System

Abstract

An object of a system according to an embodiment is to propose an appropriate countermeasure when there is a suspicion of cognitive decline or Alzheimer's disease.SOLUTION: A system according to an embodiment includes a generation AI, a conversation analysis unit, a suggestion unit, and a share unit. The generated AI interacts with the user. The conversation analysis unit analyzes the conversation content generated by the generation AI. The suggestion unit suggests a BRAIN AGE: Train Your Brain in Minutes a Day!, a quiz, or an appropriate physical exercise when cognitive decline or Alzheimer's disease is suspected on the basis of a result of the analysis by the conversation analysis unit. The sharing unit aggregates a history of conversation contents as a summary or an analysis result, and shares the history with a specific person.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 had the problem of making it difficult to quickly suggest appropriate measures when cognitive decline or Alzheimer's disease is suspected.

[0005] The system according to the embodiment aims to propose appropriate measures when cognitive decline or Alzheimer's disease is suspected. [Means for solving the problem]

[0006] The system according to the embodiment includes a generation AI, a conversation analysis unit, a suggestion unit, and a sharing unit. The generation AI interacts with the user. The conversation analysis unit analyzes the conversation content generated by the generation AI. Based on the analysis results by the conversation analysis unit, the suggestion unit suggests brain training, quizzes, or appropriate physical exercises if cognitive decline or Alzheimer's disease is suspected. The sharing unit compiles the conversation content history as a summary or analysis result and shares it with specific people. [Effects of the Invention]

[0007] The system according to the embodiment can propose appropriate measures when cognitive decline or Alzheimer's disease is suspected. [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) In a dementia prevention system according to an embodiment of the present invention, a generative AI converses with a user, analyzes the content of the conversation, and if cognitive decline or Alzheimer's is suspected, suggests brain training, quizzes, and appropriate physical exercises, and compiles the conversation history as a summary or analysis result, which is shared with specific people. This allows the dementia prevention system to prevent the user's cognitive decline and enable family members and medical professionals to provide appropriate support.

[0029] A dementia prevention system according to an embodiment includes a generation AI, a conversation analysis unit, a suggestion unit, and a sharing unit. The generation AI interacts with a user. For example, the generation AI may use a smartphone or other device to facilitate a conversation. The generation AI may ask questions such as, "What did you do today?" or "What do you think about the recent news?" to which the user responds. The conversation analysis unit analyzes the conversation content generated by the generation AI. For example, the conversation analysis unit analyzes conversational characteristics associated with Alzheimer's disease to measure the user's cognitive function. The conversation analysis unit analyzes characteristics such as repetition of the same story, increased use of "this," "that," and "that," ambiguity about time and place, and content jumps. Based on the analysis results by the conversation analysis unit, the suggestion unit suggests brain training, quizzes, or appropriate physical exercises if cognitive function decline or Alzheimer's disease is suspected. For example, the suggestion unit provides tasks such as memory training, problem-solving exercises, and attention improvement. The suggestion unit adjusts the difficulty of the tasks according to the user's progress. The sharing unit compiles the conversation history as a summary or analysis result and shares it with specific people. For example, the sharing unit provides information to specific people such as family members, nurses, and home helpers. This allows the dementia prevention system according to the embodiment to prevent a decline in the user's cognitive function and enable family members and medical professionals to provide appropriate support.

[0030] The generation AI can refer to the conversation history and generate questions based on individual interests and concerns. For example, the generation AI analyzes the user's past conversation history and generates questions based on topics that interest the user. For example, it asks questions about hobbies or travel destinations that the user has previously talked about. The generation AI also generates questions that will attract the user's attention based on the user's past conversation history. For example, it asks questions about the user's favorite movies or music. The generation AI also refers to the user's past conversation history and generates questions related to topics that interest the user. For example, it asks questions about cooking or sports that the user has previously talked about. This makes it possible to achieve more effective dialogue by generating questions based on the user's interests and concerns.

[0031] The generation AI can present visual content based on the user's hobbies and interests during a conversation. For example, the generation AI presents images and videos based on the user's hobbies and interests during a conversation. For example, if the user is interested in traveling, it will display images of beautiful scenery and tourist spots from travel destinations. The generation AI also presents related visual content during a conversation based on the user's interests. For example, if the user is interested in cooking, it will display videos showing cooking recipes and cooking methods. The generation AI also presents visual content based on the user's hobbies and interests during a conversation to liven up the conversation. For example, if the user is interested in sports, it will display sports highlights and videos of interviews with players. This makes it possible to enrich conversations by presenting visual content based on the user's hobbies and interests.

[0032] The generation AI can refer to past conversations with family and friends and provide common topics. The generation AI can, for example, analyze past conversations with the user's family and friends and provide common topics. For example, it can provide topics about travel memories the user talked about with family or hobbies shared with friends. The generation AI can also provide common topics based on past conversations with the user's family and friends. For example, it can provide topics about events the user talked about with family or experiences shared with friends. The generation AI can also refer to past conversations with the user's family and friends and provide common topics. For example, it can provide topics about how the user spent their holidays with family or hobbies shared with friends. This allows for more intimate conversations by providing common topics with the user's family and friends.

[0033] Generative AI can track conversation patterns over the long term and analyze changes in cognitive function in detail. For example, generative AI can track a user's conversation patterns over the long term and analyze changes in cognitive function in detail. For example, it can analyze the fluency of the user's conversation and the frequency of vocabulary use. Generative AI can also track a user's conversation patterns over the long term and analyze changes in cognitive function in detail. For example, it can analyze the consistency of the user's conversation and the frequency of topic changes. Generative AI can also track a user's conversation patterns over the long term and analyze changes in cognitive function in detail. For example, it can analyze the content of the user's conversation and the diversity of expressions. This allows for a detailed analysis of changes in the user's cognitive function, making it possible to take more effective measures.

[0034] The generative AI can analyze non-verbal communication and perform a comprehensive cognitive function evaluation. The generative AI, for example, analyzes the user's facial expressions and performs a comprehensive cognitive function evaluation. For example, it analyzes the user's smiling or surprised expressions and evaluates changes in emotions. The generative AI also analyzes the user's gestures and performs a comprehensive cognitive function evaluation. For example, it analyzes the user's hand movements and posture and evaluates non-verbal communication. The generative AI also analyzes the user's non-verbal communication and performs a comprehensive cognitive function evaluation. For example, it analyzes the user's gaze and body movements and evaluates the state of cognitive function. In this way, analyzing the user's non-verbal communication makes it possible to perform a more comprehensive cognitive function evaluation.

[0035] The generating AI can collect lifestyle data and analyze its correlation with cognitive function. For example, the generating AI collects the user's sleep data and analyzes its correlation with cognitive function. For example, it analyzes sleep time and sleep quality to evaluate the state of cognitive function. The generating AI also collects the user's dietary data and analyzes its correlation with cognitive function. For example, it analyzes the content and nutritional balance of meals to evaluate the state of cognitive function. The generating AI also collects the user's exercise data and analyzes its correlation with cognitive function. For example, it analyzes the frequency and intensity of exercise to evaluate the state of cognitive function. In this way, by collecting the user's lifestyle data and analyzing its correlation with cognitive function, more effective measures can be taken.

[0036] Generative AI can analyze social interaction data to help evaluate cognitive function. Generative AI can, for example, analyze a user's social media data to help evaluate cognitive function. For example, it can analyze the frequency and content of posts to evaluate the state of the user's social interactions. Generative AI can also analyze a user's email data to help evaluate cognitive function. For example, it can analyze the frequency and content of emails sent and received to evaluate the state of the user's social interactions. Generative AI can also analyze a user's social interaction data to help evaluate cognitive function. For example, it can analyze the content and frequency of social media and email exchanges to evaluate the state of the user's social interactions. In this way, analyzing a user's social interaction data can be useful in evaluating cognitive function.

[0037] The generation AI can provide an individually optimized practice program based on past cognitive practice data. The generation AI, for example, analyzes the user's past cognitive practice data and provides an individually optimized practice program. For example, it adjusts the practice content based on the user's strengths and weaknesses. The generation AI also provides an individually optimized practice program based on the user's past cognitive practice data. For example, it adjusts the practice content based on the user's progress and reaction speed. The generation AI also analyzes the user's past cognitive practice data and provides an individually optimized practice program. For example, it adjusts the practice content based on the user's accuracy rate and reaction time. In this way, by providing an individually optimized practice program based on the user's past cognitive practice data, more effective cognitive practice is possible.

[0038] The generation AI can analyze the reaction speed and accuracy rate during cognitive practice in real time and provide instantaneous feedback. For example, the generation AI can analyze the user's reaction speed during cognitive practice in real time and provide instantaneous feedback. For example, it can evaluate how quickly the user responded to a problem and adjust the next task. The generation AI can also analyze the user's accuracy rate during cognitive practice in real time and provide instantaneous feedback. For example, it can adjust the difficulty of the next task based on the percentage of problems the user answered correctly. The generation AI can also analyze the user's reaction speed and accuracy rate during cognitive practice in real time and provide instantaneous feedback. For example, it can evaluate how quickly the user answered a problem correctly and adjust the next task. In this way, more effective cognitive practice is possible by analyzing the user's reaction speed and accuracy rate during cognitive practice in real time and providing instantaneous feedback.

[0039] The generative AI can gamify cognitive practice, allowing users to practice while having fun. For example, the generative AI gamifies the user's cognitive practice, allowing them to practice while having fun. For example, it provides puzzle games and quizzes to train memory. The generative AI can also gamify the user's cognitive practice, allowing them to practice while having fun. For example, it can provide adventure games to train problem-solving skills. The generative AI can also gamify the user's cognitive practice, allowing them to practice while having fun. For example, it can provide reflex games to train attention. This allows users to practice cognitively while having fun, allowing for more effective practice.

[0040] The generative AI can make cognitive practice competitive with other users, increasing motivation. For example, the generative AI can make a user's cognitive practice competitive with other users, increasing motivation. For example, it can provide a quiz game in which users compete against other users online. The generative AI can also make a user's cognitive practice competitive, increasing motivation. For example, it can provide a game in which a ranking system is introduced and users compete against each other for scores. The generative AI can also make a user's cognitive practice competitive with other users, increasing motivation. For example, it can provide a team-based cognitive training game. This allows users to practice cognitively in a competitive format with other users, increasing their motivation.

[0041] The generation AI can provide an individually optimized exercise program based on the user's exercise history. The generation AI, for example, analyzes the user's exercise history and provides an individually optimized exercise program. For example, it adjusts appropriate exercise intensity and frequency based on the user's past exercise data. The generation AI also provides an individually optimized exercise program based on the user's exercise history. For example, it adjusts the exercise content based on the user's exercise progress and physical fitness level. The generation AI also analyzes the user's exercise history and provides an individually optimized exercise program. For example, it adjusts the exercise program based on the user's exercise results and goals. This allows for more effective exercise by providing an individually optimized exercise program based on the user's exercise history.

[0042] Generative AI can analyze posture and movements during exercise in real time and provide guidance on correct form. For example, generative AI can analyze a user's posture during exercise in real time and provide guidance on correct form. For example, if a user's posture is poor, it will suggest appropriate corrections. Generative AI can also analyze a user's movements during exercise in real time and provide guidance on correct form. For example, if a user's movements are inappropriate, it will show the correct movements. Generative AI can also analyze a user's posture and movements during exercise in real time and provide guidance on correct form. For example, if a user's movements are ineffective, it will point out areas for improvement. This allows for more effective exercise by analyzing a user's posture and movements during exercise in real time and providing guidance on correct form.

[0043] The generation AI can support exercise with virtual reality (VR) to provide a realistic exercise experience. For example, the generation AI supports a user's exercise with virtual reality (VR) to provide a realistic exercise experience. For example, the user exercises in a virtual landscape. The generation AI also supports the user's exercise with VR to provide a realistic exercise experience. For example, the user trains in a virtual gym. The generation AI also supports the user's exercise with VR to provide a realistic exercise experience. For example, the user walks or runs in a virtual natural environment. This allows the user to have a realistic exercise experience, enabling more effective exercise.

[0044] The generating AI can provide a program for sharing exercises with other users and exercising together. The generating AI, for example, provides a program for sharing a user's exercises with other users and exercising together. For example, exercising together with other users online. The generating AI also provides a program for sharing a user's exercises with other users and exercising together. For example, it provides a fitness program for groups. The generating AI also provides a program for sharing a user's exercises with other users and exercising together. For example, it provides stretching and training to be done in pairs. This allows users to exercise more effectively by exercising together with other users.

[0045] The generation AI can analyze a user's lifestyle rhythm and send reminders at the optimal timing. The generation AI can, for example, analyze a user's lifestyle rhythm and send reminders at the optimal timing. For example, it can send reminders to coincide with the user's wake-up time or meal times. The generation AI can also send reminders at the optimal timing based on the user's lifestyle rhythm. For example, it can send reminders during times when the user is relaxing. The generation AI can also analyze a user's lifestyle rhythm and send reminders at the optimal timing. For example, it can send reminders during times when the user exercises. This allows for more effective reminders by analyzing a user's lifestyle rhythm and sending reminders at the optimal timing.

[0046] The generating AI can analyze the progress data in detail and provide individually optimized feedback. The generating AI, for example, analyzes the user's progress data in detail and provides individually optimized feedback. For example, it suggests the next step based on the user's rehabilitation progress. The generating AI also provides individually optimized feedback based on the user's progress data. For example, it specifically indicates the user's exercise results and areas for improvement. The generating AI also analyzes the user's progress data in detail and provides individually optimized feedback. For example, it suggests the next task based on the user's progress in cognitive practice. This makes it possible to provide more effective feedback by analyzing the user's progress data in detail and providing individually optimized feedback.

[0047] The generation AI can visualize the progress data and provide it in an intuitively understandable format. For example, the generation AI can visualize the user's progress data and provide it in an intuitively understandable format. For example, it can display the rehabilitation progress using graphs and charts. The generation AI can also visualize the user's progress data and provide it in an intuitively understandable format. For example, it can create infographics showing the progress. The generation AI can also visualize the user's progress data and provide it in an intuitively understandable format. For example, it can create a dashboard showing the progress. This allows for more effective feedback by visualizing the user's progress data and providing it in an intuitively understandable format.

[0048] The generating AI can compare the progress with other users to increase a sense of competition. For example, the generating AI can compare the user's progress with other users to increase a sense of competition. For example, a ranking system can be introduced to compete with other users for scores. The generating AI can also compare the user's progress with other users to increase a sense of competition. For example, a leaderboard showing progress can be created. The generating AI can also compare the user's progress with other users to increase a sense of competition. For example, badges or trophies showing progress can be provided. This can increase a sense of competition by comparing the user's progress with other users.

[0049] The generating AI can provide an individually optimized rehabilitation program based on past data. The generating AI, for example, analyzes the user's past data and provides an individually optimized rehabilitation program. For example, it adjusts the rehabilitation content based on the user's strengths and weaknesses. The generating AI also provides an individually optimized rehabilitation program based on the user's past data. For example, it adjusts the rehabilitation content based on the user's progress and reaction speed. The generating AI also analyzes the user's past data and provides an individually optimized rehabilitation program. For example, it adjusts the rehabilitation content based on the user's accuracy rate and reaction time. This allows for more effective rehabilitation by providing an individually optimized rehabilitation program based on the user's past data.

[0050] The generation AI can analyze reactions in real time and instantly adjust the program. The generation AI, for example, analyzes the user's reactions in real time and instantly adjusts the program. For example, it adjusts the rehabilitation content based on the user's reaction speed and accuracy rate. The generation AI can also analyze the user's reactions in real time and instantly adjust the program. For example, it adjusts the rehabilitation content based on the user's emotional state and concentration. The generation AI can also analyze the user's reactions in real time and instantly adjust the program. For example, it adjusts the rehabilitation content based on the user's progress and reaction time. This allows for more effective rehabilitation by analyzing the user's reactions in real time and instantly adjusting the program.

[0051] Generative AI can support rehabilitation using virtual reality (VR) to provide a more immersive rehabilitation experience. For example, generative AI can support a user's rehabilitation using virtual reality (VR) to provide a more immersive rehabilitation experience. For example, the user performs rehabilitation in a virtual landscape. Generative AI can also support a user's rehabilitation using VR to provide a more immersive rehabilitation experience. For example, the user trains in a virtual gym. Generative AI can also support a user's rehabilitation using VR to provide a more immersive rehabilitation experience. For example, the user walks or runs in a virtual natural environment. This allows the user to have a more immersive rehabilitation experience, enabling more effective rehabilitation.

[0052] The generating AI can provide a program for sharing rehabilitation with other users and conducting rehabilitation collaboratively. The generating AI, for example, provides a program for sharing a user's rehabilitation with other users and conducting rehabilitation collaboratively. For example, rehabilitation is conducted online together with other users. The generating AI also provides a program for sharing a user's rehabilitation with other users and conducting rehabilitation collaboratively. For example, a group rehabilitation program is provided. The generating AI also provides a program for sharing a user's rehabilitation with other users and conducting rehabilitation collaboratively. For example, rehabilitation or training conducted in pairs is provided. This allows users to conduct rehabilitation collaboratively with other users, making rehabilitation more effective.

[0053] The generating AI can analyze the conversation history in detail and provide specific advice to family members and medical professionals. The generating AI, for example, analyzes the user's conversation history in detail and provides specific advice to family members and medical professionals. For example, it reports changes in the user's cognitive function and suggests appropriate responses. The generating AI also provides specific advice to family members and medical professionals based on the user's conversation history. For example, it reports the user's emotional state and stress level and suggests appropriate support. The generating AI also analyzes the user's conversation history in detail and provides specific advice to family members and medical professionals. For example, it reports the user's lifestyle habits and health condition and suggests an appropriate rehabilitation program. This enables more effective support by analyzing the user's conversation history in detail and providing specific advice to family members and medical professionals.

[0054] The generating AI can collect lifestyle data and evaluate the overall health condition. The generating AI, for example, collects a user's lifestyle data and evaluates the overall health condition. For example, it analyzes the user's sleep data and dietary data to evaluate the health condition. The generating AI also evaluates the overall health condition based on the user's lifestyle data. For example, it analyzes the user's exercise data and stress level to evaluate the health condition. The generating AI also collects a user's lifestyle data and evaluates the overall health condition. For example, it analyzes the user's drinking and smoking data to evaluate the health condition. In this way, by collecting the user's lifestyle data and evaluating the overall health condition, more effective support can be provided.

[0055] Generative AI can visualize data and provide it in a format that is intuitively understandable to family members and medical professionals. For example, generative AI can visualize a user's data and provide it in a format that is intuitively understandable to family members and medical professionals. For example, it can display health status using graphs and charts. Generative AI can also visualize a user's data and provide it in a format that is intuitively understandable to family members and medical professionals. For example, it can create infographics showing progress. Generative AI can also visualize a user's data and provide it in a format that is intuitively understandable to family members and medical professionals. For example, it can create a dashboard showing health status. This allows for more effective support by visualizing a user's data and providing it in a format that is intuitively understandable to family members and medical professionals.

[0056] The generating AI can compare the data with other patients to evaluate the effectiveness of treatment. For example, the generating AI may compare the user's data with other patients to evaluate the effectiveness of treatment. For example, it may compare it with the data of other patients receiving the same treatment. The generating AI may also compare the user's data with other patients to evaluate the effectiveness of treatment. For example, it may compare it with the data of other patients with the same symptoms. The generating AI may also compare the user's data with other patients to evaluate the effectiveness of treatment. For example, it may compare it with the data of other patients receiving the same rehabilitation program. This allows the user's data to be compared with other patients to evaluate the effectiveness of treatment, making more effective treatment possible.

[0057] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0058] The generative AI can present visual content based on the user's hobbies and interests during conversations. For example, if the user is interested in travel, it can display images of beautiful scenery and tourist spots from travel destinations. If the user is interested in cooking, it can display videos showing recipes and cooking methods. Furthermore, if the user is interested in sports, it can display sports highlights and videos of interviews with athletes. In this way, it is possible to enrich conversations by presenting visual content based on the user's hobbies and interests.

[0059] The generative AI can refer to past conversations with family and friends to provide common topics. For example, it can provide topics about travel memories the user shared with family or hobbies shared with friends. It can also provide topics about events the user talked about with family or experiences shared with friends. It can also provide topics about how the user spent their holidays with family or hobbies shared with friends. This allows for more intimate conversations by providing common topics with the user's family and friends.

[0060] Generative AI can track conversation patterns over the long term and perform detailed analysis of changes in cognitive function. For example, it analyzes the fluency of a user's conversation and the frequency of vocabulary use. It also analyzes the consistency of a user's conversation and the frequency of topic changes. It also analyzes the content of a user's conversation and the diversity of their expressions. This allows for a detailed analysis of changes in a user's cognitive function, enabling more effective countermeasures to be taken.

[0061] Generative AI can analyze non-verbal communication and perform a comprehensive cognitive function evaluation. For example, it can analyze the user's facial expressions and perform a comprehensive cognitive function evaluation. It can analyze the user's smiling or surprised expressions and evaluate changes in emotions. It can also analyze the user's gestures and perform a comprehensive cognitive function evaluation. It can analyze the user's hand movements and posture to evaluate non-verbal communication. It can also analyze the user's gaze and body movements to evaluate the state of cognitive function. This makes it possible to perform a more comprehensive cognitive function evaluation by analyzing the user's non-verbal communication.

[0062] Generative AI can collect lifestyle data and analyze its relationship to cognitive function. For example, it can collect a user's sleep data and analyze its relationship to cognitive function. It can analyze sleep duration and sleep quality to evaluate the state of cognitive function. It can also collect a user's dietary data and analyze its relationship to cognitive function. It can analyze the content and nutritional balance of meals to evaluate the state of cognitive function. It can also collect a user's exercise data and analyze its relationship to cognitive function. It can analyze the frequency and intensity of exercise to evaluate the state of cognitive function. In this way, by collecting a user's lifestyle data and analyzing its relationship to cognitive function, more effective measures can be taken.

[0063] Generative AI can analyze social interaction data and use it to evaluate cognitive function. For example, it can analyze a user's social media data to help evaluate cognitive function. It can analyze the frequency and content of posts to evaluate the state of the user's social interactions. It can also analyze a user's email data to help evaluate cognitive function. It can analyze the frequency and content of emails sent and received to evaluate the state of the user's social interactions. It can also analyze the content and frequency of the user's social media and email exchanges to evaluate the state of the user's social interactions. In this way, analyzing a user's social interaction data can be useful in evaluating cognitive function.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The generative AI interacts with the user. For example, the generative AI can use a smartphone or other device to facilitate a conversation with the user. The generative AI asks questions such as, "What did you do today?" or "What do you think about the recent news?", and the user responds. Step 2: The conversation analysis unit analyzes the conversation content generated by the generation AI. For example, the conversation analysis unit analyzes conversation characteristics seen in Alzheimer's disease and measures the user's cognitive function. The conversation analysis unit analyzes characteristics such as repetition of the same thing, increased use of "this," "that," and "this," ambiguity about time and place, and jumps in content. Step 3: Based on the results of the analysis by the conversation analysis unit, the suggestion unit suggests brain training, quizzes, or appropriate physical exercises if cognitive decline or Alzheimer's is suspected. For example, the suggestion unit may provide tasks such as memory training, problem-solving exercises, and attention improvement. The suggestion unit adjusts the difficulty of the tasks according to the user's progress. Step 4: The sharing unit compiles the conversation history into summaries and analysis results and shares them with specific people. For example, the sharing unit provides information to specific people such as family members, nurses, and home helpers.

[0066] (Example 2) In a dementia prevention system according to an embodiment of the present invention, a generative AI converses with a user, analyzes the content of the conversation, and if cognitive decline or Alzheimer's is suspected, suggests brain training, quizzes, and appropriate physical exercises, and compiles the conversation history as a summary or analysis result, which is shared with specific people. This allows the dementia prevention system to prevent the user's cognitive decline and enable family members and medical professionals to provide appropriate support.

[0067] A dementia prevention system according to an embodiment includes a generation AI, a conversation analysis unit, a suggestion unit, and a sharing unit. The generation AI interacts with a user. For example, the generation AI may use a smartphone or other device to facilitate a conversation. The generation AI may ask questions such as, "What did you do today?" or "What do you think about the recent news?" to which the user responds. The conversation analysis unit analyzes the conversation content generated by the generation AI. For example, the conversation analysis unit analyzes conversational characteristics associated with Alzheimer's disease to measure the user's cognitive function. The conversation analysis unit analyzes characteristics such as repetition of the same story, increased use of "this," "that," and "that," ambiguity about time and place, and content jumps. Based on the analysis results by the conversation analysis unit, the suggestion unit suggests brain training, quizzes, or appropriate physical exercises if cognitive function decline or Alzheimer's disease is suspected. For example, the suggestion unit provides tasks such as memory training, problem-solving exercises, and attention improvement. The suggestion unit adjusts the difficulty of the tasks according to the user's progress. The sharing unit compiles the conversation history as a summary or analysis result and shares it with specific people. For example, the sharing unit provides information to specific people such as family members, nurses, and home helpers. This allows the dementia prevention system according to the embodiment to prevent a decline in the user's cognitive function and enable family members and medical professionals to provide appropriate support.

[0068] The generation AI can refer to the conversation history and generate questions based on individual interests and concerns. For example, the generation AI analyzes the user's past conversation history and generates questions based on topics that interest the user. For example, it asks questions about hobbies or travel destinations that the user has previously talked about. The generation AI also generates questions that will attract the user's attention based on the user's past conversation history. For example, it asks questions about the user's favorite movies or music. The generation AI also refers to the user's past conversation history and generates questions related to topics that interest the user. For example, it asks questions about cooking or sports that the user has previously talked about. This makes it possible to achieve more effective dialogue by generating questions based on the user's interests and concerns.

[0069] The generation AI can analyze the tone of voice and speaking style to provide appropriate conversation according to the user's emotional state. For example, the generation AI can analyze the user's tone of voice in real time and provide light-hearted topics if the user is relaxed. For example, if the user speaks in a calm tone, it can ask questions about hobbies or daily events. The generation AI can also analyze the user's speaking style to provide conversation according to the user's emotional state. For example, if the user is excited, it can provide interesting topics or new information. The generation AI can also analyze the user's tone of voice and provide encouraging words or positive topics if the user is depressed. For example, if the user speaks in a sad tone, it can ask questions about happy memories or future plans. This allows for more effective dialogue by providing appropriate conversation according to the user's emotional state.

[0070] The generation AI can present visual content based on the user's hobbies and interests during a conversation. For example, the generation AI presents images and videos based on the user's hobbies and interests during a conversation. For example, if the user is interested in traveling, it will display images of beautiful scenery and tourist spots from travel destinations. The generation AI also presents related visual content during a conversation based on the user's interests. For example, if the user is interested in cooking, it will display videos showing cooking recipes and cooking methods. The generation AI also presents visual content based on the user's hobbies and interests during a conversation to liven up the conversation. For example, if the user is interested in sports, it will display sports highlights and videos of interviews with players. This makes it possible to enrich conversations by presenting visual content based on the user's hobbies and interests.

[0071] The generation AI can refer to past conversations with family and friends and provide common topics. The generation AI can, for example, analyze past conversations with the user's family and friends and provide common topics. For example, it can provide topics about travel memories the user talked about with family or hobbies shared with friends. The generation AI can also provide common topics based on past conversations with the user's family and friends. For example, it can provide topics about events the user talked about with family or experiences shared with friends. The generation AI can also refer to past conversations with the user's family and friends and provide common topics. For example, it can provide topics about how the user spent their holidays with family or hobbies shared with friends. This allows for more intimate conversations by providing common topics with the user's family and friends.

[0072] The generation AI can use its emotion estimation function to play environmental sounds or music that the user finds most relaxing during a conversation. For example, the generation AI uses its emotion estimation function to play environmental sounds that the user finds most relaxing during a conversation. For example, if the user is relaxed, natural sounds such as the sound of waves or birds chirping are played. The generation AI also analyzes the user's emotions in real time and plays relaxing music during a conversation. For example, if the user is relaxed, classical music or jazz is played. The generation AI also uses its emotion estimation function to play environmental sounds or music that the user finds most relaxing during a conversation. For example, if the user is relaxed, environmental sounds such as the sound of a babbling brook or the sound of the wind are played. This allows for more effective dialogue by playing environmental sounds or music that the user finds relaxing.

[0073] Generative AI can track conversation patterns over the long term and analyze changes in cognitive function in detail. For example, generative AI can track a user's conversation patterns over the long term and analyze changes in cognitive function in detail. For example, it can analyze the fluency of the user's conversation and the frequency of vocabulary use. Generative AI can also track a user's conversation patterns over the long term and analyze changes in cognitive function in detail. For example, it can analyze the consistency of the user's conversation and the frequency of topic changes. Generative AI can also track a user's conversation patterns over the long term and analyze changes in cognitive function in detail. For example, it can analyze the content of the user's conversation and the diversity of expressions. This allows for a detailed analysis of changes in the user's cognitive function, making it possible to take more effective measures.

[0074] The generative AI can analyze non-verbal communication and perform a comprehensive cognitive function evaluation. The generative AI, for example, analyzes the user's facial expressions and performs a comprehensive cognitive function evaluation. For example, it analyzes the user's smiling or surprised expressions and evaluates changes in emotions. The generative AI also analyzes the user's gestures and performs a comprehensive cognitive function evaluation. For example, it analyzes the user's hand movements and posture and evaluates non-verbal communication. The generative AI also analyzes the user's non-verbal communication and performs a comprehensive cognitive function evaluation. For example, it analyzes the user's gaze and body movements and evaluates the state of cognitive function. In this way, analyzing the user's non-verbal communication makes it possible to perform a more comprehensive cognitive function evaluation.

[0075] The generation AI can use the emotion estimation function to utilize emotional changes as an indicator of cognitive function. For example, the generation AI uses the emotion estimation function to utilize the user's emotional changes as an indicator of cognitive function. For example, it evaluates changes in cognitive function based on the user's emotion score. The generation AI also analyzes the user's emotional changes and uses them as an indicator of cognitive function. For example, it evaluates the stability and fluctuations of the user's emotions. The generation AI also uses the emotion estimation function to utilize the user's emotional changes as an indicator of cognitive function. For example, it evaluates the frequency of the user's positive and negative emotions. In this way, by utilizing the user's emotional changes as an indicator of cognitive function, more accurate cognitive function evaluation is possible.

[0076] The generating AI can collect lifestyle data and analyze its correlation with cognitive function. For example, the generating AI collects the user's sleep data and analyzes its correlation with cognitive function. For example, it analyzes sleep time and sleep quality to evaluate the state of cognitive function. The generating AI also collects the user's dietary data and analyzes its correlation with cognitive function. For example, it analyzes the content and nutritional balance of meals to evaluate the state of cognitive function. The generating AI also collects the user's exercise data and analyzes its correlation with cognitive function. For example, it analyzes the frequency and intensity of exercise to evaluate the state of cognitive function. In this way, by collecting the user's lifestyle data and analyzing its correlation with cognitive function, more effective measures can be taken.

[0077] Generative AI can analyze social interaction data to help evaluate cognitive function. Generative AI can, for example, analyze a user's social media data to help evaluate cognitive function. For example, it can analyze the frequency and content of posts to evaluate the state of the user's social interactions. Generative AI can also analyze a user's email data to help evaluate cognitive function. For example, it can analyze the frequency and content of emails sent and received to evaluate the state of the user's social interactions. Generative AI can also analyze a user's social interaction data to help evaluate cognitive function. For example, it can analyze the content and frequency of social media and email exchanges to evaluate the state of the user's social interactions. In this way, analyzing a user's social interaction data can be useful in evaluating cognitive function.

[0078] The generative AI can use the emotion estimation function to investigate the relationship between emotional state and cognitive function. For example, the generative AI uses the emotion estimation function to investigate the relationship between a user's emotional state and cognitive function. For example, it evaluates the state of cognitive function based on the user's emotion score. The generative AI also analyzes the user's emotional state and investigates the relationship between cognitive function. For example, it evaluates the stability and fluctuations of the user's emotions. The generative AI also uses the emotion estimation function to investigate the relationship between the user's emotional state and cognitive function. For example, it evaluates the frequency of the user's positive and negative emotions. This enables more accurate cognitive function evaluation by investigating the relationship between the user's emotional state and cognitive function.

[0079] The generation AI can provide an individually optimized practice program based on past cognitive practice data. The generation AI, for example, analyzes the user's past cognitive practice data and provides an individually optimized practice program. For example, it adjusts the practice content based on the user's strengths and weaknesses. The generation AI also provides an individually optimized practice program based on the user's past cognitive practice data. For example, it adjusts the practice content based on the user's progress and reaction speed. The generation AI also analyzes the user's past cognitive practice data and provides an individually optimized practice program. For example, it adjusts the practice content based on the user's accuracy rate and reaction time. In this way, by providing an individually optimized practice program based on the user's past cognitive practice data, more effective cognitive practice is possible.

[0080] The generation AI can analyze the reaction speed and accuracy rate during cognitive practice in real time and provide instantaneous feedback. For example, the generation AI can analyze the user's reaction speed during cognitive practice in real time and provide instantaneous feedback. For example, it can evaluate how quickly the user responded to a problem and adjust the next task. The generation AI can also analyze the user's accuracy rate during cognitive practice in real time and provide instantaneous feedback. For example, it can adjust the difficulty of the next task based on the percentage of problems the user answered correctly. The generation AI can also analyze the user's reaction speed and accuracy rate during cognitive practice in real time and provide instantaneous feedback. For example, it can evaluate how quickly the user answered a problem correctly and adjust the next task. In this way, more effective cognitive practice is possible by analyzing the user's reaction speed and accuracy rate during cognitive practice in real time and providing instantaneous feedback.

[0081] The generation AI can use the emotion estimation function to provide a practice program that helps the user maintain the most focused state. The generation AI, for example, uses the emotion estimation function to provide a practice program that helps the user maintain the most focused state. For example, it selects tasks that will increase concentration based on the user's emotion score. The generation AI also analyzes the user's emotional state in real time to provide a practice program that helps maintain concentration. For example, it selects tasks that the user can perform when they are relaxed. The generation AI also uses the emotion estimation function to provide a practice program that helps the user maintain the most focused state. For example, it provides tasks at times when the user's concentration is highest based on changes in the user's emotions. This allows for more effective cognitive practice by providing a practice program that helps the user maintain the most focused state.

[0082] The generative AI can gamify cognitive practice, allowing users to practice while having fun. For example, the generative AI gamifies the user's cognitive practice, allowing them to practice while having fun. For example, it provides puzzle games and quizzes to train memory. The generative AI can also gamify the user's cognitive practice, allowing them to practice while having fun. For example, it can provide adventure games to train problem-solving skills. The generative AI can also gamify the user's cognitive practice, allowing them to practice while having fun. For example, it can provide reflex games to train attention. This allows users to practice cognitively while having fun, allowing for more effective practice.

[0083] The generative AI can make cognitive practice competitive with other users, increasing motivation. For example, the generative AI can make a user's cognitive practice competitive with other users, increasing motivation. For example, it can provide a quiz game in which users compete against other users online. The generative AI can also make a user's cognitive practice competitive, increasing motivation. For example, it can provide a game in which a ranking system is introduced and users compete against each other for scores. The generative AI can also make a user's cognitive practice competitive with other users, increasing motivation. For example, it can provide a team-based cognitive training game. This allows users to practice cognitively in a competitive format with other users, increasing their motivation.

[0084] The generation AI can use the emotion estimation function to provide a form of cognitive practice that is most enjoyable for the user. The generation AI, for example, uses the emotion estimation function to provide a form of cognitive practice that is most enjoyable for the user. For example, it selects tasks that will increase enjoyment based on the user's emotion score. The generation AI also analyzes the user's emotional state in real time to provide a form of cognitive practice that is enjoyable. For example, it selects tasks that the user can perform when they are relaxed. The generation AI also uses the emotion estimation function to provide a form of cognitive practice that is most enjoyable for the user. For example, it provides tasks at a time when enjoyment is highest based on changes in the user's emotions. This allows for more effective practice by providing a form of cognitive practice that the user enjoys most.

[0085] The generation AI can provide an individually optimized exercise program based on the user's exercise history. The generation AI, for example, analyzes the user's exercise history and provides an individually optimized exercise program. For example, it adjusts appropriate exercise intensity and frequency based on the user's past exercise data. The generation AI also provides an individually optimized exercise program based on the user's exercise history. For example, it adjusts the exercise content based on the user's exercise progress and physical fitness level. The generation AI also analyzes the user's exercise history and provides an individually optimized exercise program. For example, it adjusts the exercise program based on the user's exercise results and goals. This allows for more effective exercise by providing an individually optimized exercise program based on the user's exercise history.

[0086] Generative AI can analyze posture and movements during exercise in real time and provide guidance on correct form. For example, generative AI can analyze a user's posture during exercise in real time and provide guidance on correct form. For example, if a user's posture is poor, it will suggest appropriate corrections. Generative AI can also analyze a user's movements during exercise in real time and provide guidance on correct form. For example, if a user's movements are inappropriate, it will show the correct movements. Generative AI can also analyze a user's posture and movements during exercise in real time and provide guidance on correct form. For example, if a user's movements are ineffective, it will point out areas for improvement. This allows for more effective exercise by analyzing a user's posture and movements during exercise in real time and providing guidance on correct form.

[0087] The generation AI can use the emotion estimation function to provide the user with the most relaxing exercise environment. The generation AI, for example, uses the emotion estimation function to provide the user with the most relaxing exercise environment. For example, it plays relaxing music or environmental sounds based on the user's emotion score. The generation AI also analyzes the user's emotional state in real time to provide a relaxing exercise environment. For example, it selects exercises to perform when the user is relaxed. The generation AI also uses the emotion estimation function to provide the user with the most relaxing exercise environment. For example, it suggests exercises to perform at times when the user is most relaxed based on the user's emotional changes. This provides the user with the most relaxing exercise environment, enabling more effective exercise.

[0088] The generation AI can support exercise with virtual reality (VR) to provide a realistic exercise experience. For example, the generation AI supports a user's exercise with virtual reality (VR) to provide a realistic exercise experience. For example, the user exercises in a virtual landscape. The generation AI also supports the user's exercise with VR to provide a realistic exercise experience. For example, the user trains in a virtual gym. The generation AI also supports the user's exercise with VR to provide a realistic exercise experience. For example, the user walks or runs in a virtual natural environment. This allows the user to have a realistic exercise experience, enabling more effective exercise.

[0089] The generating AI can provide a program for sharing exercises with other users and exercising together. The generating AI, for example, provides a program for sharing a user's exercises with other users and exercising together. For example, exercising together with other users online. The generating AI also provides a program for sharing a user's exercises with other users and exercising together. For example, it provides a fitness program for groups. The generating AI also provides a program for sharing a user's exercises with other users and exercising together. For example, it provides stretching and training to be done in pairs. This allows users to exercise more effectively by exercising together with other users.

[0090] The generation AI can use the emotion estimation function to provide the user with an exercise program that is most enjoyable. The generation AI, for example, uses the emotion estimation function to provide the user with an exercise program that is most enjoyable. For example, it selects exercises that will increase enjoyment based on the user's emotion score. The generation AI also analyzes the user's emotional state in real time to provide an enjoyable exercise program. For example, it selects exercises that the user can do when they are relaxed. The generation AI also uses the emotion estimation function to provide the user with an exercise program that is most enjoyable. For example, it suggests exercises at times that will increase enjoyment based on the user's emotional changes. This allows for more effective exercise by providing the user with an exercise program that they can enjoy most.

[0091] The generation AI can analyze a user's lifestyle rhythm and send reminders at the optimal timing. The generation AI can, for example, analyze a user's lifestyle rhythm and send reminders at the optimal timing. For example, it can send reminders to coincide with the user's wake-up time or meal times. The generation AI can also send reminders at the optimal timing based on the user's lifestyle rhythm. For example, it can send reminders during times when the user is relaxing. The generation AI can also analyze a user's lifestyle rhythm and send reminders at the optimal timing. For example, it can send reminders during times when the user exercises. This allows for more effective reminders by analyzing a user's lifestyle rhythm and sending reminders at the optimal timing.

[0092] The generating AI can analyze the progress data in detail and provide individually optimized feedback. The generating AI, for example, analyzes the user's progress data in detail and provides individually optimized feedback. For example, it suggests the next step based on the user's rehabilitation progress. The generating AI also provides individually optimized feedback based on the user's progress data. For example, it specifically indicates the user's exercise results and areas for improvement. The generating AI also analyzes the user's progress data in detail and provides individually optimized feedback. For example, it suggests the next task based on the user's progress in cognitive practice. This makes it possible to provide more effective feedback by analyzing the user's progress data in detail and providing individually optimized feedback.

[0093] The generation AI can use the emotion estimation function to provide a reminder format that most motivates the user. For example, the generation AI uses the emotion estimation function to provide a reminder format that most motivates the user. For example, it sends an encouraging message based on the user's emotion score. The generation AI also analyzes the user's emotional state in real time to provide a reminder format that increases motivation. For example, it sends a reminder when the user is relaxed. The generation AI also uses the emotion estimation function to provide a reminder format that most motivates the user. For example, it sends a positive message based on the user's emotional changes. This allows for more effective reminders by providing a reminder format that most motivates the user.

[0094] The generation AI can visualize the progress data and provide it in an intuitively understandable format. For example, the generation AI can visualize the user's progress data and provide it in an intuitively understandable format. For example, it can display the rehabilitation progress using graphs and charts. The generation AI can also visualize the user's progress data and provide it in an intuitively understandable format. For example, it can create infographics showing the progress. The generation AI can also visualize the user's progress data and provide it in an intuitively understandable format. For example, it can create a dashboard showing the progress. This allows for more effective feedback by visualizing the user's progress data and providing it in an intuitively understandable format.

[0095] The generating AI can compare the progress with other users to increase a sense of competition. For example, the generating AI can compare the user's progress with other users to increase a sense of competition. For example, a ranking system can be introduced to compete with other users for scores. The generating AI can also compare the user's progress with other users to increase a sense of competition. For example, a leaderboard showing progress can be created. The generating AI can also compare the user's progress with other users to increase a sense of competition. For example, badges or trophies showing progress can be provided. This can increase a sense of competition by comparing the user's progress with other users.

[0096] The generation AI can use the emotion estimation function to provide a progress tracking format that gives the user the most sense of accomplishment. The generation AI, for example, uses the emotion estimation function to provide a progress tracking format that gives the user the most sense of accomplishment. For example, it sends a message that enhances the sense of accomplishment based on the user's emotion score. The generation AI also analyzes the user's emotional state in real time to provide a progress tracking format that enhances the sense of accomplishment. For example, it displays the progress status when the user is relaxed. The generation AI also uses the emotion estimation function to provide a progress tracking format that gives the user the most sense of accomplishment. For example, it sends positive feedback based on the user's emotional changes. This enables more effective feedback by providing a progress tracking format that gives the user the most sense of accomplishment.

[0097] The generating AI can provide an individually optimized rehabilitation program based on past data. The generating AI, for example, analyzes the user's past data and provides an individually optimized rehabilitation program. For example, it adjusts the rehabilitation content based on the user's strengths and weaknesses. The generating AI also provides an individually optimized rehabilitation program based on the user's past data. For example, it adjusts the rehabilitation content based on the user's progress and reaction speed. The generating AI also analyzes the user's past data and provides an individually optimized rehabilitation program. For example, it adjusts the rehabilitation content based on the user's accuracy rate and reaction time. This allows for more effective rehabilitation by providing an individually optimized rehabilitation program based on the user's past data.

[0098] The generation AI can analyze reactions in real time and instantly adjust the program. The generation AI, for example, analyzes the user's reactions in real time and instantly adjusts the program. For example, it adjusts the rehabilitation content based on the user's reaction speed and accuracy rate. The generation AI can also analyze the user's reactions in real time and instantly adjust the program. For example, it adjusts the rehabilitation content based on the user's emotional state and concentration. The generation AI can also analyze the user's reactions in real time and instantly adjust the program. For example, it adjusts the rehabilitation content based on the user's progress and reaction time. This allows for more effective rehabilitation by analyzing the user's reactions in real time and instantly adjusting the program.

[0099] The generation AI can use the emotion estimation function to provide a rehabilitation environment in which the user can be most relaxed. The generation AI can use the emotion estimation function to provide a rehabilitation environment in which the user can be most relaxed. For example, it can play relaxing music or environmental sounds based on the user's emotion score. The generation AI can also analyze the user's emotional state in real time to provide a relaxing rehabilitation environment. For example, it can select rehabilitation to be performed when the user is relaxed. The generation AI can also use the emotion estimation function to provide a rehabilitation environment in which the user can be most relaxed. For example, it can suggest rehabilitation at a time when the user can be most relaxed based on changes in the user's emotions. This allows for more effective rehabilitation by providing a rehabilitation environment in which the user can be most relaxed.

[0100] Generative AI can support rehabilitation using virtual reality (VR) to provide a more immersive rehabilitation experience. For example, generative AI can support a user's rehabilitation using virtual reality (VR) to provide a more immersive rehabilitation experience. For example, the user performs rehabilitation in a virtual landscape. Generative AI can also support a user's rehabilitation using VR to provide a more immersive rehabilitation experience. For example, the user trains in a virtual gym. Generative AI can also support a user's rehabilitation using VR to provide a more immersive rehabilitation experience. For example, the user walks or runs in a virtual natural environment. This allows the user to have a more immersive rehabilitation experience, enabling more effective rehabilitation.

[0101] The generating AI can provide a program for sharing rehabilitation with other users and conducting rehabilitation collaboratively. The generating AI, for example, provides a program for sharing a user's rehabilitation with other users and conducting rehabilitation collaboratively. For example, rehabilitation is conducted online together with other users. The generating AI also provides a program for sharing a user's rehabilitation with other users and conducting rehabilitation collaboratively. For example, a group rehabilitation program is provided. The generating AI also provides a program for sharing a user's rehabilitation with other users and conducting rehabilitation collaboratively. For example, rehabilitation or training conducted in pairs is provided. This allows users to conduct rehabilitation collaboratively with other users, making rehabilitation more effective.

[0102] The generation AI can use the emotion estimation function to provide a rehabilitation program that the user will find most enjoyable. The generation AI, for example, uses the emotion estimation function to provide a rehabilitation program that the user will find most enjoyable. For example, it selects rehabilitation that will increase enjoyment based on the user's emotion score. The generation AI also analyzes the user's emotional state in real time to provide an enjoyable rehabilitation program. For example, it selects rehabilitation that will be performed when the user is relaxed. The generation AI also uses the emotion estimation function to provide a rehabilitation program that the user will find most enjoyable. For example, it suggests rehabilitation at a time when enjoyment will be highest based on the user's emotional changes. This allows for more effective rehabilitation by providing a rehabilitation program that the user will find most enjoyable.

[0103] The generating AI can analyze the conversation history in detail and provide specific advice to family members and medical professionals. The generating AI, for example, analyzes the user's conversation history in detail and provides specific advice to family members and medical professionals. For example, it reports changes in the user's cognitive function and suggests appropriate responses. The generating AI also provides specific advice to family members and medical professionals based on the user's conversation history. For example, it reports the user's emotional state and stress level and suggests appropriate support. The generating AI also analyzes the user's conversation history in detail and provides specific advice to family members and medical professionals. For example, it reports the user's lifestyle habits and health condition and suggests an appropriate rehabilitation program. This enables more effective support by analyzing the user's conversation history in detail and providing specific advice to family members and medical professionals.

[0104] The generating AI can collect lifestyle data and evaluate the overall health condition. The generating AI, for example, collects a user's lifestyle data and evaluates the overall health condition. For example, it analyzes the user's sleep data and dietary data to evaluate the health condition. The generating AI also evaluates the overall health condition based on the user's lifestyle data. For example, it analyzes the user's exercise data and stress level to evaluate the health condition. The generating AI also collects a user's lifestyle data and evaluates the overall health condition. For example, it analyzes the user's drinking and smoking data to evaluate the health condition. In this way, by collecting the user's lifestyle data and evaluating the overall health condition, more effective support can be provided.

[0105] The generation AI can use the emotion estimation function to notify family members and medical professionals of the user's emotional state in real time. For example, the generation AI uses the emotion estimation function to notify family members and medical professionals of the user's emotional state in real time. For example, if the user is feeling stressed, the generation AI notifies the family. The generation AI also analyzes the user's emotional state in real time and notifies the family members and medical professionals. For example, if the user is relaxed, the generation AI notifies the family. The generation AI also uses the emotion estimation function to notify family members and medical professionals of the user's emotional state in real time. For example, if the user is sad, the generation AI notifies the medical professionals. This enables more effective support by notifying family members and medical professionals of the user's emotional state in real time.

[0106] Generative AI can visualize data and provide it in a format that is intuitively understandable to family members and medical professionals. For example, generative AI can visualize a user's data and provide it in a format that is intuitively understandable to family members and medical professionals. For example, it can display health status using graphs and charts. Generative AI can also visualize a user's data and provide it in a format that is intuitively understandable to family members and medical professionals. For example, it can create infographics showing progress. Generative AI can also visualize a user's data and provide it in a format that is intuitively understandable to family members and medical professionals. For example, it can create a dashboard showing health status. This allows for more effective support by visualizing a user's data and providing it in a format that is intuitively understandable to family members and medical professionals.

[0107] The generating AI can compare the data with other patients to evaluate the effectiveness of treatment. For example, the generating AI may compare the user's data with other patients to evaluate the effectiveness of treatment. For example, it may compare it with the data of other patients receiving the same treatment. The generating AI may also compare the user's data with other patients to evaluate the effectiveness of treatment. For example, it may compare it with the data of other patients with the same symptoms. The generating AI may also compare the user's data with other patients to evaluate the effectiveness of treatment. For example, it may compare it with the data of other patients receiving the same rehabilitation program. This allows the user's data to be compared with other patients to evaluate the effectiveness of treatment, making more effective treatment possible.

[0108] The generation AI can use the emotion estimation function to provide family members and medical professionals with support plans based on the user's emotional state. For example, the generation AI uses the emotion estimation function to provide family members and medical professionals with support plans based on the user's emotional state. For example, if the user is feeling stressed, the generation AI can suggest activities that will help them relax. The generation AI can also analyze the user's emotional state in real time and provide support plans to family members and medical professionals. For example, if the user is relaxed, the generation AI can suggest appropriate rehabilitation. The generation AI can also use the emotion estimation function to provide family members and medical professionals with support plans based on the user's emotional state. For example, if the user is sad, the generation AI can suggest activities that will help them change their mood. This allows for more effective support by providing family members and medical professionals with support plans based on the user's emotional state.

[0109] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0110] The generative AI can analyze the user's tone of voice and speaking style to provide appropriate conversation according to their emotional state. For example, by analyzing the user's tone of voice in real time, if the user is relaxed, it can provide light-hearted topics. If the user is speaking in a calm tone, it can ask questions about hobbies and daily events. The generative AI can also analyze the user's speaking style to provide conversation according to the user's emotional state. If the user is excited, it can provide interesting topics and new information. Furthermore, the generative AI can analyze the user's tone of voice and, if the user is depressed, it can provide encouraging words and positive topics. If the user is speaking in a sad tone, it can ask questions about happy memories and future plans. This allows for more effective dialogue by providing appropriate conversation according to the user's emotional state.

[0111] The generative AI can present visual content based on the user's hobbies and interests during conversations. For example, if the user is interested in travel, it can display images of beautiful scenery and tourist spots from travel destinations. If the user is interested in cooking, it can display videos showing recipes and cooking methods. Furthermore, if the user is interested in sports, it can display sports highlights and videos of interviews with athletes. In this way, it is possible to enrich conversations by presenting visual content based on the user's hobbies and interests.

[0112] The generative AI can refer to past conversations with family and friends to provide common topics. For example, it can provide topics about travel memories the user shared with family or hobbies shared with friends. It can also provide topics about events the user talked about with family or experiences shared with friends. It can also provide topics about how the user spent their holidays with family or hobbies shared with friends. This allows for more intimate conversations by providing common topics with the user's family and friends.

[0113] Using its emotion estimation function, the generation AI can play environmental sounds or music that the user finds most relaxing during a conversation. For example, if the user is relaxed, natural sounds such as the sound of waves or birds chirping will be played. The system also analyzes the user's emotions in real time and plays relaxing music during the conversation. If the user is relaxed, classical music or jazz will be played. Furthermore, if the user is relaxed, environmental sounds such as the sound of a babbling brook or the sound of the wind will be played. This allows for more effective conversations by playing environmental sounds and music that the user finds relaxing.

[0114] Generative AI can track conversation patterns over the long term and perform detailed analysis of changes in cognitive function. For example, it analyzes the fluency of a user's conversation and the frequency of vocabulary use. It also analyzes the consistency of a user's conversation and the frequency of topic changes. It also analyzes the content of a user's conversation and the diversity of their expressions. This allows for a detailed analysis of changes in a user's cognitive function, enabling more effective countermeasures to be taken.

[0115] Generative AI can analyze non-verbal communication and perform a comprehensive cognitive function evaluation. For example, it can analyze the user's facial expressions and perform a comprehensive cognitive function evaluation. It can analyze the user's smiling or surprised expressions and evaluate changes in emotions. It can also analyze the user's gestures and perform a comprehensive cognitive function evaluation. It can analyze the user's hand movements and posture to evaluate non-verbal communication. It can also analyze the user's gaze and body movements to evaluate the state of cognitive function. This makes it possible to perform a more comprehensive cognitive function evaluation by analyzing the user's non-verbal communication.

[0116] Using its emotion estimation function, generative AI can use emotional changes as an index of cognitive function. For example, it can evaluate changes in cognitive function based on the user's emotion score. It can also analyze the user's emotional changes and use them as an index of cognitive function. It can evaluate the stability and fluctuations of the user's emotions. It can also evaluate the frequency of the user's positive and negative emotions. By using the user's emotional changes as an index of cognitive function, it becomes possible to perform more accurate cognitive function evaluations.

[0117] Generative AI can collect lifestyle data and analyze its relationship to cognitive function. For example, it can collect a user's sleep data and analyze its relationship to cognitive function. It can analyze sleep duration and sleep quality to evaluate the state of cognitive function. It can also collect a user's dietary data and analyze its relationship to cognitive function. It can analyze the content and nutritional balance of meals to evaluate the state of cognitive function. It can also collect a user's exercise data and analyze its relationship to cognitive function. It can analyze the frequency and intensity of exercise to evaluate the state of cognitive function. In this way, by collecting a user's lifestyle data and analyzing its relationship to cognitive function, more effective measures can be taken.

[0118] Generative AI can analyze social interaction data and use it to evaluate cognitive function. For example, it can analyze a user's social media data to help evaluate cognitive function. It can analyze the frequency and content of posts to evaluate the state of the user's social interactions. It can also analyze a user's email data to help evaluate cognitive function. It can analyze the frequency and content of emails sent and received to evaluate the state of the user's social interactions. It can also analyze the content and frequency of the user's social media and email exchanges to evaluate the state of the user's social interactions. In this way, analyzing a user's social interaction data can be useful in evaluating cognitive function.

[0119] Generative AI can use its emotion estimation function to investigate the relationship between emotional state and cognitive function. For example, it can evaluate the state of cognitive function based on the user's emotion score. It can also analyze the user's emotional state and investigate the relationship with cognitive function. It can evaluate the stability and fluctuation of the user's emotions. It can also evaluate the frequency of the user's positive and negative emotions. This allows for more accurate cognitive function evaluation by investigating the relationship between the user's emotional state and cognitive function.

[0120] The processing flow of the second embodiment will be briefly explained below.

[0121] Step 1: The generative AI interacts with the user. For example, the generative AI can use a smartphone or other device to facilitate a conversation with the user. The generative AI asks questions such as, "What did you do today?" or "What do you think about the recent news?", and the user responds. Step 2: The conversation analysis unit analyzes the conversation content generated by the generation AI. For example, the conversation analysis unit analyzes conversation characteristics seen in Alzheimer's disease and measures the user's cognitive function. The conversation analysis unit analyzes characteristics such as repetition of the same thing, increased use of "this," "that," and "this," ambiguity about time and place, and jumps in content. Step 3: Based on the results of the analysis by the conversation analysis unit, the suggestion unit suggests brain training, quizzes, or appropriate physical exercises if cognitive decline or Alzheimer's is suspected. For example, the suggestion unit may provide tasks such as memory training, problem-solving exercises, and attention improvement. The suggestion unit adjusts the difficulty of the tasks according to the user's progress. Step 4: The sharing unit compiles the conversation history into summaries and analysis results and shares them with specific people. For example, the sharing unit provides information to specific people such as family members, nurses, and home helpers.

[0122] 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.

[0123] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0124] 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.

[0125] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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).

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0139] 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.

[0140] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0141] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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).

[0146] 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.

[0147] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0148] 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.

[0149] 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.

[0150] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the 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 specific processing unit 290 using these models.

[0151] 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.

[0152] 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.

[0153] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0154] 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.

[0155] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0156] 7, the 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] In the robot 414, 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 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 processing similar to that of the specific processing unit 290 using these models.

[0167] 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.

[0168] 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.

[0169] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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."

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0188] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0189] 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. Equipped with generative AI, The generating AI interacts with a user, a conversation analysis unit that analyzes the conversation content generated by the generation AI; a suggestion unit that suggests brain training, quizzes, or appropriate physical exercises when cognitive decline or Alzheimer's disease is suspected based on the results of the analysis by the conversation analysis unit; a sharing unit that aggregates the history of the conversation content into a summary or analysis result and shares it with a specific person; A system characterized by:

2. The generated AI is Look at your conversation history and generate personalized questions based on your interests 2. The system of claim 1.

3. The generated AI is Analyze the tone of voice and speaking style to provide appropriate conversation depending on the emotional state 2. The system of claim 1.

4. The generated AI is Present visual content based on hobbies or interests during conversations 2. The system of claim 1.

5. The generated AI is Refer to past conversations with family or friends to find common ground 2. The system of claim 1.

Images