system

Abstract

The system according to the embodiment aims to detect abnormalities in seniors at an early stage and take appropriate measures. [Solution] The system according to the embodiment includes a conversation unit, an analysis unit, a detection unit, and a linking unit. The conversation unit engages in conversation with seniors. The analysis unit analyzes the responses of seniors obtained by the conversation unit. The detection unit detects abnormalities based on the results of the analysis by the analysis unit. The linking unit links to a specific person or institution when an abnormality is detected by the detection unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have presented challenges in detecting abnormalities in seniors early and taking appropriate action.

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

[0006] The system according to this embodiment comprises a conversation unit, an analysis unit, a detection unit, and a coordination unit. The conversation unit engages in conversation with the senior. The analysis unit analyzes the senior's responses obtained by the conversation unit. The detection unit detects anomalies based on the results analyzed by the analysis unit. The coordination unit coordinates with a specific person or organization when an anomaly is detected by the detection unit. [Effects of the Invention]

[0007] The system according to this embodiment can detect abnormalities in seniors at an early stage and take appropriate action. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) The system according to an embodiment of the present invention is a system that provides services enabling seniors to live out their later years with peace of mind. This system uses a home robot or speaker chatbot to perform dementia checks through daily conversations with seniors, and if an abnormality is detected, it connects with the appropriate person or organization. For example, the home robot or speaker chatbot engages in daily conversations with seniors, generates questions to check the seniors' cognitive function, and analyzes the seniors' answers. For example, it might ask questions such as, "What day is it today?" or "What do you think about the recent news?" Next, the chatbot analyzes the seniors' answers and checks for any abnormalities. For example, if a senior gets the date wrong or fails to give an appropriate answer to a question, the chatbot detects an abnormality. This analysis is performed using AI, which continuously monitors changes in the seniors' cognitive function. If an abnormality is detected, the chatbot connects with the appropriate person or organization. For example, it sends a notification to the senior's family, nursing home, or medical institution. This notification includes changes in the seniors' cognitive function and the specific details of the abnormality. This is expected to enable appropriate action to be taken early. Through this service, seniors can live out their later years with peace of mind. This is because chatbots in home robots and speakers can engage in daily conversations with seniors and check their cognitive function, allowing for early detection of abnormalities and appropriate action to be taken. Furthermore, it makes it easier for seniors' families, care facilities, and medical institutions to understand their condition and provide peace of mind. For example, even if a senior lives alone, daily conversations with a chatbot in a home robot or speaker can detect changes in their cognitive function early. This allows seniors to continue living independently with peace of mind, and makes it easier for families, care facilities, and medical institutions to understand their condition. This service is also provided while respecting seniors' privacy. To protect seniors' privacy, the chatbots in home robots and speakers collect only the minimum necessary information and connect it to the appropriate people or organizations. This allows seniors to use the service with confidence. The system can then routinely check seniors' cognitive function and take appropriate action if abnormalities are detected.

[0029] The system according to the embodiment comprises a conversation unit, an analysis unit, a detection unit, and a collaboration unit. The conversation unit engages in conversation with the senior. Conversations with the senior include, for example, everyday questions and conversations, but are not limited to such examples. The conversation unit includes, for example, a question generation unit that generates questions to check the senior's cognitive function. The question generation unit generates, for example, questions related to the senior's daily life. For example, it can generate questions such as "What day is it today?" or "What do you think about the recent news?" The analysis unit analyzes the senior's responses obtained by the conversation unit. The analysis unit includes, for example, an answer analysis unit in which an AI analyzes the senior's responses. The answer analysis unit analyzes the senior's responses using, for example, text analysis or speech analysis. For example, the AI ​​analyzes the senior's responses using natural language processing technology and detects anomalies. The detection unit detects anomalies based on the results analyzed by the analysis unit. The detection unit includes, for example, an anomaly determination unit that determines changes in the senior's cognitive function. For example, the anomaly determination unit uses an AI to determine changes in the senior's cognitive function. The AI ​​determines changes in the senior's cognitive function using machine learning algorithms and pattern recognition technology. The collaboration unit collaborates with the appropriate person or organization when an abnormality is detected by the detection unit. The collaboration unit includes, for example, a notification unit that sends a notification when an abnormality is detected. The notification unit sends a notification to, for example, the senior's family, nursing home, or medical institution. The notification unit can send notifications by methods such as email, phone, or app notification. As a result, the system according to the embodiment can routinely check the senior's cognitive function and take appropriate action if an abnormality is found. Some or all of the above processing in the conversation unit, analysis unit, detection unit, and collaboration unit may be performed using, for example, AI, or not using AI. For example, the conversation unit can have the AI ​​analyze the conversation with the senior, the analysis unit can have the AI ​​analyze the senior's responses, the detection unit can have the AI ​​determine changes in the senior's cognitive function, and the collaboration unit can send a notification using an AI model that sends a notification when an abnormality is detected.

[0030] The conversation unit may include a question generation unit that generates questions to check the cognitive function of seniors. The question generation unit generates questions related to the seniors' daily lives. For example, the question generation unit can generate questions about seniors' diet, exercise, and hobbies. For example, the question generation unit can generate questions such as, "What did you eat today?" or "How has your exercise been lately?" This allows for the generation of questions that effectively check the cognitive function of seniors. Some or all of the above processing in the question generation unit may be performed using AI, for example, or without AI. For example, the question generation unit can generate questions using an AI model that generates questions related to the seniors' daily lives.

[0031] The analysis unit may include an answer analysis unit that analyzes the senior's responses. The answer analysis unit uses AI to analyze the senior's responses. For example, the answer analysis unit analyzes the senior's responses using text analysis or speech analysis. For example, the AI ​​analyzes the senior's responses using natural language processing technology and detects anomalies. This allows for effective analysis of the senior's responses. Some or all of the above-described processing in the answer analysis unit may be performed using AI, for example, or without AI. For example, the answer analysis unit can analyze the senior's responses using an AI model.

[0032] The detection unit may include an anomaly detection unit that determines changes in the cognitive function of seniors. The anomaly detection unit uses AI to determine changes in the cognitive function of seniors. For example, the anomaly detection unit may use machine learning algorithms or pattern recognition techniques to determine changes in the cognitive function of seniors. This allows for effective determination of changes in the cognitive function of seniors. Some or all of the above-described processing in the anomaly detection unit may be performed using AI, for example, or without AI. For example, the anomaly detection unit may use an AI model to determine changes in the cognitive function of seniors.

[0033] The linking unit may include a notification unit that sends a notification when an abnormality is detected. The notification unit sends a notification to the senior's family, a nursing facility, or a medical institution. For example, the notification unit may send a notification by email, telephone, app notification, or other method. This allows an appropriate notification to be sent when an abnormality is detected. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit may send a notification using an AI model that sends a notification when an abnormality is detected.

[0034] The question generation unit can generate questions related to the daily life of seniors. The question generation unit generates questions related to the daily life of seniors. For example, the question generation unit can generate questions related to the senior's diet, exercise, and hobbies. For example, the question generation unit can generate questions such as, "What did you eat today?" or "How has your exercise been lately?" By generating questions related to the daily life of seniors, more effective cognitive function checks are possible. Some or all of the above-described processing in the question generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the question generation unit can generate questions using an AI model that generates questions related to the daily life of seniors.

[0035] The answer analysis unit can analyze the answers of seniors using AI. The answer analysis unit analyzes the answers of seniors using AI. For example, the answer analysis unit analyzes the answers of seniors using text analysis or voice analysis. For example, the AI ​​analyzes the answers of seniors using natural language processing technology and detects abnormalities. In this way, the use of AI improves the accuracy of analyzing the answers of seniors. Some or all of the above-mentioned processing in the answer analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the answer analysis unit can perform analysis using an AI model that analyzes the answers of seniors.

[0036] The abnormality determination unit can determine changes in the cognitive function of seniors using AI. The abnormality determination unit determines changes in the cognitive function of seniors using AI. For example, the abnormality determination unit determines changes in the cognitive function of seniors using a machine learning algorithm or pattern recognition technology. As a result, the use of AI improves the accuracy of determining changes in the cognitive function of seniors. Some or all of the above-mentioned processing in the abnormality determination unit may be performed using AI, for example, or may be performed without using AI. For example, the abnormality determination unit can make a determination using an AI model that determines changes in the cognitive function of seniors.

[0037] The notification unit can send notifications to the senior's family, nursing facilities, and medical institutions. The notification unit can send notifications to the senior's family, nursing facilities, and medical institutions. For example, the notification unit can send notifications by email, telephone, app notification, or other methods. This allows appropriate notifications to be sent to the senior's family, nursing facilities, and medical institutions. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can send notifications using an AI model that sends notifications when an abnormality is detected.

[0038] The conversation unit can analyze the senior's past conversation history and select the optimal conversation content. The conversation unit analyzes the senior's past conversation history and selects the optimal conversation content. For example, the conversation unit revisits topics that the senior has shown interest in in the past. The conversation unit can also avoid topics that the senior has avoided in the past. The conversation unit can also suggest new topics based on topics that the senior has frequently talked about in the past. This enables more effective conversations by selecting the optimal conversation content based on the senior's past conversation history. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can conduct a conversation using an AI model that analyzes the senior's past conversation history and selects the optimal conversation content.

[0039] The conversation unit can customize the conversation content based on the senior's current health condition and living situation during the conversation. The conversation unit customizes the conversation content based on the senior's current health condition and living situation during the conversation. For example, if the senior is not feeling well, the conversation unit can provide health advice. The conversation unit can also gain empathy by having the senior talk about their recent living situation. If the senior has participated in a specific event, the conversation unit can also talk about that event. This allows for more appropriate conversation by customizing the conversation content based on the senior's current health condition and living situation. Some or all of the above-described processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can conduct a conversation using an AI model that customizes the conversation content based on the senior's current health condition and living situation.

[0040] During a conversation, the conversation unit can prioritize selecting a highly relevant topic based on the senior's geographical location information. During a conversation, the conversation unit prioritizes selecting a highly relevant topic based on the senior's geographical location information. For example, the conversation unit may discuss news from the area where the senior lives. The conversation unit may also provide topics related to places the senior often visits. The conversation unit may also discuss information about local events in the senior's area. This enables a more appropriate conversation by selecting a highly relevant topic taking the senior's geographical location information into consideration. Some or all of the above-described processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit may conduct a conversation using an AI model that selects a highly relevant topic based on the senior's geographical location information.

[0041] The conversation unit can analyze the social media activity of the senior during the conversation and select relevant topics. The conversation unit can analyze the social media activity of the senior during the conversation and select relevant topics. For example, the conversation unit can discuss articles shared by the senior on social media. The conversation unit can also provide topics related to posts on which the senior has commented. The conversation unit can also discuss the latest updates from accounts the senior follows. In this way, by analyzing the social media activity of the senior and selecting relevant topics, more appropriate conversations can be held. Some or all of the above-described processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can conduct a conversation using an AI model that analyzes the social media activity of the senior and selects relevant topics.

[0042] The analysis unit can optimize the analysis algorithm by referring to the seniors' past response data during analysis. The analysis unit optimizes the analysis algorithm by referring to the seniors' past response data during analysis. For example, the analysis unit adjusts the analysis algorithm based on data of seniors' accurate responses in the past. The analysis unit can also analyze the seniors' past response patterns to improve analysis accuracy. The analysis unit can also set anomaly detection criteria by referring to the seniors' past response data. In this way, the analysis accuracy is improved by optimizing the analysis algorithm by referring to the seniors' past response data. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that optimizes the analysis algorithm by referring to the seniors' past response data.

[0043] The analysis unit can apply different analysis methods depending on the category of the senior's answer during analysis. The analysis unit can apply different analysis methods depending on the category of the senior's answer during analysis. For example, the analysis unit can apply an analysis method based on medical data to answers regarding the senior's health. The analysis unit can also apply an analysis method based on behavioral data to answers regarding the senior's lifestyle habits. The analysis unit can also apply an emotion analysis method to answers regarding the senior's emotions. In this way, by applying different analysis methods depending on the category of the senior's answer, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that applies different analysis methods depending on the category of the senior's answer.

[0044] During analysis, the analysis unit can weight the analysis based on the time when the senior submitted the answer. During analysis, the analysis unit weights the analysis based on the time when the senior submitted the answer. For example, the analysis unit may prioritize answers recently submitted by the senior. The analysis unit may also prioritize answers submitted by the senior during a specific time period. The analysis unit may also weight the analysis by referring to answers submitted in the past by the senior. In this way, weighting the analysis based on the time when the senior submitted the answer improves the accuracy of the analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may perform analysis using an AI model that weights the analysis based on the time when the senior submitted the answer.

[0045] The analysis unit can improve the accuracy of the analysis by referring to literature related to seniors during the analysis. The analysis unit can improve the accuracy of the analysis by referring to literature related to seniors during the analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to literature related to the health status of seniors. The analysis unit can also improve the accuracy of the analysis by referring to literature related to the lifestyle habits of seniors. The analysis unit can also improve the accuracy of the analysis by referring to literature related to the emotions of seniors. In this way, the accuracy of the analysis is improved by referring to literature related to seniors. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform the analysis using an AI model that improves the accuracy of the analysis by referring to literature related to seniors.

[0046] The detection unit can optimize the detection algorithm by referring to the senior's past health data during detection. The detection unit can optimize the detection algorithm by referring to the senior's past health data during detection. For example, the detection unit sets anomaly detection criteria based on the senior's past health data. The detection unit can also adjust the detection algorithm by referring to the senior's past health data. The detection unit can also analyze the senior's past health data to improve the accuracy of anomaly detection. Thus, by optimizing the detection algorithm by referring to the senior's past health data, detection accuracy is improved. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that optimizes the detection algorithm by referring to the senior's past health data.

[0047] The detection unit can customize the abnormality detection method based on the senior's lifestyle habits at the time of detection. The detection unit customizes the abnormality detection method based on the senior's lifestyle habits at the time of detection. For example, the detection unit detects abnormalities based on the senior's eating habits. The detection unit can also detect abnormalities based on the senior's exercise habits. The detection unit can also detect abnormalities based on the senior's sleeping habits. In this way, customizing the abnormality detection method based on the senior's lifestyle habits enables more appropriate abnormality detection. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that customizes the abnormality detection method based on the senior's lifestyle habits.

[0048] The detection unit can select an anomaly detection method taking into account the senior's geographical location information during detection. The detection unit selects an anomaly detection method taking into account the senior's geographical location information during detection. For example, if the senior is at home, the detection unit applies a normal detection method. Furthermore, if the senior is out, the detection unit can also detect an anomaly based on location information. Furthermore, if the senior is in a specific location, the detection unit can apply a detection method appropriate to that location. In this way, selecting an anomaly detection method taking into account the senior's geographical location information enables more appropriate anomaly detection. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that selects an anomaly detection method taking into account the senior's geographical location information.

[0049] The detection unit can analyze the social media activity of the senior at the time of detection and propose a method for detecting an anomaly. The detection unit can analyze the social media activity of the senior at the time of detection and propose a method for detecting an anomaly. For example, the detection unit detects an anomaly if the senior makes an abnormal post on social media. The detection unit can also detect an anomaly based on changes in the senior's social media activity. The detection unit can also detect an anomaly if the senior uses a specific keyword on social media. This enables more appropriate anomaly detection by analyzing the social media activity of the senior and proposing a method for detecting an anomaly. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that analyzes the social media activity of the senior and proposes a method for detecting an anomaly.

[0050] The coordination unit can select the optimal coordination method by referring to the senior's past coordination history when coordinating. The coordination unit selects the optimal coordination method by referring to the senior's past coordination history when coordinating. For example, the coordination unit re-contacts family members who have been contacted by the senior in the past. The coordination unit can also select the optimal coordination method based on the senior's past coordination history. The coordination unit can also re-contact institutions that have been contacted by the senior in the past. In this way, by selecting the optimal coordination method by referring to the senior's past coordination history, coordination accuracy is improved. Some or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can perform coordination using an AI model that selects the optimal coordination method by referring to the senior's past coordination history.

[0051] The coordination unit can customize the means of coordination based on the senior's current living situation at the time of coordination. The coordination unit customizes the means of coordination based on the senior's current living situation at the time of coordination. For example, if the senior is at home, the coordination unit contacts the senior by phone. Also, if the senior is out, the coordination unit can contact the senior by email. Also, if the senior is in a specific location, the coordination unit can select a means of contact according to that location. This enables more appropriate coordination by customizing the means of coordination based on the senior's current living situation. Some or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can perform coordination using an AI model that customizes the means of coordination based on the senior's current living situation.

[0052] The coordination unit can select the optimal coordination method taking into consideration the geographical location information of the senior when performing coordination. The coordination unit selects the optimal coordination method taking into consideration the geographical location information of the senior when performing coordination. For example, when the senior is at home, the coordination unit applies a normal coordination method. Furthermore, when the senior is out, the coordination unit can also select a coordination method based on location information. Furthermore, when the senior is in a specific location, the coordination unit can also select a coordination method according to that location. In this way, more appropriate coordination is possible by selecting the optimal coordination method taking into consideration the geographical location information of the senior. Some or all of the above-described processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can perform coordination using an AI model that selects the optimal coordination method taking into consideration the geographical location information of the senior.

[0053] The collaboration unit can analyze the senior's social media activity and suggest collaboration methods when collaborating. The collaboration unit can analyze the senior's social media activity and suggest collaboration methods when collaborating. For example, if the senior posts something unusual on social media, the collaboration unit contacts the family. The collaboration unit can also select a collaboration method based on changes in the senior's social media activity. The collaboration unit can also contact an appropriate agency when the senior uses a specific keyword on social media. This enables more appropriate collaboration by analyzing the senior's social media activity and suggesting collaboration methods. Some or all of the above-mentioned processing in the collaboration unit may be performed using, for example, AI, or may be performed without using AI. For example, the collaboration unit can perform collaboration using an AI model that analyzes the senior's social media activity and suggests collaboration methods.

[0054] The question generation unit can optimize the content of the question by referring to the senior's past answer data when generating a question. The question generation unit optimizes the content of the question by referring to the senior's past answer data when generating a question. For example, the question generation unit generates a new question based on questions that the senior has answered correctly in the past. The question generation unit can also analyze the senior's past answer patterns and generate optimal questions. The question generation unit can also generate questions for anomaly detection by referring to the senior's past answer data. In this way, the accuracy of the questions is improved by optimizing the content of the question by referring to the senior's past answer data. Some or all of the above-described processing in the question generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the question generation unit can generate questions using an AI model that optimizes the content of the question by referring to the senior's past answer data.

[0055] The question generation unit can customize the content of the question based on the lifestyle habits of the senior when generating the question. The question generation unit customizes the content of the question based on the lifestyle habits of the senior when generating the question. For example, the question generation unit generates a question about health based on the dietary habits of the senior. The question generation unit can also generate a question about exercise based on the exercise habits of the senior. The question generation unit can also generate a question about sleep based on the sleep habits of the senior. This allows for customizing the content of the question based on the lifestyle habits of the senior, making it possible to ask more appropriate questions. Some or all of the above-described processing in the question generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the question generation unit can generate questions using an AI model that customizes the content of the question based on the lifestyle habits of the senior.

[0056] When generating questions, the question generation unit can prioritize generating highly relevant questions by taking into account the geographical location information of the senior. When generating questions, the question generation unit prioritizes generating highly relevant questions by taking into account the geographical location information of the senior. For example, the question generation unit generates questions related to news about the area where the senior lives. The question generation unit can also generate questions related to places frequently visited by the senior. The question generation unit can also generate questions related to local event information of the senior. In this way, generating highly relevant questions by taking into account the geographical location information of the senior enables more appropriate questions to be asked. Some or all of the above-described processing in the question generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the question generation unit can generate questions using an AI model that generates highly relevant questions by taking into account the geographical location information of the senior.

[0057] The question generation unit can analyze the social media activity of the senior to generate a relevant question when generating a question. The question generation unit can analyze the social media activity of the senior to generate a relevant question when generating a question. For example, the question generation unit generates a question related to an article shared by the senior on social media. The question generation unit can also generate a question related to a post on which the senior has commented. The question generation unit can also generate a question related to the latest updates on accounts that the senior follows. In this way, analyzing the social media activity of the senior to generate a relevant question enables more appropriate questions to be asked. Some or all of the above-described processing in the question generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the question generation unit can generate a question using an AI model that analyzes the social media activity of the senior to generate a relevant question.

[0058] The answer analysis unit can optimize the analysis algorithm by referring to the senior's past answer data when analyzing the answer. The answer analysis unit optimizes the analysis algorithm by referring to the senior's past answer data when analyzing the answer. For example, the answer analysis unit adjusts the analysis algorithm based on data of the senior's accurate answers in the past. The answer analysis unit can also analyze the senior's past answer patterns to improve analysis accuracy. The answer analysis unit can also set criteria for anomaly detection by referring to the senior's past answer data. In this way, the analysis accuracy is improved by optimizing the analysis algorithm by referring to the senior's past answer data. Some or all of the above-mentioned processing in the answer analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer analysis unit can perform analysis using an AI model that optimizes the analysis algorithm by referring to the senior's past answer data.

[0059] When analyzing the answers, the answer analysis unit can weight the analysis based on the time when the senior submitted the answer. When analyzing the answers, the answer analysis unit weights the analysis based on the time when the senior submitted the answer. For example, the answer analysis unit may prioritize answers recently submitted by seniors in the analysis. The answer analysis unit may also prioritize answers submitted by seniors during a specific time period in the analysis. The answer analysis unit may also weight the analysis by referring to answers previously submitted by seniors. In this way, weighting the analysis based on the time when the senior submitted the answer improves the accuracy of the analysis. Some or all of the above-described processing in the answer analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer analysis unit may perform the analysis using an AI model that weights the analysis based on the time when the senior submitted the answer.

[0060] The abnormality determination unit can optimize the determination algorithm by referring to the senior's past health data when determining an abnormality. The abnormality determination unit can optimize the determination algorithm by referring to the senior's past health data when determining an abnormality. For example, the abnormality determination unit sets criteria for abnormality determination based on the senior's past health data. The abnormality determination unit can also adjust the determination algorithm by referring to the senior's past health data. The abnormality determination unit can also analyze the senior's past health data to improve the accuracy of abnormality determination. Thus, by optimizing the determination algorithm by referring to the senior's past health data, the determination accuracy is improved. Some or all of the above-described processing in the abnormality determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the abnormality determination unit can make a determination using an AI model that optimizes the determination algorithm by referring to the senior's past health data.

[0061] When determining an abnormality, the abnormality determination unit can select an abnormality determination method taking into account the senior's geographical location information. When determining an abnormality, the abnormality determination unit selects an abnormality determination method taking into account the senior's geographical location information. For example, when the senior is at home, the abnormality determination unit applies a normal determination method. Furthermore, when the senior is out, the abnormality determination unit can also determine an abnormality based on location information. Furthermore, when the senior is in a specific location, the abnormality determination unit can apply a determination method appropriate to that location. In this way, selecting an abnormality determination method taking into account the senior's geographical location information enables more appropriate abnormality determination. Some or all of the above-described processing in the abnormality determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the abnormality determination unit can make a determination using an AI model that selects an abnormality determination method taking into account the senior's geographical location information.

[0062] The notification unit can select the optimal notification method by referring to the senior's past notification history when notifying the senior. The notification unit selects the optimal notification method by referring to the senior's past notification history when notifying the senior. For example, the notification unit selects the optimal notification method based on notification methods received by the senior in the past. The notification unit can also adjust the notification content by referring to the senior's past notification history. The notification unit can also analyze the senior's past notification history and select the most effective notification method. This improves notification accuracy by selecting the optimal notification method by referring to the senior's past notification history. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can perform notification using an AI model that selects the optimal notification method by referring to the senior's past notification history.

[0063] The notification unit can select the optimal notification method by taking into account the geographical location information of the senior when making a notification. The notification unit selects the optimal notification method by taking into account the geographical location information of the senior when making a notification. For example, if the senior is at home, the notification unit applies a normal notification method. Furthermore, if the senior is out, the notification unit can also select a notification method based on location information. Furthermore, if the senior is in a specific location, the notification unit can also select a notification method according to that location. In this way, by selecting the optimal notification method by taking into account the geographical location information of the senior, more appropriate notification is possible. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can perform notification using an AI model that selects the optimal notification method by taking into account the geographical location information of the senior.

[0064] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0065] The conversation unit can analyze the senior's past conversation history and select the most appropriate conversation content. For example, the conversation unit can revisit topics that the senior has shown interest in in the past. The conversation unit can also avoid topics that the senior has avoided in the past. The conversation unit can also suggest new topics based on topics that the senior has frequently talked about in the past. This enables more effective conversations by selecting the most appropriate conversation content based on the senior's past conversation history. Some or all of the above-described processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can conduct a conversation using an AI model that analyzes the senior's past conversation history and selects the most appropriate conversation content.

[0066] During a conversation, the conversation unit can customize the content of the conversation based on the senior's current health condition and living situation. For example, if the senior is feeling unwell, the conversation unit can provide health advice. The conversation unit can also gain empathy by having the senior talk about their recent living situation. If the senior has attended a specific event, the conversation unit can also talk about that event. This allows for more appropriate conversation by customizing the content of the conversation based on the senior's current health condition and living situation. Some or all of the above-described processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can conduct a conversation using an AI model that customizes the content of the conversation based on the senior's current health condition and living situation.

[0067] During a conversation, the conversation unit can prioritize selecting highly relevant topics based on the senior's geographic location information. For example, the conversation unit can discuss news from the area where the senior lives. The conversation unit can also provide topics related to places the senior often visits. The conversation unit can also discuss information about local events in the senior's area. This allows for more appropriate conversation by selecting highly relevant topics taking the senior's geographic location information into consideration. Some or all of the above-described processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can conduct a conversation using an AI model that selects highly relevant topics based on the senior's geographic location information.

[0068] During analysis, the analysis unit can optimize the analysis algorithm by referring to the seniors' past response data. For example, the analysis unit adjusts the analysis algorithm based on data of the seniors' past accurate responses. The analysis unit can also analyze the seniors' past response patterns to improve analysis accuracy. The analysis unit can also set anomaly detection criteria by referring to the seniors' past response data. This improves analysis accuracy by optimizing the analysis algorithm by referring to the seniors' past response data. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that optimizes the analysis algorithm by referring to the seniors' past response data.

[0069] During analysis, the analysis unit can apply different analysis methods depending on the category of the senior's answer. For example, the analysis unit can apply an analysis method based on medical data to answers regarding the senior's health. The analysis unit can also apply an analysis method based on behavioral data to answers regarding the senior's lifestyle habits. The analysis unit can also apply an emotion analysis method to answers regarding the senior's emotions. By applying different analysis methods depending on the category of the senior's answer, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that applies different analysis methods depending on the category of the senior's answer.

[0070] During analysis, the analysis unit can weight the analysis based on the time when the senior submitted the answer. For example, the analysis unit can weight the analysis by placing emphasis on answers recently submitted by the senior. The analysis unit can also weight the analysis by placing emphasis on answers submitted by the senior during a specific time period. The analysis unit can also weight the analysis by referring to answers submitted in the past by the senior. In this way, weighting the analysis based on the time when the senior submitted the answer improves the accuracy of the analysis. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can perform the analysis using an AI model that weights the analysis based on the time when the senior submitted the answer.

[0071] The processing flow of the first embodiment will be briefly explained below.

[0072] Step 1: The conversation unit conducts a conversation with the senior. The conversation with the senior includes, for example, everyday questions and conversations, but is not limited to such examples. The conversation unit includes, for example, a question generation unit that generates questions to check the senior's cognitive function. The question generation unit generates, for example, questions related to the senior's daily life. For example, it can generate questions such as "What day is it today?" or "What do you think about the recent news?" Step 2: The analysis unit analyzes the responses of the seniors obtained by the conversation unit. The analysis unit, for example, includes a response analysis unit in which AI analyzes the responses of the seniors. The response analysis unit analyzes the responses of the seniors using text analysis or voice analysis, for example. For example, the AI ​​analyzes the responses of the seniors using natural language processing technology and detects abnormalities. Step 3: The detection unit detects an abnormality based on the results of the analysis by the analysis unit. The detection unit, for example, includes an abnormality determination unit that determines changes in the senior's cognitive function. The abnormality determination unit, for example, uses AI to determine changes in the senior's cognitive function. The AI ​​determines changes in the senior's cognitive function using machine learning algorithms and pattern recognition technology. Step 4: The linking unit links to appropriate people or institutions when an abnormality is detected by the detection unit. The linking unit includes, for example, a notification unit that sends a notification when an abnormality is detected. The notification unit sends a notification to, for example, the senior's family, a care facility, or a medical institution. The notification unit can send the notification by, for example, email, telephone, app notification, or other method.

[0073] (Example 2) A system according to an embodiment of the present invention provides a service that allows seniors to retire with peace of mind. This system uses a home robot or a chatbot speaker to check for dementia through daily conversations with seniors and, if an abnormality is detected, contacts appropriate individuals or organizations. For example, the home robot or chatbot speaker engages in daily conversations with seniors, generates questions to check the senior's cognitive function, and analyzes the senior's responses. For example, questions such as "What day is it today?" or "What do you think about the recent news?" are asked. The chatbot then analyzes the senior's responses and checks for abnormalities. For example, if the senior gets the date wrong or fails to provide an appropriate answer to a question, the chatbot detects the abnormality. This analysis is performed using AI, and changes in the senior's cognitive function are continuously monitored. If an abnormality is detected, the chatbot contacts appropriate individuals or organizations. For example, a notification is sent to the senior's family, a nursing home, or a medical institution. The notification includes information about the senior's cognitive function change and specific abnormalities. This is expected to lead to early and appropriate action. This service allows seniors to retire with peace of mind. This is because home robots and speaker chatbots converse with seniors on a daily basis and check their cognitive functions, allowing abnormalities to be detected early and appropriate measures to be taken. Furthermore, it also makes it easier for seniors' families, nursing homes, and medical institutions to understand their condition and keep an eye on them with peace of mind. For example, even if a senior lives alone, home robots and speaker chatbots can detect changes in their cognitive functions early by conversing with them on a daily basis. This allows seniors to continue living alone with peace of mind, and makes it easier for families, nursing homes, and medical institutions to understand their condition. Furthermore, this service is provided while respecting seniors' privacy. To protect seniors' privacy, home robots and speaker chatbots collect only the minimum amount of information necessary and connect with appropriate people and institutions. This allows seniors to use the service with peace of mind. This allows the system to check seniors' cognitive functions on a daily basis and take appropriate measures if abnormalities are detected.

[0074] The system according to the embodiment includes a conversation unit, an analysis unit, a detection unit, and a linking unit. The conversation unit engages in conversation with seniors. The conversation with seniors includes, but is not limited to, everyday questions and conversations. The conversation unit includes, for example, a question generation unit that generates questions to check the senior's cognitive function. The question generation unit generates, for example, questions related to the senior's daily life. For example, questions such as "What day is it today?" and "What do you think about the recent news?" can be generated. The analysis unit analyzes the senior's answers obtained by the conversation unit. The analysis unit includes, for example, an answer analysis unit that uses AI to analyze the senior's answers. The answer analysis unit analyzes the senior's answers using text analysis or voice analysis. For example, the AI ​​analyzes the senior's answers using natural language processing technology to detect an abnormality. The detection unit detects an abnormality based on the results of the analysis by the analysis unit. The detection unit includes, for example, an abnormality determination unit that determines a change in the senior's cognitive function. For example, the abnormality determination unit determines a change in the senior's cognitive function using AI. The AI ​​determines changes in the senior's cognitive function using machine learning algorithms and pattern recognition technology. The linking unit links to appropriate people or institutions when an abnormality is detected by the detection unit. The linking unit includes, for example, a notification unit that sends a notification when an abnormality is detected. The notification unit sends a notification to, for example, the senior's family, a nursing facility, or a medical institution. The notification unit can send the notification by email, telephone, app notification, or other methods. This allows the system according to the embodiment to routinely check the senior's cognitive function and take appropriate action when an abnormality is detected. Some or all of the above-described processes in the conversation unit, analysis unit, detection unit, and linking unit may be performed using, for example, AI, or may be performed without AI. For example, the conversation unit may use AI to analyze the conversation with the senior, the analysis unit may use AI to analyze the senior's responses, the detection unit may use AI to determine changes in the senior's cognitive function, and the linking unit may send a notification using an AI model that sends a notification when an abnormality is detected.

[0075] The conversation unit may include a question generation unit that generates questions to check the senior's cognitive function. The question generation unit generates questions related to the senior's daily life. For example, the question generation unit can generate questions related to the senior's diet, exercise, and hobbies. For example, the question generation unit can generate questions such as "What did you eat today?" or "How has your exercise been lately?" This makes it possible to generate questions to effectively check the senior's cognitive function. Some or all of the above-described processing in the question generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the question generation unit can generate questions using an AI model that generates questions related to the senior's daily life.

[0076] The analysis unit may include an answer analysis unit that analyzes the answers of seniors. The answer analysis unit analyzes the answers of seniors using AI. For example, the answer analysis unit analyzes the answers of seniors using text analysis or voice analysis. For example, the AI ​​analyzes the answers of seniors using natural language processing technology to detect abnormalities. This allows the answers of seniors to be analyzed effectively. Some or all of the above-mentioned processing in the answer analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the answer analysis unit may perform analysis using an AI model that analyzes the answers of seniors.

[0077] The detection unit can include an abnormality determination unit that determines changes in the senior's cognitive function. The abnormality determination unit determines changes in the senior's cognitive function using AI. For example, the abnormality determination unit determines changes in the senior's cognitive function using a machine learning algorithm or pattern recognition technology. This makes it possible to effectively determine changes in the senior's cognitive function. Some or all of the above-mentioned processing in the abnormality determination unit may be performed using AI, for example, or may be performed without using AI. For example, the abnormality determination unit can make a determination using an AI model that determines changes in the senior's cognitive function.

[0078] The linking unit may include a notification unit that sends a notification when an abnormality is detected. The notification unit sends a notification to the senior's family, a nursing facility, or a medical institution. For example, the notification unit may send a notification by email, telephone, app notification, or other method. This allows an appropriate notification to be sent when an abnormality is detected. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit may send a notification using an AI model that sends a notification when an abnormality is detected.

[0079] The question generation unit can generate questions related to the daily life of seniors. The question generation unit generates questions related to the daily life of seniors. For example, the question generation unit can generate questions related to the senior's diet, exercise, and hobbies. For example, the question generation unit can generate questions such as, "What did you eat today?" or "How has your exercise been lately?" By generating questions related to the daily life of seniors, more effective cognitive function checks are possible. Some or all of the above-described processing in the question generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the question generation unit can generate questions using an AI model that generates questions related to the daily life of seniors.

[0080] The answer analysis unit can analyze the answers of seniors using AI. The answer analysis unit analyzes the answers of seniors using AI. For example, the answer analysis unit analyzes the answers of seniors using text analysis or voice analysis. For example, the AI ​​analyzes the answers of seniors using natural language processing technology and detects abnormalities. In this way, the use of AI improves the accuracy of analyzing the answers of seniors. Some or all of the above-mentioned processing in the answer analysis unit may be performed using AI, for example, or may be performed without using AI. For example, the answer analysis unit can perform analysis using an AI model that analyzes the answers of seniors.

[0081] The abnormality determination unit can determine changes in the cognitive function of seniors using AI. The abnormality determination unit determines changes in the cognitive function of seniors using AI. For example, the abnormality determination unit determines changes in the cognitive function of seniors using a machine learning algorithm or pattern recognition technology. As a result, the use of AI improves the accuracy of determining changes in the cognitive function of seniors. Some or all of the above-mentioned processing in the abnormality determination unit may be performed using AI, for example, or may be performed without using AI. For example, the abnormality determination unit can make a determination using an AI model that determines changes in the cognitive function of seniors.

[0082] The notification unit can send notifications to the senior's family, nursing facilities, and medical institutions. The notification unit can send notifications to the senior's family, nursing facilities, and medical institutions. For example, the notification unit can send notifications by email, telephone, app notification, or other methods. This allows appropriate notifications to be sent to the senior's family, nursing facilities, and medical institutions. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can send notifications using an AI model that sends notifications when an abnormality is detected.

[0083] The conversation unit can estimate the senior's emotions and adjust the tone and content of the conversation based on the estimated emotions. The conversation unit can estimate the senior's emotions and adjust the tone and content of the conversation based on the estimated emotions. For example, if the senior is feeling anxious, the conversation unit can use a calm tone to provide a sense of security. If the senior is having fun, the conversation unit can use a bright tone to provide fun topics. If the senior is tired, the conversation unit can use short, concise conversations to reduce the senior's burden. This enables more appropriate conversation by adjusting the tone and content of the conversation based on the senior's emotions. Emotion estimation is achieved using an emotion estimation function, 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. Some or all of the above-mentioned processing in the conversation unit can be performed using, for example, AI, or without AI. For example, the conversation unit can conduct a conversation using an AI model that estimates the senior's emotions and adjusts the tone and content of the conversation based on the estimated emotions.

[0084] The conversation unit can analyze the senior's past conversation history and select the optimal conversation content. The conversation unit analyzes the senior's past conversation history and selects the optimal conversation content. For example, the conversation unit revisits topics that the senior has shown interest in in the past. The conversation unit can also avoid topics that the senior has avoided in the past. The conversation unit can also suggest new topics based on topics that the senior has frequently talked about in the past. This enables more effective conversations by selecting the optimal conversation content based on the senior's past conversation history. Some or all of the above-mentioned processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can conduct a conversation using an AI model that analyzes the senior's past conversation history and selects the optimal conversation content.

[0085] The conversation unit can customize the conversation content based on the senior's current health condition and living situation during the conversation. The conversation unit customizes the conversation content based on the senior's current health condition and living situation during the conversation. For example, if the senior is not feeling well, the conversation unit can provide health advice. The conversation unit can also gain empathy by having the senior talk about their recent living situation. If the senior has participated in a specific event, the conversation unit can also talk about that event. This allows for more appropriate conversation by customizing the conversation content based on the senior's current health condition and living situation. Some or all of the above-described processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can conduct a conversation using an AI model that customizes the conversation content based on the senior's current health condition and living situation.

[0086] The conversation unit can estimate the senior's emotions and adjust the frequency of conversations based on the estimated emotions. The conversation unit can estimate the senior's emotions and adjust the frequency of conversations based on the estimated emotions. For example, the conversation unit can increase the frequency of conversations if the senior feels lonely. The conversation unit can also decrease the frequency of conversations if the senior is busy. The conversation unit can also have conversations at an appropriate frequency if the senior is relaxed. This enables more appropriate conversations by adjusting the frequency of conversations according to the senior's emotions. Emotion estimation is realized using an emotion estimation function, 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. Some or all of the above-mentioned processing in the conversation unit can be performed using, for example, AI, or without AI. For example, the conversation unit can conduct a conversation using an AI model that estimates the senior's emotions and adjusts the frequency of conversations based on the estimated emotions.

[0087] During a conversation, the conversation unit can prioritize selecting a highly relevant topic based on the senior's geographical location information. During a conversation, the conversation unit prioritizes selecting a highly relevant topic based on the senior's geographical location information. For example, the conversation unit may discuss news from the area where the senior lives. The conversation unit may also provide topics related to places the senior often visits. The conversation unit may also discuss information about local events in the senior's area. This enables a more appropriate conversation by selecting a highly relevant topic taking the senior's geographical location information into consideration. Some or all of the above-described processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit may conduct a conversation using an AI model that selects a highly relevant topic based on the senior's geographical location information.

[0088] The conversation unit can analyze the social media activity of the senior during the conversation and select relevant topics. The conversation unit can analyze the social media activity of the senior during the conversation and select relevant topics. For example, the conversation unit can discuss articles shared by the senior on social media. The conversation unit can also provide topics related to posts on which the senior has commented. The conversation unit can also discuss the latest updates from accounts the senior follows. In this way, by analyzing the social media activity of the senior and selecting relevant topics, more appropriate conversations can be held. Some or all of the above-described processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can conduct a conversation using an AI model that analyzes the social media activity of the senior and selects relevant topics.

[0089] The analysis unit can estimate the senior's emotions and adjust the answer analysis method based on the estimated senior's emotions. The analysis unit can estimate the senior's emotions and adjust the answer analysis method based on the estimated senior's emotions. For example, if the senior is nervous, the analysis unit can prioritize answers to simple questions. Also, if the senior is relaxed, the analysis unit can analyze detailed answers. Also, if the senior is tired, the analysis unit can prioritize short answers. This allows for more appropriate analysis by adjusting the answer analysis method according to the senior's emotions. Emotion estimation is achieved using an emotion estimation function, 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. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can perform analysis using an AI model that estimates the senior's emotions and adjusts the answer analysis method based on the estimated senior's emotions.

[0090] The analysis unit can optimize the analysis algorithm by referring to the seniors' past response data during analysis. The analysis unit optimizes the analysis algorithm by referring to the seniors' past response data during analysis. For example, the analysis unit adjusts the analysis algorithm based on data of seniors' accurate responses in the past. The analysis unit can also analyze the seniors' past response patterns to improve analysis accuracy. The analysis unit can also set anomaly detection criteria by referring to the seniors' past response data. In this way, the analysis accuracy is improved by optimizing the analysis algorithm by referring to the seniors' past response data. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that optimizes the analysis algorithm by referring to the seniors' past response data.

[0091] The analysis unit can apply different analysis methods depending on the category of the senior's answer during analysis. The analysis unit can apply different analysis methods depending on the category of the senior's answer during analysis. For example, the analysis unit can apply an analysis method based on medical data to answers regarding the senior's health. The analysis unit can also apply an analysis method based on behavioral data to answers regarding the senior's lifestyle habits. The analysis unit can also apply an emotion analysis method to answers regarding the senior's emotions. In this way, by applying different analysis methods depending on the category of the senior's answer, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that applies different analysis methods depending on the category of the senior's answer.

[0092] The analysis unit can estimate the senior's emotions and determine the analysis priorities based on the estimated emotions. The analysis unit can estimate the senior's emotions and determine the analysis priorities based on the estimated emotions. For example, if the senior is feeling anxious, the analysis unit can prioritize analyzing answers related to emotions. Also, if the senior is relaxed, the analysis unit can prioritize analyzing answers related to health. Also, if the senior is excited, the analysis unit can prioritize analyzing answers related to lifestyle habits. This enables more appropriate analysis by determining the analysis priorities based on the senior's emotions. Emotion estimation is achieved using an emotion estimation function, 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. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can perform analysis using an AI model that estimates the senior's emotions and determines the analysis priorities based on the estimated emotions.

[0093] During analysis, the analysis unit can weight the analysis based on the time when the senior submitted the answer. During analysis, the analysis unit weights the analysis based on the time when the senior submitted the answer. For example, the analysis unit may prioritize answers recently submitted by the senior. The analysis unit may also prioritize answers submitted by the senior during a specific time period. The analysis unit may also weight the analysis by referring to answers submitted in the past by the senior. In this way, weighting the analysis based on the time when the senior submitted the answer improves the accuracy of the analysis. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may perform analysis using an AI model that weights the analysis based on the time when the senior submitted the answer.

[0094] The analysis unit can improve the accuracy of the analysis by referring to literature related to seniors during the analysis. The analysis unit can improve the accuracy of the analysis by referring to literature related to seniors during the analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to literature related to the health status of seniors. The analysis unit can also improve the accuracy of the analysis by referring to literature related to the lifestyle habits of seniors. The analysis unit can also improve the accuracy of the analysis by referring to literature related to the emotions of seniors. In this way, the accuracy of the analysis is improved by referring to literature related to seniors. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform the analysis using an AI model that improves the accuracy of the analysis by referring to literature related to seniors.

[0095] The detection unit can estimate the senior's emotions and adjust the abnormality detection criteria based on the estimated senior's emotions. The detection unit can estimate the senior's emotions and adjust the abnormality detection criteria based on the estimated senior's emotions. For example, if the senior is feeling anxious, the detection unit can detect abnormalities by focusing on changes in emotions. Furthermore, if the senior is relaxed, the detection unit can detect abnormalities by focusing on changes in health status. Furthermore, if the senior is excited, the detection unit can detect abnormalities by focusing on changes in lifestyle habits. This enables more appropriate abnormality detection by adjusting the abnormality detection criteria according to the senior's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or without AI. For example, the detection unit can perform detection using an AI model that estimates the senior's emotions and adjusts the abnormality detection criteria based on the estimated senior's emotions.

[0096] The detection unit can optimize the detection algorithm by referring to the senior's past health data during detection. The detection unit can optimize the detection algorithm by referring to the senior's past health data during detection. For example, the detection unit sets anomaly detection criteria based on the senior's past health data. The detection unit can also adjust the detection algorithm by referring to the senior's past health data. The detection unit can also analyze the senior's past health data to improve the accuracy of anomaly detection. Thus, by optimizing the detection algorithm by referring to the senior's past health data, detection accuracy is improved. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that optimizes the detection algorithm by referring to the senior's past health data.

[0097] The detection unit can customize the abnormality detection method based on the senior's lifestyle habits at the time of detection. The detection unit customizes the abnormality detection method based on the senior's lifestyle habits at the time of detection. For example, the detection unit detects abnormalities based on the senior's eating habits. The detection unit can also detect abnormalities based on the senior's exercise habits. The detection unit can also detect abnormalities based on the senior's sleeping habits. In this way, customizing the abnormality detection method based on the senior's lifestyle habits enables more appropriate abnormality detection. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that customizes the abnormality detection method based on the senior's lifestyle habits.

[0098] The detection unit can estimate the senior's emotion and adjust the frequency of anomaly detection based on the estimated senior's emotion. The detection unit can estimate the senior's emotion and adjust the frequency of anomaly detection based on the estimated senior's emotion. For example, the detection unit can increase the detection frequency when the senior is feeling anxious. The detection unit can also decrease the detection frequency when the senior is relaxed. The detection unit can also perform detection at an appropriate frequency when the senior is excited. This enables more appropriate anomaly detection by adjusting the frequency of anomaly detection according to the senior's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or without AI. For example, the detection unit can perform detection using an AI model that estimates the senior's emotion and adjusts the frequency of anomaly detection based on the estimated senior's emotion.

[0099] The detection unit can select an anomaly detection method taking into account the senior's geographical location information during detection. The detection unit selects an anomaly detection method taking into account the senior's geographical location information during detection. For example, if the senior is at home, the detection unit applies a normal detection method. Furthermore, if the senior is out, the detection unit can also detect an anomaly based on location information. Furthermore, if the senior is in a specific location, the detection unit can apply a detection method appropriate to that location. In this way, selecting an anomaly detection method taking into account the senior's geographical location information enables more appropriate anomaly detection. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that selects an anomaly detection method taking into account the senior's geographical location information.

[0100] The detection unit can analyze the social media activity of the senior at the time of detection and propose a method for detecting an anomaly. The detection unit can analyze the social media activity of the senior at the time of detection and propose a method for detecting an anomaly. For example, the detection unit detects an anomaly if the senior makes an abnormal post on social media. The detection unit can also detect an anomaly based on changes in the senior's social media activity. The detection unit can also detect an anomaly if the senior uses a specific keyword on social media. This enables more appropriate anomaly detection by analyzing the social media activity of the senior and proposing a method for detecting an anomaly. Some or all of the above-described processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can perform detection using an AI model that analyzes the social media activity of the senior and proposes a method for detecting an anomaly.

[0101] The collaboration unit can estimate the senior's emotions and adjust the collaboration method based on the estimated senior's emotions. The collaboration unit can estimate the senior's emotions and adjust the collaboration method based on the estimated senior's emotions. For example, if the senior is feeling anxious, the collaboration unit can quickly contact the family. If the senior is relaxed, the collaboration unit can also apply a normal collaboration method. If the senior is excited, the collaboration unit can also contact an appropriate agency. This enables more appropriate collaboration by adjusting the collaboration method according to the senior's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collaboration unit may be performed using AI, for example, or without AI. For example, the collaboration unit can perform collaboration using an AI model that estimates the senior's emotions and adjusts the collaboration method based on the estimated senior's emotions.

[0102] The coordination unit can select the optimal coordination method by referring to the senior's past coordination history when coordinating. The coordination unit selects the optimal coordination method by referring to the senior's past coordination history when coordinating. For example, the coordination unit re-contacts family members who have been contacted by the senior in the past. The coordination unit can also select the optimal coordination method based on the senior's past coordination history. The coordination unit can also re-contact institutions that have been contacted by the senior in the past. In this way, by selecting the optimal coordination method by referring to the senior's past coordination history, coordination accuracy is improved. Some or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can perform coordination using an AI model that selects the optimal coordination method by referring to the senior's past coordination history.

[0103] The coordination unit can customize the means of coordination based on the senior's current living situation at the time of coordination. The coordination unit customizes the means of coordination based on the senior's current living situation at the time of coordination. For example, if the senior is at home, the coordination unit contacts the senior by phone. Also, if the senior is out, the coordination unit can contact the senior by email. Also, if the senior is in a specific location, the coordination unit can select a means of contact according to that location. This enables more appropriate coordination by customizing the means of coordination based on the senior's current living situation. Some or all of the above-mentioned processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can perform coordination using an AI model that customizes the means of coordination based on the senior's current living situation.

[0104] The collaboration unit can estimate the senior's emotions and determine collaboration priorities based on the estimated senior's emotions. The collaboration unit can estimate the senior's emotions and determine collaboration priorities based on the estimated senior's emotions. For example, if the senior is feeling anxious, the collaboration unit can prioritize contacting family members. If the senior is relaxed, the collaboration unit can also apply a normal collaboration method. If the senior is excited, the collaboration unit can also prioritize contacting appropriate organizations. This enables more appropriate collaboration by determining collaboration priorities based on the senior's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the collaboration unit can be performed using AI, for example, or without AI. For example, the collaboration unit can perform collaboration using an AI model that estimates the senior's emotions and determines collaboration priorities based on the estimated senior's emotions.

[0105] The coordination unit can select the optimal coordination method taking into consideration the geographical location information of the senior when performing coordination. The coordination unit selects the optimal coordination method taking into consideration the geographical location information of the senior when performing coordination. For example, when the senior is at home, the coordination unit applies a normal coordination method. Furthermore, when the senior is out, the coordination unit can also select a coordination method based on location information. Furthermore, when the senior is in a specific location, the coordination unit can also select a coordination method according to that location. In this way, more appropriate coordination is possible by selecting the optimal coordination method taking into consideration the geographical location information of the senior. Some or all of the above-described processing in the coordination unit may be performed using, for example, AI, or may be performed without using AI. For example, the coordination unit can perform coordination using an AI model that selects the optimal coordination method taking into consideration the geographical location information of the senior.

[0106] The collaboration unit can analyze the senior's social media activity and suggest collaboration methods when collaborating. The collaboration unit can analyze the senior's social media activity and suggest collaboration methods when collaborating. For example, if the senior posts something unusual on social media, the collaboration unit contacts the family. The collaboration unit can also select a collaboration method based on changes in the senior's social media activity. The collaboration unit can also contact an appropriate agency when the senior uses a specific keyword on social media. This enables more appropriate collaboration by analyzing the senior's social media activity and suggesting collaboration methods. Some or all of the above-mentioned processing in the collaboration unit may be performed using, for example, AI, or may be performed without using AI. For example, the collaboration unit can perform collaboration using an AI model that analyzes the senior's social media activity and suggests collaboration methods.

[0107] The question generation unit can estimate the senior's emotions and adjust the content of the questions based on the estimated emotions. The question generation unit can estimate the senior's emotions and adjust the content of the questions based on the estimated emotions. For example, if the senior is feeling anxious, the question generation unit can ask a question that gives a sense of security. If the senior is relaxed, the question generation unit can ask a detailed question. If the senior is tired, the question generation unit can ask a simple question. This allows for more appropriate questions to be asked by adjusting the content of the questions according to the senior's emotions. Emotion estimation is achieved using an emotion estimation function, 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 these examples. Some or all of the above-mentioned processing in the question generation unit can be performed using, for example, AI, or can be performed without using AI. For example, the question generation unit can generate questions using an AI model that estimates the senior's emotions and adjusts the content of the questions based on the estimated emotions.

[0108] The question generation unit can optimize the content of the question by referring to the senior's past answer data when generating a question. The question generation unit optimizes the content of the question by referring to the senior's past answer data when generating a question. For example, the question generation unit generates a new question based on questions that the senior has answered correctly in the past. The question generation unit can also analyze the senior's past answer patterns and generate optimal questions. The question generation unit can also generate questions for anomaly detection by referring to the senior's past answer data. In this way, the accuracy of the questions is improved by optimizing the content of the question by referring to the senior's past answer data. Some or all of the above-described processing in the question generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the question generation unit can generate questions using an AI model that optimizes the content of the question by referring to the senior's past answer data.

[0109] The question generation unit can customize the content of the question based on the lifestyle habits of the senior when generating the question. The question generation unit customizes the content of the question based on the lifestyle habits of the senior when generating the question. For example, the question generation unit generates a question about health based on the dietary habits of the senior. The question generation unit can also generate a question about exercise based on the exercise habits of the senior. The question generation unit can also generate a question about sleep based on the sleep habits of the senior. This allows for customizing the content of the question based on the lifestyle habits of the senior, making it possible to ask more appropriate questions. Some or all of the above-described processing in the question generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the question generation unit can generate questions using an AI model that customizes the content of the question based on the lifestyle habits of the senior.

[0110] The question generation unit can estimate the senior's emotions and adjust the frequency of questions based on the estimated senior's emotions. The question generation unit can estimate the senior's emotions and adjust the frequency of questions based on the estimated senior's emotions. For example, the question generation unit can increase the frequency of questions when the senior is feeling anxious. The question generation unit can also decrease the frequency of questions when the senior is relaxed. The question generation unit can also ask questions at an appropriate frequency when the senior is excited. This allows for more appropriate questions to be asked by adjusting the frequency of questions according to the senior's emotions. Emotion estimation is achieved using an emotion estimation function, 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. Some or all of the above-mentioned processing in the question generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the question generation unit can generate questions using an AI model that estimates the senior's emotions and adjusts the frequency of questions based on the estimated senior's emotions.

[0111] When generating questions, the question generation unit can prioritize generating highly relevant questions by taking into account the geographical location information of the senior. When generating questions, the question generation unit prioritizes generating highly relevant questions by taking into account the geographical location information of the senior. For example, the question generation unit generates questions related to news about the area where the senior lives. The question generation unit can also generate questions related to places frequently visited by the senior. The question generation unit can also generate questions related to local event information of the senior. In this way, generating highly relevant questions by taking into account the geographical location information of the senior enables more appropriate questions to be asked. Some or all of the above-described processing in the question generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the question generation unit can generate questions using an AI model that generates highly relevant questions by taking into account the geographical location information of the senior.

[0112] The question generation unit can analyze the social media activity of the senior to generate a relevant question when generating a question. The question generation unit can analyze the social media activity of the senior to generate a relevant question when generating a question. For example, the question generation unit generates a question related to an article shared by the senior on social media. The question generation unit can also generate a question related to a post on which the senior has commented. The question generation unit can also generate a question related to the latest updates on accounts that the senior follows. In this way, analyzing the social media activity of the senior to generate a relevant question enables more appropriate questions to be asked. Some or all of the above-described processing in the question generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the question generation unit can generate a question using an AI model that analyzes the social media activity of the senior to generate a relevant question.

[0113] The answer analysis unit can estimate the senior's emotions and adjust the answer analysis method based on the estimated senior's emotions. The answer analysis unit can estimate the senior's emotions and adjust the answer analysis method based on the estimated senior's emotions. For example, if the senior is nervous, the answer analysis unit can prioritize answers to simple questions. Also, if the senior is relaxed, the answer analysis unit can analyze detailed answers. Also, if the senior is tired, the answer analysis unit can prioritize analyzing short answers. This allows for more appropriate analysis by adjusting the answer analysis method according to the senior's emotions. Emotion estimation is achieved using an emotion estimation function, 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. Some or all of the above-mentioned processing in the answer analysis unit can be performed using, for example, AI, or without AI. For example, the answer analysis unit can perform analysis using an AI model that estimates the senior's emotions and adjusts the answer analysis method based on the estimated senior's emotions.

[0114] The answer analysis unit can optimize the analysis algorithm by referring to the senior's past answer data when analyzing the answer. The answer analysis unit optimizes the analysis algorithm by referring to the senior's past answer data when analyzing the answer. For example, the answer analysis unit adjusts the analysis algorithm based on data of the senior's accurate answers in the past. The answer analysis unit can also analyze the senior's past answer patterns to improve analysis accuracy. The answer analysis unit can also set criteria for anomaly detection by referring to the senior's past answer data. In this way, the analysis accuracy is improved by optimizing the analysis algorithm by referring to the senior's past answer data. Some or all of the above-mentioned processing in the answer analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer analysis unit can perform analysis using an AI model that optimizes the analysis algorithm by referring to the senior's past answer data.

[0115] The answer analysis unit can estimate the senior's emotions and determine the analysis priorities based on the estimated emotions. The answer analysis unit can estimate the senior's emotions and determine the analysis priorities based on the estimated emotions. For example, if the senior is feeling anxious, the answer analysis unit can prioritize analyzing answers related to emotions. Also, if the senior is relaxed, the answer analysis unit can prioritize analyzing answers related to health. Also, if the senior is excited, the answer analysis unit can prioritize analyzing answers related to lifestyle habits. This enables more appropriate analysis by determining the analysis priorities based on the senior's emotions. Emotion estimation is achieved using an emotion estimation function, 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. Some or all of the above-mentioned processing in the answer analysis unit can be performed using, for example, AI, or without AI. For example, the answer analysis unit can perform analysis using an AI model that estimates the senior's emotions and determines the analysis priorities based on the estimated emotions.

[0116] When analyzing the answers, the answer analysis unit can weight the analysis based on the time when the senior submitted the answer. When analyzing the answers, the answer analysis unit weights the analysis based on the time when the senior submitted the answer. For example, the answer analysis unit may prioritize answers recently submitted by seniors in the analysis. The answer analysis unit may also prioritize answers submitted by seniors during a specific time period in the analysis. The answer analysis unit may also weight the analysis by referring to answers previously submitted by seniors. In this way, weighting the analysis based on the time when the senior submitted the answer improves the accuracy of the analysis. Some or all of the above-described processing in the answer analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the answer analysis unit may perform the analysis using an AI model that weights the analysis based on the time when the senior submitted the answer.

[0117] The abnormality determination unit can estimate the senior's emotions and adjust the abnormality determination criteria based on the estimated senior's emotions. The abnormality determination unit can estimate the senior's emotions and adjust the abnormality determination criteria based on the estimated senior's emotions. For example, if the senior is feeling anxious, the abnormality determination unit can determine an abnormality by focusing on changes in emotions. Furthermore, if the senior is relaxed, the abnormality determination unit can determine an abnormality by focusing on changes in health status. Furthermore, if the senior is excited, the abnormality determination unit can determine an abnormality by focusing on changes in lifestyle habits. This enables more appropriate abnormality determination by adjusting the abnormality determination criteria according to the senior's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the abnormality determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the abnormality determination unit can make a determination using an AI model that estimates the senior's emotions and adjusts the abnormality determination criteria based on the estimated senior's emotions.

[0118] The abnormality determination unit can optimize the determination algorithm by referring to the senior's past health data when determining an abnormality. The abnormality determination unit can optimize the determination algorithm by referring to the senior's past health data when determining an abnormality. For example, the abnormality determination unit sets criteria for abnormality determination based on the senior's past health data. The abnormality determination unit can also adjust the determination algorithm by referring to the senior's past health data. The abnormality determination unit can also analyze the senior's past health data to improve the accuracy of abnormality determination. Thus, by optimizing the determination algorithm by referring to the senior's past health data, the determination accuracy is improved. Some or all of the above-described processing in the abnormality determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the abnormality determination unit can make a determination using an AI model that optimizes the determination algorithm by referring to the senior's past health data.

[0119] The abnormality determination unit can estimate the senior's emotion and adjust the frequency of abnormality determination based on the estimated senior's emotion. The abnormality determination unit can estimate the senior's emotion and adjust the frequency of abnormality determination based on the estimated senior's emotion. For example, the abnormality determination unit can increase the determination frequency when the senior is feeling anxious. The abnormality determination unit can also decrease the determination frequency when the senior is relaxed. The abnormality determination unit can also make determinations at an appropriate frequency when the senior is excited. This enables more appropriate abnormality determination by adjusting the frequency of abnormality determination according to the senior's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the abnormality determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the abnormality determination unit can make a determination using an AI model that estimates the senior's emotion and adjusts the frequency of abnormality determination based on the estimated senior's emotion.

[0120] When determining an abnormality, the abnormality determination unit can select an abnormality determination method taking into account the senior's geographical location information. When determining an abnormality, the abnormality determination unit selects an abnormality determination method taking into account the senior's geographical location information. For example, when the senior is at home, the abnormality determination unit applies a normal determination method. Furthermore, when the senior is out, the abnormality determination unit can also determine an abnormality based on location information. Furthermore, when the senior is in a specific location, the abnormality determination unit can apply a determination method appropriate to that location. In this way, selecting an abnormality determination method taking into account the senior's geographical location information enables more appropriate abnormality determination. Some or all of the above-described processing in the abnormality determination unit may be performed using, for example, AI, or may be performed without using AI. For example, the abnormality determination unit can make a determination using an AI model that selects an abnormality determination method taking into account the senior's geographical location information.

[0121] The notification unit can estimate the senior's emotion and adjust the content of the notification based on the estimated senior's emotion. The notification unit can estimate the senior's emotion and adjust the content of the notification based on the estimated senior's emotion. For example, if the senior is feeling anxious, the notification unit can provide a notification with content that gives a sense of security. Furthermore, if the senior is relaxed, the notification unit can provide a notification with detailed content. Furthermore, if the senior is excited, the notification unit can provide a notification with concise content. This allows for more appropriate notification by adjusting the content of the notification according to the senior's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can provide a notification using an AI model that estimates the senior's emotion and adjusts the content of the notification based on the estimated senior's emotion.

[0122] The notification unit can select the optimal notification method by referring to the senior's past notification history when notifying the senior. The notification unit selects the optimal notification method by referring to the senior's past notification history when notifying the senior. For example, the notification unit selects the optimal notification method based on notification methods received by the senior in the past. The notification unit can also adjust the notification content by referring to the senior's past notification history. The notification unit can also analyze the senior's past notification history and select the most effective notification method. This improves notification accuracy by selecting the optimal notification method by referring to the senior's past notification history. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can perform notification using an AI model that selects the optimal notification method by referring to the senior's past notification history.

[0123] The notification unit can estimate the senior's emotions and determine the priority of notifications based on the estimated emotions. The notification unit can estimate the senior's emotions and determine the priority of notifications based on the estimated emotions. For example, if the senior is feeling anxious, the notification unit can prioritize notifying family members. If the senior is relaxed, the notification unit can also apply a normal notification method. If the senior is excited, the notification unit can also prioritize notifying appropriate institutions. This enables more appropriate notifications by determining the priority of notifications based on the senior's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the notification unit can be performed using AI, for example, or without AI. For example, the notification unit can perform notifications using an AI model that estimates the senior's emotions and determines the priority of notifications based on the estimated emotions.

[0124] The notification unit can select the optimal notification method by taking into account the geographical location information of the senior when making a notification. The notification unit selects the optimal notification method by taking into account the geographical location information of the senior when making a notification. For example, if the senior is at home, the notification unit applies a normal notification method. Furthermore, if the senior is out, the notification unit can also select a notification method based on location information. Furthermore, if the senior is in a specific location, the notification unit can also select a notification method according to that location. In this way, by selecting the optimal notification method by taking into account the geographical location information of the senior, more appropriate notification is possible. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can perform notification using an AI model that selects the optimal notification method by taking into account the geographical location information of the senior. === Hard Collateral 1-1 === Each of the multiple elements including the conversation unit, analysis unit, detection unit, and collaboration unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the conversation unit is realized by the control unit 46A of the smart device 14 and conducts daily conversations with the senior. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the senior's responses. The detection unit is realized by the specific processing unit 290 of the data processing device 12 and detects anomalies based on the analysis results. The collaboration unit is realized by the specific processing unit 290 of the data processing device 12 and sends a notification to appropriate people or institutions when an anomaly is detected. === Hard Collateral 1-2 === Each of the multiple elements including the conversation unit, analysis unit, detection unit, and collaboration unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the conversation unit is realized by the control unit 46A of the smart glasses 214 and conducts everyday conversations with the senior. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the senior's responses. The detection unit is realized by the specific processing unit 290 of the data processing device 12 and detects an abnormality based on the analysis result. The collaboration unit is realized by the specific processing unit 290 of the data processing device 12 and sends a notification to an appropriate person or institution when an abnormality is detected. === Hard Collateral 1-3 === Each of the multiple elements including the conversation unit, analysis unit, detection unit, and linkage unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the conversation unit is realized by the control unit 46A of the headset-type terminal 314 and conducts everyday conversations with the senior. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the senior's responses. The detection unit is realized by the specific processing unit 290 of the data processing device 12 and detects anomalies based on the analysis results. The linkage unit is realized by the specific processing unit 290 of the data processing device 12 and sends a notification to appropriate people or institutions when an anomaly is detected. === Hard Collateral 1-4 === Each of the multiple elements including the conversation unit, analysis unit, detection unit, and collaboration unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the conversation unit is realized by the control unit 46A of the robot 414 and conducts everyday conversations with the senior. The analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the senior's responses. The detection unit is realized by the specific processing unit 290 of the data processing device 12 and detects anomalies based on the analysis results. The collaboration unit is realized by the specific processing unit 290 of the data processing device 12 and sends a notification to appropriate people or institutions when an anomaly is detected.

[0125] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0126] The conversation unit can estimate the senior's emotions and adjust the tone and content of the conversation based on the estimated senior's emotions. For example, if the senior is feeling anxious, the conversation unit can use a calm tone to provide a sense of security. If the senior is enjoying themselves, the conversation unit can also use a bright tone to provide enjoyable topics. If the senior is tired, the conversation unit can use short, concise conversations to reduce their burden. This enables more appropriate conversations by adjusting the tone and content of the conversation based on the senior's emotions. Emotion estimation is achieved using an emotion estimation function, 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. Some or all of the above-described processing in the conversation unit may be performed using, for example, AI, or without AI. For example, the conversation unit can conduct a conversation using an AI model that estimates the senior's emotions and adjusts the tone and content of the conversation based on the estimated senior's emotions.

[0127] The conversation unit can analyze the senior's past conversation history and select the most appropriate conversation content. For example, the conversation unit can revisit topics that the senior has shown interest in in the past. The conversation unit can also avoid topics that the senior has avoided in the past. The conversation unit can also suggest new topics based on topics that the senior has frequently talked about in the past. This enables more effective conversations by selecting the most appropriate conversation content based on the senior's past conversation history. Some or all of the above-described processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can conduct a conversation using an AI model that analyzes the senior's past conversation history and selects the most appropriate conversation content.

[0128] During a conversation, the conversation unit can customize the content of the conversation based on the senior's current health condition and living situation. For example, if the senior is feeling unwell, the conversation unit can provide health advice. The conversation unit can also gain empathy by having the senior talk about their recent living situation. If the senior has attended a specific event, the conversation unit can also talk about that event. This allows for more appropriate conversation by customizing the content of the conversation based on the senior's current health condition and living situation. Some or all of the above-described processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can conduct a conversation using an AI model that customizes the content of the conversation based on the senior's current health condition and living situation.

[0129] The conversation unit can estimate the senior's emotions and adjust the frequency of conversation based on the estimated senior's emotions. For example, the conversation unit can increase the frequency of conversation if the senior feels lonely. The conversation unit can also decrease the frequency of conversation if the senior is busy. The conversation unit can also maintain a moderate frequency of conversation if the senior is relaxed. This allows for more appropriate conversation by adjusting the frequency of conversation according to the senior's emotions. The emotion estimation is realized using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the conversation unit can be performed using, for example, AI, or without AI. For example, the conversation unit can conduct a conversation using an AI model that estimates the senior's emotions and adjusts the frequency of conversation based on the estimated senior's emotions.

[0130] During a conversation, the conversation unit can prioritize selecting highly relevant topics based on the senior's geographic location information. For example, the conversation unit can discuss news from the area where the senior lives. The conversation unit can also provide topics related to places the senior often visits. The conversation unit can also discuss information about local events in the senior's area. This allows for more appropriate conversation by selecting highly relevant topics taking the senior's geographic location information into consideration. Some or all of the above-described processing in the conversation unit may be performed using, for example, AI, or may be performed without using AI. For example, the conversation unit can conduct a conversation using an AI model that selects highly relevant topics based on the senior's geographic location information.

[0131] The analysis unit can estimate the senior's emotions and adjust the answer analysis method based on the estimated senior's emotions. For example, if the senior is nervous, the analysis unit can prioritize answers to simple questions. Furthermore, if the senior is relaxed, the analysis unit can analyze detailed answers. Furthermore, if the senior is tired, the analysis unit can prioritize short answers. This allows for more appropriate analysis by adjusting the answer analysis method according to the senior's emotions. The emotion estimation is achieved using an emotion estimation function, 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. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can perform analysis using an AI model that estimates the senior's emotions and adjusts the answer analysis method based on the estimated senior's emotions.

[0132] During analysis, the analysis unit can optimize the analysis algorithm by referring to the seniors' past response data. For example, the analysis unit adjusts the analysis algorithm based on data of the seniors' past accurate responses. The analysis unit can also analyze the seniors' past response patterns to improve analysis accuracy. The analysis unit can also set anomaly detection criteria by referring to the seniors' past response data. This improves analysis accuracy by optimizing the analysis algorithm by referring to the seniors' past response data. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that optimizes the analysis algorithm by referring to the seniors' past response data.

[0133] During analysis, the analysis unit can apply different analysis methods depending on the category of the senior's answer. For example, the analysis unit can apply an analysis method based on medical data to answers regarding the senior's health. The analysis unit can also apply an analysis method based on behavioral data to answers regarding the senior's lifestyle habits. The analysis unit can also apply an emotion analysis method to answers regarding the senior's emotions. By applying different analysis methods depending on the category of the senior's answer, the accuracy of the analysis is improved. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can perform analysis using an AI model that applies different analysis methods depending on the category of the senior's answer.

[0134] The analysis unit can estimate the senior's emotions and determine the analysis priority based on the estimated senior's emotions. For example, if the senior is feeling anxious, the analysis unit can prioritize analyzing responses related to emotions. Furthermore, if the senior is relaxed, the analysis unit can prioritize analyzing responses related to health. Furthermore, if the senior is excited, the analysis unit can prioritize analyzing responses related to lifestyle habits. This enables more appropriate analysis by determining the analysis priority based on the senior's emotions. The emotion estimation is realized using an emotion estimation function, 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. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can perform analysis using an AI model that estimates the senior's emotions and determines the analysis priority based on the estimated senior's emotions.

[0135] During analysis, the analysis unit can weight the analysis based on the time when the senior submitted the answer. For example, the analysis unit can weight the analysis by placing emphasis on answers recently submitted by the senior. The analysis unit can also weight the analysis by placing emphasis on answers submitted by the senior during a specific time period. The analysis unit can also weight the analysis by referring to answers submitted in the past by the senior. In this way, weighting the analysis based on the time when the senior submitted the answer improves the accuracy of the analysis. Some or all of the above-mentioned processing in the analysis unit can be performed using, for example, AI, or can be performed without using AI. For example, the analysis unit can perform the analysis using an AI model that weights the analysis based on the time when the senior submitted the answer.

[0136] The processing flow of the second embodiment will be briefly explained below.

[0137] Step 1: The conversation unit conducts a conversation with the senior. The conversation with the senior includes, for example, everyday questions and conversations, but is not limited to such examples. The conversation unit includes, for example, a question generation unit that generates questions to check the senior's cognitive function. The question generation unit generates, for example, questions related to the senior's daily life. For example, it can generate questions such as "What day is it today?" or "What do you think about the recent news?" Step 2: The analysis unit analyzes the responses of the seniors obtained by the conversation unit. The analysis unit, for example, includes a response analysis unit in which AI analyzes the responses of the seniors. The response analysis unit analyzes the responses of the seniors using text analysis or voice analysis, for example. For example, the AI ​​analyzes the responses of the seniors using natural language processing technology and detects abnormalities. Step 3: The detection unit detects an abnormality based on the results of the analysis by the analysis unit. The detection unit, for example, includes an abnormality determination unit that determines changes in the senior's cognitive function. The abnormality determination unit, for example, uses AI to determine changes in the senior's cognitive function. The AI ​​determines changes in the senior's cognitive function using machine learning algorithms and pattern recognition technology. Step 4: The linking unit links to appropriate people or institutions when an abnormality is detected by the detection unit. The linking unit includes, for example, a notification unit that sends a notification when an abnormality is detected. The notification unit sends a notification to, for example, the senior's family, a care facility, or a medical institution. The notification unit can send the notification by, for example, email, telephone, app notification, or other method.

[0138] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0140] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0143] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0144] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] 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.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0150] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0152] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0153] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0154] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0156] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

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

[0158] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0159] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0160] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0161] 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.

[0162] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0164] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0165] 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.

[0166] 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.

[0167] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0168] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0169] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0170] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0171] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0172] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0173] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0174] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0175] 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.

[0176] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0177] 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.

[0178] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0179] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0180] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0181] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0182] 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.

[0183] 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.

[0184] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0185] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0186] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0187] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0188] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0189] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0190] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0191] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0192] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0193] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0194] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0195] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0196] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0197] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0198] 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.

[0199] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0200] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0201] 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.

[0202] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0203] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0204] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0205] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0206] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0207] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0208] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0209] [Explanation of symbols]

[0210] 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 section where participants talk with seniors, an analysis unit that analyzes the responses of the seniors obtained by the conversation unit; a detection unit that detects an abnormality based on the result of the analysis by the analysis unit; a linking unit that links to a specific person or organization when an abnormality is detected by the detection unit; Equipped with A system characterized by:

2. The conversation unit is A question generation unit is provided to generate questions to check the cognitive function of seniors. The system of claim 1 .

3. The analysis unit Equipped with a response analysis unit that analyzes responses from seniors The system of claim 1 .

4. The detection unit Equipped with an abnormality detection unit that detects changes in the cognitive function of seniors The system of claim 1 .

5. The linking unit is Equipped with a notification unit that sends a notification when an abnormality is detected The system of claim 1 .

6. The question generation unit Generate questions related to the daily lives of seniors 3. The system of claim 2.

7. The answer analysis unit AI analyzes seniors' responses 4. The system of claim 3.

8. The abnormality determination unit AI determines changes in cognitive function in seniors 5. The system of claim 4.

9. The notification unit Send notifications to the senior's family, nursing homes, and medical facilities 6. The system of claim 5.

Images