System

Abstract

To provide a system that estimates the emotions of an elderly person and provides an appropriate response accordingly.SOLUTION: A system according to an embodiment comprises an acquisition unit, an estimation unit, a determination unit, and a response unit. The acquisition unit acquires emotion estimation information for estimating the emotions of an elderly person. The estimation unit estimates the emotions of the elderly person on the basis of the emotion estimation information acquired by the acquisition unit. The determination unit determines a response according to the emotions of the elderly person as estimated by the estimation unit. The response unit gives the response determined by the determination 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] Conventional technologies have not adequately estimated the emotions of elderly people and responded accordingly, and there is room for improvement.

[0005] The system according to the embodiment aims to estimate the emotions of elderly people and take appropriate measures accordingly. [Means for solving the problem]

[0006] The system according to the embodiment includes an acquisition unit, an estimation unit, a decision unit, and a response unit. The acquisition unit acquires emotion estimation information for estimating the emotion of an elderly person. The estimation unit estimates the emotion of the elderly person based on the emotion estimation information acquired by the acquisition unit. The decision unit decides a response according to the emotion of the elderly person estimated by the estimation unit. The response unit executes the response decided by the decision unit. Effect of the Invention

[0007] The system according to the embodiment can estimate the emotions of elderly people and take appropriate measures accordingly. [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 system according to the embodiment of the present invention is a system for providing lifestyle support and health management for the elderly using an agent having an emotion engine. In this system, the agent acquires information such as the elderly's facial expression, movement, voice, heart rate, blood pressure, pupil response, brain waves, body temperature, breathing, and posted content, and estimates the elderly's emotion based on this information. Depending on the estimated emotion, the agent decides on an appropriate response and executes the response. For example, if the elderly is sad, the agent will say words to comfort them, if the elderly is happy, the agent will share the joy with them, and if the elderly is angry, the agent will provide a topic to calm them down. In addition, as health support, health checks, prevention of forgetting to take medicine, exercise support, etc. are performed. This can improve the quality of life of the elderly. For example, the agent acquires information such as the elderly's facial expression, movement, voice, heart rate, blood pressure, pupil response, brain waves, body temperature, breathing, and posted content, and estimates the elderly's emotion based on this information. Depending on the estimated emotion, the agent decides on an appropriate response and executes the response. For example, if the elderly is sad, the agent will say words to comfort them, if the elderly is happy, the agent will share the joy with them, and if the elderly is angry, the agent will provide a topic to calm them down. In addition, health support includes health checks, prevention of forgetting to take medicine, and exercise support, which can improve the quality of life of the elderly. In this way, the system can support the elderly's lifestyle and health management by estimating their emotions and responding appropriately.

[0029] The care support system according to the embodiment includes an acquisition unit, an estimation unit, a decision unit, and a corresponding unit. The acquisition unit acquires emotion estimation information for estimating the emotion of an elderly person. The emotion estimation information includes, for example, the facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content of the elderly person, but is not limited to such examples. The acquisition unit acquires the facial expression of the elderly person using, for example, a camera. The acquisition unit can also acquire the voice of the elderly person using a microphone. Furthermore, the acquisition unit can acquire the heart rate and blood pressure of the elderly person using a sensor. For example, the acquisition unit captures the facial expression of the elderly person in real time with a camera and estimates the emotion using facial expression recognition technology. The acquisition unit can also record the voice of the elderly person with a microphone and estimate the emotion using voice analysis technology. Furthermore, the acquisition unit can measure the heart rate and blood pressure of the elderly person with a sensor and estimate the emotion based on the biometric data. The estimation unit estimates the emotion of the elderly person based on the emotion estimation information acquired by the acquisition unit. The estimation unit estimates the emotion using, for example, AI. The AI ​​estimates the emotion using a model that takes the acquired information as input and outputs the emotion. For example, the estimation unit estimates the emotion using an AI model that takes facial expression data as input and outputs the emotion. The estimation unit can also estimate the emotion using an AI model that takes voice data as input and outputs the emotion. The estimation unit can also estimate the emotion using an AI model that takes biometric data as input and outputs the emotion. The determination unit determines a response according to the emotion of the elderly person estimated by the estimation unit. The determination unit determines the response using, for example, an AI. The AI ​​determines the response using a model that takes the estimated emotion as input and outputs a response. For example, the determination unit determines the response using an AI model that takes a sad emotion as input and outputs comforting words. The determination unit can also determine the response using an AI model that takes a happy emotion as input and outputs words that will make the elderly person happy together. The determination unit can also determine the response using an AI model that takes an angry emotion as input and outputs a topic to calm the elderly person. The response unit executes the response determined by the determination unit. The response unit executes the response using, for example, an AI. The AI ​​executes the response using a model that takes the determined response as input and outputs instructions for execution.For example, the response unit receives comforting words as input and vocalizes the comforting words using a voice synthesis technology. The response unit can also receive words that will make the elderly person happy together as input and vocalize the words that will make the elderly person happy together using a voice synthesis technology. The response unit can also receive a topic for calming the elderly person as input and vocalize the topic for calming the elderly person using a voice synthesis technology. In this way, the care support system according to the embodiment can support the elderly person's daily life support and health management by estimating the elderly person's emotions and taking appropriate measures.

[0030] The acquisition unit acquires emotion estimation information for estimating the emotion of the elderly person. The emotion estimation information includes, for example, the elderly person's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content, but is not limited to such examples. The acquisition unit acquires the elderly person's facial expression, for example, using a camera. The acquisition unit can also acquire the elderly person's voice using a microphone. Furthermore, the acquisition unit can also acquire the elderly person's heart rate and blood pressure using a sensor. For example, the acquisition unit captures the elderly person's facial expression in real time with a camera and estimates the emotion using facial expression recognition technology. The acquisition unit can also record the elderly person's voice with a microphone and estimate the emotion using voice analysis technology. Furthermore, the acquisition unit can measure the elderly person's heart rate and blood pressure with a sensor and estimate the emotion based on the biometric data. The acquisition unit centrally manages these data and transmits them to a central database in real time. The camera has a high resolution to capture subtle changes in facial expression on the elderly person's face, and the facial expression recognition algorithm identifies emotions such as smile, anger, and sadness with high accuracy. The microphone analyzes the tone, pitch, and speed of the elderly person's voice to detect changes in emotions. The sensor monitors fluctuations in heart rate and blood pressure in real time to grasp stress and relaxation states. This allows the acquisition unit to collect a wide range of data from various devices and grasp the situation in real time. Furthermore, the acquisition unit can centrally manage these data and link with other systems and departments as necessary. For example, the collected data is stored in a cloud server and made accessible to the estimation unit and decision unit. In addition, by adjusting the frequency and accuracy of data collection, flexible responses according to specific situations and conditions are possible. This allows the acquisition unit to efficiently and effectively collect data and improve the performance of the entire system.

[0031] The estimation unit estimates the emotion of the elderly person based on the emotion estimation information acquired by the acquisition unit. The estimation unit estimates the emotion using, for example, AI. The AI ​​estimates the emotion using a model that takes the acquired information as input and outputs the emotion. For example, the estimation unit estimates the emotion using an AI model that takes facial expression data as input and outputs the emotion. The estimation unit can also estimate the emotion using an AI model that takes voice data as input and outputs the emotion. Furthermore, the estimation unit can estimate the emotion using an AI model that takes biometric data as input and outputs the emotion. The estimation unit integrates these data and combines multiple emotion estimation models to achieve more accurate emotion estimation. For example, by combining a facial expression recognition model and a voice analysis model, emotions are estimated from both facial expressions and tone of voice. In addition, by adding biometric data, stress and relaxation states can be grasped more accurately. The estimation unit can also analyze long-term emotional fluctuations and trends by utilizing past data and statistical information. For example, based on past emotion data, emotional fluctuations in a specific time period or situation are predicted, and future measures are proposed. In addition, the estimation unit can use an anomaly detection algorithm to detect unusual emotion patterns and abnormal data and issue an early warning. This enables the estimation unit to handle not only real-time emotion estimation, but also long-term emotion management and anomaly detection, improving the reliability and safety of the entire system.

[0032] The determination unit determines a response according to the elderly person's emotion estimated by the estimation unit. The determination unit determines the response using, for example, AI. The AI ​​determines the response using a model that takes the estimated emotion as input and outputs a response. For example, the determination unit determines the response using an AI model that takes sad emotions as input and outputs comforting words. The determination unit can also determine the response using an AI model that takes happy emotions as input and outputs words that make the elderly person happy. Furthermore, the determination unit can determine the response using an AI model that takes angry emotions as input and outputs topics to calm the elderly person. The determination unit can customize these responses based on the elderly person's individual needs and past reactions. For example, the determination unit learns how a particular elderly person reacts to specific words or actions, and determines the optimal response based on that information. The determination unit can also present multiple response options and select the most appropriate response. For example, for a sad elderly person, the determination unit can provide not only comforting words but also an option to play relaxing music. Furthermore, the determination unit can continuously modify the response based on emotion data updated in real time to respond to the latest situation. This allows the decision unit to always provide the optimal response and stabilize the emotional state of the elderly person.

[0033] The response unit executes the response determined by the determination unit. The response unit executes the response using, for example, AI. The AI ​​executes the response using a model that takes the determined response as input and outputs instructions for execution. For example, the response unit inputs comforting words and utters the comforting words using speech synthesis technology. The response unit can also input words that make the elderly person happy and utter words that make the elderly person happy using speech synthesis technology. The response unit can also input topics to calm the elderly person and utter topics to calm the elderly person using speech synthesis technology. The response unit can adjust the tone and speed of the voice to provide these responses to the elderly person in a natural manner. For example, when uttering comforting words, a gentle and calm tone is used, and when uttering words to make the elderly person happy, a bright and cheerful tone is used. The response unit can also provide not only voice but also visual feedback and tactile feedback. For example, when uttering comforting words, an avatar with a gentle expression can be displayed on the screen, or a light vibration can be provided using a tactile feedback device. Furthermore, the response unit can monitor the effect of the executed response and correct the response as necessary. For example, if the emotional state of the elderly person does not improve after uttering comforting words, another response can be tried, so that the response unit can always provide the optimal response and stabilize the emotional state of the elderly person.

[0034] The determination unit determines a dialogue with the elderly person according to the elderly person's emotion as a response according to the elderly person's emotion, and the response unit can perform a dialogue according to the elderly person's emotion. For example, when the elderly person is sad, the determination unit determines a response to provide comforting words. For example, the determination unit determines a response using an AI model that receives a sad emotion as an input and outputs comforting words. In addition, the determination unit can also determine a response to share joy with the elderly person when the elderly person is happy. For example, the determination unit determines a response using an AI model that receives a happy emotion as an input and outputs comforting words. In addition, the determination unit can also determine a response to provide a topic to calm the elderly person when the elderly person is angry. For example, the determination unit determines a response using an AI model that receives an angry emotion as an input and outputs a topic to calm the elderly person. The response unit executes the response determined by the determination unit. For example, the response unit receives comforting words as an input and utters comforting words using a voice synthesis technology. In addition, the response unit can receive words that share joy with the elderly person as an input and utter words that share joy with the elderly person using a voice synthesis technology. Furthermore, the response unit can receive a topic to calm the elderly person and use voice synthesis technology to vocalize the topic to calm the elderly person. This allows for a more appropriate response by having a dialogue that matches the elderly person's emotions.

[0035] The determination unit determines health support according to the elderly person's emotion as a response according to the elderly person's emotion, and the response unit can provide health support according to the elderly person's emotion. The determination unit, for example, determines a response that prioritizes a health check when the elderly person is sad. For example, the determination unit inputs a sad emotion and determines a response using an AI model that outputs a health check. The determination unit can also determine a response that prioritizes exercise support when the elderly person is happy. For example, the determination unit inputs a happy emotion and determines a response using an AI model that outputs exercise support. The determination unit can also determine a response that prioritizes mental care when the elderly person is angry. For example, the determination unit inputs an angry emotion and determines a response using an AI model that outputs mental care. The response unit executes the response determined by the determination unit. For example, the response unit inputs a health check and executes the health check. The response unit can also input exercise support and execute exercise support. The response unit can also input mental care and execute mental care. This enables more appropriate health management by providing health support according to the elderly person's emotion.

[0036] The acquisition unit can acquire at least one of the facial expression, movement, voice, heart rate, blood pressure, pupil response, electroencephalogram, body temperature, breathing, and posted content of the elderly person as emotion estimation information. The acquisition unit acquires the facial expression of the elderly person using, for example, a camera. For example, the acquisition unit captures the facial expression of the elderly person in real time using a camera, and estimates the emotion using an emotion recognition technique. The acquisition unit can also acquire the voice of the elderly person using a microphone. For example, the acquisition unit records the voice of the elderly person using a microphone, and estimates the emotion using an audio analysis technique. Furthermore, the acquisition unit can acquire the heart rate and blood pressure of the elderly person using a sensor. For example, the acquisition unit measures the heart rate and blood pressure of the elderly person using a sensor, and estimates the emotion based on the biometric data. This improves the accuracy of emotion estimation by acquiring various information.

[0037] The acquisition unit can estimate the emotion of the elderly person and adjust the type of information to be acquired based on the estimated emotion of the elderly person. For example, when the elderly person is sad, the acquisition unit preferentially acquires the heart rate and the pupil response. For example, the acquisition unit adjusts the type of information using an AI model that takes the emotion of sadness as an input and outputs the heart rate and the pupil response. In addition, the acquisition unit can also preferentially acquire facial expressions and voice tones when the elderly person is happy. For example, the acquisition unit adjusts the type of information using an AI model that takes the emotion of happyness as an input and outputs the facial expressions and voice tones. In addition, the acquisition unit can also preferentially acquire the movement and breathing patterns when the elderly person is angry. For example, the acquisition unit adjusts the type of information using an AI model that takes the emotion of anger as an input and outputs the movement and breathing patterns. This makes it possible to acquire information according to the emotion.

[0038] The acquisition unit can analyze the elderly person's past emotion data and select the acquisition method. For example, the acquisition unit analyzes data when the elderly person was sad in the past and selects an information acquisition method in a similar situation. For example, the acquisition unit inputs past sad emotion data and selects an acquisition method using an AI model that outputs an information acquisition method. The acquisition unit can also analyze data when the elderly person was happy in the past and select an information acquisition method in a similar situation. For example, the acquisition unit inputs past happy emotion data and selects an acquisition method using an AI model that outputs an information acquisition method. The acquisition unit can also analyze data when the elderly person was angry in the past and select an information acquisition method in a similar situation. For example, the acquisition unit inputs past angry emotion data and selects an acquisition method using an AI model that outputs an information acquisition method. This improves the accuracy of information acquisition by utilizing past data.

[0039] When acquiring information, the acquisition unit can select information based on the elderly person's current health condition and living situation. For example, when the elderly person is in poor health, the acquisition unit preferentially acquires information on heart rate and blood pressure. For example, the acquisition unit selects information using an AI model that receives input of poor health and outputs heart rate and blood pressure. In addition, the acquisition unit can also acquire information for adapting to a new environment when the elderly person's living situation changes. For example, the acquisition unit selects information using an AI model that receives input of a change in living situation and outputs information for adapting to a new environment. In addition, when the elderly person has a specific health problem, the acquisition unit can also preferentially acquire information related to the problem. For example, the acquisition unit selects information using an AI model that receives input of a specific health problem and outputs information related to the problem. This makes it possible to acquire information according to the health condition and living situation.

[0040] The acquisition unit can estimate the emotion of the elderly person and determine the priority of information to be acquired based on the estimated emotion of the elderly person. For example, when the elderly person is sad, the acquisition unit preferentially acquires the heart rate and the pupil response. For example, the acquisition unit determines the priority of information using an AI model that inputs the emotion of sadness and outputs the heart rate and the pupil response. In addition, the acquisition unit can also preferentially acquire facial expressions and tone of voice when the elderly person is happy. For example, the acquisition unit determines the priority of information using an AI model that inputs the emotion of happiness and outputs the facial expressions and tone of voice. In addition, the acquisition unit can also preferentially acquire the movement and breathing patterns when the elderly person is angry. For example, the acquisition unit determines the priority of information using an AI model that inputs the emotion of anger and outputs the movement and breathing patterns. This enables efficient information acquisition by determining the priority of information according to emotion.

[0041] When acquiring information, the acquisition unit can preferentially acquire information with high relevance based on the geographical location information of the elderly person. For example, when the elderly person is at home, the acquisition unit preferentially acquires environmental information in the home. For example, the acquisition unit acquires information using an AI model that receives input that the elderly person is at home and outputs environmental information in the home. In addition, when the elderly person is out, the acquisition unit can also preferentially acquire environmental information of the destination when the elderly person is out. For example, the acquisition unit acquires information using an AI model that receives input that the elderly person is out and outputs environmental information of the destination when the elderly person is out. In addition, the acquisition unit can also preferentially acquire information related to the location when the elderly person is in a specific location. For example, the acquisition unit acquires information using an AI model that receives input that the elderly person is in a specific location and outputs information related to the location. In this way, highly relevant information can be acquired by taking into account the geographical location information.

[0042] The acquisition unit can analyze the social media activity of the elderly person when acquiring information, and acquire related information. The acquisition unit, for example, analyzes the content posted by the elderly person on social media, and acquires related emotional information. For example, the acquisition unit acquires information using an AI model that takes the content posted on social media as an input and outputs emotional information. The acquisition unit can also analyze comments received by the elderly person on social media, and acquire related emotional information. For example, the acquisition unit acquires information using an AI model that takes the comments on social media as an input and outputs emotional information. The acquisition unit can also analyze photos and videos shared by the elderly person on social media, and acquire related emotional information. For example, the acquisition unit acquires information using an AI model that takes the photos and videos on social media as an input and outputs emotional information. In this way, related emotional information can be acquired by analyzing social media activities.

[0043] The estimation unit can estimate the emotion of the elderly person and change the estimation algorithm based on the estimated emotion of the elderly person. For example, when the elderly person is sad, the estimation unit adjusts the emotion estimation algorithm to be highly sensitive. For example, the estimation unit changes the estimation algorithm using an AI model that takes a sad emotion as an input and outputs an emotion estimation algorithm adjusted to be highly sensitive. The estimation unit can also adjust the emotion estimation algorithm to be less sensitive when the elderly person is happy. For example, the estimation unit changes the estimation algorithm using an AI model that takes a happy emotion as an input and outputs an emotion estimation algorithm adjusted to be less sensitive. The estimation unit can also adjust the emotion estimation algorithm to be neutral when the elderly person is angry. For example, the estimation unit changes the estimation algorithm using an AI model that takes an angry emotion as an input and outputs an emotion estimation algorithm adjusted to be neutral. This makes it possible to adjust the estimation algorithm according to the emotion.

[0044] The estimation unit can change the level of detail of the estimation based on the importance of the acquired information at the time of estimation. For example, when information of high importance is acquired, the estimation unit performs detailed emotion estimation. For example, the estimation unit inputs information of high importance and changes the level of detail of the estimation using an AI model that outputs a detailed emotion estimation. In addition, the estimation unit can also perform simple emotion estimation when information of low importance is acquired. For example, the estimation unit inputs information of low importance and changes the level of detail of the estimation using an AI model that outputs a simple emotion estimation. In addition, the estimation unit can also perform emotion estimation with a moderate level of detail when information of medium importance is acquired. For example, the estimation unit inputs information of medium importance and changes the level of detail of the estimation using an AI model that outputs an emotion estimation with a moderate level of detail. This makes it possible to adjust the level of detail of the estimation according to the importance of the information.

[0045] The estimation unit can use different estimation algorithms depending on the category of information when making an estimation. For example, the estimation unit applies a facial expression recognition algorithm to facial expression information. For example, the estimation unit performs estimation using an AI model that receives facial expression information as input and outputs a facial expression recognition algorithm. The estimation unit can also apply a voice emotion recognition algorithm to voice information. For example, the estimation unit receives voice information as input and performs estimation using an AI model that outputs a voice emotion recognition algorithm. The estimation unit can also apply a motion analysis algorithm to movement information. For example, the estimation unit receives movement information as input and performs estimation using an AI model that outputs a motion analysis algorithm. This makes it possible to apply an estimation algorithm depending on the category of information.

[0046] The estimation unit can estimate the emotion of the elderly person and change the accuracy of the estimation based on the estimated emotion of the elderly person. For example, the estimation unit increases the accuracy of the emotion estimation when the elderly person is sad. For example, the estimation unit changes the accuracy of the estimation using an AI model that takes a sad emotion as an input and outputs an emotion estimation adjusted to a high accuracy. The estimation unit can also lower the accuracy of the emotion estimation when the elderly person is happy. For example, the estimation unit changes the accuracy of the estimation using an AI model that takes a happy emotion as an input and outputs an emotion estimation adjusted to a low accuracy. The estimation unit can also keep the accuracy of the emotion estimation neutral when the elderly person is angry. For example, the estimation unit changes the accuracy of the estimation using an AI model that takes an angry emotion as an input and outputs an emotion estimation adjusted to a neutral accuracy. This makes it possible to adjust the accuracy of the estimation according to the emotion.

[0047] The estimation unit can set the priority of estimation based on the time of information acquisition at the time of estimation. For example, the estimation unit prioritizes the latest information. For example, the estimation unit inputs the latest information and sets the priority of estimation using an AI model that prioritizes estimation. The estimation unit can also prioritize the latest information while referring to past information. For example, the estimation unit inputs past information and the latest information and sets the priority of estimation using an AI model that prioritizes the latest information. The estimation unit can also prioritize information acquired in a specific time period. For example, the estimation unit inputs information from a specific time period and sets the priority of estimation using an AI model that prioritizes information from that time period. This makes it possible to determine the priority of estimation based on the time of information acquisition.

[0048] The estimation unit can change the order of estimation based on the relevance of information at the time of estimation. For example, the estimation unit preferentially estimates information with high relevance. For example, the estimation unit takes information with high relevance as input, and changes the order of estimation using an AI model that estimates preferentially. The estimation unit can also estimate information with medium relevance next. For example, the estimation unit takes information with medium relevance as input, and changes the order of estimation using an AI model that estimates next. The estimation unit can also estimate information with low relevance last. For example, the estimation unit takes information with low relevance as input, and changes the order of estimation using an AI model that estimates last. This makes it possible to adjust the order of estimation based on the relevance of information.

[0049] The determination unit can estimate the emotion of the elderly person and change the method of determining the response based on the estimated emotion of the elderly person. For example, when the elderly person is sad, the determination unit determines the response to be to offer comforting words. For example, the determination unit inputs the sad emotion and determines the response using an AI model that outputs comforting words. In addition, the determination unit can also determine the response to be to share the joy with the elderly person when the elderly person is happy. For example, the determination unit inputs the happy emotion and determines the response using an AI model that outputs words that share the joy with the elderly person. In addition, the determination unit can also determine the response to be to provide a topic to calm the elderly person when the elderly person is angry. For example, the determination unit inputs the angry emotion and determines the response using an AI model that outputs a topic to calm the elderly person. This makes it possible to adjust the method of determining the response according to the emotion.

[0050] When determining the response, the decision unit can select the response by referring to the past emotion data of the elderly person. For example, the decision unit refers to the response when the elderly person was sad in the past and selects a similar response. For example, the decision unit inputs past sad emotion data and selects a response using an AI model that outputs a similar response. The decision unit can also select a similar response by referring to the response when the elderly person was happy in the past. For example, the decision unit inputs past happy emotion data and selects a response using an AI model that outputs a similar response. The decision unit can also select a similar response by referring to the response when the elderly person was angry in the past. For example, the decision unit inputs past angry emotion data and selects a response using an AI model that outputs a similar response. This makes it possible to select an optimal response by referring to past emotion data.

[0051] When determining the response, the decision unit can change the means of response based on the current health condition of the elderly person. For example, when the elderly person has a poor health condition, the decision unit determines a response that prioritizes a health check. For example, the decision unit inputs the poor health condition and determines the response using an AI model that outputs a health check. In addition, the decision unit can also determine a response that prioritizes exercise support when the elderly person has a good health condition. For example, the decision unit inputs the good health condition and determines the response using an AI model that outputs exercise support. In addition, the decision unit can also determine a response related to a specific health problem when the elderly person has the problem. For example, the decision unit inputs a specific health problem and determines the response using an AI model that outputs a response related to the problem. This makes it possible to customize the response according to the health condition.

[0052] The determination unit can estimate the emotion of the elderly person and set a priority order of responses based on the estimated emotion of the elderly person. For example, when the elderly person is sad, the determination unit prioritizes a comforting response. For example, the determination unit sets the priority order of responses using an AI model that takes the sad emotion as an input and outputs a comforting response. The determination unit can also prioritize a response that makes the elderly person happy together with the elderly person when the elderly person is happy. For example, the determination unit sets the priority order of responses using an AI model that takes the happy emotion as an input and outputs a happy response together with the elderly person. The determination unit can also prioritize a response that calms the elderly person when the elderly person is angry. For example, the determination unit sets the priority order of responses using an AI model that takes the angry emotion as an input and outputs a calming response. This makes it possible to determine the priority order of responses according to emotions.

[0053] When determining the response, the decision unit can select a response method based on the geographical location information of the elderly person. For example, when the elderly person is at home, the decision unit selects a response at home. For example, the decision unit inputs that the elderly person is at home and selects a response method using an AI model that outputs a response at home. In addition, the decision unit can also select a response at a destination when the elderly person is out. For example, the decision unit inputs that the elderly person is out and selects a response method using an AI model that outputs a response at a destination. In addition, the decision unit can also select a response appropriate for the location when the elderly person is in a specific location. For example, the decision unit inputs that the elderly person is in a specific location and selects a response method using an AI model that outputs a response appropriate for the location. In this way, the optimal response method can be selected by taking the geographical location information into consideration.

[0054] When determining the response, the decision unit can analyze the social media activity of the elderly person to suggest a response measure. For example, when the elderly person posts a sad post on social media, the decision unit suggests a comforting response. For example, the decision unit inputs a sad post on social media and suggests a response measure using an AI model that outputs a comforting response. In addition, the decision unit can also suggest a response to rejoice together when the elderly person posts a happy post on social media. For example, the decision unit inputs a happy post on social media and suggests a response measure using an AI model that outputs a happy response together. In addition, the decision unit can also suggest a calming response when the elderly person posts an angry post on social media. For example, the decision unit inputs an angry post on social media and suggests a response measure using an AI model that outputs a calming response. In this way, appropriate response measures can be suggested by analyzing social media activities.

[0055] The response unit can estimate the emotion of the elderly person and change the method of executing the response based on the estimated emotion of the elderly person. For example, if the elderly person is sad, the response unit uses words to comfort them. For example, the response unit uses an AI model that takes sad emotions as input and outputs words to comfort them to execute the response. In addition, the response unit can also use words to make the elderly person happy when the elderly person is happy. For example, the response unit uses an AI model that takes happy emotions as input and outputs words to make the elderly person happy to execute the response. In addition, the response unit can also provide a topic to calm the elderly person when the elderly person is angry. For example, the response unit uses an AI model that takes angry emotions as input and outputs topics to calm the elderly person to execute the response. This makes it possible to adjust the method of executing the response according to emotions.

[0056] The response unit can change the means of response based on the current health condition of the elderly person when the response is executed. For example, the response unit executes a response that prioritizes a health check when the elderly person is in poor health. For example, the response unit executes a response using an AI model that takes a poor health condition as input and outputs a health check. The response unit can also execute a response that prioritizes exercise support when the elderly person is in good health. For example, the response unit executes a response using an AI model that takes a good health condition as input and outputs exercise support. The response unit can also execute a response related to a specific health problem when the elderly person has the problem. For example, the response unit executes a response using an AI model that takes a specific health problem as input and outputs a response related to the problem. This makes it possible to customize the response according to the health condition.

[0057] The response unit can estimate the emotion of the elderly person and set a priority order of responses based on the estimated emotion of the elderly person. For example, when the elderly person is sad, the response unit prioritizes a comforting response. For example, the response unit sets a priority order of responses using an AI model that takes sad emotions as input and outputs a comforting response. In addition, the response unit can also prioritize a response that makes the elderly person happy together with the elderly person when the elderly person is happy. For example, the response unit sets a priority order of responses using an AI model that takes happy emotions as input and outputs a happy response together with the elderly person. In addition, the response unit can also prioritize a response that calms the elderly person when the elderly person is angry. For example, the response unit sets a priority order of responses using an AI model that takes angry emotions as input and outputs a calming response. This makes it possible to determine a priority order of responses according to emotions.

[0058] The response unit can select an execution method based on the geographical location information of the elderly person when executing a response. For example, when the elderly person is at home, the response unit executes a response within the home. For example, the response unit inputs that the elderly person is at home and selects an execution method using an AI model that outputs a response within the home. In addition, the response unit can also execute a response while the elderly person is out when the elderly person is out. For example, the response unit inputs that the elderly person is out and selects an execution method using an AI model that outputs a response while the elderly person is out. In addition, the response unit can also execute a response appropriate for the location when the elderly person is in a specific location. For example, the response unit inputs that the elderly person is in a specific location and selects an execution method using an AI model that outputs a response appropriate for the location. In this way, the optimal execution method can be selected by taking into account the geographical location information.

[0059] When executing the response, the response unit can analyze the social media activity of the elderly person and suggest a response measure. For example, when the elderly person posts a sad post on social media, the response unit executes a comforting response. For example, the response unit executes the response using an AI model that takes a sad social media post as input and outputs a comforting response. In addition, the response unit can also execute a response to rejoice together with the elderly person when the elderly person posts a happy post on social media. For example, the response unit executes the response using an AI model that takes a happy social media post as input and outputs a rejoice together with the elderly person. In addition, the response unit can also execute a response to calm down the elderly person when the elderly person posts an angry post on social media. For example, the response unit executes the response using an AI model that takes an angry social media post as input and outputs a calming response. In this way, appropriate response measures can be suggested by analyzing social media activities.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The acquisition unit acquires the exercise information of the elderly person, and the estimation unit can estimate the health condition of the elderly person based on the exercise information. For example, the acquisition unit estimates a good health condition when the elderly person exercises regularly, and the estimation unit estimates the health condition using an AI model that takes the exercise information as an input and outputs a good health condition. The acquisition unit can also estimate a health risk when the elderly person neglects exercise, and the estimation unit can estimate the health condition using an AI model that takes the exercise information as an input and outputs the health risk. Furthermore, the acquisition unit can estimate an adaptation state when the elderly person starts a new exercise, and the estimation unit can estimate the health condition using an AI model that takes the exercise information as an input and outputs the adaptation state. This makes it possible to estimate the health condition taking into account the exercise information.

[0062] The acquisition unit can acquire the purchase history of the elderly person, and the estimation unit can estimate the elderly person's life pattern based on the purchase history. For example, if the elderly person regularly purchases health foods, the acquisition unit estimates a health-oriented life pattern, and the estimation unit estimates the life pattern using an AI model that takes the purchase history as an input and outputs a health-oriented life pattern. In addition, the acquisition unit can estimate an active life pattern if the elderly person frequently purchases entertainment products, and the estimation unit can estimate the life pattern using an AI model that takes the purchase history as an input and outputs an active life pattern. Furthermore, the acquisition unit can estimate a life pattern requiring health management if the elderly person purchases a lot of medicines, and the estimation unit can estimate the life pattern using an AI model that takes the purchase history as an input and outputs a life pattern requiring health management. This makes it possible to estimate a life pattern taking the purchase history into consideration.

[0063] The acquisition unit can acquire the travel history of the elderly person, and the estimation unit can estimate the activity level of the elderly person based on the travel history. For example, the acquisition unit can estimate a high activity level when the elderly person travels frequently, and the estimation unit can estimate the activity level using an AI model that takes the travel history as an input and outputs a high activity level. In addition, the acquisition unit can estimate a low activity level when the elderly person refrains from traveling, and the estimation unit can estimate the activity level using an AI model that takes the travel history as an input and outputs a low activity level. Furthermore, the acquisition unit can estimate a seasonal activity level when the elderly person tends to travel in a particular season, and the estimation unit can estimate the activity level using an AI model that takes the travel history as an input and outputs a seasonal activity level. This makes it possible to estimate the activity level taking the travel history into consideration.

[0064] The acquisition unit acquires the reading history of the elderly person, and the estimation unit can estimate the intellectual activity level of the elderly person based on the reading history. For example, the acquisition unit estimates a high intellectual activity level when the elderly person reads many books, and the estimation unit estimates the intellectual activity level using an AI model that takes the reading history as an input and outputs a high intellectual activity level. In addition, the acquisition unit can estimate a knowledge level related to the genre when the elderly person likes to read books of a specific genre, and the estimation unit can estimate the intellectual activity level using an AI model that takes the reading history as an input and outputs a knowledge level related to the specific genre. Furthermore, the acquisition unit can estimate a decrease in the intellectual activity level when the elderly person stops reading, and the estimation unit can estimate the intellectual activity level using an AI model that takes the reading history as an input and outputs a decrease in the intellectual activity level. This makes it possible to estimate the intellectual activity level taking the reading history into consideration.

[0065] The acquisition unit can acquire the communication history of the elderly person, and the estimation unit can estimate the social activity level of the elderly person based on the communication history. For example, the acquisition unit estimates a high social activity level when the elderly person frequently contacts friends and family, and the estimation unit estimates the social activity level using an AI model that takes the communication history as an input and outputs a high social activity level. The acquisition unit can also estimate a low social activity level when the elderly person refrains from communication, and the estimation unit can estimate the social activity level using an AI model that takes the communication history as an input and outputs a low social activity level. Furthermore, the acquisition unit can estimate a social activity level related to a specific event when the elderly person participates in the event, and the estimation unit can estimate the social activity level using an AI model that takes the communication history as an input and outputs a social activity level related to the event. This makes it possible to estimate the social activity level taking the communication history into account.

[0066] The process flow of the first embodiment will be briefly described below.

[0067] Step 1: The acquisition unit acquires emotion estimation information for estimating the emotion of an elderly person. The emotion estimation information includes the elderly person's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content. For example, the facial expression of the elderly person is acquired using a camera, the voice of the elderly person is acquired using a microphone, and the heart rate and blood pressure of the elderly person are acquired using a sensor. Step 2: The estimation unit estimates the emotion of the elderly person based on the emotion estimation information acquired by the acquisition unit. The estimation unit estimates emotions using AI and uses a model that inputs facial expression data, voice data, and biometric data and outputs emotions. Step 3: The decision unit determines how to respond to the elderly person's emotions estimated by the estimation unit. The decision unit uses AI to determine how to respond, and uses a model that takes the estimated emotions as input and outputs a response. For example, it outputs comforting words for sad emotions, outputs happy words for happy emotions, and outputs topics to calm the elderly person for angry emotions. Step 4: The response unit executes the response determined by the decision unit. The response unit executes the response using AI, and uses a model that outputs instructions for executing the determined response as input. For example, it may use voice synthesis technology to speak comforting words, speak words of joy together, or speak a topic to calm the person down.

[0068] (Example 2) The system according to the embodiment of the present invention is a system for providing lifestyle support and health management for the elderly using an agent having an emotion engine. In this system, the agent acquires information such as the elderly's facial expression, movement, voice, heart rate, blood pressure, pupil response, brain waves, body temperature, breathing, and posted content, and estimates the elderly's emotion based on this information. Depending on the estimated emotion, the agent decides on an appropriate response and executes the response. For example, if the elderly is sad, the agent will say words to comfort them, if the elderly is happy, the agent will share the joy with them, and if the elderly is angry, the agent will provide a topic to calm them down. In addition, as health support, health checks, prevention of forgetting to take medicine, exercise support, etc. are performed. This can improve the quality of life of the elderly. For example, the agent acquires information such as the elderly's facial expression, movement, voice, heart rate, blood pressure, pupil response, brain waves, body temperature, breathing, and posted content, and estimates the elderly's emotion based on this information. Depending on the estimated emotion, the agent decides on an appropriate response and executes the response. For example, if the elderly is sad, the agent will say words to comfort them, if the elderly is happy, the agent will share the joy with them, and if the elderly is angry, the agent will provide a topic to calm them down. In addition, health support includes health checks, prevention of forgetting to take medicine, and exercise support, which can improve the quality of life of the elderly. In this way, the system can support the elderly's lifestyle and health management by estimating their emotions and responding appropriately.

[0069] The care support system according to the embodiment includes an acquisition unit, an estimation unit, a decision unit, and a corresponding unit. The acquisition unit acquires emotion estimation information for estimating the emotion of an elderly person. The emotion estimation information includes, for example, the facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content of the elderly person, but is not limited to such examples. The acquisition unit acquires the facial expression of the elderly person using, for example, a camera. The acquisition unit can also acquire the voice of the elderly person using a microphone. Furthermore, the acquisition unit can acquire the heart rate and blood pressure of the elderly person using a sensor. For example, the acquisition unit captures the facial expression of the elderly person in real time with a camera and estimates the emotion using facial expression recognition technology. The acquisition unit can also record the voice of the elderly person with a microphone and estimate the emotion using voice analysis technology. Furthermore, the acquisition unit can measure the heart rate and blood pressure of the elderly person with a sensor and estimate the emotion based on the biometric data. The estimation unit estimates the emotion of the elderly person based on the emotion estimation information acquired by the acquisition unit. The estimation unit estimates the emotion using, for example, AI. The AI ​​estimates the emotion using a model that takes the acquired information as input and outputs the emotion. For example, the estimation unit estimates the emotion using an AI model that takes facial expression data as input and outputs the emotion. The estimation unit can also estimate the emotion using an AI model that takes voice data as input and outputs the emotion. The estimation unit can also estimate the emotion using an AI model that takes biometric data as input and outputs the emotion. The determination unit determines a response according to the emotion of the elderly person estimated by the estimation unit. The determination unit determines the response using, for example, an AI. The AI ​​determines the response using a model that takes the estimated emotion as input and outputs a response. For example, the determination unit determines the response using an AI model that takes a sad emotion as input and outputs comforting words. The determination unit can also determine the response using an AI model that takes a happy emotion as input and outputs words that will make the elderly person happy together. The determination unit can also determine the response using an AI model that takes an angry emotion as input and outputs a topic to calm the elderly person. The response unit executes the response determined by the determination unit. The response unit executes the response using, for example, an AI. The AI ​​executes the response using a model that takes the determined response as input and outputs instructions for execution.For example, the response unit receives comforting words as input and vocalizes the comforting words using a voice synthesis technology. The response unit can also receive words that will make the elderly person happy together as input and vocalize the words that will make the elderly person happy together using a voice synthesis technology. The response unit can also receive a topic for calming the elderly person as input and vocalize the topic for calming the elderly person using a voice synthesis technology. In this way, the care support system according to the embodiment can support the elderly person's daily life support and health management by estimating the elderly person's emotions and taking appropriate measures.

[0070] The acquisition unit acquires emotion estimation information for estimating the emotion of the elderly person. The emotion estimation information includes, for example, the elderly person's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content, but is not limited to such examples. The acquisition unit acquires the elderly person's facial expression, for example, using a camera. The acquisition unit can also acquire the elderly person's voice using a microphone. Furthermore, the acquisition unit can also acquire the elderly person's heart rate and blood pressure using a sensor. For example, the acquisition unit captures the elderly person's facial expression in real time with a camera and estimates the emotion using facial expression recognition technology. The acquisition unit can also record the elderly person's voice with a microphone and estimate the emotion using voice analysis technology. Furthermore, the acquisition unit can measure the elderly person's heart rate and blood pressure with a sensor and estimate the emotion based on the biometric data. The acquisition unit centrally manages these data and transmits them to a central database in real time. The camera has a high resolution to capture subtle changes in facial expression on the elderly person's face, and the facial expression recognition algorithm identifies emotions such as smile, anger, and sadness with high accuracy. The microphone analyzes the tone, pitch, and speed of the elderly person's voice to detect changes in emotions. The sensor monitors fluctuations in heart rate and blood pressure in real time to grasp stress and relaxation states. This allows the acquisition unit to collect a wide range of data from various devices and grasp the situation in real time. Furthermore, the acquisition unit can centrally manage these data and link with other systems and departments as necessary. For example, the collected data is stored in a cloud server and made accessible to the estimation unit and decision unit. In addition, by adjusting the frequency and accuracy of data collection, flexible responses according to specific situations and conditions are possible. This allows the acquisition unit to efficiently and effectively collect data and improve the performance of the entire system.

[0071] The estimation unit estimates the emotion of the elderly person based on the emotion estimation information acquired by the acquisition unit. The estimation unit estimates the emotion using, for example, AI. The AI ​​estimates the emotion using a model that takes the acquired information as input and outputs the emotion. For example, the estimation unit estimates the emotion using an AI model that takes facial expression data as input and outputs the emotion. The estimation unit can also estimate the emotion using an AI model that takes voice data as input and outputs the emotion. Furthermore, the estimation unit can estimate the emotion using an AI model that takes biometric data as input and outputs the emotion. The estimation unit integrates these data and combines multiple emotion estimation models to achieve more accurate emotion estimation. For example, by combining a facial expression recognition model and a voice analysis model, emotions are estimated from both facial expressions and tone of voice. In addition, by adding biometric data, stress and relaxation states can be grasped more accurately. The estimation unit can also analyze long-term emotional fluctuations and trends by utilizing past data and statistical information. For example, based on past emotion data, emotional fluctuations in a specific time period or situation are predicted, and future measures are proposed. In addition, the estimation unit can use an anomaly detection algorithm to detect unusual emotion patterns and abnormal data and issue an early warning. This enables the estimation unit to handle not only real-time emotion estimation, but also long-term emotion management and anomaly detection, improving the reliability and safety of the entire system.

[0072] The determination unit determines a response according to the elderly person's emotion estimated by the estimation unit. The determination unit determines the response using, for example, AI. The AI ​​determines the response using a model that takes the estimated emotion as input and outputs a response. For example, the determination unit determines the response using an AI model that takes sad emotions as input and outputs comforting words. The determination unit can also determine the response using an AI model that takes happy emotions as input and outputs words that make the elderly person happy. Furthermore, the determination unit can determine the response using an AI model that takes angry emotions as input and outputs topics to calm the elderly person. The determination unit can customize these responses based on the elderly person's individual needs and past reactions. For example, the determination unit learns how a particular elderly person reacts to specific words or actions, and determines the optimal response based on that information. The determination unit can also present multiple response options and select the most appropriate response. For example, for a sad elderly person, the determination unit can provide not only comforting words but also an option to play relaxing music. Furthermore, the determination unit can continuously modify the response based on emotion data updated in real time to respond to the latest situation. This allows the decision unit to always provide the optimal response and stabilize the emotional state of the elderly person.

[0073] The response unit executes the response determined by the determination unit. The response unit executes the response using, for example, AI. The AI ​​executes the response using a model that takes the determined response as input and outputs instructions for execution. For example, the response unit inputs comforting words and utters the comforting words using speech synthesis technology. The response unit can also input words that make the elderly person happy and utter words that make the elderly person happy using speech synthesis technology. The response unit can also input topics to calm the elderly person and utter topics to calm the elderly person using speech synthesis technology. The response unit can adjust the tone and speed of the voice to provide these responses to the elderly person in a natural manner. For example, when uttering comforting words, a gentle and calm tone is used, and when uttering words to make the elderly person happy, a bright and cheerful tone is used. The response unit can also provide not only voice but also visual feedback and tactile feedback. For example, when uttering comforting words, an avatar with a gentle expression can be displayed on the screen, or a light vibration can be provided using a tactile feedback device. Furthermore, the response unit can monitor the effect of the executed response and correct the response as necessary. For example, if the emotional state of the elderly person does not improve after uttering comforting words, another response can be tried, so that the response unit can always provide the optimal response and stabilize the emotional state of the elderly person.

[0074] The determination unit determines a dialogue with the elderly person according to the elderly person's emotion as a response according to the elderly person's emotion, and the response unit can perform a dialogue according to the elderly person's emotion. For example, when the elderly person is sad, the determination unit determines a response to provide comforting words. For example, the determination unit determines a response using an AI model that receives a sad emotion as an input and outputs comforting words. In addition, the determination unit can also determine a response to share joy with the elderly person when the elderly person is happy. For example, the determination unit determines a response using an AI model that receives a happy emotion as an input and outputs comforting words. In addition, the determination unit can also determine a response to provide a topic to calm the elderly person when the elderly person is angry. For example, the determination unit determines a response using an AI model that receives an angry emotion as an input and outputs a topic to calm the elderly person. The response unit executes the response determined by the determination unit. For example, the response unit receives comforting words as an input and utters comforting words using a voice synthesis technology. In addition, the response unit can receive words that share joy with the elderly person as an input and utter words that share joy with the elderly person using a voice synthesis technology. Furthermore, the response unit can receive a topic to calm the elderly person and use voice synthesis technology to vocalize the topic to calm the elderly person. This allows for a more appropriate response by having a dialogue that matches the elderly person's emotions.

[0075] The determination unit determines health support according to the elderly person's emotion as a response according to the elderly person's emotion, and the response unit can provide health support according to the elderly person's emotion. The determination unit, for example, determines a response that prioritizes a health check when the elderly person is sad. For example, the determination unit inputs a sad emotion and determines a response using an AI model that outputs a health check. The determination unit can also determine a response that prioritizes exercise support when the elderly person is happy. For example, the determination unit inputs a happy emotion and determines a response using an AI model that outputs exercise support. The determination unit can also determine a response that prioritizes mental care when the elderly person is angry. For example, the determination unit inputs an angry emotion and determines a response using an AI model that outputs mental care. The response unit executes the response determined by the determination unit. For example, the response unit inputs a health check and executes the health check. The response unit can also input exercise support and execute exercise support. The response unit can also input mental care and execute mental care. This enables more appropriate health management by providing health support according to the elderly person's emotion.

[0076] The acquisition unit can acquire at least one of the facial expression, movement, voice, heart rate, blood pressure, pupil response, electroencephalogram, body temperature, breathing, and posted content of the elderly person as emotion estimation information. The acquisition unit acquires the facial expression of the elderly person using, for example, a camera. For example, the acquisition unit captures the facial expression of the elderly person in real time using a camera, and estimates the emotion using an emotion recognition technique. The acquisition unit can also acquire the voice of the elderly person using a microphone. For example, the acquisition unit records the voice of the elderly person using a microphone, and estimates the emotion using an audio analysis technique. Furthermore, the acquisition unit can acquire the heart rate and blood pressure of the elderly person using a sensor. For example, the acquisition unit measures the heart rate and blood pressure of the elderly person using a sensor, and estimates the emotion based on the biometric data. This improves the accuracy of emotion estimation by acquiring various information.

[0077] The acquisition unit can estimate the emotion of the elderly person and adjust the type of information to be acquired based on the estimated emotion of the elderly person. For example, when the elderly person is sad, the acquisition unit preferentially acquires the heart rate and the pupil response. For example, the acquisition unit adjusts the type of information using an AI model that takes the emotion of sadness as an input and outputs the heart rate and the pupil response. In addition, the acquisition unit can also preferentially acquire facial expressions and voice tones when the elderly person is happy. For example, the acquisition unit adjusts the type of information using an AI model that takes the emotion of happyness as an input and outputs the facial expressions and voice tones. In addition, the acquisition unit can also preferentially acquire the movement and breathing patterns when the elderly person is angry. For example, the acquisition unit adjusts the type of information using an AI model that takes the emotion of anger as an input and outputs the movement and breathing patterns. This makes it possible to acquire information according to the emotion.

[0078] The acquisition unit can analyze the elderly person's past emotion data and select the acquisition method. For example, the acquisition unit analyzes data when the elderly person was sad in the past and selects an information acquisition method in a similar situation. For example, the acquisition unit inputs past sad emotion data and selects an acquisition method using an AI model that outputs an information acquisition method. The acquisition unit can also analyze data when the elderly person was happy in the past and select an information acquisition method in a similar situation. For example, the acquisition unit inputs past happy emotion data and selects an acquisition method using an AI model that outputs an information acquisition method. The acquisition unit can also analyze data when the elderly person was angry in the past and select an information acquisition method in a similar situation. For example, the acquisition unit inputs past angry emotion data and selects an acquisition method using an AI model that outputs an information acquisition method. This improves the accuracy of information acquisition by utilizing past data.

[0079] When acquiring information, the acquisition unit can select information based on the elderly person's current health condition and living situation. For example, when the elderly person is in poor health, the acquisition unit preferentially acquires information on heart rate and blood pressure. For example, the acquisition unit selects information using an AI model that receives input of poor health and outputs heart rate and blood pressure. In addition, the acquisition unit can also acquire information for adapting to a new environment when the elderly person's living situation changes. For example, the acquisition unit selects information using an AI model that receives input of a change in living situation and outputs information for adapting to a new environment. In addition, when the elderly person has a specific health problem, the acquisition unit can also preferentially acquire information related to the problem. For example, the acquisition unit selects information using an AI model that receives input of a specific health problem and outputs information related to the problem. This makes it possible to acquire information according to the health condition and living situation.

[0080] The acquisition unit can estimate the emotion of the elderly person and determine the priority of information to be acquired based on the estimated emotion of the elderly person. For example, when the elderly person is sad, the acquisition unit preferentially acquires the heart rate and the pupil response. For example, the acquisition unit determines the priority of information using an AI model that inputs the emotion of sadness and outputs the heart rate and the pupil response. In addition, the acquisition unit can also preferentially acquire facial expressions and tone of voice when the elderly person is happy. For example, the acquisition unit determines the priority of information using an AI model that inputs the emotion of happiness and outputs the facial expressions and tone of voice. In addition, the acquisition unit can also preferentially acquire the movement and breathing patterns when the elderly person is angry. For example, the acquisition unit determines the priority of information using an AI model that inputs the emotion of anger and outputs the movement and breathing patterns. This enables efficient information acquisition by determining the priority of information according to emotion.

[0081] When acquiring information, the acquisition unit can preferentially acquire information with high relevance based on the geographical location information of the elderly person. For example, when the elderly person is at home, the acquisition unit preferentially acquires environmental information in the home. For example, the acquisition unit acquires information using an AI model that receives input that the elderly person is at home and outputs environmental information in the home. In addition, when the elderly person is out, the acquisition unit can also preferentially acquire environmental information of the destination when the elderly person is out. For example, the acquisition unit acquires information using an AI model that receives input that the elderly person is out and outputs environmental information of the destination when the elderly person is out. In addition, the acquisition unit can also preferentially acquire information related to the location when the elderly person is in a specific location. For example, the acquisition unit acquires information using an AI model that receives input that the elderly person is in a specific location and outputs information related to the location. In this way, highly relevant information can be acquired by taking into account the geographical location information.

[0082] The acquisition unit can analyze the social media activity of the elderly person when acquiring information, and acquire related information. The acquisition unit, for example, analyzes the content posted by the elderly person on social media, and acquires related emotional information. For example, the acquisition unit acquires information using an AI model that takes the content posted on social media as an input and outputs emotional information. The acquisition unit can also analyze comments received by the elderly person on social media, and acquire related emotional information. For example, the acquisition unit acquires information using an AI model that takes the comments on social media as an input and outputs emotional information. The acquisition unit can also analyze photos and videos shared by the elderly person on social media, and acquire related emotional information. For example, the acquisition unit acquires information using an AI model that takes the photos and videos on social media as an input and outputs emotional information. In this way, related emotional information can be acquired by analyzing social media activities.

[0083] The estimation unit can estimate the emotion of the elderly person and change the estimation algorithm based on the estimated emotion of the elderly person. For example, when the elderly person is sad, the estimation unit adjusts the emotion estimation algorithm to be highly sensitive. For example, the estimation unit changes the estimation algorithm using an AI model that takes a sad emotion as an input and outputs an emotion estimation algorithm adjusted to be highly sensitive. The estimation unit can also adjust the emotion estimation algorithm to be less sensitive when the elderly person is happy. For example, the estimation unit changes the estimation algorithm using an AI model that takes a happy emotion as an input and outputs an emotion estimation algorithm adjusted to be less sensitive. The estimation unit can also adjust the emotion estimation algorithm to be neutral when the elderly person is angry. For example, the estimation unit changes the estimation algorithm using an AI model that takes an angry emotion as an input and outputs an emotion estimation algorithm adjusted to be neutral. This makes it possible to adjust the estimation algorithm according to the emotion.

[0084] The estimation unit can change the level of detail of the estimation based on the importance of the acquired information at the time of estimation. For example, when information of high importance is acquired, the estimation unit performs detailed emotion estimation. For example, the estimation unit inputs information of high importance and changes the level of detail of the estimation using an AI model that outputs a detailed emotion estimation. In addition, the estimation unit can also perform simple emotion estimation when information of low importance is acquired. For example, the estimation unit inputs information of low importance and changes the level of detail of the estimation using an AI model that outputs a simple emotion estimation. In addition, the estimation unit can also perform emotion estimation with a moderate level of detail when information of medium importance is acquired. For example, the estimation unit inputs information of medium importance and changes the level of detail of the estimation using an AI model that outputs an emotion estimation with a moderate level of detail. This makes it possible to adjust the level of detail of the estimation according to the importance of the information.

[0085] The estimation unit can use different estimation algorithms depending on the category of information when making an estimation. For example, the estimation unit applies a facial expression recognition algorithm to facial expression information. For example, the estimation unit performs estimation using an AI model that receives facial expression information as input and outputs a facial expression recognition algorithm. The estimation unit can also apply a voice emotion recognition algorithm to voice information. For example, the estimation unit receives voice information as input and performs estimation using an AI model that outputs a voice emotion recognition algorithm. The estimation unit can also apply a motion analysis algorithm to movement information. For example, the estimation unit receives movement information as input and performs estimation using an AI model that outputs a motion analysis algorithm. This makes it possible to apply an estimation algorithm depending on the category of information.

[0086] The estimation unit can estimate the emotion of the elderly person and change the accuracy of the estimation based on the estimated emotion of the elderly person. For example, the estimation unit increases the accuracy of the emotion estimation when the elderly person is sad. For example, the estimation unit changes the accuracy of the estimation using an AI model that takes a sad emotion as an input and outputs an emotion estimation adjusted to a high accuracy. The estimation unit can also lower the accuracy of the emotion estimation when the elderly person is happy. For example, the estimation unit changes the accuracy of the estimation using an AI model that takes a happy emotion as an input and outputs an emotion estimation adjusted to a low accuracy. The estimation unit can also keep the accuracy of the emotion estimation neutral when the elderly person is angry. For example, the estimation unit changes the accuracy of the estimation using an AI model that takes an angry emotion as an input and outputs an emotion estimation adjusted to a neutral accuracy. This makes it possible to adjust the accuracy of the estimation according to the emotion.

[0087] The estimation unit can set the priority of estimation based on the time of information acquisition at the time of estimation. For example, the estimation unit prioritizes the latest information. For example, the estimation unit inputs the latest information and sets the priority of estimation using an AI model that prioritizes estimation. The estimation unit can also prioritize the latest information while referring to past information. For example, the estimation unit inputs past information and the latest information and sets the priority of estimation using an AI model that prioritizes the latest information. The estimation unit can also prioritize information acquired in a specific time period. For example, the estimation unit inputs information from a specific time period and sets the priority of estimation using an AI model that prioritizes information from that time period. This makes it possible to determine the priority of estimation based on the time of information acquisition.

[0088] The estimation unit can change the order of estimation based on the relevance of information at the time of estimation. For example, the estimation unit preferentially estimates information with high relevance. For example, the estimation unit takes information with high relevance as input, and changes the order of estimation using an AI model that estimates preferentially. The estimation unit can also estimate information with medium relevance next. For example, the estimation unit takes information with medium relevance as input, and changes the order of estimation using an AI model that estimates next. The estimation unit can also estimate information with low relevance last. For example, the estimation unit takes information with low relevance as input, and changes the order of estimation using an AI model that estimates last. This makes it possible to adjust the order of estimation based on the relevance of information.

[0089] The determination unit can estimate the emotion of the elderly person and change the method of determining the response based on the estimated emotion of the elderly person. For example, when the elderly person is sad, the determination unit determines the response to be to offer comforting words. For example, the determination unit inputs the sad emotion and determines the response using an AI model that outputs comforting words. In addition, the determination unit can also determine the response to be to share the joy with the elderly person when the elderly person is happy. For example, the determination unit inputs the happy emotion and determines the response using an AI model that outputs words that share the joy with the elderly person. In addition, the determination unit can also determine the response to be to provide a topic to calm the elderly person when the elderly person is angry. For example, the determination unit inputs the angry emotion and determines the response using an AI model that outputs a topic to calm the elderly person. This makes it possible to adjust the method of determining the response according to the emotion.

[0090] When determining the response, the decision unit can select the response by referring to the past emotion data of the elderly person. For example, the decision unit refers to the response when the elderly person was sad in the past and selects a similar response. For example, the decision unit inputs past sad emotion data and selects a response using an AI model that outputs a similar response. The decision unit can also select a similar response by referring to the response when the elderly person was happy in the past. For example, the decision unit inputs past happy emotion data and selects a response using an AI model that outputs a similar response. The decision unit can also select a similar response by referring to the response when the elderly person was angry in the past. For example, the decision unit inputs past angry emotion data and selects a response using an AI model that outputs a similar response. This makes it possible to select an optimal response by referring to past emotion data.

[0091] When determining the response, the decision unit can change the means of response based on the current health condition of the elderly person. For example, when the elderly person has a poor health condition, the decision unit determines a response that prioritizes a health check. For example, the decision unit inputs the poor health condition and determines the response using an AI model that outputs a health check. In addition, the decision unit can also determine a response that prioritizes exercise support when the elderly person has a good health condition. For example, the decision unit inputs the good health condition and determines the response using an AI model that outputs exercise support. In addition, the decision unit can also determine a response related to a specific health problem when the elderly person has the problem. For example, the decision unit inputs a specific health problem and determines the response using an AI model that outputs a response related to the problem. This makes it possible to customize the response according to the health condition.

[0092] The determination unit can estimate the emotion of the elderly person and set a priority order of responses based on the estimated emotion of the elderly person. For example, when the elderly person is sad, the determination unit prioritizes a comforting response. For example, the determination unit sets the priority order of responses using an AI model that takes the sad emotion as an input and outputs a comforting response. The determination unit can also prioritize a response that makes the elderly person happy together with the elderly person when the elderly person is happy. For example, the determination unit sets the priority order of responses using an AI model that takes the happy emotion as an input and outputs a happy response together with the elderly person. The determination unit can also prioritize a response that calms the elderly person when the elderly person is angry. For example, the determination unit sets the priority order of responses using an AI model that takes the angry emotion as an input and outputs a calming response. This makes it possible to determine the priority order of responses according to emotions.

[0093] When determining the response, the decision unit can select a response method based on the geographical location information of the elderly person. For example, when the elderly person is at home, the decision unit selects a response at home. For example, the decision unit inputs that the elderly person is at home and selects a response method using an AI model that outputs a response at home. In addition, the decision unit can also select a response at a destination when the elderly person is out. For example, the decision unit inputs that the elderly person is out and selects a response method using an AI model that outputs a response at a destination. In addition, the decision unit can also select a response appropriate for the location when the elderly person is in a specific location. For example, the decision unit inputs that the elderly person is in a specific location and selects a response method using an AI model that outputs a response appropriate for the location. In this way, the optimal response method can be selected by taking the geographical location information into consideration.

[0094] When determining the response, the decision unit can analyze the social media activity of the elderly person to suggest a response measure. For example, when the elderly person posts a sad post on social media, the decision unit suggests a comforting response. For example, the decision unit inputs a sad post on social media and suggests a response measure using an AI model that outputs a comforting response. In addition, the decision unit can also suggest a response to rejoice together when the elderly person posts a happy post on social media. For example, the decision unit inputs a happy post on social media and suggests a response measure using an AI model that outputs a happy response together. In addition, the decision unit can also suggest a calming response when the elderly person posts an angry post on social media. For example, the decision unit inputs an angry post on social media and suggests a response measure using an AI model that outputs a calming response. In this way, appropriate response measures can be suggested by analyzing social media activities.

[0095] The response unit can estimate the emotion of the elderly person and change the method of executing the response based on the estimated emotion of the elderly person. For example, if the elderly person is sad, the response unit uses words to comfort them. For example, the response unit uses an AI model that takes sad emotions as input and outputs words to comfort them to execute the response. In addition, the response unit can also use words to make the elderly person happy when the elderly person is happy. For example, the response unit uses an AI model that takes happy emotions as input and outputs words to make the elderly person happy to execute the response. In addition, the response unit can also provide a topic to calm the elderly person when the elderly person is angry. For example, the response unit uses an AI model that takes angry emotions as input and outputs topics to calm the elderly person to execute the response. This makes it possible to adjust the method of executing the response according to emotions.

[0096] The response unit can change the means of response based on the current health condition of the elderly person when the response is executed. For example, the response unit executes a response that prioritizes a health check when the elderly person is in poor health. For example, the response unit executes a response using an AI model that takes a poor health condition as input and outputs a health check. The response unit can also execute a response that prioritizes exercise support when the elderly person is in good health. For example, the response unit executes a response using an AI model that takes a good health condition as input and outputs exercise support. The response unit can also execute a response related to a specific health problem when the elderly person has the problem. For example, the response unit executes a response using an AI model that takes a specific health problem as input and outputs a response related to the problem. This makes it possible to customize the response according to the health condition.

[0097] The response unit can estimate the emotion of the elderly person and set a priority order of responses based on the estimated emotion of the elderly person. For example, when the elderly person is sad, the response unit prioritizes a comforting response. For example, the response unit sets a priority order of responses using an AI model that takes sad emotions as input and outputs a comforting response. In addition, the response unit can also prioritize a response that makes the elderly person happy together with the elderly person when the elderly person is happy. For example, the response unit sets a priority order of responses using an AI model that takes happy emotions as input and outputs a happy response together with the elderly person. In addition, the response unit can also prioritize a response that calms the elderly person when the elderly person is angry. For example, the response unit sets a priority order of responses using an AI model that takes angry emotions as input and outputs a calming response. This makes it possible to determine a priority order of responses according to emotions.

[0098] The response unit can select an execution method based on the geographical location information of the elderly person when executing a response. For example, when the elderly person is at home, the response unit executes a response within the home. For example, the response unit inputs that the elderly person is at home and selects an execution method using an AI model that outputs a response within the home. In addition, the response unit can also execute a response while the elderly person is out when the elderly person is out. For example, the response unit inputs that the elderly person is out and selects an execution method using an AI model that outputs a response while the elderly person is out. In addition, the response unit can also execute a response appropriate for the location when the elderly person is in a specific location. For example, the response unit inputs that the elderly person is in a specific location and selects an execution method using an AI model that outputs a response appropriate for the location. In this way, the optimal execution method can be selected by taking into account the geographical location information.

[0099] When executing the response, the response unit can analyze the social media activity of the elderly person and suggest a response measure. For example, when the elderly person posts a sad post on social media, the response unit executes a comforting response. For example, the response unit executes the response using an AI model that takes a sad social media post as input and outputs a comforting response. In addition, the response unit can also execute a response to rejoice together with the elderly person when the elderly person posts a happy post on social media. For example, the response unit executes the response using an AI model that takes a happy social media post as input and outputs a rejoice together with the elderly person. In addition, the response unit can also execute a response to calm down the elderly person when the elderly person posts an angry post on social media. For example, the response unit executes the response using an AI model that takes an angry social media post as input and outputs a calming response. In this way, appropriate response measures can be suggested by analyzing social media activities.

[0100] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0101] The acquisition unit can acquire weather information, and the estimation unit can estimate the emotion of the elderly person based on the weather information. For example, the acquisition unit can determine that the elderly person is likely to feel depressed on a rainy day, and the estimation unit can estimate the emotion using an AI model that takes weather information as an input and outputs a depressed emotion. The acquisition unit can also determine that the elderly person is likely to be active on a sunny day, and the estimation unit can estimate the emotion using an AI model that takes weather information as an input and outputs an active emotion. Furthermore, the acquisition unit can determine that the elderly person is likely to get sick on a cold day, and the estimation unit can estimate the emotion using an AI model that takes weather information as an input and outputs a feeling of poor health. This makes it possible to estimate emotions taking weather information into consideration.

[0102] The determination unit can select music according to the emotion of the elderly person, and the corresponding unit can play music according to the emotion of the elderly person. For example, when the elderly person is sad, the determination unit can select relaxing music, and the corresponding unit can play the relaxing music. Also, when the elderly person is happy, the determination unit can select up-tempo music, and the corresponding unit can play the up-tempo music. Furthermore, when the elderly person is angry, the determination unit can select calming music, and the corresponding unit can play the calming music. This makes it possible to provide emotional care using music.

[0103] The acquisition unit acquires dietary information of the elderly person, and the estimation unit can also estimate the elderly person's emotions based on the dietary information. For example, the acquisition unit estimates a healthy emotion when the elderly person eats a balanced diet, and the estimation unit estimates the emotion using an AI model that takes dietary information as an input and outputs a healthy emotion. The acquisition unit can also estimate a temporary feeling of happiness when the elderly person consumes a lot of sweets, and the estimation unit can estimate the emotion using an AI model that takes dietary information as an input and outputs a temporary feeling of happiness. Furthermore, the acquisition unit can estimate a feeling of anxiety when the elderly person does not eat a meal, and the estimation unit can estimate the emotion using an AI model that takes dietary information as an input and outputs an anxiety. This makes it possible to estimate emotions taking dietary information into account.

[0104] The acquisition unit acquires sleep information of the elderly person, and the estimation unit can also estimate the emotion of the elderly person based on the sleep information. For example, the acquisition unit estimates a stable emotion when the elderly person is getting enough sleep, and the estimation unit estimates the emotion using an AI model that takes the sleep information as an input and outputs the stable emotion. The acquisition unit can also estimate a sense of irritation when the elderly person is sleep-deprived, and the estimation unit can estimate the emotion using an AI model that takes the sleep information as an input and outputs the sense of irritation. Furthermore, the acquisition unit can estimate a sense of relaxation when the elderly person is taking a nap, and the estimation unit can estimate the emotion using an AI model that takes the sleep information as an input and outputs the sense of relaxation. This makes it possible to estimate emotions taking into account sleep information.

[0105] The acquisition unit acquires hobby activity information of the elderly person, and the estimation unit can also estimate the emotion of the elderly person based on the hobby activity information. For example, the acquisition unit estimates a sense of happiness when the elderly person is enjoying a hobby activity, and the estimation unit estimates the emotion using an AI model that takes hobby activity information as an input and outputs a sense of happiness. The acquisition unit can also estimate a sense of stress when the elderly person has stopped a hobby activity, and the estimation unit can estimate the emotion using an AI model that takes hobby activity information as an input and outputs a sense of stress. Furthermore, the acquisition unit can estimate a sense of excitement when the elderly person has started a new hobby, and the estimation unit can estimate the emotion using an AI model that takes hobby activity information as an input and outputs a sense of excitement. This makes it possible to estimate emotions taking hobby activity information into account.

[0106] The acquisition unit acquires the exercise information of the elderly person, and the estimation unit can estimate the health condition of the elderly person based on the exercise information. For example, the acquisition unit estimates a good health condition when the elderly person exercises regularly, and the estimation unit estimates the health condition using an AI model that takes the exercise information as an input and outputs a good health condition. The acquisition unit can also estimate a health risk when the elderly person neglects exercise, and the estimation unit can estimate the health condition using an AI model that takes the exercise information as an input and outputs the health risk. Furthermore, the acquisition unit can estimate an adaptation state when the elderly person starts a new exercise, and the estimation unit can estimate the health condition using an AI model that takes the exercise information as an input and outputs the adaptation state. This makes it possible to estimate the health condition taking into account the exercise information.

[0107] The acquisition unit can acquire the purchase history of the elderly person, and the estimation unit can estimate the elderly person's life pattern based on the purchase history. For example, if the elderly person regularly purchases health foods, the acquisition unit estimates a health-oriented life pattern, and the estimation unit estimates the life pattern using an AI model that takes the purchase history as an input and outputs a health-oriented life pattern. In addition, the acquisition unit can estimate an active life pattern if the elderly person frequently purchases entertainment products, and the estimation unit can estimate the life pattern using an AI model that takes the purchase history as an input and outputs an active life pattern. Furthermore, the acquisition unit can estimate a life pattern requiring health management if the elderly person purchases a lot of medicines, and the estimation unit can estimate the life pattern using an AI model that takes the purchase history as an input and outputs a life pattern requiring health management. This makes it possible to estimate a life pattern taking the purchase history into consideration.

[0108] The acquisition unit can acquire the travel history of the elderly person, and the estimation unit can estimate the activity level of the elderly person based on the travel history. For example, the acquisition unit can estimate a high activity level when the elderly person travels frequently, and the estimation unit can estimate the activity level using an AI model that takes the travel history as an input and outputs a high activity level. In addition, the acquisition unit can estimate a low activity level when the elderly person refrains from traveling, and the estimation unit can estimate the activity level using an AI model that takes the travel history as an input and outputs a low activity level. Furthermore, the acquisition unit can estimate a seasonal activity level when the elderly person tends to travel in a particular season, and the estimation unit can estimate the activity level using an AI model that takes the travel history as an input and outputs a seasonal activity level. This makes it possible to estimate the activity level taking the travel history into consideration.

[0109] The acquisition unit acquires the reading history of the elderly person, and the estimation unit can estimate the intellectual activity level of the elderly person based on the reading history. For example, the acquisition unit estimates a high intellectual activity level when the elderly person reads many books, and the estimation unit estimates the intellectual activity level using an AI model that takes the reading history as an input and outputs a high intellectual activity level. In addition, the acquisition unit can estimate a knowledge level related to the genre when the elderly person likes to read books of a specific genre, and the estimation unit can estimate the intellectual activity level using an AI model that takes the reading history as an input and outputs a knowledge level related to the specific genre. Furthermore, the acquisition unit can estimate a decrease in the intellectual activity level when the elderly person stops reading, and the estimation unit can estimate the intellectual activity level using an AI model that takes the reading history as an input and outputs a decrease in the intellectual activity level. This makes it possible to estimate the intellectual activity level taking the reading history into consideration.

[0110] The acquisition unit can acquire the communication history of the elderly person, and the estimation unit can estimate the social activity level of the elderly person based on the communication history. For example, the acquisition unit estimates a high social activity level when the elderly person frequently contacts friends and family, and the estimation unit estimates the social activity level using an AI model that takes the communication history as an input and outputs a high social activity level. The acquisition unit can also estimate a low social activity level when the elderly person refrains from communication, and the estimation unit can estimate the social activity level using an AI model that takes the communication history as an input and outputs a low social activity level. Furthermore, the acquisition unit can estimate a social activity level related to a specific event when the elderly person participates in the event, and the estimation unit can estimate the social activity level using an AI model that takes the communication history as an input and outputs a social activity level related to the event. This makes it possible to estimate the social activity level taking the communication history into account.

[0111] The process flow of the second embodiment will be briefly described below.

[0112] Step 1: The acquisition unit acquires emotion estimation information for estimating the emotion of an elderly person. The emotion estimation information includes the elderly person's facial expression, movement, voice, heart rate, blood pressure, pupil response, brainwave, body temperature, breathing, and posted content. For example, the facial expression of the elderly person is acquired using a camera, the voice of the elderly person is acquired using a microphone, and the heart rate and blood pressure of the elderly person are acquired using a sensor. Step 2: The estimation unit estimates the emotion of the elderly person based on the emotion estimation information acquired by the acquisition unit. The estimation unit estimates emotions using AI and uses a model that inputs facial expression data, voice data, and biometric data and outputs emotions. Step 3: The decision unit determines how to respond to the elderly person's emotions estimated by the estimation unit. The decision unit uses AI to determine how to respond, and uses a model that takes the estimated emotions as input and outputs a response. For example, it outputs comforting words for sad emotions, outputs happy words for happy emotions, and outputs topics to calm the elderly person for angry emotions. Step 4: The response unit executes the response determined by the decision unit. The response unit executes the response using AI, and uses a model that outputs instructions for executing the determined response as input. For example, it may use voice synthesis technology to speak comforting words, speak words of joy together, or speak a topic to calm the person down.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] For example, the acquisition unit can acquire the facial expression and voice of the elderly person using the camera 42 and microphone 38B of the smart device 14. For example, the estimation unit is realized by the specific processing unit 290 of the data processing device 12, and estimates the emotion of the elderly person based on the information from the acquisition unit. For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12, and determines a response according to the estimated emotion. For example, the response unit is realized by the control unit 46A of the smart device 14, and executes the determined response. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0117] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] For example, the acquisition unit can acquire the facial expression and voice of the elderly person using the camera 42 and microphone 238 of the smart glasses 214. For example, the estimation unit is realized by the specific processing unit 290 of the data processing device 12, and estimates the emotion of the elderly person based on information from the acquisition unit. For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12, and determines a response according to the estimated emotion. For example, the response unit is realized by the control unit 46A of the smart glasses 214, and executes the determined response. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0133] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] For example, the acquisition unit can acquire the facial expression and voice of the elderly person using the camera 42 and microphone 238 of the headset type terminal 314. For example, the estimation unit is realized by the specific processing unit 290 of the data processing device 12, and estimates the emotion of the elderly person based on information from the acquisition unit. For example, the determination unit is realized by the specific processing unit 290 of the data processing device 12, and determines a response according to the estimated emotion. For example, the response unit is realized by the control unit 46A of the headset type terminal 314, and executes the determined response. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0149] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] For example, the acquisition unit can acquire the facial expression and voice of the elderly person using the camera 42 and microphone 238 of the robot 414. For example, the estimation unit is realized by the specific processing unit 290 of the data processing device 12, and estimates the emotion of the elderly person based on the information from the acquisition unit. For example, the decision unit is realized by the specific processing unit 290 of the data processing device 12, and determines a response according to the estimated emotion. For example, the response unit is realized by the control unit 46A of the robot 414, and executes the determined response. The correspondence relationship between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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).

[0170] 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.

[0171] 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 experiences positive feelings such as "I want more" or "I want to know more."

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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 in which a processor is used 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] (Appendix 1) An acquisition unit that acquires emotion estimation information for estimating an emotion of an elderly person; an estimation unit that estimates an emotion of the elderly person based on the emotion estimation information acquired by the acquisition unit; a determination unit that determines a response according to the emotion of the elderly person estimated by the estimation unit; a response unit that executes the response determined by the determination unit. A system characterized by: (Appendix 2) The determination unit is determining a dialogue with the elderly person according to the elderly person's emotion as a response according to the elderly person's emotion; The corresponding portion is The dialogue is carried out according to the emotion of the elderly person. 2. The system of claim 1, (Appendix 3) The determination unit is determining health support according to the elderly person's feelings as a response according to the elderly person's feelings; The corresponding portion is Providing the health support according to the emotions of the elderly person 2. The system of claim 1, (Appendix 4) The acquisition unit is At least one of facial expression, movement, voice, heart rate, blood pressure, pupil response, brain wave, body temperature, respiration, and posted content of the elderly person is acquired as the emotion estimation information. 2. The system of claim 1, (Appendix 5) The acquisition unit is Estimating the emotions of an elderly person and adjusting the type of information to be acquired based on the estimated emotions of the elderly person 2. The system of claim 1, (Appendix 6) The acquisition unit is Analyze the past emotion data of the elderly and select the method of acquisition 2. The system of claim 1, (Appendix 7) The acquisition unit is When collecting information, filter it based on the senior's current health and living situation. 2. The system of claim 1, (Appendix 8) The acquisition unit is Estimating the emotions of the elderly and determining the priority of information to be acquired based on the estimated emotions of the elderly 2. The system of claim 1, (Appendix 9) The acquisition unit is When retrieving information, the system prioritizes retrieving information that is more relevant to the elderly person based on their geographic location information. 2. The system of claim 1, (Appendix 10) The acquisition unit is When acquiring information, the social media activity of the elderly is analyzed to obtain relevant information. 2. The system of claim 1, (Appendix 11) The estimation unit is Estimating the emotions of the elderly and modifying the estimation algorithm based on the estimated emotions of the elderly 2. The system of claim 1, (Appendix 12) The estimation unit is During estimation, change the level of detail of the estimation based on the importance of the information obtained 2. The system of claim 1, (Appendix 13) The estimation unit is When estimating, different estimation algorithms are used depending on the category of information 2. The system of claim 1, (Appendix 14) The estimation unit is Estimate the emotions of the elderly and change the accuracy of the estimation based on the estimated emotions of the elderly 2. The system of claim 1, (Appendix 15) The estimation unit is During estimation, prioritize estimations based on when the information was obtained 2. The system of claim 1, (Appendix 16) The estimation unit is During estimation, change the order of estimation based on the relevance of information 2. The system of claim 1, (Appendix 17) The determination unit is Estimating the emotions of the elderly and changing the response decision method based on the estimated emotions of the elderly 2. The system of claim 1, (Appendix 18) The determination unit is When deciding how to respond, the system refers to the elderly person's past emotional data and selects the appropriate response. 2. The system of claim 1, (Appendix 19) The determination unit is When deciding on care, vary care measures based on the older person's current health status 2. The system of claim 1, (Appendix 20) The determination unit is Estimating the emotions of the elderly and setting priorities for responses based on the estimated emotions of the elderly 2. The system of claim 1, (Appendix 21) The determination unit is When deciding how to respond, select the response method based on the geographic location information of the elderly person. 2. The system of claim 1, (Appendix 22) The determination unit is When making response decisions, analyze the social media activity of seniors to suggest response measures. 2. The system of claim 1, (Appendix 23) The corresponding portion is Estimating the emotions of the elderly and changing the way responses are performed based on the estimated emotions of the elderly 2. The system of claim 1, (Appendix 24) The corresponding portion is Vary the response measures based on the elderly person's current health status when the response is carried out. 2. The system of claim 1, (Appendix 25) The corresponding portion is Estimating the emotions of the elderly and setting priorities for responses based on the estimated emotions of the elderly 2. The system of claim 1, (Appendix 26) The corresponding portion is When responding, the method of response is selected based on the geographic location of the elderly person. 2. The system of claim 1, (Appendix 27) The corresponding portion is When implementing a response, analyze the social media activity of seniors to suggest response measures. 2. The system of claim 1, [Explanation of symbols]

[0185] 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. An acquisition unit that acquires emotion estimation information for estimating an emotion of an elderly person; an estimation unit that estimates an emotion of the elderly person based on the emotion estimation information acquired by the acquisition unit; a determination unit that determines a response according to the emotion of the elderly person estimated by the estimation unit; a response unit that executes the response determined by the determination unit. A system characterized by:

2. The determination unit is determining a dialogue with the elderly person according to the elderly person's emotion as a response according to the elderly person's emotion; The corresponding portion is The dialogue is carried out according to the emotion of the elderly person.

2. The system of claim 1 .

3. The determination unit is determining health support according to the elderly person's feelings as a response according to the elderly person's feelings; The corresponding portion is Providing the health support according to the emotions of the elderly person 2. The system of claim 1 .

4. The acquisition unit is At least one of facial expression, movement, voice, heart rate, blood pressure, pupil response, brain wave, body temperature, respiration, and posted content of the elderly person is acquired as the emotion estimation information.

2. The system of claim 1 .

5. The acquisition unit is Estimating an emotion of the elderly person and adjusting a type of information to be acquired based on the estimated emotion of the elderly person.

2. The system of claim 1 .

6. The acquisition unit is Analyze the past emotion data of the elderly person and select a method of acquiring the data.

2. The system of claim 1 .

7. The acquisition unit is When obtaining information, the information is filtered based on the elderly person's current health condition and living situation.

2. The system of claim 1 .

8. The acquisition unit is Estimating the emotion of the elderly person, and determining a priority order of information to be acquired based on the estimated emotion of the elderly person.

2. The system of claim 1 .

Images