System

Abstract

An object of a system according to an embodiment is to provide an elderly person with dementia with an appropriate conversation and delay the progress of dementia.SOLUTION: A system includes an acquisition unit, a generation unit, a provision unit, an analysis unit, an emotion analysis unit, and a monitoring unit. The acquisition unit acquires past memories and interests of the elderly person. The generation unit generates a conversation content based on the information acquired by the acquisition unit. The providing unit provides the elderly person with the conversation content generated by the generation unit and performs a conversation. The analysis unit analyzes the content of the dialogue performed by the providing unit and performs appropriate feedback. The emotion analysis unit analyzes the emotional state of the elderly person on the basis of the information analyzed by the analysis unit and proceeds with a conversation with an appropriate tone and content. The monitoring unit allows a doctor or a nurse to monitor the conversation content provided by the providing unit and intervene in the conversation if necessary.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has faced challenges in that it is difficult to provide appropriate conversation for elderly people with dementia, and there is a lack of effective means to slow the progression of dementia.

[0005] The system according to the embodiment aims to provide appropriate conversation for elderly people with dementia and slow the progression of dementia. [Means for solving the problem]

[0006] The system according to the embodiment includes an acquisition unit, a generation unit, a provision unit, an analysis unit, an emotion analysis unit, and a monitoring unit. The acquisition unit acquires the elderly person's past memories and interests. The generation unit generates conversation content based on the information acquired by the acquisition unit. The provision unit provides the elderly person with the conversation content generated by the generation unit and engages in dialogue. The analysis unit analyzes the content of the dialogue conducted by the provision unit and provides appropriate feedback. The emotion analysis unit analyzes the elderly person's emotional state based on the information analyzed by the analysis unit and advances the conversation with an appropriate tone and content. The monitoring unit allows a doctor or nurse to monitor the content of the dialogue conducted by the provision unit and intervene as necessary. [Effects of the Invention]

[0007] The system according to the embodiment can provide appropriate conversation for elderly people with dementia and slow the progression of dementia. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention utilizes generative AI to provide appropriate conversations to elderly people with dementia and stimulate their memory. This system generates conversation content based on the elderly's past memories and interests, and provides the generated conversation content to the elderly through dialogue, thereby stimulating the elderly's memory and slowing the progression of dementia. This system also helps reduce the elderly's anxiety and restore their self-confidence. Furthermore, it also contributes to reducing the burden on doctors and nurses and improving the quality of care. This system stimulates the elderly's memory and slows the progression of dementia. For example, the system uses information about the elderly's past events, hobbies, and family as input data, and the generative AI generates friendly conversation content. The generated conversation content is then provided to the elderly, and a dialogue is held. This dialogue stimulates the elderly's memory and slows the progression of dementia. This system also helps reduce the elderly's anxiety and restore their self-confidence. Furthermore, it also contributes to reducing the burden on doctors and nurses and improving the quality of care. This system also improves the quality of life of the elderly.

[0029] A conversation support system according to an embodiment includes an acquisition unit, a generation unit, a provision unit, an analysis unit, an emotion analysis unit, and a monitoring unit. The acquisition unit acquires the elderly's past memories and interests. For example, the acquisition unit can analyze information provided by family members or caregivers, or past photos and videos. The acquisition unit can also collect information through interviews and questionnaires. The generation unit uses a generation AI to generate conversation content based on the information acquired by the acquisition unit. For example, the generation AI generates conversation content based on the elderly's past events, hobbies, and family information. The generation AI can generate friendly conversation content using a text generation AI (e.g., LLM) or a multimodal generation AI. The provision unit provides the conversation content generated by the generation unit to the elderly and engages in a dialogue. For example, the provision unit provides the conversation content through voice or text. The provision unit can provide the conversation content in a format appropriate for the elderly using speech synthesis technology or a text display method. The analysis unit analyzes the content of the dialogue conducted by the provision unit and provides appropriate feedback. For example, the analysis unit analyzes the elderly person's reactions in real time during the dialogue and provides appropriate feedback. The emotion analysis unit analyzes the elderly person's emotional state based on the information analyzed by the analysis unit and advances the conversation in an appropriate tone and content. For example, the emotion analysis unit analyzes the elderly person's emotional state using facial expression analysis and voice analysis and advances the conversation in an appropriate tone and content. The monitoring unit allows a doctor or nurse to monitor the dialogue content conducted by the provision unit and intervene as necessary. For example, the monitoring unit monitors the dialogue content of the generation AI in real time and allows a doctor or nurse to intervene as necessary. As a result, the conversation support system according to the embodiment can stimulate the elderly person's memory and slow the progression of dementia. Furthermore, the system helps the elderly person to reduce their anxiety and regain their confidence. The system also reduces the burden on doctors and nurses and contributes to improving the quality of care.

[0030] The acquisition unit can analyze information provided by family members or caregivers, as well as past photos and videos. The acquisition unit can, for example, receive information provided by family members or caregivers. For example, it collects information such as past events, hobbies, and health conditions provided by family members or caregivers. The acquisition unit can also analyze past photos and videos. For example, it can analyze photos using image recognition technology and videos using video analysis technology. This makes it possible to more accurately acquire the elderly person's past memories and interests. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input information provided by family members or caregivers into AI, which can analyze the information to identify the elderly person's memories and interests.

[0031] The generation unit can generate conversation content based on information about the elderly person's past events, hobbies, and family. The generation unit generates conversation content based on information about the elderly person's past events, hobbies, and family, for example. For example, the generation AI generates stories about trips the elderly person took when they were young, or stories about their hobby of gardening. The generation unit can also generate conversation content by combining family information. For example, conversation content is generated that includes family members' names and relationships. This makes it possible to generate conversation content that is familiar to the elderly. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, the generation AI, for example. For example, the generation unit can input information about the elderly person's past events, hobbies, and family into the generation AI, which then generates the conversation content.

[0032] The providing unit can provide the conversation content to the elderly person through voice or text. The providing unit can provide the conversation content to the elderly person through voice or text, for example. For example, the providing unit can provide the conversation content as voice using voice synthesis technology. The providing unit can also provide the conversation content as text using a text display method. This makes it possible to provide the conversation content to the elderly person in an appropriate format. Some or all of the above-mentioned processing in the providing unit can be performed using AI, for example, or can be performed without using AI. For example, the providing unit can input the generated conversation content to AI, which can provide the conversation content as voice or text.

[0033] The analysis unit can analyze the elderly person's reactions in real time during the dialogue and provide appropriate feedback. The analysis unit, for example, analyzes the elderly person's reactions in real time during the dialogue. For example, the analysis unit analyzes the elderly person's reactions using facial expression analysis or voice analysis. The analysis unit can also analyze the elderly person's words and actions during the dialogue. For example, the analysis unit analyzes the content and tone of the elderly person's words and provides appropriate feedback. This makes it possible to provide appropriate feedback based on the elderly person's reactions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the elderly person's reaction data into AI, which can analyze the data in real time and provide feedback.

[0034] The emotion analysis unit analyzes the emotional state of the elderly person and can advance the conversation with an appropriate tone and content. The emotion analysis unit, for example, analyzes the emotional state of the elderly person. For example, the emotion analysis unit analyzes the emotional state of the elderly person using facial expression analysis or voice analysis. The emotion analysis unit can also evaluate the emotional state of the elderly person using self-reports. For example, the emotion analysis unit performs analysis based on the emotional state self-reported by the elderly person. This makes it possible to provide appropriate conversation according to the elderly person's emotional state. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the emotion analysis unit inputs the elderly person's emotional data into AI, which analyzes the emotional state and advances the conversation with an appropriate tone and content.

[0035] The monitoring unit allows a doctor or nurse to monitor the dialogue content of the generation AI and intervene as necessary. The monitoring unit, for example, allows a doctor or nurse to monitor the dialogue content of the generation AI. For example, the monitoring unit monitors the dialogue content of the generation AI in real time, allowing a doctor or nurse to intervene as necessary. The monitoring unit can also monitor the dialogue content using periodic checks or an alert system. For example, the monitoring unit issues an alert if an abnormality is detected in the dialogue content. This allows a doctor or nurse to monitor the dialogue content of the elderly person and intervene as necessary. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the dialogue content of the generation AI to AI, which can analyze the dialogue content, detect abnormalities, and issue an alert.

[0036] The acquisition unit can reflect feedback from family members and caregivers in real time when acquiring the elderly person's past memories and interests. For example, the acquisition unit reflects feedback from family members and caregivers in real time when acquiring the elderly person's past memories and interests. For example, the acquisition unit acquires the elderly person's interests based on the latest information provided by family members. The acquisition unit can also adjust the memory acquisition by reflecting the elderly person's reactions observed by the caregiver in real time. For example, the content of the memories and interests to be acquired is updated based on feedback provided by family members and caregivers. This improves the accuracy of the memories and interests to be acquired by reflecting feedback from family members and caregivers in real time. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input feedback from family members and caregivers into AI, which can analyze the feedback and adjust the acquisition of memories and interests.

[0037] The acquisition unit can improve accuracy when acquiring the elderly person's past memories and interests by combining analysis results of past photos and videos. The acquisition unit, for example, analyzes the elderly person's past photos and videos and acquires the memories and interests based on the results. For example, it analyzes photos using image recognition technology and analyzes videos using video analysis technology. The acquisition unit can also accurately select the content of memories and interests to acquire based on the analysis results of the photos and videos. For example, it can analyze the elderly person's past photos and acquire related memories. It can also analyze the elderly person's past videos to identify topics of interest. In this way, by combining the analysis results of past photos and videos, the accuracy of the acquired memories and interests can be improved. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without AI. For example, the acquisition unit can input data of past photos and videos into AI, which can acquire the memories and interests based on the analysis results.

[0038] When acquiring the elderly person's past memories and interests, the acquisition unit can automatically convert the elderly person's dictation into text using voice recognition technology. For example, the acquisition unit performs voice recognition and converts the content of the elderly person's speech into text in real time. For example, the acquisition unit can automatically convert the elderly person's dictation into text using voice recognition technology. The acquisition unit can also analyze the elderly person's dictation to acquire related memories and interests. For example, the content of the elderly person's speech can be analyzed using voice recognition technology to identify related memories and interests. The acquisition unit can also automatically record the content of the elderly person's speech using voice recognition technology and analyze it later. In this way, the use of voice recognition technology can automatically convert the elderly person's dictation into text, improving the accuracy of acquiring memories and interests. Some or all of the above-mentioned processing in the acquisition unit can be performed using, for example, AI, or without AI. For example, the acquisition unit can input the elderly person's voice data into AI, which can convert the voice data into text to acquire memories and interests.

[0039] The acquisition unit can prioritize acquiring highly relevant information by taking geographical location information into consideration when acquiring the elderly person's past memories and interests. For example, the acquisition unit prioritizes acquiring highly relevant information by taking geographical location information into consideration when acquiring the elderly person's past memories and interests. For example, the acquisition unit prioritizes acquiring memories related to places the elderly person lived. It can also prioritize acquiring interests related to places the elderly person frequently visited. For example, the acquisition unit evaluates the relevance of the elderly person's memories and interests based on the geographical location information and determines priorities. This makes it possible to prioritize acquiring highly relevant memories and interests by taking the geographical location information into consideration. Some or all of the above-described processing by the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the elderly person's geographical location information into AI, which can analyze the geographical location information to acquire the memories and interests.

[0040] The acquisition unit can analyze social media activity and acquire related information when acquiring the elderly person's past memories and interests. The acquisition unit, for example, analyzes the elderly person's social media activity to acquire related memories and interests. For example, it analyzes the content of the elderly person's social media posts to acquire related memories. It can also acquire topics of interest by referring to the activities of the elderly person's friends on social media. For example, the elderly person's memories and interests can be identified based on their social media activity history. In this way, it is possible to acquire related memories and interests by analyzing their social media activity. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the elderly person's social media data into AI, which can analyze the data to acquire memories and interests.

[0041] When acquiring the elderly person's past memories and interests, the acquisition unit can customize the acquisition method by reflecting past feedback. The acquisition unit, for example, adjusts the memory and interest acquisition method based on feedback provided by the elderly person in the past. For example, the acquisition unit analyzes the elderly person's reactions and customizes the contents of the memories and interests to be acquired. The acquisition unit can also reflect past feedback and change the priority of the memories and interests to be acquired. For example, memories and interests to which the elderly person has previously responded favorably can be preferentially acquired. In this way, by reflecting past feedback, the acquisition method can be customized and accuracy can be improved. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the elderly person's past feedback data into AI, which analyzes the data and customizes the acquisition method.

[0042] When generating conversation content, the generation unit can apply different generation algorithms based on the elderly person's past events and hobbies. For example, the generation unit can apply different generation algorithms based on the elderly person's past events and hobbies. For example, the generation AI can generate conversation content related to travel based on the elderly person's past travel experiences. The generation AI can also generate conversation content related to gardening based on the elderly person's hobby of gardening. The generation AI can also generate conversation content related to family based on information about the elderly person's family. This makes it possible to generate more friendly conversation content based on the elderly person's past events and hobbies. Some or all of the above-described processing in the generation unit can be performed using, or without, the generation AI. For example, the generation unit can input data on the elderly person's past events and hobbies into the generation AI, and the generation AI can generate conversation content by applying different generation algorithms.

[0043] When generating the conversation content, the generation unit can combine information about the elderly person's family to generate a friendly conversation. The generation unit, for example, generates the conversation content by combining information about the elderly person's family. For example, the generation AI generates the conversation content including the names and relationships of the elderly person's family members. The generation AI can also generate the conversation content incorporating anecdotes about the elderly person's family. The generation AI can also generate the conversation content based on the hobbies and interests of the elderly person's family. In this way, by combining the information about the elderly person's family members, a friendly conversation content can be generated. Some or all of the above-described processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input information about the elderly person's family members into the generation AI, which can then generate the conversation content.

[0044] When generating conversation content, the generation unit can improve the accuracy of generation by referring to the elderly person's past conversation history. The generation unit, for example, generates conversation content by referring to the elderly person's past conversation history. For example, the generation AI analyzes the elderly person's past conversation history and generates related conversation content. The generation AI can also generate topics of interest based on content that the elderly person has spoken in the past. The generation AI can also maintain consistency in the conversation content by referring to the elderly person's past conversation history. In this way, by referring to the elderly person's past conversation history, the accuracy of generation can be improved. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input the elderly person's past conversation history into the generation AI, which can then generate the conversation content.

[0045] When generating conversation content, the generation unit can determine the priority of the conversation based on the timing of past events. The generation unit, for example, determines the priority of the conversation based on the timing of past events. For example, the generation AI can prioritize events that occurred when the elderly person was young and incorporate them into the conversation content. The generation AI can also prioritize events that the elderly person experienced recently and incorporate them into the conversation content. The generation AI can also prioritize events that occurred during a period that is likely to be memorable to the elderly and incorporate them into the conversation content. This enables more effective dialogue by determining the priority of the conversation based on the timing of past events. Some or all of the above-described processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input data regarding the timing of past events into the generation AI, and the generation AI can determine the priority of the conversation.

[0046] The generation unit can adjust the order of related events when generating conversation content. The generation unit, for example, adjusts the order of related events. For example, the generation AI adjusts the order of events based on the memory of the elderly person. The generation AI can also adjust the order of events based on the interests of the elderly person. The generation AI can also adjust the order of events based on the response of the elderly person. In this way, by adjusting the order of related events, more consistent conversation content can be provided. Some or all of the above-mentioned processing in the generation unit may be performed using the generation AI, for example, or may be performed without using the generation AI. For example, the generation unit can input data of related events into the generation AI, which can then adjust the order of events.

[0047] When generating conversation content, the generation unit can adjust the use of technical terms according to the elderly person's level of expertise. The generation unit, for example, adjusts the use of technical terms according to the elderly person's level of expertise. For example, if the elderly person has technical expertise, the generation AI generates conversation content that uses a lot of technical terms. Also, if the elderly person does not have technical expertise, the generation AI can generate conversation content using simple language. Also, the generation AI can adjust the frequency of use of technical terms according to the elderly person's level of expertise. In this way, by adjusting the use of technical terms according to the elderly person's level of expertise, it is possible to provide conversation content that is easier to understand. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input data regarding the elderly person's level of expertise into the generation AI, which can then adjust the use of technical terms.

[0048] When providing the conversation content, the providing unit can optimize the timing of providing the content by referring to the elderly person's past reactions. The providing unit, for example, provides the conversation content by referring to the elderly person's past reactions. For example, the providing unit provides the conversation content at a timing when the elderly person has previously shown a favorable reaction. The providing unit can also provide the conversation content by avoiding a timing when the elderly person has previously felt stressed. The providing unit can also determine the optimal timing of providing the content based on the elderly person's past reactions. In this way, the timing of providing the content can be optimized by referring to the elderly person's past reactions. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the elderly person's past reaction data into AI, which can analyze the data to optimize the timing of providing the content.

[0049] When providing the conversation content, the providing unit can customize the audio or text format according to the elderly person's preferences. The providing unit customizes the audio or text format according to the elderly person's preferences, for example. For example, if the elderly person prefers audio format, the providing unit provides the conversation content in audio format. Furthermore, if the elderly person prefers text format, the providing unit can also provide the conversation content in text format. Furthermore, the providing unit can provide the conversation content by combining both audio and text according to the elderly person's preferences. This makes it possible to provide the conversation content in a format according to the elderly person's preferences. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input data regarding the elderly person's preferences into AI, which can analyze the data to customize the audio or text format.

[0050] When providing the conversation content, the providing unit can adjust the provision method taking into account the elderly person's current health condition. The providing unit provides the conversation content, for example, taking into account the elderly person's current health condition. For example, the providing unit provides shorter conversation content when the elderly person is tired. Furthermore, the providing unit can also provide longer conversation content when the elderly person is in good health. Furthermore, the providing unit can adjust the frequency of providing the conversation content according to the elderly person's health condition. This makes it possible to provide the conversation content in a provision method that suits the elderly person's health condition. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input data regarding the elderly person's health condition into AI, which can analyze the data and adjust the provision method.

[0051] When providing the conversation content, the providing unit can select the optimal providing method by taking into consideration the geographical location information of the elderly person. The providing unit provides the conversation content by taking into consideration, for example, the geographical location information of the elderly person. For example, when the elderly person is at home, the providing unit can provide relaxing topics. Furthermore, when the elderly person is out, the providing unit can also provide topics related to the destination. Furthermore, the providing unit can select the optimal providing method based on the geographical location information of the elderly person. In this way, the optimal providing method can be selected based on the geographical location information of the elderly person. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the geographical location information of the elderly person into AI, which can analyze the data and select the optimal providing method.

[0052] When providing the conversation content, the providing unit can analyze the social media activity of the elderly person to provide related conversation content. The providing unit, for example, analyzes the social media activity of the elderly person and provides related conversation content. For example, the providing unit provides conversations about places where the elderly person has checked in on social media. The providing unit can also analyze the content posted on social media by the elderly person and provide related topics. The providing unit can also provide related topics by referring to the activities of the elderly person's friends on social media. In this way, related conversation content can be provided by analyzing the social media activity of the elderly person. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the elderly person's social media data into AI, which analyzes the data and provides related conversation content.

[0053] When providing the conversation content, the providing unit can customize the delivery method by reflecting the elderly person's past feedback. The providing unit customizes the delivery method based on, for example, the elderly person's past feedback. For example, the providing unit prioritizes delivery methods to which the elderly person has responded favorably in the past. The providing unit can also avoid delivery methods that the elderly person has experienced stress in the past. The providing unit can also customize the delivery method based on the elderly person's past feedback. In this way, by reflecting the elderly person's past feedback, the delivery method can be customized and accuracy can be improved. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the elderly person's past feedback data into AI, which can analyze the data and customize the delivery method.

[0054] When analyzing the content of a dialogue, the analysis unit can improve the accuracy of the analysis by referring to the elderly person's past reactions. The analysis unit, for example, analyzes the content of the dialogue by referring to the elderly person's past reactions. For example, the analysis unit improves the analysis accuracy of the dialogue content based on the elderly person's past reactions. The analysis unit can also adjust the analysis results by referring to emotions shown by the elderly person in the past. The analysis unit can also analyze the elderly person's past reactions and improve the analysis method. In this way, the accuracy of the analysis can be improved by referring to the elderly person's past reactions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the elderly person's past reaction data into AI, which analyzes the data to improve the accuracy of the analysis.

[0055] When analyzing the content of the dialogue, the analysis unit can provide an analysis result taking into account the health condition of the elderly person. The analysis unit, for example, analyzes the content of the dialogue taking into account the health condition of the elderly person. For example, the analysis unit adjusts the analysis result according to the health condition of the elderly person. The analysis unit can also provide a simple analysis result when the elderly person is tired. The analysis unit can also provide a detailed analysis result when the elderly person is in good health. This makes it possible to provide an analysis result according to the health condition of the elderly person. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data regarding the health condition of the elderly person into AI, which then analyzes the data and provides an analysis result.

[0056] When analyzing the content of the dialogue, the analysis unit can improve the analysis method by reflecting feedback from the elderly person's family. The analysis unit improves the analysis method of the dialogue content, for example, based on feedback from the elderly person's family. For example, the analysis unit adjusts the analysis method based on feedback provided by the elderly person's family. The analysis unit can also improve the analysis results by reflecting the opinions of the elderly person's family. The analysis unit can also improve the accuracy of the analysis based on the feedback from the elderly person's family. In this way, the analysis method can be improved and the accuracy can be improved by reflecting the feedback from the elderly person's family. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input feedback data from the elderly person's family into AI, which analyzes the data and improves the analysis method.

[0057] When analyzing the content of the dialogue, the analysis unit can provide an analysis result taking into account the geographical location information of the elderly person. The analysis unit, for example, analyzes the content of the dialogue taking into account the geographical location information of the elderly person. For example, if the elderly person is at home, the analysis unit can provide an analysis result related to the home. Furthermore, if the elderly person is out, the analysis unit can also provide an analysis result related to the destination. Furthermore, the analysis unit can provide an optimal analysis result based on the geographical location information of the elderly person. This makes it possible to provide an optimal analysis result based on the geographical location information of the elderly person. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the geographical location information of the elderly person to AI, which can analyze the data and provide an analysis result.

[0058] When analyzing the content of the conversation, the analysis unit can improve the accuracy of the analysis by analyzing the social media activities of the elderly. The analysis unit, for example, analyzes the social media activities of the elderly and analyzes the content of the conversation. For example, the analysis unit analyzes the content of the elderly's posts on social media to improve the accuracy of the analysis. The analysis unit can also improve the analysis results by referring to the activities of the elderly's friends on social media. The analysis unit can also adjust the analysis method based on the elderly's social media activity history. In this way, the accuracy of the analysis can be improved by analyzing the elderly's social media activities. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the elderly's social media data into AI, which analyzes the data to improve the accuracy of the analysis.

[0059] When analyzing the content of the dialogue, the analysis unit can customize the analysis method by reflecting the elderly person's past feedback. The analysis unit customizes the analysis method for the content of the dialogue based on, for example, the elderly person's past feedback. For example, the analysis unit adjusts the analysis method based on feedback provided by the elderly person in the past. The analysis unit can also improve the analysis results by referring to the elderly person's past responses. The analysis unit can also improve the accuracy of the analysis based on the elderly person's past feedback. In this way, the analysis method can be customized and the accuracy can be improved by reflecting the elderly person's past feedback. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the elderly person's past feedback data into AI, which analyzes the data and customizes the analysis method.

[0060] When performing emotion analysis, the emotion analysis unit can improve the accuracy of the analysis by referring to the elderly person's past emotional states. The emotion analysis unit, for example, performs emotion analysis by referring to the elderly person's past emotional states. For example, the emotion analysis unit improves the accuracy of the emotion analysis based on the elderly person's past emotional states. The emotion analysis unit can also adjust the analysis results by referring to emotions expressed by the elderly person in the past. The emotion analysis unit can also analyze the elderly person's past emotional states and improve the analysis method. In this way, the accuracy of the emotion analysis can be improved by referring to the elderly person's past emotional states. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the elderly person's past emotional data into AI, which analyzes the data to improve the accuracy of the emotion analysis.

[0061] When performing emotion analysis, the emotion analysis unit can provide analysis results taking into account the health condition of the elderly person. The emotion analysis unit performs emotion analysis taking into account, for example, the health condition of the elderly person. For example, the emotion analysis unit adjusts the emotion analysis result according to the elderly person's health condition. The emotion analysis unit can also provide a simple emotion analysis result if the elderly person is tired. The emotion analysis unit can also provide a detailed emotion analysis result if the elderly person is in good health. This makes it possible to provide emotion analysis results according to the elderly person's health condition. Some or all of the above-mentioned processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input data regarding the elderly person's health condition into AI, which then analyzes the data and provides emotion analysis results.

[0062] When performing emotion analysis, the emotion analysis unit can improve the analysis method by reflecting feedback from the elderly person's family. The emotion analysis unit, for example, improves the emotion analysis method based on feedback from the elderly person's family. For example, the emotion analysis unit adjusts the emotion analysis method based on feedback provided by the elderly person's family. The emotion analysis unit can also improve the emotion analysis results by reflecting the opinions of the elderly person's family. The emotion analysis unit can also improve the accuracy of the emotion analysis based on feedback from the elderly person's family. In this way, by reflecting the feedback from the elderly person's family, the emotion analysis method can be improved and the accuracy can be increased. Some or all of the above-mentioned processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input feedback data from the elderly person's family into AI, which analyzes the data and improves the emotion analysis method.

[0063] When performing emotion analysis, the emotion analysis unit can provide analysis results taking into account the geographical location information of the elderly person. The emotion analysis unit performs emotion analysis, for example, taking into account the geographical location information of the elderly person. For example, if the elderly person is at home, the emotion analysis unit can provide emotion analysis results related to the home. Furthermore, if the elderly person is out, the emotion analysis unit can also provide emotion analysis results related to the destination. Furthermore, the emotion analysis unit can provide optimal emotion analysis results based on the geographical location information of the elderly person. This makes it possible to provide optimal emotion analysis results based on the geographical location information of the elderly person. Some or all of the above-described processing in the emotion analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the emotion analysis unit can input the geographical location information of the elderly person into AI, which can analyze the data and provide emotion analysis results.

[0064] When performing emotion analysis, the emotion analysis unit can analyze the social media activities of the elderly to improve the accuracy of the analysis. The emotion analysis unit, for example, analyzes the social media activities of the elderly to perform emotion analysis. For example, the emotion analysis unit analyzes the content of the elderly's social media posts to improve the accuracy of the emotion analysis. The emotion analysis unit can also improve the emotion analysis results by referring to the activities of the elderly's friends on social media. The emotion analysis unit can also adjust the analysis method based on the elderly's social media activity history. In this way, the accuracy of the emotion analysis can be improved by analyzing the elderly's social media activities. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the elderly's social media data into AI, which then analyzes the data to improve the accuracy of the emotion analysis.

[0065] When performing emotion analysis, the emotion analysis unit can customize the analysis method by reflecting the elderly person's past feedback. The emotion analysis unit customizes the emotion analysis method based on, for example, the elderly person's past feedback. For example, the emotion analysis unit adjusts the analysis method based on feedback provided by the elderly person in the past. The emotion analysis unit can also improve the analysis results by referring to the elderly person's past reactions. The emotion analysis unit can also improve the accuracy of the analysis based on the elderly person's past feedback. In this way, by reflecting the elderly person's past feedback, the emotion analysis method can be customized and the accuracy can be improved. Some or all of the above-mentioned processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the elderly person's past feedback data into AI, which analyzes the data and customizes the analysis method.

[0066] When performing monitoring, the monitoring unit can improve the accuracy of the monitoring by referring to the elderly person's past dialogue history. The monitoring unit, for example, performs monitoring by referring to the elderly person's past dialogue history. For example, the monitoring unit improves the accuracy of the monitoring based on the elderly person's past dialogue history. The monitoring unit can also adjust the monitoring results by referring to the elderly person's past responses. The monitoring unit can also analyze the elderly person's past dialogue history and improve the monitoring method. In this way, the accuracy of monitoring can be improved by referring to the elderly person's past dialogue history. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the elderly person's past dialogue history data into AI, which can analyze the data to improve the accuracy of monitoring.

[0067] When performing monitoring, the monitoring unit can provide monitoring results taking into account the health condition of the elderly person. The monitoring unit, for example, performs monitoring taking into account the health condition of the elderly person. For example, the monitoring unit adjusts the monitoring results according to the health condition of the elderly person. The monitoring unit can also provide simple monitoring results when the elderly person is tired. The monitoring unit can also provide detailed monitoring results when the elderly person is in good health. This makes it possible to provide monitoring results according to the health condition of the elderly person. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input data regarding the health condition of the elderly person into AI, which can analyze the data and provide monitoring results.

[0068] When performing monitoring, the monitoring unit can improve the monitoring method by reflecting feedback from the elderly person's family. The monitoring unit, for example, improves the monitoring method based on feedback from the elderly person's family. For example, the monitoring unit adjusts the monitoring method based on feedback provided by the elderly person's family. The monitoring unit can also improve the monitoring results by reflecting the opinions of the elderly person's family. The monitoring unit can also improve the accuracy of the monitoring based on feedback from the elderly person's family. In this way, the monitoring method can be improved and the accuracy can be increased by reflecting the feedback from the elderly person's family. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input feedback data from the elderly person's family into AI, which can analyze the data and improve the monitoring method.

[0069] When performing monitoring, the monitoring unit can provide monitoring results taking into account the geographical location information of the elderly person. The monitoring unit performs monitoring, for example, taking into account the geographical location information of the elderly person. For example, when the elderly person is at home, the monitoring unit can provide monitoring results related to the home. Furthermore, when the elderly person is out, the monitoring unit can also provide monitoring results related to the destination. Furthermore, the monitoring unit can provide optimal monitoring results based on the geographical location information of the elderly person. This makes it possible to provide optimal monitoring results based on the geographical location information of the elderly person. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the geographical location information of the elderly person into AI, which can analyze the data and provide monitoring results.

[0070] When performing monitoring, the monitoring unit can analyze the social media activities of the elderly to improve the accuracy of the monitoring. The monitoring unit, for example, analyzes the social media activities of the elderly to perform monitoring. For example, the monitoring unit analyzes the content of the elderly's social media posts to improve the accuracy of the monitoring. The monitoring unit can also improve the monitoring results by referring to the activities of the elderly's friends on social media. The monitoring unit can also adjust the monitoring method based on the elderly's social media activity history. In this way, the accuracy of the monitoring can be improved by analyzing the elderly's social media activities. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the elderly's social media data into AI, which analyzes the data to improve the accuracy of the monitoring.

[0071] When performing monitoring, the monitoring unit can customize the monitoring method by reflecting the elderly person's past feedback. The monitoring unit customizes the monitoring method based on, for example, the elderly person's past feedback. For example, the monitoring unit adjusts the monitoring method based on feedback provided by the elderly person in the past. The monitoring unit can also improve the monitoring results by referring to the elderly person's past responses. The monitoring unit can also improve the accuracy of the monitoring based on the elderly person's past feedback. In this way, the monitoring method can be customized and accuracy can be improved by reflecting the elderly person's past feedback. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the elderly person's past feedback data into AI, which can analyze the data and customize the monitoring method.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] When acquiring the elderly person's past memories and interests, the acquisition unit can automatically convert the elderly person's dictation into text using voice recognition technology. For example, the acquisition unit can recognize the voice of the elderly person in real time and convert it into text. The acquisition unit can also analyze the elderly person's dictation to acquire related memories and interests. For example, the acquisition unit can analyze the voice of the elderly person using voice recognition technology to identify related memories and interests. The acquisition unit can also automatically record the voice of the elderly person using voice recognition technology and analyze it later. In this way, the voice recognition technology can be used to automatically convert the elderly person's dictation into text, improving the accuracy of acquiring memories and interests. Some or all of the above-mentioned processing in the acquisition unit can be performed using, for example, AI, or without AI. For example, the acquisition unit can input the elderly person's voice data into AI, which can convert the voice data into text to acquire memories and interests.

[0074] When generating conversation content, the generation unit can apply different generation algorithms based on the elderly person's past events and hobbies. For example, the generation AI can generate conversation content related to travel based on the elderly person's past travel experiences. The generation AI can also generate conversation content related to gardening based on the elderly person's gardening hobby. The generation AI can also generate conversation content related to family based on information about the elderly person's family. This makes it possible to generate more friendly conversation content based on the elderly person's past events and hobbies. Some or all of the above-described processing in the generation unit can be performed using, or without, the generation AI. For example, the generation unit can input data on the elderly person's past events and hobbies into the generation AI, and the generation AI can generate conversation content by applying different generation algorithms.

[0075] When providing the conversation content, the providing unit can optimize the timing of providing the conversation content by referring to the elderly person's past reactions. For example, the providing unit provides the conversation content at a timing when the elderly person has previously shown a favorable reaction. The providing unit can also provide the conversation content by avoiding a timing when the elderly person has previously felt stressed. The providing unit can also determine the optimal timing of providing the conversation content based on the elderly person's past reactions. In this way, the timing of providing the conversation content can be optimized by referring to the elderly person's past reactions. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the elderly person's past reaction data into AI, which can analyze the data to optimize the timing of providing the conversation content.

[0076] When analyzing the content of a dialogue, the analysis unit can improve the accuracy of the analysis by referring to the elderly person's past reactions. For example, the analysis unit can improve the analysis accuracy of the dialogue content based on the elderly person's past reactions. The analysis unit can also adjust the analysis results by referring to emotions expressed by the elderly person in the past. The analysis unit can also analyze the elderly person's past reactions and improve the analysis method. In this way, the accuracy of the analysis can be improved by referring to the elderly person's past reactions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the elderly person's past reaction data into AI, which then analyzes the data to improve the accuracy of the analysis.

[0077] When performing monitoring, the monitoring unit can improve the accuracy of the monitoring by referring to the elderly person's past dialogue history. For example, the monitoring unit improves the accuracy of the monitoring based on the elderly person's past dialogue history. The monitoring unit can also adjust the monitoring results by referring to the elderly person's past responses. The monitoring unit can also analyze the elderly person's past dialogue history and improve the monitoring method. In this way, the accuracy of monitoring can be improved by referring to the elderly person's past dialogue history. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the elderly person's past dialogue history data into AI, which analyzes the data to improve the accuracy of the monitoring.

[0078] The processing flow of the first embodiment will be briefly explained below.

[0079] Step 1: The acquisition unit acquires the elderly person's past memories and interests. For example, information is collected from family members and caregivers, through analysis of past photos and videos, and through interviews and questionnaires. Step 2: The generation unit generates conversation content based on the information acquired by the acquisition unit. Using generation AI, conversation content is generated based on the elderly person's past events, hobbies, and family information. Friendly conversation content is generated using text generation AI (e.g., LLM) and multimodal generation AI. Step 3: The providing unit provides the conversation content generated by the generating unit to the elderly person and engages in a dialogue. The conversation content is provided through voice or text, and the conversation content is provided in a format appropriate for the elderly person using voice synthesis technology or a text display method. Step 4: The analysis unit analyzes the content of the dialogue conducted by the provision unit and provides appropriate feedback. The analysis unit analyzes the elderly person's reactions in real time during the dialogue and provides appropriate feedback. Step 5: The emotion analysis unit analyzes the emotional state of the elderly person based on the information analyzed by the analysis unit, and proceeds with the conversation in an appropriate tone and content.The emotional state of the elderly person is analyzed using facial expression analysis and voice analysis, and proceeds with the conversation in an appropriate tone and content. Step 6: The monitoring unit allows doctors and nurses to monitor the dialogue carried out by the provider and intervene as necessary. The dialogue carried out by the generating AI is monitored in real time, and doctors and nurses can intervene as necessary.

[0080] (Example 2) A system according to an embodiment of the present invention utilizes generative AI to provide appropriate conversations to elderly people with dementia and stimulate their memory. This system generates conversation content based on the elderly's past memories and interests, and provides the generated conversation content to the elderly through dialogue, thereby stimulating the elderly's memory and slowing the progression of dementia. This system also helps reduce the elderly's anxiety and restore their self-confidence. Furthermore, it also contributes to reducing the burden on doctors and nurses and improving the quality of care. This system stimulates the elderly's memory and slows the progression of dementia. For example, the system uses information about the elderly's past events, hobbies, and family as input data, and the generative AI generates friendly conversation content. The generated conversation content is then provided to the elderly, and a dialogue is held. This dialogue stimulates the elderly's memory and slows the progression of dementia. This system also helps reduce the elderly's anxiety and restore their self-confidence. Furthermore, it also contributes to reducing the burden on doctors and nurses and improving the quality of care. This system also improves the quality of life of the elderly.

[0081] A conversation support system according to an embodiment includes an acquisition unit, a generation unit, a provision unit, an analysis unit, an emotion analysis unit, and a monitoring unit. The acquisition unit acquires the elderly's past memories and interests. For example, the acquisition unit can analyze information provided by family members or caregivers, or past photos and videos. The acquisition unit can also collect information through interviews and questionnaires. The generation unit uses a generation AI to generate conversation content based on the information acquired by the acquisition unit. For example, the generation AI generates conversation content based on the elderly's past events, hobbies, and family information. The generation AI can generate friendly conversation content using a text generation AI (e.g., LLM) or a multimodal generation AI. The provision unit provides the conversation content generated by the generation unit to the elderly and engages in a dialogue. For example, the provision unit provides the conversation content through voice or text. The provision unit can provide the conversation content in a format appropriate for the elderly using speech synthesis technology or a text display method. The analysis unit analyzes the content of the dialogue conducted by the provision unit and provides appropriate feedback. For example, the analysis unit analyzes the elderly person's reactions in real time during the dialogue and provides appropriate feedback. The emotion analysis unit analyzes the elderly person's emotional state based on the information analyzed by the analysis unit and advances the conversation in an appropriate tone and content. For example, the emotion analysis unit analyzes the elderly person's emotional state using facial expression analysis and voice analysis and advances the conversation in an appropriate tone and content. The monitoring unit allows a doctor or nurse to monitor the dialogue content conducted by the provision unit and intervene as necessary. For example, the monitoring unit monitors the dialogue content of the generation AI in real time and allows a doctor or nurse to intervene as necessary. As a result, the conversation support system according to the embodiment can stimulate the elderly person's memory and slow the progression of dementia. Furthermore, the system helps the elderly person to reduce their anxiety and regain their confidence. The system also reduces the burden on doctors and nurses and contributes to improving the quality of care.

[0082] The acquisition unit can analyze information provided by family members or caregivers, as well as past photos and videos. The acquisition unit can, for example, receive information provided by family members or caregivers. For example, it collects information such as past events, hobbies, and health conditions provided by family members or caregivers. The acquisition unit can also analyze past photos and videos. For example, it can analyze photos using image recognition technology and videos using video analysis technology. This makes it possible to more accurately acquire the elderly person's past memories and interests. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input information provided by family members or caregivers into AI, which can analyze the information to identify the elderly person's memories and interests.

[0083] The generation unit can generate conversation content based on information about the elderly person's past events, hobbies, and family. The generation unit generates conversation content based on information about the elderly person's past events, hobbies, and family, for example. For example, the generation AI generates stories about trips the elderly person took when they were young, or stories about their hobby of gardening. The generation unit can also generate conversation content by combining family information. For example, conversation content is generated that includes family members' names and relationships. This makes it possible to generate conversation content that is familiar to the elderly. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, the generation AI, for example. For example, the generation unit can input information about the elderly person's past events, hobbies, and family into the generation AI, which then generates the conversation content.

[0084] The providing unit can provide the conversation content to the elderly person through voice or text. The providing unit can provide the conversation content to the elderly person through voice or text, for example. For example, the providing unit can provide the conversation content as voice using voice synthesis technology. The providing unit can also provide the conversation content as text using a text display method. This makes it possible to provide the conversation content to the elderly person in an appropriate format. Some or all of the above-mentioned processing in the providing unit can be performed using AI, for example, or can be performed without using AI. For example, the providing unit can input the generated conversation content to AI, which can provide the conversation content as voice or text.

[0085] The analysis unit can analyze the elderly person's reactions in real time during the dialogue and provide appropriate feedback. The analysis unit, for example, analyzes the elderly person's reactions in real time during the dialogue. For example, the analysis unit analyzes the elderly person's reactions using facial expression analysis or voice analysis. The analysis unit can also analyze the elderly person's words and actions during the dialogue. For example, the analysis unit analyzes the content and tone of the elderly person's words and provides appropriate feedback. This makes it possible to provide appropriate feedback based on the elderly person's reactions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the elderly person's reaction data into AI, which can analyze the data in real time and provide feedback.

[0086] The emotion analysis unit analyzes the emotional state of the elderly person and can advance the conversation with an appropriate tone and content. The emotion analysis unit, for example, analyzes the emotional state of the elderly person. For example, the emotion analysis unit analyzes the emotional state of the elderly person using facial expression analysis or voice analysis. The emotion analysis unit can also evaluate the emotional state of the elderly person using self-reports. For example, the emotion analysis unit performs analysis based on the emotional state self-reported by the elderly person. This makes it possible to provide appropriate conversation according to the elderly person's emotional state. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the emotion analysis unit inputs the elderly person's emotional data into AI, which analyzes the emotional state and advances the conversation with an appropriate tone and content.

[0087] The monitoring unit allows a doctor or nurse to monitor the dialogue content of the generation AI and intervene as necessary. The monitoring unit, for example, allows a doctor or nurse to monitor the dialogue content of the generation AI. For example, the monitoring unit monitors the dialogue content of the generation AI in real time, allowing a doctor or nurse to intervene as necessary. The monitoring unit can also monitor the dialogue content using periodic checks or an alert system. For example, the monitoring unit issues an alert if an abnormality is detected in the dialogue content. This allows a doctor or nurse to monitor the dialogue content of the elderly person and intervene as necessary. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the dialogue content of the generation AI to AI, which can analyze the dialogue content, detect abnormalities, and issue an alert.

[0088] The acquisition unit can estimate the elderly person's emotions and adjust the timing of acquiring memories and interests based on the estimated elderly person's emotions. The acquisition unit, for example, estimates the elderly person's emotions. For example, the acquisition unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The acquisition unit can also evaluate the elderly person's emotions using self-reports. For example, the acquisition unit performs analysis based on the elderly person's self-reported emotional state. Next, the acquisition unit adjusts the timing of acquiring memories and interests based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, the timing of acquiring past memories and interests can be increased. If the elderly person is stressed, the timing of acquiring memories and interests can be reduced, allowing more time for relaxation. If the elderly person is excited, topics of interest can be preferentially acquired to promote dialogue. This makes it possible to adjust the timing of acquiring memories and interests according to the elderly person's emotional state. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit may input emotional data of the elderly person into AI, which may analyze the emotional state and adjust the timing of acquiring memories and interests.

[0089] The acquisition unit can reflect feedback from family members and caregivers in real time when acquiring the elderly person's past memories and interests. For example, the acquisition unit reflects feedback from family members and caregivers in real time when acquiring the elderly person's past memories and interests. For example, the acquisition unit acquires the elderly person's interests based on the latest information provided by family members. The acquisition unit can also adjust the memory acquisition by reflecting the elderly person's reactions observed by the caregiver in real time. For example, the content of the memories and interests to be acquired is updated based on feedback provided by family members and caregivers. This improves the accuracy of the memories and interests to be acquired by reflecting feedback from family members and caregivers in real time. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input feedback from family members and caregivers into AI, which can analyze the feedback and adjust the acquisition of memories and interests.

[0090] The acquisition unit can improve accuracy when acquiring the elderly person's past memories and interests by combining analysis results of past photos and videos. The acquisition unit, for example, analyzes the elderly person's past photos and videos and acquires the memories and interests based on the results. For example, it analyzes photos using image recognition technology and analyzes videos using video analysis technology. The acquisition unit can also accurately select the content of memories and interests to acquire based on the analysis results of the photos and videos. For example, it can analyze the elderly person's past photos and acquire related memories. It can also analyze the elderly person's past videos to identify topics of interest. In this way, by combining the analysis results of past photos and videos, the accuracy of the acquired memories and interests can be improved. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without AI. For example, the acquisition unit can input data of past photos and videos into AI, which can acquire the memories and interests based on the analysis results.

[0091] When acquiring the elderly person's past memories and interests, the acquisition unit can automatically convert the elderly person's dictation into text using voice recognition technology. For example, the acquisition unit performs voice recognition and converts the content of the elderly person's speech into text in real time. For example, the acquisition unit can automatically convert the elderly person's dictation into text using voice recognition technology. The acquisition unit can also analyze the elderly person's dictation to acquire related memories and interests. For example, the content of the elderly person's speech can be analyzed using voice recognition technology to identify related memories and interests. The acquisition unit can also automatically record the content of the elderly person's speech using voice recognition technology and analyze it later. In this way, the use of voice recognition technology can automatically convert the elderly person's dictation into text, improving the accuracy of acquiring memories and interests. Some or all of the above-mentioned processing in the acquisition unit can be performed using, for example, AI, or without AI. For example, the acquisition unit can input the elderly person's voice data into AI, which can convert the voice data into text to acquire memories and interests.

[0092] The acquisition unit can estimate the elderly person's emotions and determine the priority of memories and interests to be acquired based on the estimated elderly person's emotions. The acquisition unit, for example, estimates the elderly person's emotions. For example, the acquisition unit can estimate the elderly person's emotions using facial expression analysis or voice analysis. The acquisition unit can also evaluate the elderly person's emotions using self-reports. For example, the acquisition unit performs analysis based on the elderly person's self-reported emotional state. Next, the acquisition unit determines the priority of memories and interests to be acquired based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, it can prioritize acquiring pleasant memories and interests. Also, if the elderly person is stressed, it can prioritize acquiring relaxing memories and interests. Also, if the elderly person is excited, it can prioritize acquiring stimulating memories and interests. This makes it possible to prioritize memories and interests according to the elderly person's emotional state. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit may input emotional data of the elderly person into AI, which may analyze the emotional state and determine the priorities of memories and interests.

[0093] The acquisition unit can prioritize acquiring highly relevant information by taking geographical location information into consideration when acquiring the elderly person's past memories and interests. For example, the acquisition unit prioritizes acquiring highly relevant information by taking geographical location information into consideration when acquiring the elderly person's past memories and interests. For example, the acquisition unit prioritizes acquiring memories related to places the elderly person lived. It can also prioritize acquiring interests related to places the elderly person frequently visited. For example, the acquisition unit evaluates the relevance of the elderly person's memories and interests based on the geographical location information and determines priorities. This makes it possible to prioritize acquiring highly relevant memories and interests by taking the geographical location information into consideration. Some or all of the above-described processing by the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the elderly person's geographical location information into AI, which can analyze the geographical location information to acquire the memories and interests.

[0094] The acquisition unit can analyze social media activity and acquire related information when acquiring the elderly person's past memories and interests. The acquisition unit, for example, analyzes the elderly person's social media activity to acquire related memories and interests. For example, it analyzes the content of the elderly person's social media posts to acquire related memories. It can also acquire topics of interest by referring to the activities of the elderly person's friends on social media. For example, the elderly person's memories and interests can be identified based on their social media activity history. In this way, it is possible to acquire related memories and interests by analyzing their social media activity. Some or all of the above-described processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the elderly person's social media data into AI, which can analyze the data to acquire memories and interests.

[0095] When acquiring the elderly person's past memories and interests, the acquisition unit can customize the acquisition method by reflecting past feedback. The acquisition unit, for example, adjusts the memory and interest acquisition method based on feedback provided by the elderly person in the past. For example, the acquisition unit analyzes the elderly person's reactions and customizes the contents of the memories and interests to be acquired. The acquisition unit can also reflect past feedback and change the priority of the memories and interests to be acquired. For example, memories and interests to which the elderly person has previously responded favorably can be preferentially acquired. In this way, by reflecting past feedback, the acquisition method can be customized and accuracy can be improved. Some or all of the above-mentioned processing in the acquisition unit may be performed using, for example, AI, or may be performed without using AI. For example, the acquisition unit can input the elderly person's past feedback data into AI, which analyzes the data and customizes the acquisition method.

[0096] The generation unit can estimate the elderly person's emotions and adjust the way the conversation content is expressed based on the estimated elderly person's emotions. The generation unit, for example, estimates the elderly person's emotions. For example, the generation unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The generation unit can also evaluate the elderly person's emotions using self-reports. For example, the generation unit performs analysis based on the elderly person's self-reported emotional state. Next, the generation unit adjusts the way the conversation content is expressed based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, the generation unit can generate the conversation content in a calm tone. If the elderly person is stressed, the generation unit can generate the conversation content in a gentle tone. If the elderly person is excited, the generation unit can generate the conversation content in a lively tone. This makes it possible to provide the conversation content in an expression method that corresponds to the elderly person's emotional state. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, a generation AI. For example, the generation unit may input emotional data of the elderly person to the generation AI, which may then analyze the emotional state and adjust the way the conversation content is expressed.

[0097] When generating conversation content, the generation unit can apply different generation algorithms based on the elderly person's past events and hobbies. For example, the generation unit can apply different generation algorithms based on the elderly person's past events and hobbies. For example, the generation AI can generate conversation content related to travel based on the elderly person's past travel experiences. The generation AI can also generate conversation content related to gardening based on the elderly person's hobby of gardening. The generation AI can also generate conversation content related to family based on information about the elderly person's family. This makes it possible to generate more friendly conversation content based on the elderly person's past events and hobbies. Some or all of the above-described processing in the generation unit can be performed using, or without, the generation AI. For example, the generation unit can input data on the elderly person's past events and hobbies into the generation AI, and the generation AI can generate conversation content by applying different generation algorithms.

[0098] When generating the conversation content, the generation unit can combine information about the elderly person's family to generate a friendly conversation. The generation unit, for example, generates the conversation content by combining information about the elderly person's family. For example, the generation AI generates the conversation content including the names and relationships of the elderly person's family members. The generation AI can also generate the conversation content incorporating anecdotes about the elderly person's family. The generation AI can also generate the conversation content based on the hobbies and interests of the elderly person's family. In this way, by combining the information about the elderly person's family members, a friendly conversation content can be generated. Some or all of the above-described processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input information about the elderly person's family members into the generation AI, which can then generate the conversation content.

[0099] When generating conversation content, the generation unit can improve the accuracy of generation by referring to the elderly person's past conversation history. The generation unit, for example, generates conversation content by referring to the elderly person's past conversation history. For example, the generation AI analyzes the elderly person's past conversation history and generates related conversation content. The generation AI can also generate topics of interest based on content that the elderly person has spoken in the past. The generation AI can also maintain consistency in the conversation content by referring to the elderly person's past conversation history. In this way, by referring to the elderly person's past conversation history, the accuracy of generation can be improved. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input the elderly person's past conversation history into the generation AI, which can then generate the conversation content.

[0100] The generation unit can estimate the elderly person's emotions and adjust the length of the conversation content based on the estimated elderly person's emotions. The generation unit, for example, estimates the elderly person's emotions. For example, the generation unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The generation unit can also evaluate the elderly person's emotions using self-reports. For example, the generation unit performs analysis based on the elderly person's self-reported emotional state. Next, the generation unit adjusts the length of the conversation content based on the elderly person's estimated emotions. For example, if the elderly person is relaxed, a longer conversation content can be generated. Also, if the elderly person is stressed, a shorter conversation content can be generated. Also, if the elderly person is excited, a conversation content of an appropriate length can be generated. This allows the length of the conversation content to be adjusted according to the elderly person's emotional state. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, the generation AI, or without the generation AI. For example, the generation unit can input the elderly person's emotional data into the generation AI, which can then analyze the emotional state and adjust the length of the conversation.

[0101] When generating conversation content, the generation unit can determine the priority of the conversation based on the timing of past events. The generation unit, for example, determines the priority of the conversation based on the timing of past events. For example, the generation AI can prioritize events that occurred when the elderly person was young and incorporate them into the conversation content. The generation AI can also prioritize events that the elderly person experienced recently and incorporate them into the conversation content. The generation AI can also prioritize events that occurred during a period that is likely to be memorable to the elderly and incorporate them into the conversation content. This enables more effective dialogue by determining the priority of the conversation based on the timing of past events. Some or all of the above-described processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input data regarding the timing of past events into the generation AI, and the generation AI can determine the priority of the conversation.

[0102] The generation unit can adjust the order of related events when generating conversation content. The generation unit, for example, adjusts the order of related events. For example, the generation AI adjusts the order of events based on the memory of the elderly person. The generation AI can also adjust the order of events based on the interests of the elderly person. The generation AI can also adjust the order of events based on the response of the elderly person. In this way, by adjusting the order of related events, more consistent conversation content can be provided. Some or all of the above-mentioned processing in the generation unit may be performed using the generation AI, for example, or may be performed without using the generation AI. For example, the generation unit can input data of related events into the generation AI, which can then adjust the order of events.

[0103] When generating conversation content, the generation unit can adjust the use of technical terms according to the elderly person's level of expertise. The generation unit, for example, adjusts the use of technical terms according to the elderly person's level of expertise. For example, if the elderly person has technical expertise, the generation AI generates conversation content that uses a lot of technical terms. Also, if the elderly person does not have technical expertise, the generation AI can generate conversation content using simple language. Also, the generation AI can adjust the frequency of use of technical terms according to the elderly person's level of expertise. In this way, by adjusting the use of technical terms according to the elderly person's level of expertise, it is possible to provide conversation content that is easier to understand. Some or all of the above-mentioned processing in the generation unit may be performed using, or without, the generation AI. For example, the generation unit can input data regarding the elderly person's level of expertise into the generation AI, which can then adjust the use of technical terms.

[0104] The providing unit can estimate the elderly person's emotions and adjust the method of providing the conversation content based on the estimated elderly person's emotions. The providing unit, for example, estimates the elderly person's emotions. For example, the providing unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The providing unit can also evaluate the elderly person's emotions using self-reports. For example, the providing unit performs analysis based on the elderly person's self-reported emotional state. Next, the providing unit adjusts the method of providing the conversation content based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, the conversation content can be provided in a calm tone. If the elderly person is stressed, the conversation content can be provided in a gentle tone. If the elderly person is excited, the conversation content can be provided in a lively tone. This allows the conversation content to be provided in a manner appropriate to the elderly person's emotional state. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the providing unit can be performed, for example, using AI or without AI. For example, the provision unit can input the elderly person's emotional data into the AI, which can then analyze the emotional state and adjust how the conversation content is provided.

[0105] When providing the conversation content, the providing unit can optimize the timing of providing the content by referring to the elderly person's past reactions. The providing unit, for example, provides the conversation content by referring to the elderly person's past reactions. For example, the providing unit provides the conversation content at a timing when the elderly person has previously shown a favorable reaction. The providing unit can also provide the conversation content by avoiding a timing when the elderly person has previously felt stressed. The providing unit can also determine the optimal timing of providing the content based on the elderly person's past reactions. In this way, the timing of providing the content can be optimized by referring to the elderly person's past reactions. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the elderly person's past reaction data into AI, which can analyze the data to optimize the timing of providing the content.

[0106] When providing the conversation content, the providing unit can customize the audio or text format according to the elderly person's preferences. The providing unit customizes the audio or text format according to the elderly person's preferences, for example. For example, if the elderly person prefers audio format, the providing unit provides the conversation content in audio format. Furthermore, if the elderly person prefers text format, the providing unit can also provide the conversation content in text format. Furthermore, the providing unit can provide the conversation content by combining both audio and text according to the elderly person's preferences. This makes it possible to provide the conversation content in a format according to the elderly person's preferences. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input data regarding the elderly person's preferences into AI, which can analyze the data to customize the audio or text format.

[0107] When providing the conversation content, the providing unit can adjust the provision method taking into account the elderly person's current health condition. The providing unit provides the conversation content, for example, taking into account the elderly person's current health condition. For example, the providing unit provides shorter conversation content when the elderly person is tired. Furthermore, the providing unit can also provide longer conversation content when the elderly person is in good health. Furthermore, the providing unit can adjust the frequency of providing the conversation content according to the elderly person's health condition. This makes it possible to provide the conversation content in a provision method that suits the elderly person's health condition. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input data regarding the elderly person's health condition into AI, which can analyze the data and adjust the provision method.

[0108] The providing unit can estimate the elderly person's emotions and adjust the order in which the conversation contents are provided based on the estimated elderly person's emotions. The providing unit, for example, estimates the elderly person's emotions. For example, the providing unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The providing unit can also evaluate the elderly person's emotions using self-reports. For example, the providing unit performs analysis based on the elderly person's self-reported emotional state. Next, the providing unit adjusts the order in which the conversation contents are provided based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, pleasant topics can be provided preferentially. Also, if the elderly person is stressed, relaxing topics can be provided preferentially. Also, if the elderly person is excited, stimulating topics can be provided preferentially. This allows the conversation contents to be provided in an order that corresponds to the elderly person's emotional state. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the providing unit can be performed, for example, using AI or without AI. For example, the provision department can input the elderly person's emotional data into AI, which can then analyze the emotional state and adjust the provision order.

[0109] When providing the conversation content, the providing unit can select the optimal providing method by taking into consideration the geographical location information of the elderly person. The providing unit provides the conversation content by taking into consideration, for example, the geographical location information of the elderly person. For example, when the elderly person is at home, the providing unit can provide relaxing topics. Furthermore, when the elderly person is out, the providing unit can also provide topics related to the destination. Furthermore, the providing unit can select the optimal providing method based on the geographical location information of the elderly person. In this way, the optimal providing method can be selected based on the geographical location information of the elderly person. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the geographical location information of the elderly person into AI, which can analyze the data and select the optimal providing method.

[0110] When providing the conversation content, the providing unit can analyze the social media activity of the elderly person to provide related conversation content. The providing unit, for example, analyzes the social media activity of the elderly person and provides related conversation content. For example, the providing unit provides conversations about places where the elderly person has checked in on social media. The providing unit can also analyze the content posted on social media by the elderly person and provide related topics. The providing unit can also provide related topics by referring to the activities of the elderly person's friends on social media. In this way, related conversation content can be provided by analyzing the social media activity of the elderly person. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the elderly person's social media data into AI, which analyzes the data and provides related conversation content.

[0111] When providing the conversation content, the providing unit can customize the delivery method by reflecting the elderly person's past feedback. The providing unit customizes the delivery method based on, for example, the elderly person's past feedback. For example, the providing unit prioritizes delivery methods to which the elderly person has responded favorably in the past. The providing unit can also avoid delivery methods that the elderly person has experienced stress in the past. The providing unit can also customize the delivery method based on the elderly person's past feedback. In this way, by reflecting the elderly person's past feedback, the delivery method can be customized and accuracy can be improved. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the elderly person's past feedback data into AI, which can analyze the data and customize the delivery method.

[0112] The analysis unit can estimate the elderly person's emotions and adjust the dialogue analysis method based on the estimated elderly person's emotions. The analysis unit, for example, estimates the elderly person's emotions. For example, the analysis unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The analysis unit can also evaluate the elderly person's emotions using self-reports. For example, the analysis unit performs analysis based on the elderly person's self-reported emotional state. Next, the analysis unit adjusts the dialogue analysis method based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, a detailed analysis can be performed. If the elderly person is stressed, a simple analysis can be performed. If the elderly person is excited, an analysis focusing on a specific emotion can be performed. This allows the dialogue content to be analyzed using an analysis method appropriate for the elderly person's emotional state. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the elderly person's emotional data into the AI, which can then analyze their emotional state and adjust how it analyzes the dialogue.

[0113] When analyzing the content of a dialogue, the analysis unit can improve the accuracy of the analysis by referring to the elderly person's past reactions. The analysis unit, for example, analyzes the content of the dialogue by referring to the elderly person's past reactions. For example, the analysis unit improves the analysis accuracy of the dialogue content based on the elderly person's past reactions. The analysis unit can also adjust the analysis results by referring to emotions shown by the elderly person in the past. The analysis unit can also analyze the elderly person's past reactions and improve the analysis method. In this way, the accuracy of the analysis can be improved by referring to the elderly person's past reactions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the elderly person's past reaction data into AI, which analyzes the data to improve the accuracy of the analysis.

[0114] When analyzing the content of the dialogue, the analysis unit can provide an analysis result taking into account the health condition of the elderly person. The analysis unit, for example, analyzes the content of the dialogue taking into account the health condition of the elderly person. For example, the analysis unit adjusts the analysis result according to the health condition of the elderly person. The analysis unit can also provide a simple analysis result when the elderly person is tired. The analysis unit can also provide a detailed analysis result when the elderly person is in good health. This makes it possible to provide an analysis result according to the health condition of the elderly person. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data regarding the health condition of the elderly person into AI, which then analyzes the data and provides an analysis result.

[0115] When analyzing the content of the dialogue, the analysis unit can improve the analysis method by reflecting feedback from the elderly person's family. The analysis unit improves the analysis method of the dialogue content, for example, based on feedback from the elderly person's family. For example, the analysis unit adjusts the analysis method based on feedback provided by the elderly person's family. The analysis unit can also improve the analysis results by reflecting the opinions of the elderly person's family. The analysis unit can also improve the accuracy of the analysis based on the feedback from the elderly person's family. In this way, the analysis method can be improved and the accuracy can be improved by reflecting the feedback from the elderly person's family. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input feedback data from the elderly person's family into AI, which analyzes the data and improves the analysis method.

[0116] The analysis unit can estimate the elderly person's emotions and adjust the display method of the analysis results based on the estimated elderly person's emotions. The analysis unit, for example, estimates the elderly person's emotions. For example, the analysis unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The analysis unit can also evaluate the elderly person's emotions using self-reports. For example, the analysis unit performs analysis based on the elderly person's self-reported emotional state. Next, the analysis unit adjusts the display method of the analysis results based on the elderly person's estimated emotions. For example, if the elderly person is relaxed, detailed analysis results can be displayed. If the elderly person is stressed, simple analysis results can be displayed. If the elderly person is excited, analysis results focusing on specific emotions can be displayed. This makes it possible to provide analysis results in a display method appropriate for the elderly person's emotional state. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the emotional data of an elderly person into the AI, which can then analyze the emotional state and adjust the display method.

[0117] When analyzing the content of the dialogue, the analysis unit can provide an analysis result taking into account the geographical location information of the elderly person. The analysis unit, for example, analyzes the content of the dialogue taking into account the geographical location information of the elderly person. For example, if the elderly person is at home, the analysis unit can provide an analysis result related to the home. Furthermore, if the elderly person is out, the analysis unit can also provide an analysis result related to the destination. Furthermore, the analysis unit can provide an optimal analysis result based on the geographical location information of the elderly person. This makes it possible to provide an optimal analysis result based on the geographical location information of the elderly person. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the geographical location information of the elderly person to AI, which can analyze the data and provide an analysis result.

[0118] When analyzing the content of the conversation, the analysis unit can improve the accuracy of the analysis by analyzing the social media activities of the elderly. The analysis unit, for example, analyzes the social media activities of the elderly and analyzes the content of the conversation. For example, the analysis unit analyzes the content of the elderly's posts on social media to improve the accuracy of the analysis. The analysis unit can also improve the analysis results by referring to the activities of the elderly's friends on social media. The analysis unit can also adjust the analysis method based on the elderly's social media activity history. In this way, the accuracy of the analysis can be improved by analyzing the elderly's social media activities. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the elderly's social media data into AI, which analyzes the data to improve the accuracy of the analysis.

[0119] When analyzing the content of the dialogue, the analysis unit can customize the analysis method by reflecting the elderly person's past feedback. The analysis unit customizes the analysis method for the content of the dialogue based on, for example, the elderly person's past feedback. For example, the analysis unit adjusts the analysis method based on feedback provided by the elderly person in the past. The analysis unit can also improve the analysis results by referring to the elderly person's past responses. The analysis unit can also improve the accuracy of the analysis based on the elderly person's past feedback. In this way, the analysis method can be customized and the accuracy can be improved by reflecting the elderly person's past feedback. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the elderly person's past feedback data into AI, which analyzes the data and customizes the analysis method.

[0120] The emotion analysis unit can estimate the emotion of the elderly person and adjust the emotion analysis method based on the estimated emotion of the elderly person. The emotion analysis unit, for example, estimates the emotion of the elderly person. For example, the emotion analysis unit estimates the emotion of the elderly person using facial expression analysis or voice analysis. The emotion analysis unit can also evaluate the emotion of the elderly person using self-reports. For example, the emotion analysis unit performs analysis based on the emotional state self-reported by the elderly person. Next, the emotion analysis unit adjusts the emotion analysis method based on the estimated emotion of the elderly person. For example, if the elderly person is relaxed, detailed emotion analysis can be performed. If the elderly person is stressed, simple emotion analysis can be performed. If the elderly person is excited, emotion analysis focusing on a specific emotion can be performed. This allows emotion analysis to be performed in a manner appropriate to the elderly person's emotional state. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the emotion analysis unit can be performed using, for example, AI, or without AI. For example, the emotion analysis unit can input the emotional data of elderly people into the AI, which can then analyze their emotional state and adjust the emotion analysis method.

[0121] When performing emotion analysis, the emotion analysis unit can improve the accuracy of the analysis by referring to the elderly person's past emotional states. The emotion analysis unit, for example, performs emotion analysis by referring to the elderly person's past emotional states. For example, the emotion analysis unit improves the accuracy of the emotion analysis based on the elderly person's past emotional states. The emotion analysis unit can also adjust the analysis results by referring to emotions expressed by the elderly person in the past. The emotion analysis unit can also analyze the elderly person's past emotional states and improve the analysis method. In this way, the accuracy of the emotion analysis can be improved by referring to the elderly person's past emotional states. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the elderly person's past emotional data into AI, which analyzes the data to improve the accuracy of the emotion analysis.

[0122] When performing emotion analysis, the emotion analysis unit can provide analysis results taking into account the health condition of the elderly person. The emotion analysis unit performs emotion analysis taking into account, for example, the health condition of the elderly person. For example, the emotion analysis unit adjusts the emotion analysis result according to the elderly person's health condition. The emotion analysis unit can also provide a simple emotion analysis result if the elderly person is tired. The emotion analysis unit can also provide a detailed emotion analysis result if the elderly person is in good health. This makes it possible to provide emotion analysis results according to the elderly person's health condition. Some or all of the above-mentioned processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input data regarding the elderly person's health condition into AI, which then analyzes the data and provides emotion analysis results.

[0123] When performing emotion analysis, the emotion analysis unit can improve the analysis method by reflecting feedback from the elderly person's family. The emotion analysis unit, for example, improves the emotion analysis method based on feedback from the elderly person's family. For example, the emotion analysis unit adjusts the emotion analysis method based on feedback provided by the elderly person's family. The emotion analysis unit can also improve the emotion analysis results by reflecting the opinions of the elderly person's family. The emotion analysis unit can also improve the accuracy of the emotion analysis based on feedback from the elderly person's family. In this way, by reflecting the feedback from the elderly person's family, the emotion analysis method can be improved and the accuracy can be increased. Some or all of the above-mentioned processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input feedback data from the elderly person's family into AI, which analyzes the data and improves the emotion analysis method.

[0124] The emotion analysis unit can estimate the emotion of the elderly person and adjust the display method of the emotion analysis result based on the estimated emotion of the elderly person. The emotion analysis unit, for example, estimates the emotion of the elderly person. For example, the emotion analysis unit estimates the emotion of the elderly person using facial expression analysis or voice analysis. The emotion analysis unit can also evaluate the emotion of the elderly person using self-reports. For example, the emotion analysis unit performs analysis based on the emotional state self-reported by the elderly person. Next, the emotion analysis unit adjusts the display method of the emotion analysis result based on the estimated emotion of the elderly person. For example, if the elderly person is relaxed, a detailed emotion analysis result can be displayed. If the elderly person is stressed, a simple emotion analysis result can be displayed. If the elderly person is excited, an emotion analysis result focusing on a specific emotion can be displayed. This makes it possible to provide the emotion analysis result in a display method appropriate for the emotional state of the elderly person. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit may input the emotion data of the elderly person into AI, which may analyze the emotional state and adjust the display method.

[0125] When performing emotion analysis, the emotion analysis unit can provide analysis results taking into account the geographical location information of the elderly person. The emotion analysis unit performs emotion analysis, for example, taking into account the geographical location information of the elderly person. For example, if the elderly person is at home, the emotion analysis unit can provide emotion analysis results related to the home. Furthermore, if the elderly person is out, the emotion analysis unit can also provide emotion analysis results related to the destination. Furthermore, the emotion analysis unit can provide optimal emotion analysis results based on the geographical location information of the elderly person. This makes it possible to provide optimal emotion analysis results based on the geographical location information of the elderly person. Some or all of the above-described processing in the emotion analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the emotion analysis unit can input the geographical location information of the elderly person into AI, which can analyze the data and provide emotion analysis results.

[0126] When performing emotion analysis, the emotion analysis unit can analyze the social media activities of the elderly to improve the accuracy of the analysis. The emotion analysis unit, for example, analyzes the social media activities of the elderly to perform emotion analysis. For example, the emotion analysis unit analyzes the content of the elderly's social media posts to improve the accuracy of the emotion analysis. The emotion analysis unit can also improve the emotion analysis results by referring to the activities of the elderly's friends on social media. The emotion analysis unit can also adjust the analysis method based on the elderly's social media activity history. In this way, the accuracy of the emotion analysis can be improved by analyzing the elderly's social media activities. Some or all of the above-described processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the elderly's social media data into AI, which then analyzes the data to improve the accuracy of the emotion analysis.

[0127] When performing emotion analysis, the emotion analysis unit can customize the analysis method by reflecting the elderly person's past feedback. The emotion analysis unit customizes the emotion analysis method based on, for example, the elderly person's past feedback. For example, the emotion analysis unit adjusts the analysis method based on feedback provided by the elderly person in the past. The emotion analysis unit can also improve the analysis results by referring to the elderly person's past reactions. The emotion analysis unit can also improve the accuracy of the analysis based on the elderly person's past feedback. In this way, by reflecting the elderly person's past feedback, the emotion analysis method can be customized and the accuracy can be improved. Some or all of the above-mentioned processing in the emotion analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the emotion analysis unit can input the elderly person's past feedback data into AI, which analyzes the data and customizes the analysis method.

[0128] The monitoring unit can estimate the elderly person's emotions and adjust the monitoring method based on the estimated elderly person's emotions. The monitoring unit, for example, estimates the elderly person's emotions. For example, the monitoring unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The monitoring unit can also evaluate the elderly person's emotions using self-reports. For example, the monitoring unit performs analysis based on the elderly person's self-reported emotional state. Next, the monitoring unit adjusts the monitoring method based on the elderly person's estimated emotions. For example, if the elderly person is relaxed, detailed monitoring can be performed. If the elderly person is stressed, simple monitoring can be performed. If the elderly person is excited, monitoring can be performed focusing on a specific emotion. This allows monitoring to be performed in a manner appropriate to the elderly person's emotional state. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the monitoring unit can be performed using, for example, AI, or without AI. For example, the monitoring unit can input the elderly person's emotional data into the AI, which can then analyze their emotional state and adjust the monitoring method.

[0129] When performing monitoring, the monitoring unit can improve the accuracy of the monitoring by referring to the elderly person's past dialogue history. The monitoring unit, for example, performs monitoring by referring to the elderly person's past dialogue history. For example, the monitoring unit improves the accuracy of the monitoring based on the elderly person's past dialogue history. The monitoring unit can also adjust the monitoring results by referring to the elderly person's past responses. The monitoring unit can also analyze the elderly person's past dialogue history and improve the monitoring method. In this way, the accuracy of monitoring can be improved by referring to the elderly person's past dialogue history. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the elderly person's past dialogue history data into AI, which can analyze the data to improve the accuracy of monitoring.

[0130] When performing monitoring, the monitoring unit can provide monitoring results taking into account the health condition of the elderly person. The monitoring unit, for example, performs monitoring taking into account the health condition of the elderly person. For example, the monitoring unit adjusts the monitoring results according to the health condition of the elderly person. The monitoring unit can also provide simple monitoring results when the elderly person is tired. The monitoring unit can also provide detailed monitoring results when the elderly person is in good health. This makes it possible to provide monitoring results according to the health condition of the elderly person. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input data regarding the health condition of the elderly person into AI, which can analyze the data and provide monitoring results.

[0131] When performing monitoring, the monitoring unit can improve the monitoring method by reflecting feedback from the elderly person's family. The monitoring unit, for example, improves the monitoring method based on feedback from the elderly person's family. For example, the monitoring unit adjusts the monitoring method based on feedback provided by the elderly person's family. The monitoring unit can also improve the monitoring results by reflecting the opinions of the elderly person's family. The monitoring unit can also improve the accuracy of the monitoring based on feedback from the elderly person's family. In this way, the monitoring method can be improved and the accuracy can be increased by reflecting the feedback from the elderly person's family. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input feedback data from the elderly person's family into AI, which can analyze the data and improve the monitoring method.

[0132] The monitoring unit can estimate the elderly person's emotions and adjust the display method of the monitoring results based on the estimated elderly person's emotions. The monitoring unit, for example, estimates the elderly person's emotions. For example, the monitoring unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The monitoring unit can also evaluate the elderly person's emotions using self-reports. For example, the monitoring unit performs analysis based on the elderly person's self-reported emotional state. Next, the monitoring unit adjusts the display method of the monitoring results based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, detailed monitoring results can be displayed. If the elderly person is stressed, simple monitoring results can be displayed. If the elderly person is excited, monitoring results focusing on a specific emotion can be displayed. This makes it possible to provide monitoring results in a display method appropriate for the elderly person's emotional state. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the monitoring unit can be performed, for example, using AI or without AI. For example, the monitoring unit can input the elderly person's emotional data into the AI, which can then analyze their emotional state and adjust the display method.

[0133] When performing monitoring, the monitoring unit can provide monitoring results taking into account the geographical location information of the elderly person. The monitoring unit performs monitoring, for example, taking into account the geographical location information of the elderly person. For example, when the elderly person is at home, the monitoring unit can provide monitoring results related to the home. Furthermore, when the elderly person is out, the monitoring unit can also provide monitoring results related to the destination. Furthermore, the monitoring unit can provide optimal monitoring results based on the geographical location information of the elderly person. This makes it possible to provide optimal monitoring results based on the geographical location information of the elderly person. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the geographical location information of the elderly person into AI, which can analyze the data and provide monitoring results.

[0134] When performing monitoring, the monitoring unit can analyze the social media activities of the elderly to improve the accuracy of the monitoring. The monitoring unit, for example, analyzes the social media activities of the elderly to perform monitoring. For example, the monitoring unit analyzes the content of the elderly's social media posts to improve the accuracy of the monitoring. The monitoring unit can also improve the monitoring results by referring to the activities of the elderly's friends on social media. The monitoring unit can also adjust the monitoring method based on the elderly's social media activity history. In this way, the accuracy of the monitoring can be improved by analyzing the elderly's social media activities. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the elderly's social media data into AI, which analyzes the data to improve the accuracy of the monitoring.

[0135] When performing monitoring, the monitoring unit can customize the monitoring method by reflecting the elderly person's past feedback. The monitoring unit customizes the monitoring method based on, for example, the elderly person's past feedback. For example, the monitoring unit adjusts the monitoring method based on feedback provided by the elderly person in the past. The monitoring unit can also improve the monitoring results by referring to the elderly person's past responses. The monitoring unit can also improve the accuracy of the monitoring based on the elderly person's past feedback. In this way, the monitoring method can be customized and accuracy can be improved by reflecting the elderly person's past feedback. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the elderly person's past feedback data into AI, which can analyze the data and customize the monitoring method. === Hard Collateral 1-1 === Each of the multiple elements, including the acquisition unit, generation unit, provision unit, analysis unit, emotion analysis unit, and monitoring unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the acquisition unit can detect the facial expressions and voice of the elderly person using the camera 42 and microphone 38B of the smart device 14 and estimate the elderly person's emotions using the specific processing unit 290 of the data processing device 12. For example, the generation unit can generate conversation content using a generation AI using the specific processing unit 290 of the data processing device 12. For example, the provision unit can provide the generated conversation content to the elderly person using the control unit 46A of the smart device 14. For example, the analysis unit can analyze the content of the dialogue using the specific processing unit 290 of the data processing device 12 and provide appropriate feedback. For example, the emotion analysis unit can analyze the emotional state of the elderly person using the specific processing unit 290 of the data processing device 12 and advance the conversation with an appropriate tone and content. For example, the monitoring unit can allow a doctor or nurse to monitor the dialogue content using the control unit 46A of the smart device 14 and intervene as necessary. === Hard Collateral 1-2 === Each of the multiple elements, including the acquisition unit, generation unit, provision unit, analysis unit, emotion analysis unit, and monitoring unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the acquisition unit can detect the facial expression and voice of the elderly person using the camera 42 and microphone 238 of the smart glasses 214 and estimate the elderly person's emotion using the specific processing unit 290 of the data processing device 12. For example, the generation unit can generate conversation content using a generation AI using the specific processing unit 290 of the data processing device 12. For example, the provision unit can provide the generated conversation content to the elderly person using the control unit 46A of the smart glasses 214. For example, the analysis unit can analyze the content of the dialogue using the specific processing unit 290 of the data processing device 12 and provide appropriate feedback. For example, the emotion analysis unit can analyze the emotional state of the elderly person using the specific processing unit 290 of the data processing device 12 and advance the conversation with an appropriate tone and content. For example, the monitoring unit can allow a doctor or nurse to monitor the dialogue content using the control unit 46A of the smart glasses 214 and intervene as necessary. === Hard Collateral 1-3 === Each of the multiple elements, including the acquisition unit, generation unit, provision unit, analysis unit, emotion analysis unit, and monitoring unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the acquisition unit can detect the facial expressions and voice of the elderly person using the camera 42 and microphone 238 of the headset-type terminal 314 and estimate the elderly person's emotions using the specific processing unit 290 of the data processing device 12. For example, the generation unit can generate conversation content using a generation AI using the specific processing unit 290 of the data processing device 12. For example, the provision unit can provide the generated conversation content to the elderly person using the control unit 46A of the headset-type terminal 314. For example, the analysis unit can analyze the content of the dialogue using the specific processing unit 290 of the data processing device 12 and provide appropriate feedback. For example, the emotion analysis unit can analyze the emotional state of the elderly person using the specific processing unit 290 of the data processing device 12 and advance the conversation with an appropriate tone and content. For example, the monitoring unit can allow a doctor or nurse to monitor the dialogue content using the control unit 46A of the headset-type terminal 314 and intervene as necessary. === Hard Collateral 1-4 === Each of the multiple elements, including the acquisition unit, generation unit, provision unit, analysis unit, emotion analysis unit, and monitoring unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the acquisition unit can detect the facial expressions and voice of the elderly person using the camera 42 and microphone 238 of the robot 414 and estimate the elderly person's emotions using the specific processing unit 290 of the data processing device 12. For example, the generation unit can generate conversation content using a generation AI using the specific processing unit 290 of the data processing device 12. For example, the provision unit can provide the conversation content generated using the control unit 46A of the robot 414 to the elderly person. For example, the analysis unit can analyze the content of the dialogue using the specific processing unit 290 of the data processing device 12 and provide appropriate feedback. For example, the emotion analysis unit can analyze the emotional state of the elderly person using the specific processing unit 290 of the data processing device 12 and advance the conversation with an appropriate tone and content. For example, the monitoring unit can allow a doctor or nurse to monitor the dialogue content using the control unit 46A of the robot 414 and intervene as necessary.

[0136] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0137] When acquiring the elderly person's past memories and interests, the acquisition unit can automatically convert the elderly person's dictation into text using voice recognition technology. For example, the acquisition unit can recognize the voice of the elderly person in real time and convert it into text. The acquisition unit can also analyze the elderly person's dictation to acquire related memories and interests. For example, the acquisition unit can analyze the voice of the elderly person using voice recognition technology to identify related memories and interests. The acquisition unit can also automatically record the voice of the elderly person using voice recognition technology and analyze it later. In this way, the voice recognition technology can be used to automatically convert the elderly person's dictation into text, improving the accuracy of acquiring memories and interests. Some or all of the above-mentioned processing in the acquisition unit can be performed using, for example, AI, or without AI. For example, the acquisition unit can input the elderly person's voice data into AI, which can convert the voice data into text to acquire memories and interests.

[0138] When generating conversation content, the generation unit can apply different generation algorithms based on the elderly person's past events and hobbies. For example, the generation AI can generate conversation content related to travel based on the elderly person's past travel experiences. The generation AI can also generate conversation content related to gardening based on the elderly person's gardening hobby. The generation AI can also generate conversation content related to family based on information about the elderly person's family. This makes it possible to generate more friendly conversation content based on the elderly person's past events and hobbies. Some or all of the above-described processing in the generation unit can be performed using, or without, the generation AI. For example, the generation unit can input data on the elderly person's past events and hobbies into the generation AI, and the generation AI can generate conversation content by applying different generation algorithms.

[0139] When providing the conversation content, the providing unit can optimize the timing of providing the conversation content by referring to the elderly person's past reactions. For example, the providing unit provides the conversation content at a timing when the elderly person has previously shown a favorable reaction. The providing unit can also provide the conversation content by avoiding a timing when the elderly person has previously felt stressed. The providing unit can also determine the optimal timing of providing the conversation content based on the elderly person's past reactions. In this way, the timing of providing the conversation content can be optimized by referring to the elderly person's past reactions. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input the elderly person's past reaction data into AI, which can analyze the data to optimize the timing of providing the conversation content.

[0140] When analyzing the content of a dialogue, the analysis unit can improve the accuracy of the analysis by referring to the elderly person's past reactions. For example, the analysis unit can improve the analysis accuracy of the dialogue content based on the elderly person's past reactions. The analysis unit can also adjust the analysis results by referring to emotions expressed by the elderly person in the past. The analysis unit can also analyze the elderly person's past reactions and improve the analysis method. In this way, the accuracy of the analysis can be improved by referring to the elderly person's past reactions. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input the elderly person's past reaction data into AI, which then analyzes the data to improve the accuracy of the analysis.

[0141] When performing monitoring, the monitoring unit can improve the accuracy of the monitoring by referring to the elderly person's past dialogue history. For example, the monitoring unit improves the accuracy of the monitoring based on the elderly person's past dialogue history. The monitoring unit can also adjust the monitoring results by referring to the elderly person's past responses. The monitoring unit can also analyze the elderly person's past dialogue history and improve the monitoring method. In this way, the accuracy of monitoring can be improved by referring to the elderly person's past dialogue history. Some or all of the above-mentioned processing in the monitoring unit may be performed using, for example, AI, or may be performed without using AI. For example, the monitoring unit can input the elderly person's past dialogue history data into AI, which analyzes the data to improve the accuracy of the monitoring.

[0142] The acquisition unit can estimate the elderly person's emotions and adjust the timing of acquiring memories and interests based on the estimated emotions. For example, the acquisition unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The acquisition unit can also evaluate the elderly person's emotions using self-reports. For example, the acquisition unit performs analysis based on the elderly person's self-reported emotional state. Next, the acquisition unit adjusts the timing of acquiring memories and interests based on the estimated emotions of the elderly person. For example, if the elderly person is relaxed, the timing of acquiring past memories and interests can be increased. If the elderly person is stressed, the timing of acquiring memories and interests can be reduced, allowing more time for relaxation. If the elderly person is excited, topics of interest can be preferentially acquired to promote dialogue. This makes it possible to adjust the timing of acquiring memories and interests according to the elderly person's emotional state. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the acquisition unit can be performed using, for example, AI or without AI. For example, the acquisition unit can input the elderly person's emotional data into the AI, which can then analyze the emotional state and adjust the timing of acquiring memories and interests.

[0143] The generation unit can estimate the elderly person's emotions and adjust the way the conversation content is expressed based on the estimated elderly person's emotions. For example, the generation unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The generation unit can also evaluate the elderly person's emotions using self-reports. For example, the generation unit performs analysis based on the elderly person's self-reported emotional state. Next, the generation unit adjusts the way the conversation content is expressed based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, the generation unit can generate the conversation content in a calm tone. If the elderly person is stressed, the generation unit can generate the conversation content in a gentle tone. If the elderly person is excited, the generation unit can generate the conversation content in a lively tone. This allows the conversation content to be provided in an expression method that corresponds to the elderly person's emotional state. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the generation unit can input emotional data of an elderly person into the generation AI, which can then analyze the emotional state and adjust the way the conversation content is expressed.

[0144] The providing unit can estimate the elderly person's emotions and adjust the method of providing the conversation content based on the estimated elderly person's emotions. For example, the providing unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The providing unit can also evaluate the elderly person's emotions using self-reports. For example, the providing unit performs analysis based on the elderly person's self-reported emotional state. Next, the providing unit adjusts the method of providing the conversation content based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, the conversation content can be provided in a calm tone. If the elderly person is stressed, the conversation content can be provided in a gentle tone. If the elderly person is excited, the conversation content can be provided in a lively tone. This allows the conversation content to be provided in a manner appropriate to the elderly person's emotional state. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the providing unit can be performed, for example, using AI or without AI. For example, the provision department can input the elderly person's emotional data into the AI, which can then analyze the emotional state and adjust the provision method.

[0145] The analysis unit can estimate the elderly person's emotions and adjust the dialogue analysis method based on the estimated elderly person's emotions. For example, the analysis unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The analysis unit can also evaluate the elderly person's emotions using self-reports. For example, the analysis unit performs analysis based on the elderly person's self-reported emotional state. Next, the analysis unit adjusts the dialogue analysis method based on the elderly person's estimated emotions. For example, if the elderly person is relaxed, a detailed analysis can be performed. If the elderly person is stressed, a simple analysis can be performed. If the elderly person is excited, an analysis focusing on a specific emotion can be performed. This allows the dialogue content to be analyzed using an analysis method appropriate for the elderly person's emotional state. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the elderly person's emotional data into the AI, which can then analyze their emotional state and adjust how it analyzes the dialogue.

[0146] The monitoring unit can estimate the elderly person's emotions and adjust the monitoring method based on the estimated elderly person's emotions. For example, the monitoring unit estimates the elderly person's emotions using facial expression analysis or voice analysis. The monitoring unit can also evaluate the elderly person's emotions using self-reports. For example, the monitoring unit performs analysis based on the elderly person's self-reported emotional state. Next, the monitoring unit adjusts the monitoring method based on the elderly person's estimated emotions. For example, if the elderly person is relaxed, detailed monitoring can be performed. If the elderly person is stressed, simple monitoring can be performed. If the elderly person is excited, monitoring can be performed focusing on a specific emotion. This allows monitoring to be performed in a manner appropriate to the elderly person's emotional state. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the monitoring unit can be performed using, for example, AI, or without AI. For example, the monitoring unit can input the elderly person's emotional data into the AI, which can then analyze their emotional state and adjust the monitoring method.

[0147] The processing flow of the second embodiment will be briefly explained below.

[0148] Step 1: The acquisition unit acquires the elderly person's past memories and interests. For example, information is collected from family members and caregivers, through analysis of past photos and videos, and through interviews and questionnaires. Step 2: The generation unit generates conversation content based on the information acquired by the acquisition unit. Using generation AI, conversation content is generated based on the elderly person's past events, hobbies, and family information. Friendly conversation content is generated using text generation AI (e.g., LLM) and multimodal generation AI. Step 3: The providing unit provides the conversation content generated by the generating unit to the elderly person and engages in a dialogue. The conversation content is provided through voice or text, and the conversation content is provided in a format appropriate for the elderly person using voice synthesis technology or a text display method. Step 4: The analysis unit analyzes the content of the dialogue conducted by the provision unit and provides appropriate feedback. The analysis unit analyzes the elderly person's reactions in real time during the dialogue and provides appropriate feedback. Step 5: The emotion analysis unit analyzes the emotional state of the elderly person based on the information analyzed by the analysis unit, and proceeds with the conversation in an appropriate tone and content.The emotional state of the elderly person is analyzed using facial expression analysis and voice analysis, and proceeds with the conversation in an appropriate tone and content. Step 6: The monitoring unit allows doctors and nurses to monitor the dialogue carried out by the provider and intervene as necessary. The dialogue carried out by the generating AI is monitored in real time, and doctors and nurses can intervene as necessary.

[0149] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0150] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0152] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0153] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0154] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0155] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0156] 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.

[0157] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0158] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0159] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0160] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0161] 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.

[0162] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0163] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0164] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0165] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0166] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0167] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0168] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0169] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0170] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0171] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0172] 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.

[0173] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0174] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0175] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0176] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset 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.

[0177] 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.

[0178] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0179] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0180] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0181] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0182] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0183] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0184] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0185] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0186] 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.

[0187] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0188] 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.

[0189] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0190] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0191] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0192] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0193] 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.

[0194] 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.

[0195] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0196] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0197] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0198] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0199] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0200] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0201] The correspondence between each part and the device or control part is not limited to the above example, and various modifications are possible.

[0202] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0203] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0204] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0205] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0206] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0207] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0208] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0209] 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.

[0210] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0211] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0212] 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.

[0213] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0214] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0215] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0216] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0217] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0218] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0219] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0220] [Explanation of symbols]

[0221] 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 the past memories and interests of the elderly; a generation unit that generates conversation content based on the information acquired by the acquisition unit; a providing unit that provides the conversation content generated by the generating unit to the elderly person and engages in a dialogue; an analysis unit that analyzes the content of the dialogue performed by the provision unit and provides appropriate feedback; an emotion analysis unit that analyzes the emotional state of the elderly person based on the information analyzed by the analysis unit and advances the conversation with an appropriate tone and content; a monitoring unit that allows a doctor or nurse to monitor the content of the dialogue carried out by the providing unit and intervene as necessary; Equipped with A system characterized by:

2. The acquisition unit Analyze information provided by family and caregivers, as well as past photos and videos 2. The system of claim 1.

3. The generation unit Generate conversation content based on the elderly person's past events, hobbies, and family information 2. The system of claim 1.

4. The providing unit Providing conversational content to seniors through voice and text 2. The system of claim 1.

5. The analysis unit Analyzes the elderly person's reactions in real time during the conversation and provides appropriate feedback 2. The system of claim 1.

6. The emotion analysis unit Analyzing the emotional state of the elderly and conducting conversations with appropriate tone and content 2. The system of claim 1.

7. The monitoring unit Doctors and nurses can monitor the content of the generated AI's dialogue and intervene as necessary.

2. The system of claim 1.

8. The acquisition unit Estimate the emotions of the elderly and adjust the timing of memory and interest acquisition based on the estimated emotions of the elderly.

2. The system of claim 1.

Images