System

Abstract

To provide a system capable of detecting the decline of cognitive function at an early stage to take appropriate measures.SOLUTION: A system in an embodiment includes a conversation promotion unit, an analysis unit, a determination unit, a providing unit, and a storage unit. The conversation promotion unit facilitates conversation. The analysis unit analyzes the conversation history generated by the conversation promotion unit. The determination unit determines decreased cognitive function based on the results analyzed by the analysis unit. The providing unit provides brain training or quizzes based on the results determined by the determination unit. The storage unit stores the results provided by the providing unit to share the same with family members or healthcare professionals.SELECTED DRAWING: Figure 1

Description

[Technical field]

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

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

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] With conventional technology, it was difficult to detect a decline in cognitive function early and take appropriate measures.

[0005] The system according to the embodiment aims to detect a decline in cognitive function at an early stage and take appropriate measures. [Means for solving the problem]

[0006] The system according to the embodiment includes a conversation promotion unit, an analysis unit, a determination unit, a provision unit, and a storage unit. The conversation promotion unit promotes conversation. The analysis unit analyzes the conversation history generated by the conversation promotion unit. The determination unit determines a decline in cognitive function based on the result of the analysis by the analysis unit. The provision unit provides brain training or quizzes based on the result determined by the determination unit. The storage unit stores the result provided by the provision unit and shares it with family members or medical professionals. Effect of the Invention

[0007] The system according to the embodiment can detect a decline in cognitive function at an early stage and take appropriate measures. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The dementia prevention system according to the embodiment of the present invention is a system that simulates "interaction with people," which is effective as part of dementia prevention. In this system, the user starts a conversation with the generation AI, and the generation AI generates an appropriate response to the user's remarks and continues the conversation. For example, if the user says, "The weather is nice today," the generation AI responds, "Yes, it might be good to go for a walk." In this way, the generation AI promotes natural conversation with the user. Next, the conversation history is analyzed by the generation AI. The generation AI analyzes the content and frequency of the conversation, the user's response, etc., and determines whether there is a suspicion of cognitive decline or dementia. For example, if the user repeats the same topic or changes the choice of words, it can detect signs of cognitive decline or dementia. If there is a suspicion of cognitive decline or dementia, the generation AI provides the user with simple brain training or quizzes. For example, it may provide quizzes to test memory or calculation problems to stimulate the user's cognitive function. This can maintain and improve the user's cognitive function. Furthermore, a summary of the conversation history and the diagnosis results are kept as history and shared with specific people such as family members, nurses, and home helpers. This allows the state of the user's cognitive function to be understood and appropriate support to be provided. For example, a family member can notice a decline in the user's cognitive function and visit a medical institution early. This system simulates "interaction with people" for dementia prevention, and can maintain and improve the user's cognitive function. In addition, family members, nurses, home helpers, etc. can understand the state of the user's cognitive function and provide appropriate support. This allows the dementia prevention system to maintain and improve the user's cognitive function.

[0029] The dementia prevention system according to the embodiment includes a conversation promotion unit, an analysis unit, a determination unit, a provision unit, and a storage unit. The conversation promotion unit uses a generation AI to generate an appropriate response to a user's statement and continue the conversation. For example, if the user says, "The weather is nice today," the generation AI responds, "Yes, it might be nice to go for a walk." The conversation promotion unit can also estimate the user's emotions and select a conversation topic based on the estimated emotions. For example, if the user is sad, the generation AI selects a topic that includes words of encouragement or comfort. The analysis unit uses the generation AI to analyze the conversation history, and analyzes the content and frequency of the conversation and the user's reaction. For example, when a user repeats the same topic or changes the way of choosing words, it detects signs of cognitive function decline. The determination unit determines the decline in cognitive function based on the results analyzed by the analysis unit using the generation AI. For example, it determines the decline in cognitive function using a specific behavioral pattern or a scoring system. The provision unit provides brain training and quizzes based on the results determined by the determination unit using the generation AI. For example, quizzes to test memory and calculation problems are given to stimulate the user's cognitive function. The storage unit uses the generation AI to store the results provided by the providing unit and share them with specific people. For example, summaries of conversation history and diagnosis results are stored and shared with family members, nurses, home helpers, etc. In this way, the dementia prevention system according to the embodiment can maintain and improve the user's cognitive function.

[0030] The conversation promotion unit uses the generation AI to generate an appropriate response to the user's statement and continue the conversation. For example, if the user says, "The weather is nice today," the generation AI responds, "Yes, it might be nice to go for a walk." The generation AI uses natural language processing technology to understand the user's statement and generate an appropriate response. Specifically, it analyzes the user's statement and performs grammatical analysis and semantic analysis to understand its context and intent. In addition, the generation AI can generate more personalized responses by taking into account past conversation history and the user's preferences. For example, if the user has previously said, "I like walks," the generation AI responds, "The weather is nice today, so it might be nice to go for a walk." The conversation promotion unit can also estimate the user's emotions and select a conversation topic based on the estimated emotions. Voice analysis and facial expression recognition technology can be used for emotion estimation. For example, emotions can be estimated from the user's tone of voice and speaking style, and if the user is sad, the generation AI selects a topic that includes words of encouragement and comfort. This allows the conversation promotion unit to provide conversation that is in tune with the user's emotions, helping to stabilize the user's psychology. Furthermore, the conversation promotion unit can select conversation topics based on the user's interests and concerns. For example, if the user enjoys gardening as a hobby, the generation AI can arouse the user's interest and stimulate conversation by asking questions such as, "What kind of flowers have you planted recently?" This allows the conversation promotion unit to maintain and improve cognitive function through natural conversation with the user.

[0031] The analysis unit uses the generation AI to analyze the conversation history, and analyzes the content and frequency of the conversation, as well as the user's reaction. Specifically, the content of the conversation is saved as text data and analyzed using natural language processing technology. For example, signs of cognitive decline are detected when the user repeats the same topic or changes in the choice of words. When analyzing the content of the conversation, the generation AI can detect changes in the frequency of keyword appearance and context. For example, if the user repeatedly makes statements such as "I talked about the same thing yesterday," the generation AI can detect this pattern and suggest the possibility of cognitive decline. In addition, voice analysis and facial expression recognition technology can be used to analyze the user's reaction. For example, the user's tone of voice, speaking style, and changes in facial expressions are analyzed to estimate the user's emotions and psychological state. This allows the analysis unit to capture changes in the user's cognitive function from multiple angles. In addition, the analysis unit can also analyze the frequency and duration of conversations. For example, if the user's frequency of conversations has decreased or the duration of conversations has become shorter than before, the generation AI can detect the change and evaluate it as a sign of cognitive decline. This enables the analysis unit to detect changes in the user's cognitive function at an early stage and provide information for taking appropriate measures.

[0032] The judgment unit judges the decline in cognitive function based on the results of the analysis by the analysis unit using the generation AI. Specifically, the cognitive function decline is judged using a specific behavioral pattern or a scoring system. For example, the frequency with which the user repeats the same topic, changes in the choice of words, changes in the frequency and duration of conversations, etc. are scored and evaluated comprehensively. The generation AI quantifies the state of the user's cognitive function based on these data, and judges the decline in cognitive function if it exceeds a certain standard. The judgment unit can also evaluate changes in the user's cognitive function by comparing it with past data. For example, it compares past conversation history with current conversation history to evaluate the progress of the decline in cognitive function. This allows the judgment unit to accurately grasp the state of the user's cognitive function and provide information for taking appropriate measures. Furthermore, the judgment unit can detect unusual patterns or abnormal data using an anomaly detection algorithm and issue an early warning. For example, if a user suddenly stops talking or suddenly changes the way he or she chooses words, the generation AI detects the abnormality and issues an early warning. This allows the judgment unit to detect the decline in the user's cognitive function early and respond quickly.

[0033] The providing unit provides brain training and quizzes based on the results determined by the determining unit using the generating AI. Specifically, it provides quizzes and calculation problems that test memory, stimulating the user's cognitive function. The generating AI can select brain training and quizzes of appropriate difficulty and content according to the state of the user's cognitive function. For example, if the user's memory is declining, the generating AI will provide a quiz to strengthen the memory. It can also analyze the user's reactions and answers and provide appropriate feedback. For example, if the user answers the quiz correctly, the generating AI will provide encouraging words such as "That's great!" to motivate the user. Furthermore, the providing unit can customize the content of the brain training and quizzes based on the user's interests and concerns. For example, if the user is interested in history, the generating AI can provide a quiz about history to draw out the user's interest and allow the user to enjoy brain training. This allows the providing unit to provide effective brain training and quizzes to maintain and improve the user's cognitive function.

[0034] The storage unit uses the generation AI to store the results provided by the provision unit and share them with specific people. Specifically, it stores a summary of the conversation history and the diagnosis results, and shares them with family members, nurses, home helpers, etc. The generation AI can organize the conversation history and diagnosis results and store them in an easy-to-understand format. For example, it organizes the conversation history by date and highlights important points and abnormal patterns. It also visualizes the diagnosis results as graphs and charts, so that the state of the user's cognitive function can be understood at a glance. Furthermore, the storage unit can safely manage the stored data and set access restrictions as necessary. For example, it allows only specific people such as family members, nurses, and home helpers to access the data. In addition, the storage unit can regularly back up data to prevent data loss or damage. This allows the storage unit to accurately record the state of the user's cognitive function and provide information to take appropriate measures. Furthermore, the storage unit can analyze long-term trends and patterns based on the stored data. For example, it can grasp the tendency of changes in the user's cognitive function based on past data and predict future risks. This enables the storage unit to provide information for taking effective measures to maintain and improve the user's cognitive function.

[0035] The conversation promotion unit can generate an appropriate response to the user's utterance. The conversation promotion unit uses the generation AI to generate an appropriate response to the user's utterance. For example, if the user says, "The weather is nice today," the generation AI responds, "Yes, it might be nice to go for a walk." The conversation promotion unit can also estimate the user's emotions and select a conversation topic based on the estimated emotions. For example, if the user is sad, the generation AI selects a topic that includes words of encouragement and comfort. This can promote natural conversation with the user.

[0036] The analysis unit can analyze the content and frequency of conversations, as well as the user's reactions. The analysis unit uses generative AI to analyze the conversation history, and analyzes the content and frequency of conversations, as well as the user's reactions. For example, it detects signs of cognitive decline, such as when a user repeats the same topic or when the choice of words changes. The analysis unit can use techniques such as text analysis and sentiment analysis to perform a detailed analysis of the content and frequency of conversations, as well as the user's reactions. This allows the state of the user's cognitive function to be understood.

[0037] The judgment unit can detect signs of cognitive decline. The judgment unit judges the decline in cognitive function based on the results of the analysis by the analysis unit using the generation AI. For example, the judgment unit judges the decline in cognitive function using a specific behavioral pattern or a scoring system. The judgment unit can detect signs of cognitive decline using a diagnostic algorithm. This makes it possible to detect the decline in cognitive function early.

[0038] The providing unit can provide quizzes or calculation problems that test memory. The providing unit provides brain training and quizzes based on the results determined by the determining unit using the generation AI. For example, quizzes that test memory and calculation problems are presented to stimulate the user's cognitive function. The providing unit can provide brain training and quizzes that are suitable for the user, taking into consideration the type of problem and difficulty setting. This can maintain and improve the user's cognitive function.

[0039] The storage unit can store a summary of the conversation history and the diagnosis results, and share them with family members or medical professionals. The storage unit stores the results provided by the provision unit using the generation AI, and shares them with specific people. For example, the storage unit can store a summary of the conversation history and the diagnosis results, and share them with family members, nurses, home helpers, etc. The storage unit can store data in an appropriate manner, taking into consideration the data format, storage period, etc. This allows the state of the user's cognitive function to be shared with family members, nurses, home helpers, etc., and appropriate support can be provided.

[0040] The conversation promotion unit can analyze the user's past conversation history and select the optimal way to proceed with the conversation. The conversation promotion unit uses a generation AI to analyze the user's past conversation history and select the optimal way to proceed with the conversation. For example, topics that the user has shown interest in in the past can be brought up again. Topics that the user has avoided in the past can also be avoided. Furthermore, topics that the user has talked about extensively in the past can also be selected with priority. This makes it possible to select the optimal way to proceed with the conversation for the user based on the past conversation history.

[0041] The conversation promotion unit can customize the content of the conversation based on the user's current interests and concerns when promoting the conversation. The conversation promotion unit uses the generation AI to customize the content of the conversation based on the user's current interests and concerns when promoting the conversation. For example, the user can talk about a book that he or she recently read. The user can also talk about a movie that he or she recently watched. Furthermore, the user can talk about an event that he or she recently attended. This makes it possible to improve the quality of the conversation by customizing the content of the conversation based on the user's current interests and concerns.

[0042] The conversation promotion unit can prioritize selecting highly relevant topics based on the user's geographic location information when promoting a conversation. The conversation promotion unit prioritizes selecting highly relevant topics taking into account the user's geographic location information when promoting a conversation using the generation AI. For example, the user can talk about news from the area where the user lives. The user can also talk about places that the user has recently visited. Furthermore, the user can talk about travel destinations that the user is planning. This makes it possible to improve the quality of the conversation by selecting highly relevant topics based on the user's geographic location information.

[0043] The conversation promotion unit can analyze the user's social media activity and select related topics when promoting a conversation. The conversation promotion unit uses the generation AI to analyze the user's social media activity and select related topics when promoting a conversation. For example, the user can talk about articles that they recently shared. The user can also talk about posts that they recently commented on. Furthermore, the user can talk about content that they recently "liked." This makes it possible to improve the quality of conversation by selecting related topics based on the user's social media activity.

[0044] The analysis unit can adjust the level of detail of the analysis based on the importance of the conversation when analyzing the conversation. The analysis unit can adjust the level of detail of the analysis based on the importance of the conversation when analyzing the conversation using the generative AI. For example, important topics can be analyzed in detail. General topics can also be analyzed simply. Furthermore, topics emphasized by the user can be analyzed intensively. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the conversation.

[0045] The analysis unit can apply different analysis algorithms depending on the category of the conversation when analyzing the conversation. The analysis unit can apply different analysis algorithms depending on the category of the conversation when analyzing the conversation using the generative AI. For example, a health-related algorithm can be applied to topics about health. A hobby-related algorithm can also be applied to topics about hobbies. Furthermore, a family-related algorithm can be applied to topics about family. In this way, the analysis accuracy can be improved by applying an appropriate analysis algorithm depending on the category of the conversation.

[0046] When analyzing a conversation, the analysis unit can determine the priority of the analysis based on the time when the conversation was submitted. When analyzing a conversation using the generative AI, the analysis unit determines the priority of the analysis based on the time when the conversation was submitted. For example, recent conversations can be analyzed preferentially. Also, past conversations can be postponed. Furthermore, conversations that were concentrated in a specific period can be analyzed preferentially. This enables efficient analysis by determining the priority of the analysis based on the time when the conversation was submitted.

[0047] The analysis unit can adjust the order of analysis based on the relevance of the conversations when analyzing the conversations. The analysis unit can adjust the order of analysis based on the relevance of the conversations when analyzing the conversations using the generative AI. For example, highly relevant conversations can be analyzed with priority. Less relevant conversations can also be postponed. Furthermore, conversations related to a specific theme can be analyzed together. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the conversations.

[0048] When determining whether cognitive function has declined, the determination unit can improve the accuracy of the determination by referring to the user's past cognitive function data. When determining whether cognitive function has declined using the generation AI, the determination unit can improve the accuracy of the determination by referring to the user's past cognitive function data. For example, the determination unit can refer to the user's past cognitive function test results. The determination unit can also refer to the user's past conversation history. Furthermore, the determination unit can also refer to the user's past health check results. In this way, the determination unit can improve the accuracy of the determination by referring to the past cognitive function data.

[0049] When determining whether cognitive function has declined, the determination unit can make a determination based on the user's living situation and health condition. When determining whether cognitive function has declined using the generation AI, the determination unit makes a determination taking into account the user's living situation and health condition. For example, the user's lifestyle habits are taken into account. The user's health condition can also be taken into account. Furthermore, the user's social activities can also be taken into account. This allows for a more accurate determination by taking into account the user's living situation and health condition.

[0050] The determination unit can make a determination taking into account the user's geographical location information when determining a decline in cognitive function. When using the generation AI to determine a decline in cognitive function, the determination unit makes a determination taking into account the user's geographical location information. For example, medical information about the area in which the user lives can be taken into account. Information about places recently visited by the user can also be taken into account. Furthermore, information about travel destinations that the user is planning can also be taken into account. As a result, by taking into account the user's geographical location information, a more accurate determination can be made.

[0051] The determination unit can improve the accuracy of the determination when determining a decline in cognitive function by analyzing the user's social media activity. When determining a decline in cognitive function using the generative AI, the determination unit can improve the accuracy of the determination by analyzing the user's social media activity. For example, the content of articles recently shared by the user can be analyzed. The content of posts recently commented on by the user can also be analyzed. Furthermore, the content of posts that the user recently "liked" can also be analyzed. In this way, the accuracy of the determination can be improved by analyzing the user's social media activity.

[0052] The providing unit can adjust the difficulty level by referring to the user's past scores when providing brain training exercises or quizzes. When providing brain training exercises or quizzes using the generation AI, the providing unit adjusts the difficulty level by referring to the user's past scores. For example, if the user has scored high in the past, the difficulty level can be increased. Also, if the user has scored low in the past, the difficulty level can be lowered. Furthermore, a quiz of an appropriate level of difficulty can be provided based on the user's past scores. This makes it possible to maintain and improve cognitive function by providing brain training exercises or quizzes of an appropriate level of difficulty based on the user's past scores.

[0053] The provision unit can customize the content based on the user's current cognitive function state when providing brain training exercises and quizzes. When providing brain training exercises and quizzes using the generation AI, the provision unit customizes the content based on the user's current cognitive function state. For example, if the user's cognitive function is declining, an easy quiz can be provided. Also, if the user's cognitive function is maintained, a standard quiz can be provided. Furthermore, if the user's cognitive function is improving, a more difficult quiz can be provided. This makes it possible to maintain and improve cognitive function by providing appropriate brain training exercises and quizzes based on the user's current cognitive function state.

[0054] The provision unit can select the content in consideration of the geographical location information of the user when providing brain training exercises and quizzes. When providing brain training exercises and quizzes using the generation AI, the provision unit selects the content in consideration of the geographical location information of the user. For example, a quiz related to the area where the user lives can be provided. In addition, a quiz related to places recently visited by the user can be provided. Furthermore, a quiz related to a travel destination that the user is planning can be provided. In this way, by providing appropriate brain training exercises and quizzes based on the geographical location information of the user, cognitive function can be maintained and improved.

[0055] When providing brain training exercises and quizzes, the provision unit can select the content by analyzing the user's social media activity. When providing brain training exercises and quizzes using the generation AI, the provision unit selects the content by analyzing the user's social media activity. For example, a quiz related to an article recently shared by the user can be provided. Also, a quiz related to a post recently commented on by the user can be provided. Furthermore, a quiz related to content that the user recently "liked" can be provided. In this way, by providing appropriate brain training exercises and quizzes based on the user's social media activity, cognitive function can be maintained and improved.

[0056] When saving data, the storage unit can optimize the storage method by referring to past saved data. When saving data using the generation AI, the storage unit optimizes the storage method by referring to past saved data. For example, the storage unit can refer to the format of the past saved data and save the data in the same format. In addition, the storage unit can refer to the contents of the past saved data and save highly relevant data preferentially. Furthermore, the storage location of the past saved data can be referenced and the data can be saved in the same location. In this way, the storage method can be optimized by referring to the past saved data, making data management more efficient.

[0057] When saving data, the storage unit can weight the saved data based on the time of submission of the conversation. When saving data using the generation AI, the storage unit weights the saved data based on the time of submission of the conversation. For example, recent conversation data can be saved preferentially. Also, past conversation data can be postponed. Furthermore, conversation data that was concentrated in a specific period can be saved preferentially. In this way, by weighting the saved data based on the time of submission of the conversation, important data can be saved preferentially.

[0058] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0059] The dementia prevention system can further include a sensor unit that acquires the user's physical activity data. The sensor unit collects data such as the user's number of steps, heart rate, and sleep patterns, and provides the data to the analysis unit. For example, the sensor unit can record how much the user walks on a daily basis to determine whether lack of exercise is affecting cognitive function. It can also monitor heart rate fluctuations and sleep quality to evaluate the effects of stress and fatigue on cognitive function. This makes it possible to comprehensively evaluate cognitive function based on physical activity data.

[0060] The conversation promotion unit can provide conversation topics customized based on the user's hobbies and interests. For example, if the user is interested in music, the latest music news and topics about artists can be provided. If the user enjoys gardening, topics about seasonal flowers and how to grow plants can be provided. Furthermore, if the user likes traveling, topics about recommended travel spots and local culture can be provided. This enables conversation according to the user's interests, improving the quality of the conversation.

[0061] The analysis unit can monitor a user's conversation patterns over the long term and detect changes. For example, it can detect subtle changes such as when a user no longer uses words that they used frequently before or when the tempo of their conversation slows down. It can also detect when the content of a user's conversation becomes increasingly monotonous or when the range of topics they discuss becomes narrower. This makes it possible to detect a decline in cognitive function early and take appropriate measures.

[0062] The determination unit can take into account the user's social activity data when determining the decline in the user's cognitive function. For example, data such as how frequently the user meets with friends and family and participates in social events can be collected and analyzed. The determination unit can also take into account how much online interaction the user has. This allows the impact of a decrease in social activity on cognitive function to be evaluated and a comprehensive determination to be made.

[0063] The providing unit can provide a rehabilitation program according to the state of the user's cognitive function. For example, a user with reduced cognitive function can be provided with simple memory training or a game that improves attention. Also, a user with maintained cognitive function can be provided with quizzes that encourage more complex problem solving or logical thinking. Furthermore, a user with improved cognitive function can be provided with challenging puzzles or strategy games. This enables appropriate rehabilitation according to the state of the user's cognitive function.

[0064] The process flow of the first embodiment will be briefly described below.

[0065] Step 1: The conversation promotion unit uses the generation AI to generate an appropriate response to the user's utterance and continue the conversation. For example, if the user says, "The weather is nice today," the generation AI responds, "Yes, maybe it would be nice to go for a walk." The conversation promotion unit can also estimate the user's emotions and select a conversation topic based on the estimated emotions. For example, if the user is sad, the generation AI selects a topic that includes words of encouragement and comfort. Step 2: The analysis unit uses the generative AI to analyze the conversation history, and analyzes the content and frequency of the conversations, as well as the user's reactions. For example, it detects signs of cognitive decline, such as when the user repeats the same topics or changes in word choice. Step 3: The judgment unit judges the decline in cognitive function based on the results of the analysis by the analysis unit using the generation AI. For example, the decline in cognitive function is judged using a specific behavioral pattern or a scoring system. Step 4: The provision unit uses the generation AI to provide brain training and quizzes based on the results determined by the determination unit. For example, it may provide quizzes to test memory or calculation problems to stimulate the user's cognitive functions. Step 5: The storage unit uses the generation AI to store the results provided by the provider unit and share them with specific people. For example, it stores a summary of the conversation history and the diagnosis results and shares them with family members, nurses, home helpers, etc.

[0066] (Example 2) The dementia prevention system according to the embodiment of the present invention is a system that simulates "interaction with people," which is effective as part of dementia prevention. In this system, the user starts a conversation with the generation AI, and the generation AI generates an appropriate response to the user's remarks and continues the conversation. For example, if the user says, "The weather is nice today," the generation AI responds, "Yes, it might be good to go for a walk." In this way, the generation AI promotes natural conversation with the user. Next, the conversation history is analyzed by the generation AI. The generation AI analyzes the content and frequency of the conversation, the user's response, etc., and determines whether there is a suspicion of cognitive decline or dementia. For example, if the user repeats the same topic or changes the choice of words, it can detect signs of cognitive decline or dementia. If there is a suspicion of cognitive decline or dementia, the generation AI provides the user with simple brain training or quizzes. For example, it may provide quizzes to test memory or calculation problems to stimulate the user's cognitive function. This can maintain and improve the user's cognitive function. Furthermore, a summary of the conversation history and the diagnosis results are kept as history and shared with specific people such as family members, nurses, and home helpers. This allows the state of the user's cognitive function to be understood and appropriate support to be provided. For example, a family member can notice a decline in the user's cognitive function and visit a medical institution early. This system simulates "interaction with people" for dementia prevention, and can maintain and improve the user's cognitive function. In addition, family members, nurses, home helpers, etc. can understand the state of the user's cognitive function and provide appropriate support. This allows the dementia prevention system to maintain and improve the user's cognitive function.

[0067] The dementia prevention system according to the embodiment includes a conversation promotion unit, an analysis unit, a determination unit, a provision unit, and a storage unit. The conversation promotion unit uses a generation AI to generate an appropriate response to a user's statement and continue the conversation. For example, if the user says, "The weather is nice today," the generation AI responds, "Yes, it might be nice to go for a walk." The conversation promotion unit can also estimate the user's emotions and select a conversation topic based on the estimated emotions. For example, if the user is sad, the generation AI selects a topic that includes words of encouragement or comfort. The analysis unit uses the generation AI to analyze the conversation history, and analyzes the content and frequency of the conversation and the user's reaction. For example, when a user repeats the same topic or changes the way of choosing words, it detects signs of cognitive function decline. The determination unit determines the decline in cognitive function based on the results analyzed by the analysis unit using the generation AI. For example, it determines the decline in cognitive function using a specific behavioral pattern or a scoring system. The provision unit provides brain training and quizzes based on the results determined by the determination unit using the generation AI. For example, quizzes to test memory and calculation problems are given to stimulate the user's cognitive function. The storage unit uses the generation AI to store the results provided by the providing unit and share them with specific people. For example, summaries of conversation history and diagnosis results are stored and shared with family members, nurses, home helpers, etc. In this way, the dementia prevention system according to the embodiment can maintain and improve the user's cognitive function.

[0068] The conversation promotion unit uses the generation AI to generate an appropriate response to the user's statement and continue the conversation. For example, if the user says, "The weather is nice today," the generation AI responds, "Yes, it might be nice to go for a walk." The generation AI uses natural language processing technology to understand the user's statement and generate an appropriate response. Specifically, it analyzes the user's statement and performs grammatical analysis and semantic analysis to understand its context and intent. In addition, the generation AI can generate more personalized responses by taking into account past conversation history and the user's preferences. For example, if the user has previously said, "I like walks," the generation AI responds, "The weather is nice today, so it might be nice to go for a walk." The conversation promotion unit can also estimate the user's emotions and select a conversation topic based on the estimated emotions. Voice analysis and facial expression recognition technology can be used for emotion estimation. For example, emotions can be estimated from the user's tone of voice and speaking style, and if the user is sad, the generation AI selects a topic that includes words of encouragement and comfort. This allows the conversation promotion unit to provide conversation that is in tune with the user's emotions, helping to stabilize the user's psychology. Furthermore, the conversation promotion unit can select conversation topics based on the user's interests and concerns. For example, if the user enjoys gardening as a hobby, the generation AI can arouse the user's interest and stimulate conversation by asking questions such as, "What kind of flowers have you planted recently?" This allows the conversation promotion unit to maintain and improve cognitive function through natural conversation with the user.

[0069] The analysis unit uses the generation AI to analyze the conversation history, and analyzes the content and frequency of the conversation, as well as the user's reaction. Specifically, the content of the conversation is saved as text data and analyzed using natural language processing technology. For example, signs of cognitive decline are detected when the user repeats the same topic or changes in the choice of words. When analyzing the content of the conversation, the generation AI can detect changes in the frequency of keyword appearance and context. For example, if the user repeatedly makes statements such as "I talked about the same thing yesterday," the generation AI can detect this pattern and suggest the possibility of cognitive decline. In addition, voice analysis and facial expression recognition technology can be used to analyze the user's reaction. For example, the tone of the user's voice, speaking style, and changes in facial expressions are analyzed to estimate the user's emotions and psychological state. This allows the analysis unit to capture changes in the user's cognitive function from multiple angles. In addition, the analysis unit can analyze the frequency and duration of conversations. For example, if the user's frequency of conversations has decreased or the duration of conversations has become shorter than before, the generation AI can detect the change and evaluate it as a sign of cognitive decline. This enables the analysis unit to detect changes in the user's cognitive function at an early stage and provide information for taking appropriate measures.

[0070] The judgment unit judges the decline in cognitive function based on the results of the analysis by the analysis unit using the generation AI. Specifically, the cognitive function decline is judged using a specific behavioral pattern or a scoring system. For example, the frequency with which the user repeats the same topic, changes in the choice of words, changes in the frequency and duration of conversations, etc. are scored and evaluated comprehensively. The generation AI quantifies the state of the user's cognitive function based on these data, and judges the decline in cognitive function if it exceeds a certain standard. The judgment unit can also evaluate changes in the user's cognitive function by comparing it with past data. For example, it compares past conversation history with current conversation history to evaluate the progress of the decline in cognitive function. This allows the judgment unit to accurately grasp the state of the user's cognitive function and provide information for taking appropriate measures. Furthermore, the judgment unit can detect unusual patterns or abnormal data using an anomaly detection algorithm and issue an early warning. For example, if a user suddenly stops talking or suddenly changes the way he or she chooses words, the generation AI detects the abnormality and issues an early warning. This allows the judgment unit to detect the decline in the user's cognitive function early and respond quickly.

[0071] The providing unit provides brain training and quizzes based on the results determined by the determining unit using the generating AI. Specifically, it provides quizzes and calculation problems that test memory, stimulating the user's cognitive function. The generating AI can select brain training and quizzes of appropriate difficulty and content according to the state of the user's cognitive function. For example, if the user's memory is declining, the generating AI will provide a quiz to strengthen the memory. It can also analyze the user's reactions and answers and provide appropriate feedback. For example, if the user answers the quiz correctly, the generating AI will provide encouraging words such as "That's great!" to motivate the user. Furthermore, the providing unit can customize the content of the brain training and quizzes based on the user's interests and concerns. For example, if the user is interested in history, the generating AI can provide a quiz about history to draw out the user's interest and allow the user to enjoy brain training. This allows the providing unit to provide effective brain training and quizzes to maintain and improve the user's cognitive function.

[0072] The storage unit uses the generation AI to store the results provided by the provision unit and share them with specific people. Specifically, it stores a summary of the conversation history and the diagnosis results, and shares them with family members, nurses, home helpers, etc. The generation AI can organize the conversation history and diagnosis results and store them in an easy-to-understand format. For example, it organizes the conversation history by date and highlights important points and abnormal patterns. It also visualizes the diagnosis results as graphs and charts, so that the state of the user's cognitive function can be understood at a glance. Furthermore, the storage unit can safely manage the stored data and set access restrictions as necessary. For example, it allows only specific people such as family members, nurses, and home helpers to access the data. In addition, the storage unit can regularly back up data to prevent data loss or damage. This allows the storage unit to accurately record the state of the user's cognitive function and provide information to take appropriate measures. Furthermore, the storage unit can analyze long-term trends and patterns based on the stored data. For example, it can grasp the tendency of changes in the user's cognitive function based on past data and predict future risks. This enables the storage unit to provide information for taking effective measures to maintain and improve the user's cognitive function.

[0073] The conversation promotion unit can generate an appropriate response to the user's utterance. The conversation promotion unit uses the generation AI to generate an appropriate response to the user's utterance. For example, if the user says, "The weather is nice today," the generation AI responds, "Yes, it might be nice to go for a walk." The conversation promotion unit can also estimate the user's emotions and select a conversation topic based on the estimated emotions. For example, if the user is sad, the generation AI selects a topic that includes words of encouragement and comfort. This can promote natural conversation with the user.

[0074] The analysis unit can analyze the content and frequency of conversations, as well as the user's reactions. The analysis unit uses generative AI to analyze the conversation history, and analyzes the content and frequency of conversations, as well as the user's reactions. For example, it detects signs of cognitive decline, such as when a user repeats the same topic or when the choice of words changes. The analysis unit can use techniques such as text analysis and sentiment analysis to perform a detailed analysis of the content and frequency of conversations, as well as the user's reactions. This allows the state of the user's cognitive function to be understood.

[0075] The judgment unit can detect signs of cognitive decline. The judgment unit judges the decline in cognitive function based on the results of the analysis by the analysis unit using the generation AI. For example, the judgment unit judges the decline in cognitive function using a specific behavioral pattern or a scoring system. The judgment unit can detect signs of cognitive decline using a diagnostic algorithm. This makes it possible to detect the decline in cognitive function early.

[0076] The providing unit can provide quizzes or calculation problems that test memory. The providing unit provides brain training and quizzes based on the results determined by the determining unit using the generation AI. For example, quizzes that test memory and calculation problems are presented to stimulate the user's cognitive function. The providing unit can provide brain training and quizzes that are suitable for the user, taking into consideration the type of problem and difficulty setting. This can maintain and improve the user's cognitive function.

[0077] The storage unit can store a summary of the conversation history and the diagnosis results, and share them with family members or medical professionals. The storage unit stores the results provided by the provision unit using the generation AI, and shares them with specific people. For example, the storage unit can store a summary of the conversation history and the diagnosis results, and share them with family members, nurses, home helpers, etc. The storage unit can store data in an appropriate manner, taking into consideration the data format, storage period, etc. This allows the state of the user's cognitive function to be shared with family members, nurses, home helpers, etc., and appropriate support can be provided.

[0078] The conversation promotion unit can estimate the user's emotions and select a conversation topic based on the estimated user's emotions. The conversation promotion unit estimates the user's emotions using the generation AI and selects a conversation topic based on the estimated emotions. For example, if the user is sad, the generation AI selects a topic including encouraging or comforting words. Also, if the user is excited, the generation AI can select an interesting topic or a challenging topic. Furthermore, if the user is relaxed, the generation AI can select a topic with a relaxed atmosphere. This allows the quality of the conversation to be improved by selecting an appropriate conversation topic according to the user's emotions. The emotion estimation is realized using an emotion estimation function using, for example, 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.

[0079] The conversation promotion unit can analyze the user's past conversation history and select the optimal way to proceed with the conversation. The conversation promotion unit uses a generation AI to analyze the user's past conversation history and select the optimal way to proceed with the conversation. For example, topics that the user has shown interest in in the past can be brought up again. Topics that the user has avoided in the past can also be avoided. Furthermore, topics that the user has talked about extensively in the past can also be selected with priority. This makes it possible to select the optimal way to proceed with the conversation for the user based on the past conversation history.

[0080] The conversation promotion unit can customize the content of the conversation based on the user's current interests and concerns when promoting the conversation. The conversation promotion unit uses the generation AI to customize the content of the conversation based on the user's current interests and concerns when promoting the conversation. For example, the user can talk about a book that he or she recently read. The user can also talk about a movie that he or she recently watched. Furthermore, the user can talk about an event that he or she recently attended. This makes it possible to improve the quality of the conversation by customizing the content of the conversation based on the user's current interests and concerns.

[0081] The conversation promotion unit can estimate the user's emotion and adjust the tempo of the conversation based on the estimated user's emotion. The conversation promotion unit estimates the user's emotion using the generation AI and adjusts the tempo of the conversation based on the estimated emotion. For example, when the user is nervous, the conversation can proceed at a slow tempo. When the user is relaxed, the conversation can also proceed at a natural tempo. Furthermore, when the user is in a hurry, the conversation can also proceed at a fast tempo. This can improve the quality of the conversation by providing an appropriate conversation tempo according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, 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.

[0082] The conversation promotion unit can prioritize selecting highly relevant topics based on the user's geographic location information when promoting a conversation. The conversation promotion unit prioritizes selecting highly relevant topics taking into account the user's geographic location information when promoting a conversation using the generation AI. For example, the user can talk about news from the area where the user lives. The user can also talk about places that the user has recently visited. Furthermore, the user can talk about travel destinations that the user is planning. This makes it possible to improve the quality of the conversation by selecting highly relevant topics based on the user's geographic location information.

[0083] The conversation promotion unit can analyze the user's social media activity and select related topics when promoting a conversation. The conversation promotion unit uses the generation AI to analyze the user's social media activity and select related topics when promoting a conversation. For example, the user can talk about articles that they recently shared. The user can also talk about posts that they recently commented on. Furthermore, the user can talk about content that they recently "liked." This makes it possible to improve the quality of conversation by selecting related topics based on the user's social media activity.

[0084] The analysis unit can estimate the user's emotion and adjust the conversation analysis method based on the estimated user's emotion. The analysis unit estimates the user's emotion using the generation AI and adjusts the conversation analysis method based on the estimated emotion. For example, if the user is sad, the analysis can be performed with emphasis on the emotional tone. Also, if the user is excited, the analysis can be performed with emphasis on the diversity of topics. Furthermore, if the user is relaxed, the analysis can be performed with emphasis on the flow of the conversation. This makes it possible to improve the accuracy of conversation analysis by providing an appropriate analysis method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, 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.

[0085] The analysis unit can adjust the level of detail of the analysis based on the importance of the conversation when analyzing the conversation. The analysis unit can adjust the level of detail of the analysis based on the importance of the conversation when analyzing the conversation using the generative AI. For example, important topics can be analyzed in detail. General topics can also be analyzed simply. Furthermore, topics emphasized by the user can be analyzed intensively. This allows for efficient analysis by adjusting the level of detail of the analysis based on the importance of the conversation.

[0086] The analysis unit can apply different analysis algorithms depending on the category of the conversation when analyzing the conversation. The analysis unit can apply different analysis algorithms depending on the category of the conversation when analyzing the conversation using the generative AI. For example, a health-related algorithm can be applied to topics about health. A hobby-related algorithm can also be applied to topics about hobbies. Furthermore, a family-related algorithm can be applied to topics about family. In this way, the analysis accuracy can be improved by applying an appropriate analysis algorithm depending on the category of the conversation.

[0087] The analysis unit can estimate the user's emotion and adjust the display method of the analysis result based on the estimated user's emotion. The analysis unit estimates the user's emotion using the generation AI and adjusts the display method of the analysis result based on the estimated emotion. For example, when the user is nervous, a simple and highly visible display method is provided. Also, when the user is relaxed, a display method including detailed information can be provided. Furthermore, when the user is in a hurry, a display method that focuses on the main points can be provided. This allows a deeper understanding of the analysis result by providing an appropriate display method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0088] When analyzing a conversation, the analysis unit can determine the priority of the analysis based on the time when the conversation was submitted. When analyzing a conversation using the generative AI, the analysis unit determines the priority of the analysis based on the time when the conversation was submitted. For example, recent conversations can be analyzed preferentially. Also, past conversations can be postponed. Furthermore, conversations that were concentrated in a specific period can be analyzed preferentially. This enables efficient analysis by determining the priority of the analysis based on the time when the conversation was submitted.

[0089] The analysis unit can adjust the order of analysis based on the relevance of the conversations when analyzing the conversations. The analysis unit can adjust the order of analysis based on the relevance of the conversations when analyzing the conversations using the generative AI. For example, highly relevant conversations can be analyzed with priority. Less relevant conversations can also be postponed. Furthermore, conversations related to a specific theme can be analyzed together. This allows for efficient analysis by adjusting the order of analysis based on the relevance of the conversations.

[0090] The determination unit can estimate the user's emotion and adjust the criteria for determining the decline in cognitive function based on the estimated emotion of the user. The determination unit estimates the user's emotion using the generation AI and adjusts the criteria for determining the decline in cognitive function based on the estimated emotion. For example, if the user is sad, the determination is made with emphasis on the emotional tone. Also, if the user is excited, the determination can be made with emphasis on the diversity of topics. Furthermore, if the user is relaxed, the determination can be made with emphasis on the flow of the conversation. In this way, by providing an appropriate determination criterion according to the user's emotion, the decline in cognitive function can be accurately determined. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0091] When determining whether cognitive function has declined, the determination unit can improve the accuracy of the determination by referring to the user's past cognitive function data. When determining whether cognitive function has declined using the generation AI, the determination unit can improve the accuracy of the determination by referring to the user's past cognitive function data. For example, the determination unit can refer to the user's past cognitive function test results. The determination unit can also refer to the user's past conversation history. Furthermore, the determination unit can also refer to the user's past health check results. In this way, the determination unit can improve the accuracy of the determination by referring to the past cognitive function data.

[0092] When determining whether cognitive function has declined, the determination unit can make a determination based on the user's living situation and health condition. When determining whether cognitive function has declined using the generation AI, the determination unit makes a determination taking into account the user's living situation and health condition. For example, the user's lifestyle habits are taken into account. The user's health condition can also be taken into account. Furthermore, the user's social activities can also be taken into account. This allows for a more accurate determination by taking into account the user's living situation and health condition.

[0093] The determination unit can estimate the user's emotion and adjust the display method of the determination result based on the estimated user's emotion. The determination unit estimates the user's emotion using the generation AI and adjusts the display method of the determination result based on the estimated emotion. For example, when the user is nervous, a simple and highly visible display method is provided. Also, when the user is relaxed, a display method including detailed information can be provided. Furthermore, when the user is in a hurry, a display method that focuses on the main points can be provided. This allows the user to deepen their understanding of the determination result by providing an appropriate display method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0094] The determination unit can make a determination taking into account the user's geographical location information when determining a decline in cognitive function. When using the generation AI to determine a decline in cognitive function, the determination unit makes a determination taking into account the user's geographical location information. For example, medical information about the area in which the user lives can be taken into account. Information about places recently visited by the user can also be taken into account. Furthermore, information about travel destinations that the user is planning can also be taken into account. As a result, by taking into account the user's geographical location information, a more accurate determination can be made.

[0095] The determination unit can improve the accuracy of the determination when determining a decline in cognitive function by analyzing the user's social media activity. When determining a decline in cognitive function using the generative AI, the determination unit can improve the accuracy of the determination by analyzing the user's social media activity. For example, the content of articles recently shared by the user can be analyzed. The content of posts recently commented on by the user can also be analyzed. Furthermore, the content of posts that the user recently "liked" can also be analyzed. In this way, the accuracy of the determination can be improved by analyzing the user's social media activity.

[0096] The providing unit can estimate the user's emotions and adjust the contents of the brain training and quiz to be provided based on the estimated user's emotions. The providing unit estimates the user's emotions using the generation AI and adjusts the contents of the brain training and quiz to be provided based on the estimated emotions. For example, if the user is relaxed, a quiz with a relaxing atmosphere can be provided. Also, if the user is excited, a challenging quiz can be provided. Furthermore, if the user is sad, a quiz including encouraging words can be provided. In this way, by providing appropriate brain training and quizzes according to the user's emotions, it is possible to maintain and improve cognitive function. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0097] The providing unit can adjust the difficulty level by referring to the user's past scores when providing brain training exercises or quizzes. When providing brain training exercises or quizzes using the generation AI, the providing unit adjusts the difficulty level by referring to the user's past scores. For example, if the user has scored high in the past, the difficulty level can be increased. Also, if the user has scored low in the past, the difficulty level can be lowered. Furthermore, a quiz of an appropriate level of difficulty can be provided based on the user's past scores. This makes it possible to maintain and improve cognitive function by providing brain training exercises or quizzes of an appropriate level of difficulty based on the user's past scores.

[0098] The provision unit can customize the content based on the user's current cognitive function state when providing brain training exercises and quizzes. When providing brain training exercises and quizzes using the generation AI, the provision unit customizes the content based on the user's current cognitive function state. For example, if the user's cognitive function is declining, an easy quiz can be provided. Also, if the user's cognitive function is maintained, a standard quiz can be provided. Furthermore, if the user's cognitive function is improving, a more difficult quiz can be provided. This makes it possible to maintain and improve cognitive function by providing appropriate brain training exercises and quizzes based on the user's current cognitive function state.

[0099] The providing unit can estimate the user's emotions and adjust the order of brain training exercises and quizzes to be provided based on the estimated user's emotions. The providing unit estimates the user's emotions using the generation AI and adjusts the order of brain training exercises and quizzes to be provided based on the estimated emotions. For example, if the user is relaxed, a quiz with a relaxing atmosphere can be provided first. Also, if the user is excited, a challenging quiz can be provided first. Furthermore, if the user is sad, a quiz containing encouraging words can be provided first. In this way, by providing brain training exercises and quizzes in an appropriate order according to the user's emotions, it is possible to maintain and improve cognitive function. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0100] The provision unit can select the content in consideration of the geographical location information of the user when providing brain training exercises and quizzes. When providing brain training exercises and quizzes using the generation AI, the provision unit selects the content in consideration of the geographical location information of the user. For example, a quiz related to the area where the user lives can be provided. In addition, a quiz related to places recently visited by the user can be provided. Furthermore, a quiz related to a travel destination that the user is planning can be provided. In this way, by providing appropriate brain training exercises and quizzes based on the geographical location information of the user, cognitive function can be maintained and improved.

[0101] When providing brain training exercises and quizzes, the provision unit can select the content by analyzing the user's social media activity. When providing brain training exercises and quizzes using the generation AI, the provision unit selects the content by analyzing the user's social media activity. For example, a quiz related to an article recently shared by the user can be provided. Also, a quiz related to a post recently commented on by the user can be provided. Furthermore, a quiz related to content that the user recently "liked" can be provided. In this way, by providing appropriate brain training exercises and quizzes based on the user's social media activity, cognitive function can be maintained and improved.

[0102] The storage unit can estimate the user's emotion and select data to be stored based on the estimated user's emotion. The storage unit estimates the user's emotion using the generation AI and selects data to be stored based on the estimated emotion. For example, if the user is sad, data is selected with emphasis on emotional tone. In addition, if the user is excited, data can be selected with emphasis on topic diversity. Furthermore, if the user is relaxed, data can be selected with emphasis on the flow of conversation. In this way, the usefulness of data can be improved by storing appropriate data according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples.

[0103] When saving data, the storage unit can optimize the storage method by referring to past saved data. When saving data using the generation AI, the storage unit optimizes the storage method by referring to past saved data. For example, the storage unit can refer to the format of the past saved data and save the data in the same format. In addition, the storage unit can refer to the contents of the past saved data and save highly relevant data preferentially. Furthermore, the storage location of the past saved data can be referenced and the data can be saved in the same location. In this way, the storage method can be optimized by referring to the past saved data, making data management more efficient.

[0104] The storage unit can estimate the user's emotion and adjust the display method of the stored data based on the estimated user's emotion. The storage unit estimates the user's emotion using the generation AI and adjusts the display method of the stored data based on the estimated emotion. For example, when the user is nervous, a simple and highly visible display method is provided. Also, when the user is relaxed, a display method including detailed information can be provided. Furthermore, when the user is in a hurry, a display method that focuses on the main points can be provided. This allows the user to deepen their understanding of the stored data by providing an appropriate display method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples.

[0105] When saving data, the storage unit can weight the saved data based on the time of submission of the conversation. When saving data using the generation AI, the storage unit weights the saved data based on the time of submission of the conversation. For example, recent conversation data can be saved preferentially. Also, past conversation data can be postponed. Furthermore, conversation data that was concentrated in a specific period can be saved preferentially. In this way, by weighting the saved data based on the time of submission of the conversation, important data can be saved preferentially.

[0106] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0107] The dementia prevention system can further include a sensor unit that acquires the user's physical activity data. The sensor unit collects data such as the user's number of steps, heart rate, and sleep patterns, and provides the data to the analysis unit. For example, the sensor unit can record how much the user walks on a daily basis to determine whether lack of exercise is affecting cognitive function. It can also monitor heart rate fluctuations and sleep quality to evaluate the effects of stress and fatigue on cognitive function. This makes it possible to comprehensively evaluate cognitive function based on physical activity data.

[0108] The conversation promotion unit can provide conversation topics customized based on the user's hobbies and interests. For example, if the user is interested in music, the latest music news and topics about artists can be provided. If the user enjoys gardening, topics about seasonal flowers and how to grow plants can be provided. Furthermore, if the user likes traveling, topics about recommended travel spots and local culture can be provided. This enables conversation according to the user's interests, improving the quality of the conversation.

[0109] The analysis unit can monitor a user's conversation patterns over the long term and detect changes. For example, it can detect subtle changes such as when a user no longer uses words that they used frequently before or when the tempo of their conversation slows down. It can also detect when the content of a user's conversation becomes increasingly monotonous or when the range of topics they discuss becomes narrower. This makes it possible to detect a decline in cognitive function early and take appropriate measures.

[0110] The determination unit can take into account the user's social activity data when determining the decline in the user's cognitive function. For example, data such as how frequently the user meets with friends and family and participates in social events can be collected and analyzed. The determination unit can also take into account how much online interaction the user has. This allows the impact of a decrease in social activity on cognitive function to be evaluated and a comprehensive determination to be made.

[0111] The providing unit can provide a rehabilitation program according to the state of the user's cognitive function. For example, a user with reduced cognitive function can be provided with simple memory training or a game that improves attention. Also, a user with maintained cognitive function can be provided with quizzes that encourage more complex problem solving or logical thinking. Furthermore, a user with improved cognitive function can be provided with challenging puzzles or strategy games. This enables appropriate rehabilitation according to the state of the user's cognitive function.

[0112] The conversation promotion unit can estimate the user's emotions and adjust the tone of the conversation based on the estimated emotions. For example, if the user is depressed, the conversation can be encouraged in a gentle tone. If the user is excited, the conversation can be continued in an energetic tone. If the user is relaxed, the conversation can be continued in a gentle tone. In this way, the quality of the conversation can be improved by providing an appropriate conversation tone according to the user's emotions.

[0113] The analysis unit can estimate the user's emotions and adjust the conversation analysis method based on the estimated emotions. For example, if the user is sad, the analysis can be focused on the emotional tone. If the user is excited, the analysis can be focused on the diversity of topics. Furthermore, if the user is relaxed, the analysis can be focused on the flow of the conversation. In this way, the accuracy of the conversation analysis can be improved by providing an appropriate analysis method according to the user's emotions.

[0114] The determination unit can estimate the user's emotion and adjust the criteria for determining whether or not cognitive function has declined based on the estimated emotion. For example, if the user is sad, the determination can be made with emphasis on emotional tone. If the user is excited, the determination can be made with emphasis on the diversity of topics. Furthermore, if the user is relaxed, the determination can be made with emphasis on the flow of conversation. In this way, by providing appropriate determination criteria according to the user's emotion, it is possible to accurately determine whether or not cognitive function has declined.

[0115] The providing unit can estimate the user's emotions and adjust the contents of the brain training and quizzes to be provided based on the estimated emotions. For example, if the user is relaxed, a quiz with a relaxing atmosphere can be provided. Also, if the user is excited, a challenging quiz can be provided. Furthermore, if the user is sad, a quiz including words of encouragement can be provided. In this way, by providing appropriate brain training and quizzes according to the user's emotions, it is possible to maintain and improve cognitive function.

[0116] The storage unit can estimate the user's emotion and select data to be stored based on the estimated emotion. For example, if the user is sad, data can be selected with emphasis on emotional tone. If the user is excited, data can be selected with emphasis on topic diversity. Furthermore, if the user is relaxed, data can be selected with emphasis on the flow of conversation. In this way, the usefulness of the data can be improved by storing appropriate data according to the user's emotion.

[0117] The process flow of the second embodiment will be briefly described below.

[0118] Step 1: The conversation promotion unit uses the generation AI to generate an appropriate response to the user's utterance and continue the conversation. For example, if the user says, "The weather is nice today," the generation AI responds, "Yes, maybe it would be nice to go for a walk." The conversation promotion unit can also estimate the user's emotions and select a conversation topic based on the estimated emotions. For example, if the user is sad, the generation AI selects a topic that includes words of encouragement and comfort. Step 2: The analysis unit uses the generative AI to analyze the conversation history, and analyzes the content and frequency of the conversations, as well as the user's reactions. For example, it detects signs of cognitive decline, such as when the user repeats the same topics or changes in word choice. Step 3: The judgment unit judges the decline in cognitive function based on the results of the analysis by the analysis unit using the generation AI. For example, the decline in cognitive function is judged using a specific behavioral pattern or a scoring system. Step 4: The provision unit uses the generation AI to provide brain training and quizzes based on the results determined by the determination unit. For example, it may provide quizzes to test memory or calculation problems to stimulate the user's cognitive functions. Step 5: The storage unit uses the generation AI to store the results provided by the provider unit and share them with specific people. For example, it stores a summary of the conversation history and the diagnosis results and shares them with family members, nurses, home helpers, etc.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0120] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0121] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0122] Each of the multiple elements including the above-mentioned conversation promotion unit, analysis unit, determination unit, provision unit, and storage unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the conversation promotion unit is realized by the control unit 46A of the smart device 14, and generates an appropriate response to a user's remark. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the conversation history. The determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and determines a decline in cognitive function. The provision unit is realized, for example, by the control unit 46A of the smart device 14, and provides brain training and quizzes. The storage unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and stores a summary of the conversation history and a diagnosis result, and shares it with a specific person. The correspondence relationship between each unit and the device or the control unit is not limited to the above-mentioned example, and various changes are possible.

[0123] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0124] 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.

[0125] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0126] 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.

[0127] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0128] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0129] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0130] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0131] 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.

[0132] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0133] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0134] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0135] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0137] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0138] Each of the multiple elements including the above-mentioned conversation promotion unit, analysis unit, determination unit, provision unit, and storage unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the conversation promotion unit is realized by the control unit 46A of the smart glasses 214, and generates an appropriate response to a user's utterance. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the conversation history. The determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and determines a decline in cognitive function. The provision unit is realized, for example, by the control unit 46A of the smart glasses 214, and provides brain training and quizzes. The storage unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and stores a summary of the conversation history and diagnosis results, and shares them with a specific person. The correspondence between each unit and the device and the control unit is not limited to the above-mentioned example, and various changes are possible.

[0139] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0140] 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.

[0141] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0142] 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.

[0143] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0144] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0145] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0146] 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.

[0147] 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.

[0148] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0149] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0150] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0151] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0153] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0154] Each of the multiple elements including the above-mentioned conversation promotion unit, analysis unit, determination unit, provision unit, and storage unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the conversation promotion unit is realized by the control unit 46A of the headset type terminal 314, and generates an appropriate response to the user's remark. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the conversation history. The determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and determines the decline in cognitive function. The provision unit is realized, for example, by the control unit 46A of the headset type terminal 314, and provides brain training and quizzes. The storage unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and stores a summary of the conversation history and diagnosis results, and shares them with a specific person. The correspondence relationship between each unit and the device and the control unit is not limited to the above-mentioned example, and various changes are possible.

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

[0156] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0157] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0158] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0159] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0161] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0162] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0163] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0164] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0165] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0166] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0167] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0168] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0169] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0170] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0171] Each of the multiple elements including the above-mentioned conversation promotion unit, analysis unit, determination unit, provision unit, and storage unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the conversation promotion unit is realized by the control unit 46A of the robot 414, and generates an appropriate response to a user's remark. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the conversation history. The determination unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and determines a decline in cognitive function. The provision unit is realized, for example, by the control unit 46A of the robot 414, and provides brain training and quizzes. The storage unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and stores a summary of the conversation history and diagnosis results, and shares them with a specific person. The correspondence between each unit and the device and the control unit is not limited to the above-mentioned example, and various changes are possible.

[0172] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0173] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0174] These emotions are distributed in the three o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0175] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out on emotion map 400 you go, the more visible the emotions become (the more they are expressed in behavior).

[0176] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0177] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0178] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0179] 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.

[0180] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0181] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0182] 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.

[0183] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0184] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0185] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0186] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0187] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0188] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0189] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0190] (Appendix 1) A conversation facilitator that promotes conversation; an analysis unit that analyzes the conversation history generated by the conversation promotion unit; A determination unit for determining a decline in cognitive function based on the results of the analysis by the analysis unit; a providing unit that provides a brain training or quiz based on the result determined by the determining unit; A storage unit that stores the results provided by the providing unit and shares them with a family member or a medical professional. A system characterized by: (Appendix 2) The conversation promotion unit includes: Generate appropriate responses to user utterances 2. The system of claim 1, (Appendix 3) The analysis unit includes: Analyze conversation content, frequency, and user responses 2. The system of claim 1, (Appendix 4) The determination unit is Detect signs of cognitive decline 2. The system of claim 1, (Appendix 5) The providing unit is Offering quizzes or math problems to test your memory 2. The system of claim 1, (Appendix 6) The storage unit includes: Save and share conversation history summaries and diagnostic results with family members or healthcare professionals 2. The system of claim 1, (Appendix 7) The conversation promotion unit includes: Estimate user emotions and select conversation topics based on the estimated user emotions 2. The system of claim 1, (Appendix 8) The conversation promotion unit includes: Analyze the user's past conversation history and choose the best way to proceed with the conversation 2. The system of claim 1, (Appendix 9) The conversation promotion unit includes: When facilitating a conversation, customize the content of the conversation based on the user's current interests 2. The system of claim 1, (Appendix 10) The conversation promotion unit includes: Estimate the user's emotions and adjust the tempo of the conversation based on the estimated user's emotions 2. The system of claim 1, (Appendix 11) The conversation promotion unit includes: When facilitating conversations, prioritize relevant topics based on the user's geographic location 2. The system of claim 1, (Appendix 12) The conversation promotion unit includes: When facilitating conversations, analyze users' social media activity and select relevant topics 2. The system of claim 1, (Appendix 13) The analysis unit includes: Infer user sentiment and adjust conversation analysis methods based on the inferred user sentiment 2. The system of claim 1, (Appendix 14) The analysis unit includes: When analyzing conversations, adjust the analysis detail based on the importance of the conversation 2. The system of claim 1, (Appendix 15) The analysis unit includes: When analyzing conversations, apply different analysis algorithms depending on the category of the conversation 2. The system of claim 1, (Appendix 16) The analysis unit includes: Infer user sentiment and adjust how analysis results are displayed based on the inferred user sentiment 2. The system of claim 1, (Appendix 17) The analysis unit includes: When analyzing conversations, prioritize analysis based on when the conversations were submitted 2. The system of claim 1, (Appendix 18) The analysis unit includes: When analyzing conversations, adjust the order of analysis based on conversation relevance 2. The system of claim 1, (Appendix 19) The determination unit is A method for detecting cognitive decline based on a user's emotion is provided. 2. The system of claim 1, (Appendix 20) The determination unit is When assessing cognitive decline, the accuracy of the assessment is improved by referring to the user's past cognitive function data. 2. The system of claim 1, (Appendix 21) The determination unit is When assessing cognitive decline, the assessment is based on the user's living situation and health condition. 2. The system of claim 1, (Appendix 22) The determination unit is To estimate a user's emotion and adjust a method of displaying a judgment result based on the estimated user's emotion. 2. The system of claim 1, (Appendix 23) The determination unit is When assessing cognitive decline, the assessment takes into account the user's geographic location information. 2. The system of claim 1, (Appendix 24) The determination unit is Analyzing users' social media activity to improve accuracy in assessing cognitive decline 2. The system of claim 1, (Appendix 25) The providing unit is Estimate the user's emotions and adjust the content of brain training and quizzes based on the estimated user emotions 2. The system of claim 1, (Appendix 26) The providing unit is When providing brain training or quizzes, adjust the difficulty level by referring to the user's past performance 2. The system of claim 1, (Appendix 27) The providing unit is When providing brain training and quizzes, customize the content based on the user's current cognitive function state 2. The system of claim 1, (Appendix 28) The providing unit is Infer the user's emotions and adjust the order of brain training and quizzes provided based on the estimated user emotions 2. The system of claim 1, (Appendix 29) The providing unit is When providing brain training and quizzes, select content taking into account the user's geographic location information 2. The system of claim 1, (Appendix 30) The providing unit is When providing brain training and quizzes, we analyze users' social media activity to select content. 2. The system of claim 1, (Appendix 31) The storage unit includes: Infer the user's emotions and select the data to be saved based on the estimated user emotions. 2. The system of claim 1, (Appendix 32) The storage unit includes: When storing data, optimize the storage method by referencing past stored data 2. The system of claim 1, (Appendix 33) The storage unit includes: Inferring user emotion and adjusting the display method of stored data based on the estimated user emotion 2. The system of claim 1, (Appendix 34) The storage unit includes: When storing data, we weight the data we store based on when the conversation was submitted 2. The system of claim 1, [Explanation of symbols]

[0191] 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 conversation facilitator that promotes conversation; an analysis unit that analyzes the conversation history generated by the conversation promotion unit; A determination unit for determining a decline in cognitive function based on the results of the analysis by the analysis unit; a providing unit that provides a brain training or quiz based on the result determined by the determining unit; A storage unit that stores the results provided by the providing unit and shares them with a family member or a medical professional. A system characterized by:

2. The conversation promotion unit includes: Generate appropriate responses to user utterances 2. The system of claim 1 .

3. The analysis unit includes: Analyze the content and frequency of conversations and user responses 2. The system of claim 1 .

4. The determination unit is Detect signs of cognitive decline 2. The system of claim 1 .

5. The providing unit is Offering quizzes or math problems to test your memory 2. The system of claim 1 .

6. The storage unit includes: Save and share conversation history summaries and diagnostic results with family members or healthcare professionals 2. The system of claim 1 .

7. The conversation promotion unit includes: Estimate user emotions and select conversation topics based on the estimated user emotions 2. The system of claim 1 .

8. The conversation promotion unit includes: Analyze the user's past conversation history and choose the best way to proceed with the conversation 2. The system of claim 1 .

Images