder content based on the voice commands. For example, if the patient says, "Tell me when to take my medicine," the reminder unit can recognize the voice command and remind the patient when to take the medicine. Also, if the patient asks, "What's my next appointment?" the reminder unit can notify the patient of the next appointment. Furthermore, if the patient says, "Stop the reminder," the reminder unit can pause the reminder. This makes it possible to flexibly adjust the reminder content based on the patient's voice commands.

[0120] The identification unit can analyze the walking pattern of the patient and detect an abnormal walking pattern. For example, if the patient is walking in a different way from a normal walking pattern, the identification unit can detect the abnormality and notify the notification unit. Also, if the patient falls, the identification unit can detect the fall and issue an emergency warning to the warning unit. Furthermore, the identification unit can learn the walking pattern of the patient and issue a warning if the walking pattern differs from the normal walking pattern. This makes it possible to detect abnormalities early on based on the walking pattern of the patient.

[0121] The notification unit can estimate the patient's emotion and adjust the notification expression method based on the estimated emotion. For example, if the patient is feeling stressed, the notification unit can provide a simple and highly visible notification method. If the patient is relaxed, a normal notification method can be used. Furthermore, if the patient is excited, a calm notification method can be provided. In this way, an appropriate notification method according to the patient's emotion can be provided.

[0122] The detection unit can detect changes in behavior and emotions by using the patient's biological information. For example, it can monitor the patient's heart rate and blood pressure to detect abnormal changes. It can also monitor the patient's body temperature and respiratory rate to detect abnormal changes. Furthermore, it can register the patient's biological information in a database and refer to it at the time of detection. This allows appropriate detection to be performed based on the patient's biological information.

[0123] The warning unit can estimate the patient's emotion and adjust the timing of the warning based on the estimated emotion. For example, if the patient is relaxed, the normal warning schedule can be followed. Also, if the patient is stressed, the timing of the warning can be delayed. Furthermore, if the patient is excited, the timing of the warning can be adjusted and the warning can be given after the patient has calmed down. In this way, the warning can be given at an appropriate timing according to the patient's emotion.

[0124] The reminder unit can prioritize relevant reminders by taking into account the geographic location information of the patient. For example, if the patient is at home, reminders about daily schedules can be prioritized. Also, if the patient is out, reminders about the time to take medicine can be prioritized. Furthermore, if the patient is in a specific location, reminders related to that location can be sent. This allows appropriate reminders to be sent based on the patient's location information.

[0125] The identification unit can improve the identification accuracy by utilizing the voice characteristics of the family member or caregiver. For example, the identification accuracy can be improved by analyzing the tone and pitch of the family member or caregiver's voice. In addition, the voice characteristics of the family member or caregiver can be registered in a database and referenced during identification. Furthermore, the identification algorithm can be strengthened by learning the voice patterns of the family member or caregiver. This makes it possible to improve the identification accuracy based on the voice characteristics of the family member or caregiver.

[0126] The notification unit can analyze the patient's social media activity and provide relevant notifications. For example, if a patient posts on social media that he or she plans to attend a specific event, a notification related to the event can be provided. Also, if a patient shares information about a specific medication on social media, a notification can be provided of the time to take the medication. Furthermore, if a patient posts on social media that he or she plans to go to a specific place, a notification related to the place can be provided. In this way, appropriate notifications can be provided based on the patient's social media activity.

[0127] The detection unit can estimate the patient's emotion and adjust the display method of the detection result based on the estimated emotion. For example, if the patient is relaxed, a normal display method can be used. If the patient is stressed, a simple and highly visible display method can be provided. If the patient is excited, a calm display method can be provided. In this way, an appropriate display method according to the patient's emotion can be provided.

[0128] The warning unit can prioritize highly relevant warnings by taking into account the geographic location information of family members and doctors. For example, if a family member or doctor is nearby, a warning with high urgency can be prioritized. If a family member or doctor is far away, a normal warning schedule can be followed. Furthermore, the optimal warning method can be selected based on the geographic location information of family members and doctors. This makes it possible to issue appropriate warnings based on the location information of family members and doctors.

[0129] The process flow of the second embodiment will be briefly described below.

[0130] Step 1: The reminder unit reminds the dementia patient about their daily schedule or when to take their medicine. The reminder unit can provide multimodal notifications that combine visual, auditory, and tactile sensations, and can personalize the reminder method based on the patient's preferences and past behavioral history. It can also dynamically adjust the reminder content based on the patient's activity level and weather information, and adaptively change the effective reminder method by learning the patient's response to reminders. Step 2: The identification unit identifies the family member or caregiver using face recognition. The identification unit can improve the identification accuracy by using the location information of the family member or caregiver, and can also identify the family member or caregiver by identifying a specific scent. Step 3: The notification unit notifies the dementia patient of the identification result by the identification unit. Step 4: The detection unit detects changes in the behavior or emotions of the dementia patient. The detection unit can estimate the patient's emotions and improve the accuracy of detecting changes in behavior and emotions based on the estimated patient's emotions. It can also improve the detection accuracy by referring to the patient's past behavioral history, biometric information, geographic location information, and social media activity. Step 5: The warning unit issues a warning to the family and the doctor based on the detection result by the detection unit. The warning unit issues a warning at the optimal timing taking into account the schedules of the family and the doctor, and adjusts the urgency of the warning based on the location information of the dementia patient. In addition, the warning unit can estimate the patient's emotions, adjust the timing of the warning based on the estimated patient's emotions, and select the optimal warning method by referring to the past reaction history of the family and the doctor. The warning unit can dynamically adjust the warning content based on the patient's current health condition and activity level, and prioritize highly relevant warnings taking into account the geographic location information of the family and the doctor. It can also analyze the patient's social media activity and issue relevant warnings.

[0131] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0132] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0133] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0134] For example, the reminding unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the identification unit is realized by the camera 42 of the smart device 14 and the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the notification unit is realized by the output device 40 of the smart device 14 and the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the detection unit is realized by the camera 42 of the smart device 14 and the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the warning unit is realized by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0135] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0136] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0137] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0138] The 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.

[0139] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0140] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0141] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0142] Fig. 4 shows an example of 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.

[0143] 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.

[0144] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0145] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0146] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0147] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0148] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0149] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0150] For example, the reminding unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the identification unit is realized by the camera 42 of the smart glasses 214 and the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the notification unit is realized by the speaker 240 of the smart glasses 214 and the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the detection unit is realized by the camera 42 of the smart glasses 214 and the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the warning unit is realized by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0151] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0152] 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.

[0153] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0154] 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.

[0155] 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 the voice according to instructions from the processor 46.

[0156] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0157] 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 performed in a secure state.

[0158] 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.

[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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0161] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific 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.

[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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0163] 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 voice indicating a user input for 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0165] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0166] For example, the reminding unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the identification unit is realized by the camera 42 of the headset type terminal 314 and the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the notification unit is realized by the speaker 240 of the headset type terminal 314 and the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the detection unit is realized by the camera 42 of the headset type terminal 314 and the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the warning unit is realized by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0167] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0168] 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.

[0169] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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.

[0170] 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.

[0171] 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 the voice according to instructions from the processor 46.

[0172] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0173] 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 performed in a secure state.

[0174] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0175] 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.

[0176] 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.

[0177] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0178] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0179] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0180] 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 a voice indicating a user input for 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.

[0181] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0182] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0183] For example, the reminding unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the identification unit is realized by the camera 42 of the robot 414 and the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the notification unit is realized by the speaker 240 of the robot 414 and the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the detection unit is realized by the camera 42 of the robot 414 and the control unit 46A or the specific processing unit 290 of the data processing device 12. For example, the warning unit is realized by the specific processing unit 290 of the data processing device 12. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0184] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0185] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0186] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0187] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0188] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0189] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0190] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0191] 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.

[0192] 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 Universal Serial Bus (USB) 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.

[0193] In addition, 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 upon request from the data processing device 12.

[0194] 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.

[0195] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0196] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0197] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0198] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0199] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0200] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0201] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0202] (Appendix 1) A reminder section that reminds the dementia patient about their daily schedule or when to take their medicine; An identification unit that identifies a family member or a caregiver using facial recognition; a notification unit that notifies the dementia patient of a recognition result by the recognition unit; A detection unit that detects a change in behavior or emotion of the dementia patient; and a warning unit that issues a warning to a family member or a doctor based on the detection result by the detection unit. A system characterized by: (Appendix 2) The reminding unit is Multimodal notifications combining visual, auditory, and tactile sensations 2. The system of claim 1, (Appendix 3) The reminding unit is Personalize the reminder method based on the dementia patient's preferences and past behavioral history. 2. The system of claim 1, (Appendix 4) The warning unit is Providing timely warnings based on the schedule of the family member or doctor 2. The system of claim 1, (Appendix 5) The reminding unit is Dynamically adjust the content of the reminders based on the dementia patient's activity level and weather information. 2. The system of claim 1, (Appendix 6) The identification unit is Improve identification accuracy by utilizing location information of the family member or caregiver 2. The system of claim 1, (Appendix 7) The warning unit is Adjusting the urgency of warnings based on the location information of the dementia patient 2. The system of claim 1, (Appendix 8) The reminding unit is The system learns the dementia patient's response to reminders and adaptively changes the effective reminder method. 2. The system of claim 1, (Appendix 9) The identification unit is Identifying a family member or caregiver by identifying the family member's or caregiver's particular scent 2. The system of claim 1, (Appendix 10) The reminding unit is Estimate the patient's emotions and adjust the timing of reminders based on the estimated patient emotions 2. The system of claim 1, (Appendix 11) The reminding unit is Analyze the patient's past reminder history and select the most appropriate reminder method 2. The system of claim 1, (Appendix 12) The reminding unit is Dynamically adjust reminders based on the patient's current health and activity level 2. The system of claim 1, (Appendix 13) The reminding unit is Estimate the patient's emotions and prioritize reminders based on the estimated patient emotions 2. The system of claim 1, (Appendix 14) The reminding unit is During reminders, the geographic location of the patient is taken into account to prioritize the most relevant reminders 2. The system of claim 1, (Appendix 15) The reminding unit is At the time of reminder, analyze the patient's social media activity to provide relevant reminders 2. The system of claim 1, (Appendix 16) The identification unit is Estimating a patient's emotion and improving the accuracy of identification based on the estimated patient's emotion 2. The system of claim 1, (Appendix 17) The identification unit is When identifying a person, the accuracy of the identification is improved by referencing the past visit history of the family or caregiver. 2. The system of claim 1, (Appendix 18) The identification unit is During identification, the accuracy of identification is improved by utilizing the voice characteristics of family members and caregivers. 2. The system of claim 1, (Appendix 19) The identification unit is Estimating a patient's emotion and adjusting the display method of the identification result based on the estimated patient's emotion 2. The system of claim 1, (Appendix 20) The identification unit is Improve accuracy of identification by using family members or caregivers' clothing and belongings 2. The system of claim 1, (Appendix 21) The identification unit is Improve accuracy of identification by using the walking patterns of family members or caregivers 2. The system of claim 1, (Appendix 22) The notification unit is Inferring patient emotion and adjusting notification language based on the inferred patient emotion 2. The system of claim 1, (Appendix 23) The notification unit is When notifying, the optimal notification method is selected by referring to the patient's past reaction history. 2. The system of claim 1, (Appendix 24) The notification unit is At the time of notification, dynamically adjust notification content based on the patient's current activity 2. The system of claim 1, (Appendix 25) The notification unit is Estimate the patient's emotions and prioritize notifications based on the estimated patient emotions 2. The system of claim 1, (Appendix 26) The notification unit is When sending notifications, the geographic location of the patient is taken into consideration to prioritize the most relevant notifications. 2. The system of claim 1, (Appendix 27) The notification unit is At the time of notification, analyze the patient's social media activity and provide relevant notifications 2. The system of claim 1, (Appendix 28) The detection unit is Improve the accuracy of estimating a patient's emotions and detecting changes in behavior and emotions based on the estimated patient emotions 2. The system of claim 1, (Appendix 29) The detection unit is When detecting, the accuracy of detection is improved by referring to the patient's past behavioral history. 2. The system of claim 1, (Appendix 30) The detection unit is During detection, the patient's biometric information is used to detect changes in behavior and emotions. 2. The system of claim 1, (Appendix 31) The detection unit is Estimating the patient's emotions and adjusting the display method of the detection results based on the estimated patient's emotions 2. The system of claim 1, (Appendix 32) The detection unit is During detection, the geographic location of the patient is taken into account to detect changes in behavior and emotions. 2. The system of claim 1, (Appendix 33) The detection unit is Upon detection, the patient's social media activity is analyzed to detect changes in behavior and emotions. 2. The system of claim 1, (Appendix 34) The warning unit is Estimate the patient's emotions and adjust the timing of warnings based on the estimated patient emotions 2. The system of claim 1, (Appendix 35) The warning unit is When a warning is issued, the system will select the most appropriate warning method by referring to the past reaction history of family members and doctors. 2. The system of claim 1, (Appendix 36) The warning unit is At the time of the alert, dynamically adjust the alert content based on the patient's current health status and activity level 2. The system of claim 1, (Appendix 37) The warning unit is Estimate the patient's emotions and prioritize alerts based on the estimated patient emotions 2. The system of claim 1, (Appendix 38) The warning unit is When alerts occur, they take into account the geographic location of family and doctors to prioritize more relevant alerts 2. The system of claim 1, (Appendix 39) The warning unit is Upon alert, analyze the patient's social media activity and provide relevant alerts 2. The system of claim 1, [Explanation of symbols]

[0203] 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 reminder section that reminds the dementia patient about their daily schedule or when to take their medicine; An identification unit that identifies a family member or a caregiver using facial recognition; a notification unit that notifies the dementia patient of a recognition result by the recognition unit; A detection unit that detects a change in behavior or emotion of the dementia patient; and a warning unit that issues a warning to a family member or a doctor based on the detection result by the detection unit. A system characterized by:

2. The reminding unit is Multimodal notifications combining visual, auditory, and tactile sensations 2. The system of claim 1 .

3. The reminding unit is Personalize the reminder method based on the dementia patient's preferences and past behavioral history.

2. The system of claim 1 .

4. The warning unit is Providing timely warnings based on the schedule of the family member or doctor 2. The system of claim 1 .

5. The reminding unit is Dynamically adjust the content of the reminders based on the dementia patient's activity level and weather information.

2. The system of claim 1 .

6. The identification unit is Improve identification accuracy by utilizing location information of the family member or caregiver 2. The system of claim 1 .

7. The warning unit is Adjusting the urgency of warnings based on the location information of the dementia patient 2. The system of claim 1 .

8. The reminding unit is The system learns the dementia patient's response to reminders and adaptively changes the effective reminder method.

2. The system of claim 1 .

Images