System

Abstract

An object of the system according to the embodiment is to detect an abnormality in content of a conversation or a manner of speaking at an early stage and take appropriate measures.SOLUTION: A system according to an embodiment includes a recording unit, an analysis unit, and a notification unit. The recording unit records the content of the conversation, the way of speaking, and the time from the question to the answer. The analysis unit analyzes the data recorded by the recording unit and detects an abnormality (for example, an abnormality in the content of a conversation or the way of speaking). The notification unit performs notification to a family member or a doctor in charge based on the abnormality detected by the analysis unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including 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 detect abnormalities in the content or manner of speech early and take appropriate action.

[0005] The system according to the embodiment aims to detect abnormalities in the content of conversation or speaking style at an early stage and take appropriate measures. [Means for solving the problem]

[0006] The system according to the embodiment includes a recording unit, an analysis unit, and a notification unit. The recording unit records the content of the conversation, the speaking style, and the time from the question to the answer. The analysis unit analyzes the data recorded by the recording unit and detects abnormalities (e.g., abnormalities in the content of the conversation or the speaking style). The notification unit notifies family members or the doctor in charge based on the abnormalities detected by the analysis unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect abnormalities in the content of conversation or speaking style at an early stage and take appropriate measures. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention uses a device equipped with a generative AI to record and analyze a subject's daily conversations, enabling early detection of early symptoms of diseases such as Alzheimer's. In this system, the subject and the generative AI converse daily. The generative AI records the content of the conversation, speaking style, and the time between question and answer. The system analyzes the recorded data to detect abnormalities and notifies the subject's family or doctor if an abnormality is detected. For example, the generative AI might ask, "What did you do today?" and the subject responds, "I went for a walk today." The content of the conversation, speaking style, and the time between question and answer are recorded. The recorded data is then analyzed by the generative AI. The generative AI uses natural language processing technology to analyze the content of the conversation and detect abnormalities. For example, if the subject's speaking style suddenly changes or their reaction time slows, the generative AI detects this as an abnormality. If an abnormality is detected, the system notifies the subject's family or doctor. For example, the generative AI might send a notification saying, "An abnormality has been observed in the subject's speaking style." This allows treatment to begin before the initial symptoms appear. This allows the system to record and analyze the subject's everyday conversations, making it possible to detect early symptoms of diseases such as Alzheimer's at an early stage and notify family members or doctors. For example, if early symptoms of Alzheimer's are detected, early treatment can be started to slow the progression of the condition.

[0029] A conversation analysis system according to an embodiment includes a recording unit, an analysis unit, and a notification unit. The recording unit records the content of a conversation between a subject and a generation AI, the speaking style, and the time from a question to an answer. For example, the recording unit saves the content of a conversation between the subject and the generation AI as text data. The recording unit can also record characteristics of the subject's speaking style (e.g., tone of voice, speed, accent, etc.) as audio data. The recording unit can also measure the time from a question to an answer in seconds and save the data. For example, the recording unit measures the time between the question and the answer when the generation AI asks, "What did you do today?" and the subject replies, "I went for a walk today." The analysis unit uses the generation AI to analyze the data recorded by the recording unit and detect anomalies. For example, the analysis unit can analyze the content of the conversation using natural language processing technology and detect anomalies. For example, the analysis unit can analyze the content of the conversation using morphological analysis and detect anomalies. The analysis unit can also analyze changes in the subject's speaking style and reaction time to detect anomalies. For example, the analysis unit analyzes changes in the tone or speed of the subject's voice to detect abnormalities. The notification unit notifies a family member or a doctor based on the abnormality detected by the analysis unit. For example, when an abnormality is detected, the notification unit notifies a family member or a doctor by email or app notification. For example, the notification unit sends a notification stating, "An abnormality has been observed in the subject's speaking style." In this way, the conversation analysis system according to the embodiment can detect abnormalities early and notify a family member or a doctor by recording and analyzing the subject's everyday conversations.

[0030] The recording unit can record the content of the conversation between the subject and the generating AI (e.g., a chatbot), the speaking style, and the time from question to answer. For example, the recording unit saves the content of the conversation between the subject and the generating AI as text data. The recording unit can also record the subject's speaking characteristics (e.g., tone of voice, speed, accent, etc.) as audio data. Furthermore, the recording unit can measure the time from question to answer in seconds and save the data. For example, the recording unit measures the time between the generating AI asking, "What did you do today?" and the subject responding, "I went for a walk today." This allows for detailed recording of the content of the conversation between the subject and the generating AI, the speaking style, and the reaction time. Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit can save the content of the conversation by the generating AI as text data, record speaking characteristics as audio data, and measure the time from question to answer.

[0031] The analysis unit can analyze the content of the conversation using natural language processing technology (e.g., morphological analysis) and detect anomalies. The analysis unit can analyze the content of the conversation using natural language processing technology, for example, and detect anomalies. For example, the analysis unit can analyze the content of the conversation using morphological analysis and detect anomalies. The analysis unit can also analyze the content of the conversation using grammatical analysis and detect anomalies. The analysis unit can also analyze the content of the conversation using semantic analysis and detect anomalies. For example, the analysis unit can break down the content of the conversation into smaller parts using morphological analysis and detect anomalies. Grammatical analysis analyzes the grammatical structure of the conversation and detects anomalies. Semantic analysis analyzes the meaning of the conversation and detects anomalies. In this way, by using natural language processing technology, the content of the conversation can be analyzed in detail and anomalies can be detected. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can analyze the content of the conversation using a generation AI and detect anomalies.

[0032] The notification unit can notify family members or the doctor in charge when an abnormality (e.g., abnormalities in the content of conversation or speaking style) is detected. For example, when an abnormality is detected, the notification unit notifies the family members or the doctor in charge by email or app notification. For example, the notification unit sends a notification stating, "An abnormality has been observed in the subject's speaking style." The notification unit can also send a notification including details of the abnormality. For example, the notification unit sends a notification stating, "An abnormality has been observed in the subject's speaking style. Specifically, the tone of voice suddenly changed and reaction time became slower." Furthermore, the notification unit can have a function to automatically call an emergency contact when an abnormality is detected. For example, when an abnormality is detected, the notification unit automatically calls the family members or the doctor in charge to notify them of the abnormality. This allows the family members or the doctor in charge to be promptly notified when an abnormality is detected. Some or all of the above-described processing by the notification unit may be performed, for example, using AI or without AI. For example, the notification unit can notify the family members or the doctor in charge of an abnormality detected by the generation AI.

[0033] The analysis unit can analyze changes in the speaking style and reaction time of the subject and detect abnormalities (e.g., changes in speaking style and abnormal reaction time). The analysis unit can, for example, analyze changes in the speaking style and reaction time of the subject and detect abnormalities. For example, the analysis unit can analyze changes in the tone and speed of the subject's voice and detect abnormalities. The analysis unit can also analyze delays in the subject's reaction time and detect abnormalities. Furthermore, the analysis unit can analyze the speaking pattern of the subject and detect abnormalities. For example, the analysis unit analyzes changes in the tone of the subject's voice and detects abnormalities. Regarding changes in speed, an abnormality is detected when the speaking speed of the subject suddenly slows down or speeds up. Regarding delays in reaction time, an abnormality is detected when the time between a question and an answer becomes longer than usual. Regarding speaking pattern, an abnormality is detected when the speaking style of the subject lacks consistency. In this way, by analyzing changes in the speaking style and reaction time of the subject, abnormalities can be detected early. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the analysis unit may use the generation AI to analyze changes in the subject's speaking style or reaction time and detect abnormalities.

[0034] The notification unit can send an abnormality detected by the generation AI (e.g., a chatbot) to a family member or a doctor via email or app notification. For example, the notification unit can send an email or app notification of an abnormality detected by the generation AI to a family member or a doctor. For example, the notification unit can send a notification stating, "An abnormality has been observed in the subject's speaking style." The notification unit can also send a notification including details of the abnormality. For example, the notification unit can send a notification stating, "An abnormality has been observed in the subject's speaking style. Specifically, the subject's tone of voice suddenly changed and their reaction time became slower." The notification unit can also have a function to automatically call an emergency contact when an abnormality is detected. For example, the notification unit can automatically call a family member or a doctor to notify them of the abnormality when an abnormality is detected. This allows the family member or a doctor to be promptly notified by email or app notification when an abnormality is detected. Some or all of the above-described processing by the notification unit can be performed using, for example, AI, or can be performed without using AI. For example, the notification unit can notify a family member or a doctor of an abnormality detected by the generation AI.

[0035] The recording unit can analyze the subject's past conversation history and select the optimal recording method (e.g., audio recording, text recording). The recording unit, for example, analyzes the subject's past conversation history and selects the optimal recording method. For example, the recording unit prioritizes recording topics that the subject has frequently talked about in the past. The recording unit can also adjust the recording method for conversations during a specific time period based on the subject's past conversation history. Furthermore, the recording unit can analyze trends in the content of conversations that the subject has previously talked about and optimize the recording method. For example, the recording unit prioritizes recording topics that the subject has previously talked about. Adjusts the recording method for conversations during a specific time period. Analyzes trends in the content of conversations that have previously been talked about and optimizes the recording method. In this way, the optimal recording method can be selected by analyzing the past conversation history. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can use a generation AI to analyze the subject's past conversation history and select the optimal recording method.

[0036] The recording unit can filter (e.g., extract important conversation content) based on the subject's current health condition and living situation when recording a conversation. The recording unit can filter (e.g., extract important conversation content) based on the subject's current health condition and living situation when recording a conversation. For example, when the subject is in poor health, the recording unit simplifies the conversation record and records only the minimum necessary information. Furthermore, when the subject is healthy, the recording unit can record detailed conversation content and collect more data. Furthermore, the recording unit can adjust the conversation recording method according to the subject's living situation. For example, when the subject is in poor health, the recording unit simplifies the conversation record and records only the minimum necessary information. When the subject is healthy, the recording unit records detailed conversation content and collects more data. The conversation recording method is adjusted according to the living situation. In this way, by adjusting the conversation recording method according to the subject's health condition and living situation, more appropriate data can be collected. Some or all of the above-mentioned processing in the recording unit may be performed, for example, using AI or without AI. For example, the recording unit allows the generating AI to filter based on the subject's health condition and living situation.

[0037] When recording a conversation, the recording unit can select the optimal recording means depending on the input method of the subject (e.g., voice, text, gesture). When recording a conversation, the recording unit can select the optimal recording means depending on the input method of the subject. For example, when the subject speaks by voice, the recording unit records the conversation content using voice recognition technology. Furthermore, when the subject speaks by text, the recording unit can also record the text input. Furthermore, when the subject speaks by gesture, the recording unit can also record the conversation content using gesture recognition technology. For example, when the subject speaks by voice, the recording unit records the conversation content using voice recognition technology. When the subject speaks by text, the recording unit records the text input. When the subject speaks by gesture, the recording unit records the conversation content using gesture recognition technology. In this way, by selecting the optimal recording means depending on the input method of the subject, more accurate data can be collected. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can have a generation AI select the optimal recording means depending on the input method of the subject.

[0038] When recording a conversation, the recording unit can prioritize recording highly relevant conversations by taking into account the geographical location information of the subject. For example, when recording a conversation, the recording unit prioritizes recording highly relevant conversations by taking into account the geographical location information of the subject. For example, when the subject is in a specific location, the recording unit prioritizes recording conversation content related to the location. Furthermore, when the subject is traveling, the recording unit can also prioritize recording conversation content related to traveling. Furthermore, when the subject is at home, the recording unit can prioritize recording conversation content related to daily life. For example, when the subject is in a specific location, the recording unit prioritizes recording conversation content related to the location. When traveling, the recording unit prioritizes recording conversation content related to traveling. When at home, the recording unit prioritizes recording conversation content related to daily life. This allows more useful data to be collected by prioritizing recording highly relevant conversations based on the geographical location information of the subject. Some or all of the above-described processing in the recording unit may be performed, for example, using AI, or may be performed without using AI. For example, the recording unit can prioritize recording highly relevant conversations by using a generation AI to consider the geographical location information of the subject.

[0039] The recording unit can analyze the social media activity of the subject and record related conversations when recording a conversation. For example, the recording unit can analyze the social media activity of the subject and record related conversations when recording a conversation. For example, the recording unit can prioritize recording topics that the subject is talking about on social media. The recording unit can also analyze the content of the subject's social media posts and record related conversations. Furthermore, the recording unit can also record related conversations with reference to the activities of the subject's friends on social media. For example, the recording unit prioritizes recording topics that the subject is talking about on social media. The recording unit can analyze the content of the social media posts and record related conversations. The recording unit can also record related conversations with reference to the activities of the subject's friends on social media. In this way, more useful data can be collected by recording related conversations based on the subject's social media activity. Some or all of the above-mentioned processing in the recording unit can be performed, for example, using AI, or can be performed without using AI. For example, the recording unit can use a generation AI to analyze the subject's social media activity and record related conversations.

[0040] The recording unit can customize the recording method by reflecting the subject's past feedback when recording a conversation. For example, when recording a conversation, the recording unit customizes the recording method by reflecting the subject's past feedback. For example, the recording unit preferentially uses a recording method that the subject has previously preferred. The recording unit can also optimize the recording method based on the subject's past feedback. Furthermore, the recording unit can avoid recording methods that the subject has previously been dissatisfied with. For example, the recording unit preferentially uses a recording method that the subject has previously preferred. The recording unit optimizes the recording method based on the subject's past feedback. The recording unit avoids recording methods that the subject has previously been dissatisfied with. In this way, more appropriate data can be collected by customizing the recording method based on the subject's past feedback. Some or all of the above-described processing in the recording unit may be performed, for example, using AI, or may be performed without using AI. For example, the recording unit can customize the recording method by having the generation AI reflect the subject's past feedback.

[0041] The analysis unit can adjust the level of detail of the analysis based on the importance (e.g., urgency) of the conversation during analysis. The analysis unit can, for example, adjust the level of detail of the analysis based on the importance of the conversation during analysis. For example, the analysis unit performs a detailed analysis of important conversation content. The analysis unit can also perform a concise analysis of general conversation content. The analysis unit can also perform a particularly detailed analysis of conversation content related to the subject's health condition. For example, the analysis unit performs a detailed analysis of important conversation content. The analysis unit performs a concise analysis of general conversation content. The analysis unit performs a particularly detailed analysis of conversation content related to the subject's health condition. In this way, by adjusting the level of detail of the analysis according to the importance of the conversation, important conversation content can be analyzed in detail. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the level of detail of the analysis based on the importance of the conversation using the generation AI.

[0042] The analysis unit can apply different analysis algorithms depending on the category of the conversation (e.g., medical, everyday conversation) during analysis. The analysis unit can, for example, apply different analysis algorithms depending on the category of the conversation during analysis. For example, the analysis unit can apply a specific health analysis algorithm to conversation content related to health. The analysis unit can also apply a general analysis algorithm to conversation content related to daily life. The analysis unit can also apply an emotion analysis algorithm to conversation content related to emotions. For example, the analysis unit can apply a specific health analysis algorithm to conversation content related to health. The analysis unit can apply a general analysis algorithm to conversation content related to daily life. The analysis unit can apply an emotion analysis algorithm to conversation content related to emotions. This allows for applying an appropriate analysis algorithm depending on the category of the conversation, thereby providing more accurate analysis results. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the analysis unit can apply different analysis algorithms depending on the category of the conversation using a generation AI.

[0043] During analysis, the analysis unit can improve the accuracy (e.g., precision) of the analysis by referring to past analysis results of the subject. During analysis, the analysis unit can improve the accuracy of the analysis by referring to past analysis results of the subject. For example, the analysis unit corrects the current analysis result based on the past analysis results of the subject. The analysis unit can also extract specific trends from the past analysis results of the subject and reflect them in the current analysis. Furthermore, the analysis unit can optimize the analysis algorithm by referring to the past analysis results of the subject. For example, the analysis unit corrects the current analysis result based on the past analysis results of the subject. Specific trends are extracted from the past analysis results and reflected in the current analysis. The analysis algorithm is optimized by referring to the past analysis results. In this way, the accuracy of the current analysis result can be improved by referring to the past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can improve the accuracy of the analysis by using a generation AI to refer to the past analysis results of the subject.

[0044] The analysis unit can determine the priority of analysis based on the time of occurrence of the conversation (e.g., the most recent conversation) during analysis. The analysis unit can, for example, determine the priority of analysis based on the time of occurrence of the conversation during analysis. For example, the analysis unit prioritizes analyzing the content of the most recent conversation. The analysis unit can also prioritize analyzing the content of the conversation that occurred during a specific time period. Furthermore, the analysis unit can also prioritize analyzing the content of the conversation related to the subject's health condition. For example, the analysis unit prioritizes analyzing the content of the most recent conversation. The analysis unit prioritizes analyzing the content of the conversation that occurred during a specific time period. The analysis unit prioritizes analyzing the content of the conversation related to the health condition. In this way, by determining the priority of analysis based on the time of occurrence of the conversation, important content of the conversation can be analyzed preferentially. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can determine the priority of analysis based on the time of occurrence of the conversation using a generation AI.

[0045] The analysis unit can adjust the order of analysis based on the relevance of the conversations (e.g., conversations about the same topic) during analysis. The analysis unit can, for example, adjust the order of analysis based on the relevance of the conversations during analysis. For example, the analysis unit prioritizes analyzing important conversation content. The analysis unit can also prioritize analyzing highly relevant conversation content. Furthermore, the analysis unit can also prioritize analyzing conversation content related to the subject's health condition. For example, the analysis unit prioritizes analyzing important conversation content. Highly relevant conversation content. Conversation content related to the health condition can be prioritized. In this way, by adjusting the order of analysis based on the relevance of the conversations, important conversation content can be prioritized for analysis. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the order of analysis based on the relevance of the conversations using the generation AI.

[0046] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the subject's level of expertise (e.g., whether or not the subject has medical knowledge). The analysis unit, for example, adjusts the use of technical terms in the analysis according to the subject's level of expertise during analysis. For example, if the subject has technical expertise, the analysis unit uses detailed technical terms. Furthermore, if the subject has general knowledge, the analysis unit can also use concise technical terms. Furthermore, if the subject does not have technical expertise, the analysis unit can provide analysis results in easy-to-understand language. For example, if the subject has technical expertise, the analysis unit uses detailed technical terms. If the subject has general knowledge, the analysis unit uses concise technical terms. If the subject does not have technical expertise, the analysis unit provides analysis results in easy-to-understand language. In this way, by adjusting the use of technical terms in the analysis according to the subject's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the use of technical terms in the analysis according to the subject's level of expertise.

[0047] The notification unit can adjust the level of detail of the notification based on the importance (e.g., urgency) of the abnormality at the time of notification. The notification unit, for example, adjusts the level of detail of the notification based on the importance of the abnormality at the time of notification. For example, the notification unit provides detailed notification for important abnormalities. The notification unit can also provide brief notification for general abnormalities. The notification unit can also provide particularly detailed notification for abnormalities related to the subject's health condition. For example, the notification unit provides detailed notification for important abnormalities. The notification unit provides brief notification for general abnormalities. The notification unit provides particularly detailed notification for abnormalities related to the subject's health condition. In this way, by adjusting the level of detail of the notification according to the importance of the abnormality, important abnormalities can be notified in detail. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI or may be performed without using AI. For example, the notification unit can adjust the level of detail of the notification based on the importance of the abnormality using a generation AI.

[0048] The notification unit can apply different notification algorithms depending on the category of the abnormality (e.g., medical, daily life) when making a notification. The notification unit, for example, applies different notification algorithms depending on the category of the abnormality when making a notification. For example, the notification unit applies a specific health notification algorithm to an abnormality related to health. The notification unit can also apply a general notification algorithm to an abnormality related to daily life. The notification unit can also apply an emotion notification algorithm to an abnormality related to emotion. For example, the notification unit applies a specific health notification algorithm to an abnormality related to health. The notification unit applies a general notification algorithm to an abnormality related to daily life. The notification unit applies an emotion notification algorithm to an abnormality related to emotion. This allows for more accurate notification by applying an appropriate notification algorithm depending on the category of the abnormality. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can use a generation AI to apply different notification algorithms depending on the category of the abnormality.

[0049] The notification unit can improve the accuracy (e.g., precision) of the notification by referring to the target person's past notification results when notifying the target person. The notification unit can improve the accuracy of the notification by referring to the target person's past notification results when notifying the target person. For example, the notification unit corrects the current notification result based on the target person's past notification results. The notification unit can also extract specific trends from the target person's past notification results and reflect them in the current notification. Furthermore, the notification unit can optimize the notification algorithm by referring to the target person's past notification results. For example, the notification unit corrects the current notification result based on the target person's past notification results. The notification unit extracts specific trends from the past notification results and reflects them in the current notification. The notification algorithm is optimized by referring to the past notification results. In this way, the accuracy of the current notification result can be improved by referring to the past notification results. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can improve the accuracy of the notification by using a generation AI to refer to the target person's past notification results.

[0050] The notification unit can determine the priority of notifications based on the time of occurrence of an abnormality (e.g., the most recent abnormality) at the time of notification. The notification unit, for example, determines the priority of notifications based on the time of occurrence of an abnormality at the time of notification. For example, the notification unit prioritizes notification of recently occurring abnormalities. The notification unit can also prioritize notification of abnormalities that occurred in a specific time period. Furthermore, the notification unit can also prioritize notification of abnormalities related to the subject's health condition. For example, the notification unit prioritizes notification of recently occurring abnormalities. The notification unit prioritizes notification of abnormalities that occurred in a specific time period. The notification unit prioritizes notification of abnormalities related to the subject's health condition. In this way, by determining the priority of notifications based on the time of occurrence of an abnormality, it is possible to prioritize notification of important abnormalities. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can use a generation AI to determine the priority of notifications based on the time of occurrence of an abnormality.

[0051] The notification unit can adjust the order of notifications based on the relevance of the anomalies (e.g., anomalies related to the same topic) when notifying. The notification unit, for example, adjusts the order of notifications based on the relevance of the anomalies when notifying. For example, the notification unit prioritizes notifying important anomalies. The notification unit can also prioritize notifying highly relevant anomalies. Furthermore, the notification unit can also prioritize notifying anomalies related to the health condition of the subject. For example, the notification unit prioritizes notifying important anomalies. The notification unit prioritizes notifying highly relevant anomalies. The notification unit prioritizes notifying anomalies related to the health condition. In this way, by adjusting the order of notifications based on the relevance of the anomalies, important anomalies can be prioritized. Some or all of the above-described processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can adjust the order of notifications based on the relevance of the anomalies using a generation AI.

[0052] The notification unit can adjust the use of technical terms in the notification depending on the subject's level of expertise (e.g., whether or not the subject has medical knowledge) when notifying the subject. The notification unit can, for example, adjust the use of technical terms in the notification depending on the subject's level of expertise when notifying the subject. For example, if the subject has technical knowledge, the notification unit uses detailed technical terms. Also, if the subject has general knowledge, the notification unit can use concise technical terms. Furthermore, if the subject does not have technical knowledge, the notification unit can provide the notification in easy-to-understand language. For example, if the subject has technical knowledge, the notification unit uses detailed technical terms. If the subject has general knowledge, the notification unit uses concise technical terms. If the subject does not have technical knowledge, the notification unit provides the notification in easy-to-understand language. In this way, by adjusting the use of technical terms in the notification depending on the subject's level of expertise, the notification can be made easier to understand. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can adjust the use of technical terms in the notification depending on the subject's level of expertise using a generation AI.

[0053] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0054] When recording the content of a subject's conversation, the recording unit can adjust the frequency and timing of recording taking into account the subject's lifestyle rhythm and daily activity pattern. For example, if the subject is active in the morning, the recording unit can prioritize recording morning conversations. Also, if the subject is relaxed at night, the recording unit can record nighttime conversations in detail. Furthermore, the recording unit can particularly carefully record weekend conversations based on the subject's weekend activity pattern. This allows for more appropriate data to be collected according to the subject's lifestyle rhythm and activity pattern.

[0055] When analyzing the subject's conversation content, the analysis unit can improve the accuracy of the analysis by referring to the subject's past health checkup results and medical records. For example, the analysis unit can analyze the current conversation content based on the subject's past health checkup results and detect abnormalities. The analysis unit can also extract specific medical history and symptoms from the subject's medical records and reflect them in the analysis. Furthermore, the analysis unit can optimize the analysis algorithm by referring to the subject's past medical data. This makes it possible to provide more accurate analysis results by utilizing past medical data.

[0056] When an abnormality is detected, the notification unit can notify not only the subject's family and doctor, but also local nursing care services and support organizations. For example, when an abnormality is detected, the notification unit notifies local nursing care services by email or app notification. The notification unit can also notify support organizations, including details of the abnormality. Furthermore, in an emergency, the notification unit can automatically call local nursing care services to notify them of the abnormality. This allows for a rapid response in cooperation with the local support network when an abnormality is detected.

[0057] When recording the content of a conversation of a subject, the recording unit can classify conversation topics based on the subject's hobbies and interests and preferentially record conversations related to specific topics. For example, if the subject is interested in music, the recording unit can preferentially record conversations related to music. Also, if the subject is interested in sports, the recording unit can record conversations related to sports in detail. Furthermore, if the subject is interested in traveling, the recording unit can particularly carefully record conversations related to travel. This makes it possible to collect more useful data according to the subject's hobbies and interests.

[0058] When analyzing the content of a subject's conversation, the analysis unit can adjust the analysis algorithm taking into account the subject's cultural background and linguistic characteristics. For example, if the subject speaks a specific dialect, the analysis unit applies an analysis algorithm that corresponds to that dialect. The analysis unit can also reflect specific cultural expressions and phrases in the analysis based on the subject's cultural background. Furthermore, if the subject speaks multiple languages, the analysis unit can apply analysis algorithms that correspond to multiple languages. This makes it possible to provide more accurate analysis results that correspond to the subject's cultural background and linguistic characteristics.

[0059] The processing flow of the first embodiment will be briefly explained below.

[0060] Step 1: The recording unit records the content of the conversation between the subject and the generating AI, the speaking style, and the time from question to answer. For example, the recording unit saves the content of the subject's conversation with the generating AI as text data. The recording unit can also record the subject's speaking style characteristics (e.g., tone of voice, speed, accent, etc.) as audio data. Furthermore, the recording unit can measure the time from question to answer in seconds and save this as data. For example, the recording unit measures the time between the generating AI asking, "What did you do today?" and the subject replying, "I went for a walk today." Step 2: The analysis unit uses the generation AI to analyze the data recorded by the recording unit and detect anomalies. For example, the analysis unit uses natural language processing technology to analyze the content of the conversation and detect anomalies. For example, the analysis unit can analyze the content of the conversation and detect anomalies using morphological analysis. The analysis unit can also analyze changes in the subject's speaking style and reaction time to detect anomalies. For example, the analysis unit can analyze changes in the subject's tone and speed of voice to detect anomalies. Step 3: The notification unit notifies the family or the doctor in charge based on the abnormality detected by the analysis unit. For example, if an abnormality is detected, the notification unit notifies the family or the doctor in charge by email or app notification. For example, the notification unit sends a notification saying, "An abnormality has been observed in the subject's speaking style."

[0061] (Example 2) A system according to an embodiment of the present invention uses a device equipped with a generative AI to record and analyze a subject's daily conversations, enabling early detection of early symptoms of diseases such as Alzheimer's. In this system, the subject and the generative AI converse daily. The generative AI records the content of the conversation, speaking style, and the time between question and answer. The system analyzes the recorded data to detect abnormalities and notifies the subject's family or doctor if an abnormality is detected. For example, the generative AI might ask, "What did you do today?" and the subject responds, "I went for a walk today." The content of the conversation, speaking style, and the time between question and answer are recorded. The recorded data is then analyzed by the generative AI. The generative AI uses natural language processing technology to analyze the content of the conversation and detect abnormalities. For example, if the subject's speaking style suddenly changes or their reaction time slows, the generative AI detects this as an abnormality. If an abnormality is detected, the system notifies the subject's family or doctor. For example, the generative AI might send a notification saying, "An abnormality has been observed in the subject's speaking style." This allows treatment to begin before the initial symptoms appear. This allows the system to record and analyze the subject's everyday conversations, making it possible to detect early symptoms of diseases such as Alzheimer's at an early stage and notify family members or doctors. For example, if early symptoms of Alzheimer's are detected, early treatment can be started to slow the progression of the condition.

[0062] A conversation analysis system according to an embodiment includes a recording unit, an analysis unit, and a notification unit. The recording unit records the content of a conversation between a subject and a generation AI, the speaking style, and the time from a question to an answer. For example, the recording unit saves the content of a conversation between the subject and the generation AI as text data. The recording unit can also record characteristics of the subject's speaking style (e.g., tone of voice, speed, accent, etc.) as audio data. The recording unit can also measure the time from a question to an answer in seconds and save the data. For example, the recording unit measures the time between the question and the answer when the generation AI asks, "What did you do today?" and the subject replies, "I went for a walk today." The analysis unit uses the generation AI to analyze the data recorded by the recording unit and detect anomalies. For example, the analysis unit can analyze the content of the conversation using natural language processing technology and detect anomalies. For example, the analysis unit can analyze the content of the conversation using morphological analysis and detect anomalies. The analysis unit can also analyze changes in the subject's speaking style and reaction time to detect anomalies. For example, the analysis unit analyzes changes in the tone or speed of the subject's voice to detect abnormalities. The notification unit notifies a family member or a doctor based on the abnormality detected by the analysis unit. For example, when an abnormality is detected, the notification unit notifies a family member or a doctor by email or app notification. For example, the notification unit sends a notification stating, "An abnormality has been observed in the subject's speaking style." In this way, the conversation analysis system according to the embodiment can detect abnormalities early and notify a family member or a doctor by recording and analyzing the subject's everyday conversations.

[0063] The recording unit can record the content of the conversation between the subject and the generating AI (e.g., a chatbot), the speaking style, and the time from question to answer. For example, the recording unit saves the content of the conversation between the subject and the generating AI as text data. The recording unit can also record the subject's speaking characteristics (e.g., tone of voice, speed, accent, etc.) as audio data. Furthermore, the recording unit can measure the time from question to answer in seconds and save the data. For example, the recording unit measures the time between the generating AI asking, "What did you do today?" and the subject responding, "I went for a walk today." This allows for detailed recording of the content of the conversation between the subject and the generating AI, the speaking style, and the reaction time. Some or all of the above-described processing in the recording unit may be performed using, or without, AI. For example, the recording unit can save the content of the conversation by the generating AI as text data, record speaking characteristics as audio data, and measure the time from question to answer.

[0064] The analysis unit can analyze the content of the conversation using natural language processing technology (e.g., morphological analysis) and detect anomalies. The analysis unit can analyze the content of the conversation using natural language processing technology, for example, and detect anomalies. For example, the analysis unit can analyze the content of the conversation using morphological analysis and detect anomalies. The analysis unit can also analyze the content of the conversation using grammatical analysis and detect anomalies. The analysis unit can also analyze the content of the conversation using semantic analysis and detect anomalies. For example, the analysis unit can break down the content of the conversation into smaller parts using morphological analysis and detect anomalies. Grammatical analysis analyzes the grammatical structure of the conversation and detects anomalies. Semantic analysis analyzes the meaning of the conversation and detects anomalies. In this way, by using natural language processing technology, the content of the conversation can be analyzed in detail and anomalies can be detected. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can analyze the content of the conversation using a generation AI and detect anomalies.

[0065] The notification unit can notify family members or the doctor in charge when an abnormality (e.g., abnormalities in the content of conversation or speaking style) is detected. For example, when an abnormality is detected, the notification unit notifies the family members or the doctor in charge by email or app notification. For example, the notification unit sends a notification stating, "An abnormality has been observed in the subject's speaking style." The notification unit can also send a notification including details of the abnormality. For example, the notification unit sends a notification stating, "An abnormality has been observed in the subject's speaking style. Specifically, the tone of voice suddenly changed and reaction time became slower." Furthermore, the notification unit can have a function to automatically call an emergency contact when an abnormality is detected. For example, when an abnormality is detected, the notification unit automatically calls the family members or the doctor in charge to notify them of the abnormality. This allows the family members or the doctor in charge to be promptly notified when an abnormality is detected. Some or all of the above-described processing by the notification unit may be performed, for example, using AI or without AI. For example, the notification unit can notify the family members or the doctor in charge of an abnormality detected by the generation AI.

[0066] The analysis unit can analyze changes in the speaking style and reaction time of the subject and detect abnormalities (e.g., changes in speaking style and abnormal reaction time). The analysis unit can, for example, analyze changes in the speaking style and reaction time of the subject and detect abnormalities. For example, the analysis unit can analyze changes in the tone and speed of the subject's voice and detect abnormalities. The analysis unit can also analyze delays in the subject's reaction time and detect abnormalities. Furthermore, the analysis unit can analyze the speaking pattern of the subject and detect abnormalities. For example, the analysis unit analyzes changes in the tone of the subject's voice and detects abnormalities. Regarding changes in speed, an abnormality is detected when the speaking speed of the subject suddenly slows down or speeds up. Regarding delays in reaction time, an abnormality is detected when the time between a question and an answer becomes longer than usual. Regarding speaking pattern, an abnormality is detected when the speaking style of the subject lacks consistency. In this way, by analyzing changes in the speaking style and reaction time of the subject, abnormalities can be detected early. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the analysis unit may use the generation AI to analyze changes in the subject's speaking style or reaction time and detect abnormalities.

[0067] The notification unit can send an abnormality detected by the generation AI (e.g., a chatbot) to a family member or a doctor via email or app notification. For example, the notification unit can send an email or app notification of an abnormality detected by the generation AI to a family member or a doctor. For example, the notification unit can send a notification stating, "An abnormality has been observed in the subject's speaking style." The notification unit can also send a notification including details of the abnormality. For example, the notification unit can send a notification stating, "An abnormality has been observed in the subject's speaking style. Specifically, the subject's tone of voice suddenly changed and their reaction time became slower." The notification unit can also have a function to automatically call an emergency contact when an abnormality is detected. For example, the notification unit can automatically call a family member or a doctor to notify them of the abnormality when an abnormality is detected. This allows the family member or a doctor to be promptly notified by email or app notification when an abnormality is detected. Some or all of the above-described processing by the notification unit can be performed using, for example, AI, or can be performed without using AI. For example, the notification unit can notify a family member or a doctor of an abnormality detected by the generation AI.

[0068] The recording unit can estimate the subject's emotion (e.g., joy, anger, sadness) and adjust the conversation recording method based on the estimated emotion. The recording unit, for example, estimates the subject's emotion and adjusts the conversation recording method based on the estimated emotion. For example, if the subject is stressed, the recording unit simplifies the conversation recording and records only the minimum necessary information. Also, if the subject is relaxed, the recording unit can record detailed conversation content and collect more data. Furthermore, if the subject is tired, the recording unit can adjust the conversation recording to shorten the time. For example, if the subject is stressed, the recording unit simplifies the conversation recording and records only the minimum necessary information. If the subject is relaxed, the recording unit records detailed conversation content and collects more data. If the subject is tired, the recording unit adjusts the conversation recording to shorten the time. In this way, by adjusting the conversation recording method according to the subject's emotion, more appropriate data can be collected. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation AI may estimate the subject's emotions, and the recording unit may adjust the method of recording the conversation based on the estimated emotions.

[0069] The recording unit can analyze the subject's past conversation history and select the optimal recording method (e.g., audio recording, text recording). The recording unit, for example, analyzes the subject's past conversation history and selects the optimal recording method. For example, the recording unit prioritizes recording topics that the subject has frequently talked about in the past. The recording unit can also adjust the recording method for conversations during a specific time period based on the subject's past conversation history. Furthermore, the recording unit can analyze trends in the content of conversations that the subject has previously talked about and optimize the recording method. For example, the recording unit prioritizes recording topics that the subject has previously talked about. Adjusts the recording method for conversations during a specific time period. Analyzes trends in the content of conversations that have previously been talked about and optimizes the recording method. In this way, the optimal recording method can be selected by analyzing the past conversation history. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can use a generation AI to analyze the subject's past conversation history and select the optimal recording method.

[0070] The recording unit can filter (e.g., extract important conversation content) based on the subject's current health condition and living situation when recording a conversation. The recording unit can filter (e.g., extract important conversation content) based on the subject's current health condition and living situation when recording a conversation. For example, when the subject is in poor health, the recording unit simplifies the conversation record and records only the minimum necessary information. Furthermore, when the subject is healthy, the recording unit can record detailed conversation content and collect more data. Furthermore, the recording unit can adjust the conversation recording method according to the subject's living situation. For example, when the subject is in poor health, the recording unit simplifies the conversation record and records only the minimum necessary information. When the subject is healthy, the recording unit records detailed conversation content and collects more data. The conversation recording method is adjusted according to the living situation. In this way, by adjusting the conversation recording method according to the subject's health condition and living situation, more appropriate data can be collected. Some or all of the above-mentioned processing in the recording unit may be performed, for example, using AI or without AI. For example, the recording unit allows the generating AI to filter based on the subject's health condition and living situation.

[0071] When recording a conversation, the recording unit can select the optimal recording means depending on the input method of the subject (e.g., voice, text, gesture). When recording a conversation, the recording unit can select the optimal recording means depending on the input method of the subject. For example, when the subject speaks by voice, the recording unit records the conversation content using voice recognition technology. Furthermore, when the subject speaks by text, the recording unit can also record the text input. Furthermore, when the subject speaks by gesture, the recording unit can also record the conversation content using gesture recognition technology. For example, when the subject speaks by voice, the recording unit records the conversation content using voice recognition technology. When the subject speaks by text, the recording unit records the text input. When the subject speaks by gesture, the recording unit records the conversation content using gesture recognition technology. In this way, by selecting the optimal recording means depending on the input method of the subject, more accurate data can be collected. Some or all of the above-mentioned processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit can have a generation AI select the optimal recording means depending on the input method of the subject.

[0072] The recording unit can estimate the subject's emotions (e.g., joy, anger, sadness) and determine the priority of conversations to be recorded based on the estimated emotions. The recording unit can estimate the subject's emotions and determine the priority of conversations to be recorded based on the estimated emotions. For example, if the subject is stressed, the recording unit can prioritize recording important conversation content. Also, if the subject is relaxed, the recording unit can prioritize recording detailed conversation content. Furthermore, if the subject is tired, the recording unit can prioritize recording conversation content that can be completed in a short time. For example, if the subject is stressed, the recording unit can prioritize recording important conversation content. If the subject is relaxed, the recording unit can prioritize recording detailed conversation content. If the subject is tired, the recording unit can prioritize recording conversation content that can be completed in a short time. In this way, by determining the priority of conversations to be recorded according to the subject's emotions, important conversation content can be prioritized and recorded. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the recording unit may be performed using, for example, AI, or may be performed without using AI. For example, the recording unit may use a generation AI to estimate the emotions of the subject and determine the priority of the conversation to be recorded based on the estimated emotions.

[0073] When recording a conversation, the recording unit can prioritize recording highly relevant conversations by taking into account the geographical location information of the subject. For example, when recording a conversation, the recording unit prioritizes recording highly relevant conversations by taking into account the geographical location information of the subject. For example, when the subject is in a specific location, the recording unit prioritizes recording conversation content related to the location. Furthermore, when the subject is traveling, the recording unit can also prioritize recording conversation content related to traveling. Furthermore, when the subject is at home, the recording unit can prioritize recording conversation content related to daily life. For example, when the subject is in a specific location, the recording unit prioritizes recording conversation content related to the location. When traveling, the recording unit prioritizes recording conversation content related to traveling. When at home, the recording unit prioritizes recording conversation content related to daily life. This allows more useful data to be collected by prioritizing recording highly relevant conversations based on the geographical location information of the subject. Some or all of the above-described processing in the recording unit may be performed, for example, using AI, or may be performed without using AI. For example, the recording unit can prioritize recording highly relevant conversations by using a generation AI to consider the geographical location information of the subject.

[0074] The recording unit can analyze the social media activity of the subject and record related conversations when recording a conversation. For example, the recording unit can analyze the social media activity of the subject and record related conversations when recording a conversation. For example, the recording unit can prioritize recording topics that the subject is talking about on social media. The recording unit can also analyze the content of the subject's social media posts and record related conversations. Furthermore, the recording unit can also record related conversations with reference to the activities of the subject's friends on social media. For example, the recording unit prioritizes recording topics that the subject is talking about on social media. The recording unit can analyze the content of the social media posts and record related conversations. The recording unit can also record related conversations with reference to the activities of the subject's friends on social media. In this way, more useful data can be collected by recording related conversations based on the subject's social media activity. Some or all of the above-mentioned processing in the recording unit can be performed, for example, using AI, or can be performed without using AI. For example, the recording unit can use a generation AI to analyze the subject's social media activity and record related conversations.

[0075] The recording unit can customize the recording method by reflecting the subject's past feedback when recording a conversation. For example, when recording a conversation, the recording unit customizes the recording method by reflecting the subject's past feedback. For example, the recording unit preferentially uses a recording method that the subject has previously preferred. The recording unit can also optimize the recording method based on the subject's past feedback. Furthermore, the recording unit can avoid recording methods that the subject has previously been dissatisfied with. For example, the recording unit preferentially uses a recording method that the subject has previously preferred. The recording unit optimizes the recording method based on the subject's past feedback. The recording unit avoids recording methods that the subject has previously been dissatisfied with. In this way, more appropriate data can be collected by customizing the recording method based on the subject's past feedback. Some or all of the above-described processing in the recording unit may be performed, for example, using AI, or may be performed without using AI. For example, the recording unit can customize the recording method by having the generation AI reflect the subject's past feedback.

[0076] The analysis unit can estimate the subject's emotion (e.g., joy, anger, sadness) and adjust the analysis expression method based on the estimated emotion. The analysis unit, for example, estimates the subject's emotion and adjusts the analysis expression method based on the estimated emotion. For example, if the subject is stressed, the analysis unit provides a concise and easy-to-understand analysis result. Furthermore, if the subject is relaxed, the analysis unit can provide a detailed analysis result. Furthermore, if the subject is tired, the analysis unit can provide a key point analysis result. For example, if the subject is stressed, the analysis unit provides a concise and easy-to-understand analysis result. If the subject is relaxed, the analysis unit provides a detailed analysis result. If the subject is tired, the analysis unit provides a key point analysis result. In this way, by adjusting the analysis expression method according to the subject's emotion, more appropriate analysis results can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the analysis unit may use the generation AI to estimate the subject's emotions and adjust the method of expression of the analysis based on the estimated emotions.

[0077] The analysis unit can adjust the level of detail of the analysis based on the importance (e.g., urgency) of the conversation during analysis. The analysis unit can, for example, adjust the level of detail of the analysis based on the importance of the conversation during analysis. For example, the analysis unit performs a detailed analysis of important conversation content. The analysis unit can also perform a concise analysis of general conversation content. The analysis unit can also perform a particularly detailed analysis of conversation content related to the subject's health condition. For example, the analysis unit performs a detailed analysis of important conversation content. The analysis unit performs a concise analysis of general conversation content. The analysis unit performs a particularly detailed analysis of conversation content related to the subject's health condition. In this way, by adjusting the level of detail of the analysis according to the importance of the conversation, important conversation content can be analyzed in detail. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the level of detail of the analysis based on the importance of the conversation using the generation AI.

[0078] The analysis unit can apply different analysis algorithms depending on the category of the conversation (e.g., medical, everyday conversation) during analysis. The analysis unit can, for example, apply different analysis algorithms depending on the category of the conversation during analysis. For example, the analysis unit can apply a specific health analysis algorithm to conversation content related to health. The analysis unit can also apply a general analysis algorithm to conversation content related to daily life. The analysis unit can also apply an emotion analysis algorithm to conversation content related to emotions. For example, the analysis unit can apply a specific health analysis algorithm to conversation content related to health. The analysis unit can apply a general analysis algorithm to conversation content related to daily life. The analysis unit can apply an emotion analysis algorithm to conversation content related to emotions. This allows for applying an appropriate analysis algorithm depending on the category of the conversation, thereby providing more accurate analysis results. Some or all of the above-mentioned processing in the analysis unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the analysis unit can apply different analysis algorithms depending on the category of the conversation using a generation AI.

[0079] During analysis, the analysis unit can improve the accuracy (e.g., precision) of the analysis by referring to past analysis results of the subject. During analysis, the analysis unit can improve the accuracy of the analysis by referring to past analysis results of the subject. For example, the analysis unit corrects the current analysis result based on the past analysis results of the subject. The analysis unit can also extract specific trends from the past analysis results of the subject and reflect them in the current analysis. Furthermore, the analysis unit can optimize the analysis algorithm by referring to the past analysis results of the subject. For example, the analysis unit corrects the current analysis result based on the past analysis results of the subject. Specific trends are extracted from the past analysis results and reflected in the current analysis. The analysis algorithm is optimized by referring to the past analysis results. In this way, the accuracy of the current analysis result can be improved by referring to the past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can improve the accuracy of the analysis by using a generation AI to refer to the past analysis results of the subject.

[0080] The analysis unit can estimate the subject's emotion (e.g., joy, anger, sadness) and adjust the length of the analysis based on the estimated emotion. The analysis unit, for example, estimates the subject's emotion and adjusts the length of the analysis based on the estimated emotion. For example, if the subject is stressed, the analysis unit provides a short and concise analysis result. Also, if the subject is relaxed, the analysis unit can provide a detailed analysis result. Furthermore, if the subject is tired, the analysis unit can provide a concise analysis result. For example, if the subject is stressed, the analysis unit provides a short and concise analysis result. If the subject is relaxed, the analysis unit provides a detailed analysis result. If the subject is tired, the analysis unit provides a concise analysis result. In this way, by adjusting the length of the analysis according to the subject's emotion, more appropriate analysis results can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the analysis unit may use the generation AI to estimate the subject's emotions and adjust the length of the analysis based on the estimated emotions.

[0081] The analysis unit can determine the priority of analysis based on the time of occurrence of the conversation (e.g., the most recent conversation) during analysis. The analysis unit can, for example, determine the priority of analysis based on the time of occurrence of the conversation during analysis. For example, the analysis unit prioritizes analyzing the content of the most recent conversation. The analysis unit can also prioritize analyzing the content of the conversation that occurred during a specific time period. Furthermore, the analysis unit can also prioritize analyzing the content of the conversation related to the subject's health condition. For example, the analysis unit prioritizes analyzing the content of the most recent conversation. The analysis unit prioritizes analyzing the content of the conversation that occurred during a specific time period. The analysis unit prioritizes analyzing the content of the conversation related to the health condition. In this way, by determining the priority of analysis based on the time of occurrence of the conversation, important content of the conversation can be analyzed preferentially. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can determine the priority of analysis based on the time of occurrence of the conversation using a generation AI.

[0082] The analysis unit can adjust the order of analysis based on the relevance of the conversations (e.g., conversations about the same topic) during analysis. The analysis unit can, for example, adjust the order of analysis based on the relevance of the conversations during analysis. For example, the analysis unit prioritizes analyzing important conversation content. The analysis unit can also prioritize analyzing highly relevant conversation content. Furthermore, the analysis unit can also prioritize analyzing conversation content related to the subject's health condition. For example, the analysis unit prioritizes analyzing important conversation content. Highly relevant conversation content. Conversation content related to the health condition can be prioritized. In this way, by adjusting the order of analysis based on the relevance of the conversations, important conversation content can be prioritized for analysis. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the order of analysis based on the relevance of the conversations using the generation AI.

[0083] During analysis, the analysis unit can adjust the use of technical terms in the analysis according to the subject's level of expertise (e.g., whether or not the subject has medical knowledge). The analysis unit, for example, adjusts the use of technical terms in the analysis according to the subject's level of expertise during analysis. For example, if the subject has technical expertise, the analysis unit uses detailed technical terms. Furthermore, if the subject has general knowledge, the analysis unit can also use concise technical terms. Furthermore, if the subject does not have technical expertise, the analysis unit can provide analysis results in easy-to-understand language. For example, if the subject has technical expertise, the analysis unit uses detailed technical terms. If the subject has general knowledge, the analysis unit uses concise technical terms. If the subject does not have technical expertise, the analysis unit provides analysis results in easy-to-understand language. In this way, by adjusting the use of technical terms in the analysis according to the subject's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the use of technical terms in the analysis according to the subject's level of expertise.

[0084] The notification unit can estimate the emotion of the target person (e.g., joy, anger, sadness) and adjust the notification method based on the estimated emotion. The notification unit, for example, estimates the emotion of the target person and adjusts the notification method based on the estimated emotion. For example, if the target person is stressed, the notification unit provides a concise and easy-to-understand notification. Furthermore, if the target person is relaxed, the notification unit can also provide a detailed notification. Furthermore, if the target person is tired, the notification unit can also provide a notification that focuses on the main points. For example, if the target person is stressed, the notification unit provides a concise and easy-to-understand notification. If the target person is relaxed, the notification unit provides a detailed notification. If the target person is tired, the notification unit provides a notification that focuses on the main points. In this way, by adjusting the notification method according to the target person's emotion, more appropriate notification can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI or without AI. For example, the notification unit can use the generation AI to estimate the target person's emotions and adjust the notification method based on the estimated emotions.

[0085] The notification unit can adjust the level of detail of the notification based on the importance (e.g., urgency) of the abnormality at the time of notification. The notification unit, for example, adjusts the level of detail of the notification based on the importance of the abnormality at the time of notification. For example, the notification unit provides detailed notification for important abnormalities. The notification unit can also provide brief notification for general abnormalities. The notification unit can also provide particularly detailed notification for abnormalities related to the subject's health condition. For example, the notification unit provides detailed notification for important abnormalities. The notification unit provides brief notification for general abnormalities. The notification unit provides particularly detailed notification for abnormalities related to the subject's health condition. In this way, by adjusting the level of detail of the notification according to the importance of the abnormality, important abnormalities can be notified in detail. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI or may be performed without using AI. For example, the notification unit can adjust the level of detail of the notification based on the importance of the abnormality using a generation AI.

[0086] The notification unit can apply different notification algorithms depending on the category of the abnormality (e.g., medical, daily life) when making a notification. The notification unit, for example, applies different notification algorithms depending on the category of the abnormality when making a notification. For example, the notification unit applies a specific health notification algorithm to an abnormality related to health. The notification unit can also apply a general notification algorithm to an abnormality related to daily life. The notification unit can also apply an emotion notification algorithm to an abnormality related to emotion. For example, the notification unit applies a specific health notification algorithm to an abnormality related to health. The notification unit applies a general notification algorithm to an abnormality related to daily life. The notification unit applies an emotion notification algorithm to an abnormality related to emotion. This allows for more accurate notification by applying an appropriate notification algorithm depending on the category of the abnormality. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can use a generation AI to apply different notification algorithms depending on the category of the abnormality.

[0087] The notification unit can improve the accuracy (e.g., precision) of the notification by referring to the target person's past notification results when notifying the target person. The notification unit can improve the accuracy of the notification by referring to the target person's past notification results when notifying the target person. For example, the notification unit corrects the current notification result based on the target person's past notification results. The notification unit can also extract specific trends from the target person's past notification results and reflect them in the current notification. Furthermore, the notification unit can optimize the notification algorithm by referring to the target person's past notification results. For example, the notification unit corrects the current notification result based on the target person's past notification results. The notification unit extracts specific trends from the past notification results and reflects them in the current notification. The notification algorithm is optimized by referring to the past notification results. In this way, the accuracy of the current notification result can be improved by referring to the past notification results. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can improve the accuracy of the notification by using a generation AI to refer to the target person's past notification results.

[0088] The notification unit can estimate the emotion of the target person (e.g., joy, anger, sadness) and adjust the length of the notification based on the estimated emotion. The notification unit, for example, estimates the emotion of the target person and adjusts the length of the notification based on the estimated emotion. For example, if the target person is stressed, the notification unit provides a short and to-the-point notification. Furthermore, if the target person is relaxed, the notification unit can also provide a detailed notification. Furthermore, if the target person is tired, the notification unit can also provide a concise notification. For example, if the target person is stressed, the notification unit provides a short and to-the-point notification. If the target person is relaxed, the notification unit provides a detailed notification. If the target person is tired, the notification unit can also provide a concise notification. In this way, by adjusting the length of the notification according to the target person's emotion, more appropriate notification can be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the notification unit can be performed, for example, using AI or without AI. For example, the notification unit can use the generation AI to estimate the target person's emotions and adjust the length of the notification based on the estimated emotions.

[0089] The notification unit can determine the priority of notifications based on the time of occurrence of an abnormality (e.g., the most recent abnormality) at the time of notification. The notification unit, for example, determines the priority of notifications based on the time of occurrence of an abnormality at the time of notification. For example, the notification unit prioritizes notification of recently occurring abnormalities. The notification unit can also prioritize notification of abnormalities that occurred in a specific time period. Furthermore, the notification unit can also prioritize notification of abnormalities related to the subject's health condition. For example, the notification unit prioritizes notification of recently occurring abnormalities. The notification unit prioritizes notification of abnormalities that occurred in a specific time period. The notification unit prioritizes notification of abnormalities related to the subject's health condition. In this way, by determining the priority of notifications based on the time of occurrence of an abnormality, it is possible to prioritize notification of important abnormalities. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can use a generation AI to determine the priority of notifications based on the time of occurrence of an abnormality.

[0090] The notification unit can adjust the order of notifications based on the relevance of the anomalies (e.g., anomalies related to the same topic) when notifying. The notification unit, for example, adjusts the order of notifications based on the relevance of the anomalies when notifying. For example, the notification unit prioritizes notifying important anomalies. The notification unit can also prioritize notifying highly relevant anomalies. Furthermore, the notification unit can also prioritize notifying anomalies related to the health condition of the subject. For example, the notification unit prioritizes notifying important anomalies. The notification unit prioritizes notifying highly relevant anomalies. The notification unit prioritizes notifying anomalies related to the health condition. In this way, by adjusting the order of notifications based on the relevance of the anomalies, important anomalies can be prioritized. Some or all of the above-described processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can adjust the order of notifications based on the relevance of the anomalies using a generation AI.

[0091] The notification unit can adjust the use of technical terms in the notification depending on the subject's level of expertise (e.g., whether or not the subject has medical knowledge) when notifying the subject. The notification unit can, for example, adjust the use of technical terms in the notification depending on the subject's level of expertise when notifying the subject. For example, if the subject has technical knowledge, the notification unit uses detailed technical terms. Also, if the subject has general knowledge, the notification unit can use concise technical terms. Furthermore, if the subject does not have technical knowledge, the notification unit can provide the notification in easy-to-understand language. For example, if the subject has technical knowledge, the notification unit uses detailed technical terms. If the subject has general knowledge, the notification unit uses concise technical terms. If the subject does not have technical knowledge, the notification unit provides the notification in easy-to-understand language. In this way, by adjusting the use of technical terms in the notification depending on the subject's level of expertise, the notification can be made easier to understand. Some or all of the above-mentioned processing in the notification unit may be performed, for example, using AI, or may be performed without using AI. For example, the notification unit can adjust the use of technical terms in the notification depending on the subject's level of expertise using a generation AI. === Hard Collateral 1-1 === Each of the multiple elements, including the recording unit, analysis unit, and notification unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the recording unit is realized by the control unit 46A of the smart device 14 and records the content of the conversation between the subject and the generating AI, the speaking style, and the time from question to answer. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the recorded data to detect abnormalities. The notification unit is realized, for example, by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12 and notifies a family member or doctor in charge if an abnormality is detected. The recording unit can, for example, estimate the subject's emotions and adjust the conversation recording method based on the estimated emotions. === Hard Collateral 1-2 === Each of the multiple elements, including the recording unit, analysis unit, and notification unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the recording unit is realized by the control unit 46A of the smart glasses 214 and records the content of the conversation between the subject and the generation AI, the speaking style, and the time from question to answer. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the recorded data to detect abnormalities. The notification unit is realized, for example, by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12 and notifies a family member or doctor in charge if an abnormality is detected. The recording unit can, for example, estimate the subject's emotions and adjust the conversation recording method based on the estimated emotions. === Hard Collateral 1-3 === Each of the multiple elements, including the recording unit, analysis unit, and notification unit, described above, is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the recording unit is realized by the control unit 46A of the headset-type terminal 314 and records the content of the conversation between the subject and the generation AI, the speaking style, and the time from question to answer. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the recorded data to detect abnormalities. The notification unit is realized, for example, by the control unit 46A of the headset-type terminal 314 or the specific processing unit 290 of the data processing device 12 and notifies a family member or doctor in charge if an abnormality is detected. For example, the recording unit can estimate the subject's emotions and adjust the conversation recording method based on the estimated emotions. === Hard Collateral 1-4 === Each of the multiple elements, including the recording unit, analysis unit, and notification unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the recording unit is realized by the control unit 46A of the robot 414 and records the content of the conversation between the subject and the generating AI, the speaking style, and the time from question to answer. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the recorded data to detect abnormalities. The notification unit is realized, for example, by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12 and notifies family members or the doctor in charge if an abnormality is detected. The recording unit can, for example, estimate the subject's emotions and adjust the method of recording the conversation based on the estimated emotions.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] When recording the content of a subject's conversation, the recording unit can adjust the frequency and timing of recording taking into account the subject's lifestyle rhythm and daily activity pattern. For example, if the subject is active in the morning, the recording unit can prioritize recording morning conversations. Also, if the subject is relaxed at night, the recording unit can record nighttime conversations in detail. Furthermore, the recording unit can particularly carefully record weekend conversations based on the subject's weekend activity pattern. This allows for more appropriate data to be collected according to the subject's lifestyle rhythm and activity pattern.

[0094] When analyzing the subject's conversation content, the analysis unit can improve the accuracy of the analysis by referring to the subject's past health checkup results and medical records. For example, the analysis unit can analyze the current conversation content based on the subject's past health checkup results and detect abnormalities. The analysis unit can also extract specific medical history and symptoms from the subject's medical records and reflect them in the analysis. Furthermore, the analysis unit can optimize the analysis algorithm by referring to the subject's past medical data. This makes it possible to provide more accurate analysis results by utilizing past medical data.

[0095] When an abnormality is detected, the notification unit can notify not only the subject's family and doctor, but also local nursing care services and support organizations. For example, when an abnormality is detected, the notification unit notifies local nursing care services by email or app notification. The notification unit can also notify support organizations, including details of the abnormality. Furthermore, in an emergency, the notification unit can automatically call local nursing care services to notify them of the abnormality. This allows for a rapid response in cooperation with the local support network when an abnormality is detected.

[0096] When recording the content of a conversation of a subject, the recording unit can classify conversation topics based on the subject's hobbies and interests and preferentially record conversations related to specific topics. For example, if the subject is interested in music, the recording unit can preferentially record conversations related to music. Also, if the subject is interested in sports, the recording unit can record conversations related to sports in detail. Furthermore, if the subject is interested in traveling, the recording unit can particularly carefully record conversations related to travel. This makes it possible to collect more useful data according to the subject's hobbies and interests.

[0097] When analyzing the content of a subject's conversation, the analysis unit can adjust the analysis algorithm taking into account the subject's cultural background and linguistic characteristics. For example, if the subject speaks a specific dialect, the analysis unit applies an analysis algorithm that corresponds to that dialect. The analysis unit can also reflect specific cultural expressions and phrases in the analysis based on the subject's cultural background. Furthermore, if the subject speaks multiple languages, the analysis unit can apply analysis algorithms that correspond to multiple languages. This makes it possible to provide more accurate analysis results that correspond to the subject's cultural background and linguistic characteristics.

[0098] The recording unit can estimate the subject's emotions and adjust the conversation recording method based on the estimated emotions. For example, if the subject is feeling happy, the recording unit records detailed conversation content and collects more data. Also, if the subject is feeling angry, the recording unit can simplify the conversation recording and record only the minimum amount of information necessary. Furthermore, if the subject is feeling sad, the recording unit can adjust the conversation recording to be completed in a shorter period of time. In this way, by adjusting the conversation recording method according to the subject's emotions, more appropriate data can be collected.

[0099] The analysis unit can estimate the subject's emotions and adjust the way the analysis is presented based on the estimated emotions. For example, if the subject is feeling happy, the analysis unit can provide detailed analysis results. If the subject is feeling angry, the analysis unit can also provide concise and easy-to-understand analysis results. Furthermore, if the subject is feeling sad, the analysis unit can also provide analysis results that focus on the main points. In this way, by adjusting the way the analysis is presented depending on the subject's emotions, more appropriate analysis results can be provided.

[0100] The notification unit can estimate the emotion of the target person and adjust the notification method based on the estimated emotion. For example, if the target person is feeling happy, the notification unit can provide a detailed notification. If the target person is feeling angry, the notification unit can also provide a concise and easy-to-understand notification. Furthermore, if the target person is feeling sad, the notification unit can also provide a notification that focuses on the main points. In this way, by adjusting the notification method according to the target person's emotion, more appropriate notifications can be provided.

[0101] The recording unit can estimate the emotion of the subject and determine the priority of the conversation to be recorded based on the estimated emotion. For example, if the subject is feeling happy, the recording unit can prioritize recording detailed conversation content. Also, if the subject is feeling angry, the recording unit can prioritize recording important conversation content. Furthermore, if the subject is feeling sad, the recording unit can prioritize recording conversation content that can be completed in a short time. In this way, by determining the priority of the conversation to be recorded according to the emotion of the subject, important conversation content can be recorded with priority.

[0102] The analysis unit can estimate the subject's emotions and adjust the length of the analysis based on the estimated emotions. For example, if the subject is feeling happy, the analysis unit can provide a detailed analysis result. If the subject is feeling angry, the analysis unit can also provide a short, concise analysis result. Furthermore, if the subject is feeling sad, the analysis unit can also provide a concise analysis result. In this way, by adjusting the length of the analysis according to the subject's emotions, more appropriate analysis results can be provided.

[0103] The processing flow of the second embodiment will be briefly explained below.

[0104] Step 1: The recording unit records the content of the conversation between the subject and the generating AI, the speaking style, and the time from question to answer. For example, the recording unit saves the content of the subject's conversation with the generating AI as text data. The recording unit can also record the subject's speaking style characteristics (e.g., tone of voice, speed, accent, etc.) as audio data. Furthermore, the recording unit can measure the time from question to answer in seconds and save this as data. For example, the recording unit measures the time between the generating AI asking, "What did you do today?" and the subject replying, "I went for a walk today." Step 2: The analysis unit uses the generation AI to analyze the data recorded by the recording unit and detect anomalies. For example, the analysis unit uses natural language processing technology to analyze the content of the conversation and detect anomalies. For example, the analysis unit can analyze the content of the conversation and detect anomalies using morphological analysis. The analysis unit can also analyze changes in the subject's speaking style and reaction time to detect anomalies. For example, the analysis unit can analyze changes in the subject's tone and speed of voice to detect anomalies. Step 3: The notification unit notifies the family or the doctor in charge based on the abnormality detected by the analysis unit. For example, if an abnormality is detected, the notification unit notifies the family or the doctor in charge by email or app notification. For example, the notification unit sends a notification saying, "An abnormality has been observed in the subject's speaking style."

[0105] 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.

[0106] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0107] 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.

[0108] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0109] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0110] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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).

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0125] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0126] 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.

[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 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.

[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. 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.

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

[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 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.

[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 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.

[0140] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0141] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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).

[0162] 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.

[0163] 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."

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] [Explanation of symbols]

[0177] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. A recording section records the content of the conversation, speaking style, and the time from question to answer; an analysis unit that analyzes the data recorded by the recording unit and detects abnormalities; a notification unit that notifies a family member or a doctor in charge based on the abnormality detected by the analysis unit. A system characterized by:

2. The recording unit Record the content of the conversation between the subject and the generated AI, the way they speak, and the time between the question and the answer.

2. The system of claim 1.

3. The analysis unit Analyze conversation content using natural language processing technology and detect anomalies 2. The system of claim 1.

4. The notification unit Notify family members or doctors if an abnormality is detected 2. The system of claim 1.

5. The analysis unit Analyze changes in the subject's speaking style and reaction time to detect abnormalities 2. The system of claim 1.

6. The notification unit Any abnormalities detected by the generated AI will be sent to family members or doctors via email or app notification.

2. The system of claim 1.

7. The recording unit Inferring the subject's emotions and adjusting how the conversation is recorded based on those emotions 2. The system of claim 1.

8. The recording unit Analyze the target person's past conversation history and select the optimal recording method 2. The system of claim 1.

9. The recording unit When recording conversations, filter them based on the subject's current health and living situation.

2. The system of claim 1.

10. The recording unit When recording conversations, choose the best recording method based on the input method of the subject 2. The system of claim 1.

Images