system

Abstract

The system according to the embodiment aims to enable elderly people to live without feeling lonely. [Solution] A system according to an embodiment includes an ascertaining unit, a generating unit, a dialogue unit, and a reminding unit. The ascertaining unit grasps hobbies and interests. The generating unit creates a pseudo-personality based on the hobbies and interests grasped by the ascertaining unit. The dialogue unit allows the elderly person to dialogue with the pseudo-personality created by the generating unit. The reminding unit provides reminders based on the dialogue held by the dialogue 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 do not provide sufficient effective measures to help elderly people live without feeling lonely, and there is room for improvement.

[0005] The system according to the embodiment aims to enable elderly people to live without feeling lonely. [Means for solving the problem]

[0006] The system according to the embodiment includes a grasping unit, a generating unit, a dialogue unit, and a reminding unit. The grasping unit grasps hobbies and interests. The generating unit creates a pseudo-personality based on the hobbies and interests grasped by the grasping unit. The dialogue unit allows the elderly person to dialogue with the pseudo-personality created by the generating unit. The reminding unit provides reminders based on the dialogue held by the dialogue unit. [Effects of the Invention]

[0007] The system according to the embodiment can enable elderly people to live without feeling lonely. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A system according to an embodiment of the present invention uses a generation AI to create pseudo-personalities and create good-old-fashioned neighbors so that elderly people can live without feeling lonely. This system allows elderly people to talk with multiple pseudo-neighbors through the generation AI. For example, the system can respond to a variety of topics, from hobbies, travel, and food to health care and neighborhood gossip, facilitating smooth communication. Within these topics, the system can provide information necessary for daily life and provide reminders (e.g., "Tomorrow's hospital appointment starts at 10 a.m."). This allows elderly people to live without feeling lonely and improve their quality of life. For example, the generation AI can identify the elderly person's hobbies and interests and create a pseudo-personality based on them. For example, for an elderly person who enjoys traveling, the system can generate a pseudo-neighbor who is knowledgeable about travel topics. The elderly then talks with the pseudo-neighbor through the generation AI. The system can respond to a variety of topics, such as food and health care advice. This allows elderly people to enjoy everyday conversations. Furthermore, the generation AI can provide information necessary for daily life and provide reminders. For example, by being reminded of tomorrow's hospital appointment, elderly people can keep to their schedule without forgetting. This service allows elderly people to live without feeling lonely, improving their quality of life. For example, conversations with virtual neighbors can increase the enjoyment of everyday life, and receiving health care advice can also help maintain health. In this way, the system allows elderly people to live without feeling lonely, improving their quality of life.

[0029] The system according to the embodiment includes a comprehension unit, a generation unit, a dialogue unit, and a reminder unit. The comprehension unit comprehends the hobbies and interests of the elderly. For example, the comprehension unit can collect the elderly's favorite hobbies and interests, such as music, sports, and reading. The comprehension unit can comprehend the elderly's hobbies and interests through, for example, questionnaires or interviews. The comprehension unit can also comprehend the elderly's hobbies and interests by analyzing social media or past behavioral history. The generation unit uses a generation AI to create a pseudo-personality based on the hobbies and interests comprehended by the comprehension unit. For example, for an elderly person who likes traveling, the generation unit generates a pseudo-personality that is knowledgeable about travel topics. The generation unit can use the generation AI to set personality traits and a dialogue style to create the pseudo-personality. For example, the generation AI generates a pseudo-personality that likes traveling based on the elderly's hobbies and interests. The generation unit can also evolve the pseudo-personality by having the generation AI learn the elderly's reactions. The dialogue unit allows the elderly person to interact with the pseudo-personality created by the generation unit. For example, the dialogue unit uses a generation AI to have a dialogue between the elderly person and a pseudo-personality. The dialogue unit can respond to various topics, such as health care and neighborhood gossip. The dialogue unit can realize a natural dialogue using the generation AI. The reminder unit provides reminders based on the dialogue conducted by the dialogue unit. For example, the reminder unit uses the generation AI to provide reminders of information necessary for daily life. For example, the reminder unit can remind the elderly person of tomorrow's hospital appointment time, so that the elderly person will not forget to complete their schedule. The reminder unit can provide reminders using the generation AI by means of voice notification, text message, or the like. As a result, the system according to the embodiment can enable the elderly person to live without feeling lonely and improve their quality of life.

[0030] The generation unit can use the generation AI to create a pseudo-personality based on the hobbies and interests of the elderly person. For example, the generation unit uses the generation AI to create a pseudo-personality based on the hobbies and interests of the elderly person. For example, for an elderly person who likes traveling, the generation unit generates a pseudo-personality that is knowledgeable about travel topics. The generation unit can also use the generation AI to set personality traits and a conversation style to create a pseudo-personality. For example, the generation unit generates a pseudo-personality that likes traveling based on the hobbies and interests of the elderly person. Furthermore, the generation unit can have the generation AI learn the elderly person's reactions and evolve the pseudo-personality. For example, the generation AI learns the elderly person's reactions and adjusts the personality traits and conversation style of the pseudo-personality. This generates a pseudo-personality based on the hobbies and interests of the elderly person, enabling a more friendly conversation. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the generation unit can create a pseudo-personality using a generative AI model for generating a pseudo-personality based on the hobbies and interests of an elderly person.

[0031] The dialogue unit can use the generation AI to have a dialogue between the elderly person and the pseudo-personality. The dialogue unit, for example, uses the generation AI to have a dialogue between the elderly person and the pseudo-personality. For example, the dialogue unit generates prompts for the generation AI to have a dialogue between the elderly person and the pseudo-personality, thereby realizing a natural dialogue. The dialogue unit can also use the generation AI to respond to various topics, such as health management and neighborhood gossip. For example, the dialogue unit can have the generation AI provide advice on health management. The dialogue unit can also have the generation AI provide information on neighborhood gossip. Furthermore, the dialogue unit can use the generation AI to estimate the elderly person's emotions and adjust the content and tone of the dialogue. For example, the dialogue unit can have the generation AI estimate the elderly person's emotions and conduct the dialogue in a relaxed tone. This enables a natural dialogue by using the generation AI. Some or all of the above-mentioned processing in the dialogue unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the dialogue unit can realize the dialogue using a generative AI model for having a dialogue between the elderly person and the pseudo-personality.

[0032] The reminding unit can use a generating AI to remind the elderly about information necessary for daily life. The reminding unit, for example, uses a generating AI to remind the elderly about information necessary for daily life. For example, the reminding unit uses a generating AI to manage the elderly's schedule and send reminders. The reminding unit can also use a generating AI to send reminders by voice notification, text message, or other methods. For example, the reminding unit uses a generating AI to remind the elderly about tomorrow's hospital appointment. The reminding unit can also use a generating AI to estimate the elderly's emotions and adjust the reminding method. For example, the reminding unit uses a generating AI to estimate the elderly's emotions and send reminders in a relaxed tone. This allows the elderly to remember to manage information necessary for daily life. Some or all of the above-mentioned processing in the reminding unit may be performed using, for example, a generating AI, or may be performed without using a generating AI. For example, the reminding unit can realize reminders using a generating AI model for reminding the elderly about information necessary for daily life.

[0033] The generation unit can use the generation AI to learn the reactions of the elderly and evolve the pseudo-personality. The generation unit, for example, uses the generation AI to learn the reactions of the elderly and evolve the pseudo-personality. For example, the generation unit uses the generation AI to learn the reactions of the elderly and adjust the personality traits and conversation style of the pseudo-personality. The generation unit can also use the generation AI to improve the knowledge and skills of the pseudo-personality based on the reactions of the elderly. For example, the generation unit uses the generation AI to learn the reactions of the elderly and update the knowledge of the pseudo-personality. This allows the pseudo-personality to evolve based on the reactions of the elderly, enabling more appropriate conversations. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the generation unit can learn the reactions of the elderly and evolve the pseudo-personality using a generation AI model for evolving the pseudo-personality.

[0034] The dialogue unit can respond to at least one or more topics of health care or neighborhood gossip using a generation AI. The dialogue unit can respond to various topics, such as health care or neighborhood gossip, using, for example, a generation AI. For example, the dialogue unit can provide advice on health care using the generation AI. The dialogue unit can also provide information on neighborhood gossip using the generation AI. Furthermore, the dialogue unit can estimate the elderly person's emotions and adjust the content and tone of the dialogue using the generation AI. For example, the dialogue unit can estimate the elderly person's emotions using the generation AI and conduct the dialogue in a relaxed tone. This allows the elderly person to enjoy dialogue on a variety of topics. Some or all of the above-mentioned processing in the dialogue unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the dialogue unit can realize dialogue using a generation AI model for responding to various topics, such as health care or neighborhood gossip.

[0035] The ascertaining unit can analyze the elderly person's past behavioral history and select an appropriate method for ascertaining the elderly person's hobbies and interests. The ascertaining unit can, for example, use a generation AI to analyze the elderly person's past behavioral history and select an appropriate method for ascertaining the elderly person's hobbies and interests. For example, the ascertaining unit can cause the generation AI to ascertain optimal hobbies and interests based on events and activities the elderly person frequently participated in in the past. The ascertaining unit can also ascertain optimal hobbies and interests based on places the elderly person has visited or traveled to in the past. Furthermore, the ascertaining unit can ascertain optimal hobbies and interests based on books the elderly person has read or movies they have watched in the past. In this way, optimal hobbies and interests can be ascertained based on the elderly person's past behavioral history. The behavioral history is analyzed, for example, using a generation AI. The generation AI can analyze the past behavioral history and extract patterns of hobbies and interests. Some or all of the above-described processing in the ascertaining unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the ascertaining unit can analyze the past behavioral history and ascertain the hobbies and interests using a generation AI model for ascertaining hobbies and interests.

[0036] The comprehension unit can filter the hobbies and interests based on the elderly person's current living situation and health condition when comprehending the hobbies and interests. The comprehension unit, for example, uses a generation AI to filter the hobbies and interests based on the elderly person's current living situation and health condition when comprehending the hobbies and interests. For example, if the elderly person's health is poor, the comprehension unit can cause the generation AI to prioritize comprehending hobbies and interests that do not require much physical effort. Furthermore, if the elderly person's living situation is busy, the comprehension unit can also prioritize comprehending hobbies and interests that can be enjoyed in a short amount of time. Furthermore, if the elderly person's living situation is stable, the comprehension unit can prioritize comprehending hobbies and interests that can be continued over the long term. This makes it possible to comprehend the hobbies and interests according to the elderly person's living situation and health condition. The filtering of the living situation and health condition is performed, for example, using a generation AI. The generation AI can analyze the elderly person's living situation and health condition and select appropriate hobbies and interests. Some or all of the above-described processing in the comprehension unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the comprehension unit can understand hobbies and interests using generative AI models to filter lifestyle and health conditions.

[0037] The ascertaining unit can prioritize relevant information by taking into account the geographical location information of the elderly person when ascertaining the hobbies and interests. The ascertaining unit, for example, uses a generation AI to prioritize relevant information by taking into account the geographical location information of the elderly person when ascertaining the hobbies and interests. For example, the ascertaining unit identifies the most suitable hobbies and interests for the generation AI based on events and activities in the area where the elderly person lives. The ascertaining unit can also identify the most suitable hobbies and interests for the generation AI based on events and activities held near places frequently visited by the elderly person. Furthermore, the ascertaining unit can also identify the most suitable hobbies and interests for the generation AI based on the culture and traditions of the area where the elderly person lives. This makes it possible to ascertain the hobbies and interests based on the geographical location information of the elderly person. The geographical location information is taken into account by, for example, a generation AI. The generation AI can analyze the geographical location information of the elderly person and select appropriate hobbies and interests. Some or all of the above-described processing by the ascertaining unit may be performed by, for example, a generation AI, or may be performed without using a generation AI. For example, the ascertaining unit can identify the hobbies and interests using a generation AI model for ascertaining hobbies and interests by taking into account geographical location information.

[0038] The identification unit can analyze the elderly person's social media activity and identify related information when identifying the elderly person's hobbies and interests. The identification unit can, for example, use a generation AI to analyze the elderly person's social media activity and identify related information when identifying the elderly person's hobbies and interests. For example, the identification unit can identify the most suitable hobbies and interests for the generation AI based on content frequently shared by the elderly person on social media. The identification unit can also identify the most suitable hobbies and interests for the generation AI based on the content of accounts the elderly person follows on social media. Furthermore, the identification unit can identify the most suitable hobbies and interests for the generation AI based on the content of groups and communities the elderly person participates in on social media. This makes it possible to identify the elderly person's hobbies and interests based on their social media activity. The analysis of social media activity can be performed, for example, using a generation AI. The generation AI can analyze the elderly person's social media activity and select appropriate hobbies and interests. Some or all of the above-described processing in the identification unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the identification unit can identify the hobbies and interests using a generation AI model for analyzing social media activity to identify hobbies and interests.

[0039] The generation unit can adjust the level of detail of the pseudo-personality based on the importance of the elderly person's hobbies and interests when generating the pseudo-personality. The generation unit can adjust the level of detail of the pseudo-personality based on the importance of the elderly person's hobbies and interests when generating the pseudo-personality, for example, using a generation AI. For example, the generation unit can generate a pseudo-personality with detailed knowledge of hobbies in which the elderly person is particularly interested. The generation unit can also generate a pseudo-personality with basic knowledge of hobbies in which the elderly person is not very interested. Furthermore, the generation unit can generate a pseudo-personality with moderate knowledge of hobbies in which the elderly person has recently become interested. This makes it possible to generate a pseudo-personality based on the importance of the elderly person's hobbies and interests. The importance evaluation is performed, for example, using a generation AI. The generation AI can analyze the importance of the elderly person's hobbies and interests and determine an appropriate level of detail of the generation. Some or all of the above-described processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generator can generate a pseudo-personality using a generative AI model to adjust the level of detail of the generation based on the importance of hobbies and interests.

[0040] The generation unit can apply different generation algorithms depending on the category of the elderly person when generating the pseudo-personality. The generation unit can, for example, use a generation AI to apply different generation algorithms depending on the category of the elderly person when generating the pseudo-personality. For example, if the elderly person is interested in health management, the generation AI can generate a pseudo-personality with knowledge about health. Furthermore, if the elderly person is interested in travel, the generation unit can generate a pseudo-personality with knowledge about travel. Furthermore, if the elderly person is interested in food, the generation AI can generate a pseudo-personality with knowledge about food. This makes it possible to generate pseudo-personalities according to the category of the elderly person. The application of categories is performed, for example, using a generation AI. The generation AI can analyze the category of the elderly person and select an appropriate generation algorithm. Some or all of the above-mentioned processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generation unit can generate a pseudo-personality using a generation AI model for applying a generation algorithm depending on the category.

[0041] The generation unit can determine the generation priority based on the elderly person's past dialogue history when generating the pseudo-personality. The generation unit can determine the generation priority based on the elderly person's past dialogue history when generating the pseudo-personality, for example, using a generation AI. For example, the generation unit can generate an optimal pseudo-personality based on topics that the elderly person frequently talked about in the past. The generation unit can also generate an optimal pseudo-personality based on topics that the elderly person has shown interest in in the past. Furthermore, the generation unit can generate an optimal pseudo-personality based on topics that the elderly person has avoided in the past. This makes it possible to generate a pseudo-personality based on the elderly person's past dialogue history. The dialogue history can be analyzed using, for example, a generation AI. The generation AI can analyze the elderly person's dialogue history and determine appropriate generation priorities. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the generation unit can generate a pseudo-personality using a generation AI model for determining generation priorities based on a dialogue history.

[0042] The generation unit can adjust the order of generation based on the elderly's relevance when generating pseudo-personalities. The generation unit can adjust the order of generation based on the elderly's relevance when generating pseudo-personalities, for example, using a generation AI. For example, the generation unit can prioritize generating pseudo-personalities related to topics that the elderly are most interested in. The generation unit can also generate pseudo-personalities related to topics that the elderly are second most interested in next. Furthermore, the generation unit can generate pseudo-personalities related to topics that the elderly are least interested in last. This enables the generation of pseudo-personalities based on the elderly's relevance. The evaluation of relevance is performed, for example, using a generation AI. The generation AI can analyze the degree of similarity of the elderly's interests and common topics and determine an appropriate generation order. Some or all of the above-mentioned processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generation unit can generate pseudo-personalities using a generation AI model for adjusting the order of generation based on relevance.

[0043] The dialogue unit can adjust the level of detail of the dialogue based on the importance of the topic during the dialogue. The dialogue unit can, for example, use a generation AI to adjust the level of detail of the dialogue based on the importance of the topic during the dialogue. For example, the dialogue unit can have the generation AI provide detailed information on topics that the elderly are particularly interested in. The dialogue unit can also have the generation AI provide basic information on topics that the elderly are not very interested in. Furthermore, the dialogue unit can have the generation AI provide medium information on topics in which the elderly have recently become interested. This makes it possible to adjust the level of detail of the dialogue according to the importance of the topic. The importance is evaluated, for example, using a generation AI. The generation AI can analyze the elderly's level of interest and influence and determine an appropriate level of detail of the dialogue. Some or all of the above-mentioned processing in the dialogue unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the dialogue unit can realize the dialogue using a generation AI model for adjusting the level of detail of the dialogue based on the importance of the topic.

[0044] The dialogue unit can apply different dialogue algorithms depending on the topic category during dialogue. The dialogue unit, for example, uses a generation AI to apply different dialogue algorithms depending on the topic category during dialogue. For example, when the topic is about health management, the dialogue unit can apply a dialogue algorithm in which the generation AI has knowledge about health. Furthermore, when the topic is about travel, the dialogue unit can apply a dialogue algorithm in which the generation AI has knowledge about travel. Furthermore, when the topic is about food, the dialogue unit can apply a dialogue algorithm in which the generation AI has knowledge about food. This makes it possible to apply a dialogue algorithm depending on the topic category. The category is applied using, for example, a generation AI. The generation AI can analyze the type of topic and the area of ​​interest and select an appropriate dialogue algorithm. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the dialogue unit can realize a dialogue using a generation AI model for applying a dialogue algorithm depending on the topic category.

[0045] The dialogue unit can determine the priority of dialogues based on the time when the topic was submitted during the dialogue. The dialogue unit can, for example, use a generation AI to determine the priority of dialogues based on the time when the topic was submitted during the dialogue. For example, the dialogue unit can have the generation AI prioritize dialogues regarding topics that the elderly person has recently become interested in. The dialogue unit can also have the generation AI next conduct dialogues regarding topics that the elderly person was interested in in the past. Furthermore, the dialogue unit can have the generation AI last conduct dialogues regarding topics that the elderly person is not very interested in. This makes it possible to determine the priority of dialogues based on the time when the topic was submitted. The submission time is evaluated using, for example, a generation AI. The generation AI can analyze the submission date and time and frequency of topics and determine appropriate dialogue priorities. Some or all of the above-mentioned processing in the dialogue unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the dialogue unit can realize dialogues using a generation AI model for determining the priority of dialogues based on the time when the topic was submitted.

[0046] The dialogue unit can adjust the order of dialogues based on the relevance of topics during dialogue. The dialogue unit can adjust the order of dialogues based on the relevance of topics during dialogue, for example, using a generation AI. For example, the dialogue unit can have the generation AI prioritize dialogues regarding topics in which the elderly are most interested. The dialogue unit can also have the generation AI next dialogue regarding topics in which the elderly are second most interested. Furthermore, the dialogue unit can have the generation AI last dialogue regarding topics in which the elderly are least interested. This makes it possible to adjust the order of dialogues based on the relevance of topics. The evaluation of relevance is performed, for example, using a generation AI. The generation AI can analyze the commonality of topics and the degree of agreement of interests and determine an appropriate order of dialogues. Some or all of the above-mentioned processing in the dialogue unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the dialogue unit can realize dialogues using a generation AI model for adjusting the order of dialogues based on the relevance of topics.

[0047] The reminding unit can select the optimal reminding method by analyzing the elderly person's past behavioral history when reminding. The reminding unit can select the optimal reminding method by using, for example, a generation AI. For example, the reminding unit can select the optimal reminding method based on plans that the elderly person tends to forget in the past. The reminding unit can also select the optimal reminding method based on actions that the elderly person frequently performed in the past. Furthermore, the reminding unit can also select the optimal reminding method based on plans that the elderly person considered important in the past. This makes it possible to select the optimal reminding method based on the elderly person's past behavioral history. The behavioral history is analyzed, for example, using a generation AI. The generation AI can analyze the elderly person's behavioral history and select an appropriate reminding method. Some or all of the above-mentioned processing in the reminding unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the reminding unit can realize reminding using a generation AI model for analyzing the behavioral history and selecting a reminding method.

[0048] The reminding unit can customize the reminder means based on the elderly person's current living situation when giving a reminder. The reminding unit can customize the reminder means based on the elderly person's current living situation when giving a reminder, for example, using a generation AI. For example, if the elderly person is busy, the generation AI can provide a short, to-the-point reminder. Furthermore, if the elderly person is relaxed, the generation AI can provide a detailed reminder. Furthermore, if the elderly person is not feeling well, the generation AI can provide a gentler reminder. This enables customization of the reminder means according to the elderly person's living situation. The evaluation of the living situation is performed, for example, using a generation AI. The generation AI can analyze the elderly person's living situation and select an appropriate reminder means. Some or all of the above-described processing in the reminding unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the reminding unit can realize reminders using a generation AI model for customizing the reminder means based on the living situation.

[0049] The reminding unit can select the optimal reminding method by taking into account the geographical location information of the elderly person when reminding. The reminding unit, for example, uses a generation AI to select the optimal reminding method by taking into account the geographical location information of the elderly person when reminding. For example, if the elderly person is at home, the reminding unit can have the generation AI perform a reminder that should be performed at home. Also, if the elderly person is out, the reminding unit can also perform a reminder that should be performed while the elderly person is out. Furthermore, if the elderly person is in a specific location, the generation AI can perform a reminder related to that location. This makes it possible to select the optimal reminding method based on the elderly person's geographical location information. The geographical location information is taken into account by, for example, a generation AI. The generation AI can analyze the elderly person's geographical location information and select an appropriate reminding method. Some or all of the above-mentioned processing in the reminding unit may be performed by, for example, a generation AI, or may be performed without using a generation AI. For example, the reminding unit can realize reminding by using a generation AI model for selecting a reminding method by taking into account geographical location information.

[0050] The reminding unit can analyze the elderly person's social media activity and suggest a reminder method when reminding the elderly person. The reminding unit can, for example, use a generation AI to analyze the elderly person's social media activity and suggest a reminder method when reminding the elderly person. For example, the reminding unit can use the generation AI to suggest the optimal reminder method based on the content frequently shared by the elderly person on social media. The reminding unit can also use the generation AI to suggest the optimal reminder method based on the content of accounts the elderly person follows on social media. Furthermore, the reminding unit can also use the generation AI to suggest the optimal reminder method based on the content of groups and communities the elderly person participates in on social media. This makes it possible to suggest reminder methods based on the elderly person's social media activity. The analysis of social media activity can be performed, for example, using a generation AI. The generation AI can analyze the elderly person's social media activity and select an appropriate reminder method. Some or all of the above-mentioned processing in the reminding unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the reminding unit can realize reminders using a generation AI model for analyzing social media activity and suggesting reminder methods.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The system can further include a health monitoring unit that monitors the elderly person's health data in real time. The health monitoring unit collects health data such as the elderly person's heart rate, blood pressure, and body temperature using a wearable device, for example. The collected data is analyzed using generative AI, and if an abnormality is detected, the elderly person is notified through the dialogue unit. The health monitoring unit can also provide health management advice based on the collected data. For example, if the heart rate is high, advice on relaxation is provided. This allows the elderly person's health condition to be understood in real time and appropriate measures to be taken.

[0053] When generating a pseudo-personality, the generation unit can analyze the elderly person's past conversation history and adjust the content and style of the conversation. For example, the generation unit generates an optimal pseudo-personality based on topics that the elderly person has frequently talked about in the past. The generation unit can also generate an optimal pseudo-personality based on topics that the elderly person has shown interest in in the past. Furthermore, the generation unit can also generate an optimal pseudo-personality based on topics that the elderly person has avoided in the past. This makes it possible to generate a pseudo-personality based on the elderly person's past conversation history.

[0054] The system can further include a local information provider that provides local event and activity information taking into account the elderly person's geographic location information. The local information provider, for example, collects events and activities in the area where the elderly person lives and uses the generation AI to provide information appropriate for the elderly person. For example, it can provide information on hobby clubs and health events held in the neighborhood. The local information provider can also use the generation AI to provide optimal information based on events and activities held near places frequently visited by the elderly person. This makes it easier for the elderly person to participate in local events and activities.

[0055] The system can further include a social media analysis unit that analyzes the social media activities of seniors and provides relevant information. For example, the social media analysis unit allows the generation AI to provide the most appropriate information based on the content that seniors frequently share on social media. The social media analysis unit can also allow the generation AI to provide the most appropriate information based on the content of accounts that seniors follow. Furthermore, the social media analysis unit can allow the generation AI to provide the most appropriate information based on the content of groups and communities that seniors participate in. This makes it possible to provide information based on seniors' social media activities.

[0056] The system can further include a behavioral history analysis unit that analyzes the elderly person's past behavioral history and selects a method for identifying appropriate hobbies and interests. The behavioral history analysis unit allows the generation AI to identify optimal hobbies and interests based on, for example, events and activities that the elderly person frequently participated in in the past. The behavioral history analysis unit can also allow the generation AI to identify optimal hobbies and interests based on places the elderly person has visited or traveled to in the past. Furthermore, the behavioral history analysis unit can also allow the generation AI to identify optimal hobbies and interests based on books the elderly person has read or movies they have watched in the past. This makes it possible to identify optimal hobbies and interests based on past behavioral history.

[0057] The system can further include a lifestyle situation filtering unit that filters the hobbies and interests based on the elderly person's current lifestyle and health condition. For example, if the elderly person's health condition is poor, the lifestyle situation filtering unit allows the generation AI to prioritize hobbies and interests that do not require much physical effort. In addition, if the elderly person's lifestyle is busy, the lifestyle situation filtering unit can also prioritize hobbies and interests that can be enjoyed in a short amount of time. Furthermore, if the elderly person's lifestyle is stable, the lifestyle situation filtering unit can also prioritize hobbies and interests that can be continued over the long term. This makes it possible to identify hobbies and interests that correspond to the elderly person's lifestyle and health condition.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The identification unit identifies the hobbies and interests of the elderly. For example, the identification unit can collect information on the elderly's favorite hobbies and interests, such as music, sports, and reading. The identification unit identifies the elderly's hobbies and interests through questionnaires and interviews. It can also identify the elderly's hobbies and interests by analyzing social media and past behavioral history. Step 2: The generation unit uses the generation AI to create a pseudo-personality based on the hobbies and interests identified by the identification unit. For example, for an elderly person who likes to travel, the generation unit generates a pseudo-personality that is knowledgeable about travel topics. The generation unit can use the generation AI to set personality traits and conversation styles to create a pseudo-personality. The generation unit can also have the generation AI learn the elderly person's reactions and evolve the pseudo-personality. Step 3: The dialogue unit allows the elderly person to converse with the pseudo-personality created by the generation unit. For example, the dialogue unit uses a generation AI to hold a dialogue between the elderly person and the pseudo-personality. The dialogue unit can handle a variety of topics, such as health care and neighborhood gossip. The dialogue unit can use the generation AI to realize a natural dialogue. Step 4: The reminder unit provides reminders based on the dialogue carried out by the dialogue unit. For example, the reminder unit uses a generation AI to provide reminders of information necessary for daily life. The reminder unit can remind elderly people of tomorrow's hospital appointment time so that they do not forget to complete their schedule. The reminder unit can provide reminders using generation AI in the form of voice notifications, text messages, and other methods.

[0060] (Example 2) A system according to an embodiment of the present invention uses a generation AI to create pseudo-personalities and create good-old-fashioned neighbors so that elderly people can live without feeling lonely. This system allows elderly people to talk with multiple pseudo-neighbors through the generation AI. For example, the system can respond to a variety of topics, from hobbies, travel, and food to health care and neighborhood gossip, facilitating smooth communication. Within these topics, the system can provide information necessary for daily life and provide reminders (e.g., "Tomorrow's hospital appointment starts at 10 a.m."). This allows elderly people to live without feeling lonely and improve their quality of life. For example, the generation AI can identify the elderly person's hobbies and interests and create a pseudo-personality based on them. For example, for an elderly person who enjoys traveling, the system can generate a pseudo-neighbor who is knowledgeable about travel topics. The elderly then talks with the pseudo-neighbor through the generation AI. The system can respond to a variety of topics, such as food and health care advice. This allows elderly people to enjoy everyday conversations. Furthermore, the generation AI can provide information necessary for daily life and provide reminders. For example, by being reminded of tomorrow's hospital appointment, elderly people can keep to their schedule without forgetting. This service allows elderly people to live without feeling lonely, improving their quality of life. For example, conversations with virtual neighbors can increase the enjoyment of everyday life, and receiving health care advice can also help maintain health. In this way, the system allows elderly people to live without feeling lonely, improving their quality of life.

[0061] The system according to the embodiment includes a comprehension unit, a generation unit, a dialogue unit, and a reminder unit. The comprehension unit comprehends the hobbies and interests of the elderly. For example, the comprehension unit can collect the elderly's favorite hobbies and interests, such as music, sports, and reading. The comprehension unit can comprehend the elderly's hobbies and interests through, for example, questionnaires or interviews. The comprehension unit can also comprehend the elderly's hobbies and interests by analyzing social media or past behavioral history. The generation unit uses a generation AI to create a pseudo-personality based on the hobbies and interests comprehended by the comprehension unit. For example, for an elderly person who likes traveling, the generation unit generates a pseudo-personality that is knowledgeable about travel topics. The generation unit can use the generation AI to set personality traits and a dialogue style to create the pseudo-personality. For example, the generation AI generates a pseudo-personality that likes traveling based on the elderly's hobbies and interests. The generation unit can also evolve the pseudo-personality by having the generation AI learn the elderly's reactions. The dialogue unit allows the elderly person to interact with the pseudo-personality created by the generation unit. For example, the dialogue unit uses a generation AI to have a dialogue between the elderly person and a pseudo-personality. The dialogue unit can respond to various topics, such as health care and neighborhood gossip. The dialogue unit can realize a natural dialogue using the generation AI. The reminder unit provides reminders based on the dialogue conducted by the dialogue unit. For example, the reminder unit uses the generation AI to provide reminders of information necessary for daily life. For example, the reminder unit can remind the elderly person of tomorrow's hospital appointment time, so that the elderly person will not forget to complete their schedule. The reminder unit can provide reminders using the generation AI by means of voice notification, text message, or the like. As a result, the system according to the embodiment can enable the elderly person to live without feeling lonely and improve their quality of life.

[0062] The generation unit can use the generation AI to create a pseudo-personality based on the hobbies and interests of the elderly person. For example, the generation unit uses the generation AI to create a pseudo-personality based on the hobbies and interests of the elderly person. For example, for an elderly person who likes traveling, the generation unit generates a pseudo-personality that is knowledgeable about travel topics. The generation unit can also use the generation AI to set personality traits and a conversation style to create a pseudo-personality. For example, the generation unit generates a pseudo-personality that likes traveling based on the hobbies and interests of the elderly person. Furthermore, the generation unit can have the generation AI learn the elderly person's reactions and evolve the pseudo-personality. For example, the generation AI learns the elderly person's reactions and adjusts the personality traits and conversation style of the pseudo-personality. This generates a pseudo-personality based on the hobbies and interests of the elderly person, enabling a more friendly conversation. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the generation unit can create a pseudo-personality using a generative AI model for generating a pseudo-personality based on the hobbies and interests of an elderly person.

[0063] The dialogue unit can use the generation AI to have a dialogue between the elderly person and the pseudo-personality. The dialogue unit, for example, uses the generation AI to have a dialogue between the elderly person and the pseudo-personality. For example, the dialogue unit generates prompts for the generation AI to have a dialogue between the elderly person and the pseudo-personality, thereby realizing a natural dialogue. The dialogue unit can also use the generation AI to respond to various topics, such as health management and neighborhood gossip. For example, the dialogue unit can have the generation AI provide advice on health management. The dialogue unit can also have the generation AI provide information on neighborhood gossip. Furthermore, the dialogue unit can use the generation AI to estimate the elderly person's emotions and adjust the content and tone of the dialogue. For example, the dialogue unit can have the generation AI estimate the elderly person's emotions and conduct the dialogue in a relaxed tone. This enables a natural dialogue by using the generation AI. Some or all of the above-mentioned processing in the dialogue unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the dialogue unit can realize the dialogue using a generative AI model for having a dialogue between the elderly person and the pseudo-personality.

[0064] The reminding unit can use a generating AI to remind the elderly about information necessary for daily life. The reminding unit, for example, uses a generating AI to remind the elderly about information necessary for daily life. For example, the reminding unit uses a generating AI to manage the elderly's schedule and send reminders. The reminding unit can also use a generating AI to send reminders by voice notification, text message, or other methods. For example, the reminding unit uses a generating AI to remind the elderly about tomorrow's hospital appointment. The reminding unit can also use a generating AI to estimate the elderly's emotions and adjust the reminding method. For example, the reminding unit uses a generating AI to estimate the elderly's emotions and send reminders in a relaxed tone. This allows the elderly to remember to manage information necessary for daily life. Some or all of the above-mentioned processing in the reminding unit may be performed using, for example, a generating AI, or may be performed without using a generating AI. For example, the reminding unit can realize reminders using a generating AI model for reminding the elderly about information necessary for daily life.

[0065] The generation unit can use the generation AI to learn the reactions of the elderly and evolve the pseudo-personality. The generation unit, for example, uses the generation AI to learn the reactions of the elderly and evolve the pseudo-personality. For example, the generation unit uses the generation AI to learn the reactions of the elderly and adjust the personality traits and conversation style of the pseudo-personality. The generation unit can also use the generation AI to improve the knowledge and skills of the pseudo-personality based on the reactions of the elderly. For example, the generation unit uses the generation AI to learn the reactions of the elderly and update the knowledge of the pseudo-personality. This allows the pseudo-personality to evolve based on the reactions of the elderly, enabling more appropriate conversations. Some or all of the above-mentioned processing in the generation unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the generation unit can learn the reactions of the elderly and evolve the pseudo-personality using a generation AI model for evolving the pseudo-personality.

[0066] The dialogue unit can respond to at least one or more topics of health care or neighborhood gossip using a generation AI. The dialogue unit can respond to various topics, such as health care or neighborhood gossip, using, for example, a generation AI. For example, the dialogue unit can provide advice on health care using the generation AI. The dialogue unit can also provide information on neighborhood gossip using the generation AI. Furthermore, the dialogue unit can estimate the elderly person's emotions and adjust the content and tone of the dialogue using the generation AI. For example, the dialogue unit can estimate the elderly person's emotions using the generation AI and conduct the dialogue in a relaxed tone. This allows the elderly person to enjoy dialogue on a variety of topics. Some or all of the above-mentioned processing in the dialogue unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the dialogue unit can realize dialogue using a generation AI model for responding to various topics, such as health care or neighborhood gossip.

[0067] The grasping unit can estimate the elderly person's emotions and adjust the method of grasping the hobbies and interests based on the estimated elderly person's emotions. The grasping unit can, for example, use a generation AI to estimate the elderly person's emotions and adjust the method of grasping the hobbies and interests based on the estimated elderly person's emotions. For example, if the grasping unit determines that the elderly person is sad, the generation AI can prioritize relaxing hobbies and interests. Furthermore, if the elderly person is excited, the grasping unit can prioritize active hobbies and interests. Furthermore, if the elderly person is tired, the grasping unit can prioritize relaxing hobbies and interests. This makes it possible to grasp the hobbies and interests according to the elderly person'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 grasping unit can be performed, for example, using the generation AI, or without using the generation AI. For example, the comprehension unit can grasp the hobbies and interests of an elderly person using a generative AI model to estimate the elderly person's emotions and adjust the method of grasping the hobbies and interests.

[0068] The ascertaining unit can analyze the elderly person's past behavioral history and select an appropriate method for ascertaining the elderly person's hobbies and interests. The ascertaining unit can, for example, use a generation AI to analyze the elderly person's past behavioral history and select an appropriate method for ascertaining the elderly person's hobbies and interests. For example, the ascertaining unit can cause the generation AI to ascertain optimal hobbies and interests based on events and activities the elderly person frequently participated in in the past. The ascertaining unit can also ascertain optimal hobbies and interests based on places the elderly person has visited or traveled to in the past. Furthermore, the ascertaining unit can ascertain optimal hobbies and interests based on books the elderly person has read or movies they have watched in the past. In this way, optimal hobbies and interests can be ascertained based on the elderly person's past behavioral history. The behavioral history is analyzed, for example, using a generation AI. The generation AI can analyze the past behavioral history and extract patterns of hobbies and interests. Some or all of the above-described processing in the ascertaining unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the ascertaining unit can analyze the past behavioral history and ascertain the hobbies and interests using a generation AI model for ascertaining hobbies and interests.

[0069] The comprehension unit can filter the hobbies and interests based on the elderly person's current living situation and health condition when comprehending the hobbies and interests. The comprehension unit, for example, uses a generation AI to filter the hobbies and interests based on the elderly person's current living situation and health condition when comprehending the hobbies and interests. For example, if the elderly person's health is poor, the comprehension unit can cause the generation AI to prioritize comprehending hobbies and interests that do not require much physical effort. Furthermore, if the elderly person's living situation is busy, the comprehension unit can also prioritize comprehending hobbies and interests that can be enjoyed in a short amount of time. Furthermore, if the elderly person's living situation is stable, the comprehension unit can prioritize comprehending hobbies and interests that can be continued over the long term. This makes it possible to comprehend the hobbies and interests according to the elderly person's living situation and health condition. The filtering of the living situation and health condition is performed, for example, using a generation AI. The generation AI can analyze the elderly person's living situation and health condition and select appropriate hobbies and interests. Some or all of the above-described processing in the comprehension unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the comprehension unit can understand hobbies and interests using generative AI models to filter lifestyle and health conditions.

[0070] The grasping unit can estimate the elderly person's emotions and determine the priority of the hobbies and interests to be grasped based on the estimated elderly person's emotions. The grasping unit can, for example, use a generation AI to estimate the elderly person's emotions and determine the priority of the hobbies and interests to be grasped based on the estimated elderly person's emotions. For example, if the elderly person is sad, the grasping unit can cause the generation AI to prioritize relaxing hobbies and interests to grasp. Furthermore, if the elderly person is excited, the grasping unit can cause the generation AI to prioritize active hobbies and interests to grasp. Furthermore, if the elderly person is tired, the grasping unit can prioritize relaxing hobbies and interests to grasp. This makes it possible to determine the priority of hobbies and interests according to the elderly person'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 grasping unit can be performed, for example, using the generation AI, or without using the generation AI. For example, the comprehension unit can estimate the elderly person's emotions and grasp their hobbies and interests using a generative AI model to prioritize hobbies and interests.

[0071] The ascertaining unit can prioritize relevant information by taking into account the geographical location information of the elderly person when ascertaining the hobbies and interests. The ascertaining unit, for example, uses a generation AI to prioritize relevant information by taking into account the geographical location information of the elderly person when ascertaining the hobbies and interests. For example, the ascertaining unit identifies the most suitable hobbies and interests for the generation AI based on events and activities in the area where the elderly person lives. The ascertaining unit can also identify the most suitable hobbies and interests for the generation AI based on events and activities held near places frequently visited by the elderly person. Furthermore, the ascertaining unit can also identify the most suitable hobbies and interests for the generation AI based on the culture and traditions of the area where the elderly person lives. This makes it possible to ascertain the hobbies and interests based on the geographical location information of the elderly person. The geographical location information is taken into account by, for example, a generation AI. The generation AI can analyze the geographical location information of the elderly person and select appropriate hobbies and interests. Some or all of the above-described processing by the ascertaining unit may be performed by, for example, a generation AI, or may be performed without using a generation AI. For example, the ascertaining unit can identify the hobbies and interests using a generation AI model for ascertaining hobbies and interests by taking into account geographical location information.

[0072] The identification unit can analyze the elderly person's social media activity and identify related information when identifying the elderly person's hobbies and interests. The identification unit can, for example, use a generation AI to analyze the elderly person's social media activity and identify related information when identifying the elderly person's hobbies and interests. For example, the identification unit can identify the most suitable hobbies and interests for the generation AI based on content frequently shared by the elderly person on social media. The identification unit can also identify the most suitable hobbies and interests for the generation AI based on the content of accounts the elderly person follows on social media. Furthermore, the identification unit can identify the most suitable hobbies and interests for the generation AI based on the content of groups and communities the elderly person participates in on social media. This makes it possible to identify the elderly person's hobbies and interests based on their social media activity. The analysis of social media activity can be performed, for example, using a generation AI. The generation AI can analyze the elderly person's social media activity and select appropriate hobbies and interests. Some or all of the above-described processing in the identification unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the identification unit can identify the hobbies and interests using a generation AI model for analyzing social media activity to identify hobbies and interests.

[0073] The generation unit can estimate the elderly person's emotions and adjust the pseudo-personality generation method based on the estimated elderly person's emotions. The generation unit can, for example, use a generation AI to estimate the elderly person's emotions and adjust the pseudo-personality generation method based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, the generation AI can generate a pseudo-personality with a calm personality. Also, if the elderly person is excited, the generation unit can generate a pseudo-personality with a lively personality. Furthermore, if the elderly person is sad, the generation AI can generate a pseudo-personality with a comforting personality. This makes it possible to generate a pseudo-personality according to the elderly person's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the generation unit can generate a pseudo-personality using a generative AI model to estimate the emotions of an elderly person and adjust the method for generating the pseudo-personality.

[0074] The generation unit can adjust the level of detail of the pseudo-personality based on the importance of the elderly person's hobbies and interests when generating the pseudo-personality. The generation unit can adjust the level of detail of the pseudo-personality based on the importance of the elderly person's hobbies and interests when generating the pseudo-personality, for example, using a generation AI. For example, the generation unit can generate a pseudo-personality with detailed knowledge of hobbies in which the elderly person is particularly interested. The generation unit can also generate a pseudo-personality with basic knowledge of hobbies in which the elderly person is not very interested. Furthermore, the generation unit can generate a pseudo-personality with moderate knowledge of hobbies in which the elderly person has recently become interested. This makes it possible to generate a pseudo-personality based on the importance of the elderly person's hobbies and interests. The importance evaluation is performed, for example, using a generation AI. The generation AI can analyze the importance of the elderly person's hobbies and interests and determine an appropriate level of detail of the generation. Some or all of the above-described processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generator can generate a pseudo-personality using a generative AI model to adjust the level of detail of the generation based on the importance of hobbies and interests.

[0075] The generation unit can apply different generation algorithms depending on the category of the elderly person when generating the pseudo-personality. The generation unit can, for example, use a generation AI to apply different generation algorithms depending on the category of the elderly person when generating the pseudo-personality. For example, if the elderly person is interested in health management, the generation AI can generate a pseudo-personality with knowledge about health. Furthermore, if the elderly person is interested in travel, the generation unit can generate a pseudo-personality with knowledge about travel. Furthermore, if the elderly person is interested in food, the generation AI can generate a pseudo-personality with knowledge about food. This makes it possible to generate pseudo-personalities according to the category of the elderly person. The application of categories is performed, for example, using a generation AI. The generation AI can analyze the category of the elderly person and select an appropriate generation algorithm. Some or all of the above-mentioned processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generation unit can generate a pseudo-personality using a generation AI model for applying a generation algorithm depending on the category.

[0076] The generation unit can estimate the elderly person's emotions and adjust the characteristics of the pseudo-personality based on the estimated elderly person's emotions. The generation unit can, for example, use a generation AI to estimate the elderly person's emotions and adjust the characteristics of the pseudo-personality based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, the generation AI can generate a pseudo-personality with a calm personality. Also, if the elderly person is excited, the generation unit can generate a pseudo-personality with a lively personality. Furthermore, if the elderly person is sad, the generation AI can generate a pseudo-personality with a comforting personality. This makes it possible to adjust the characteristics of the pseudo-personality according to the elderly person's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the generation unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the generation unit can generate a pseudo-personality using a generative AI model to estimate the emotions of an elderly person and adjust the characteristics of the pseudo-personality.

[0077] The generation unit can determine the generation priority based on the elderly person's past dialogue history when generating the pseudo-personality. The generation unit can determine the generation priority based on the elderly person's past dialogue history when generating the pseudo-personality, for example, using a generation AI. For example, the generation unit can generate an optimal pseudo-personality based on topics that the elderly person frequently talked about in the past. The generation unit can also generate an optimal pseudo-personality based on topics that the elderly person has shown interest in in the past. Furthermore, the generation unit can generate an optimal pseudo-personality based on topics that the elderly person has avoided in the past. This makes it possible to generate a pseudo-personality based on the elderly person's past dialogue history. The dialogue history can be analyzed using, for example, a generation AI. The generation AI can analyze the elderly person's dialogue history and determine appropriate generation priorities. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the generation unit can generate a pseudo-personality using a generation AI model for determining generation priorities based on a dialogue history.

[0078] The generation unit can adjust the order of generation based on the elderly's relevance when generating pseudo-personalities. The generation unit can adjust the order of generation based on the elderly's relevance when generating pseudo-personalities, for example, using a generation AI. For example, the generation unit can prioritize generating pseudo-personalities related to topics that the elderly are most interested in. The generation unit can also generate pseudo-personalities related to topics that the elderly are second most interested in next. Furthermore, the generation unit can generate pseudo-personalities related to topics that the elderly are least interested in last. This enables the generation of pseudo-personalities based on the elderly's relevance. The evaluation of relevance is performed, for example, using a generation AI. The generation AI can analyze the degree of similarity of the elderly's interests and common topics and determine an appropriate generation order. Some or all of the above-mentioned processing in the generation unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the generation unit can generate pseudo-personalities using a generation AI model for adjusting the order of generation based on relevance.

[0079] The dialogue unit can estimate the elderly person's emotions and adjust the dialogue expression method based on the estimated elderly person's emotions. The dialogue unit can estimate the elderly person's emotions using, for example, a generation AI and adjust the dialogue expression method based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, the dialogue unit can have the generation AI speak in a calm tone. Also, if the elderly person is excited, the dialogue unit can have the generation AI speak in a lively tone. Furthermore, if the elderly person is sad, the dialogue unit can have the generation AI speak in a comforting tone. This makes it possible to adjust the dialogue expression method according to the elderly person'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 dialogue unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the dialogue unit can realize the dialogue using a generation AI model for estimating the elderly person's emotions and adjusting the dialogue expression method.

[0080] The dialogue unit can adjust the level of detail of the dialogue based on the importance of the topic during the dialogue. The dialogue unit can, for example, use a generation AI to adjust the level of detail of the dialogue based on the importance of the topic during the dialogue. For example, the dialogue unit can have the generation AI provide detailed information on topics that the elderly are particularly interested in. The dialogue unit can also have the generation AI provide basic information on topics that the elderly are not very interested in. Furthermore, the dialogue unit can have the generation AI provide medium information on topics in which the elderly have recently become interested. This makes it possible to adjust the level of detail of the dialogue according to the importance of the topic. The importance is evaluated, for example, using a generation AI. The generation AI can analyze the elderly's level of interest and influence and determine an appropriate level of detail of the dialogue. Some or all of the above-mentioned processing in the dialogue unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the dialogue unit can realize the dialogue using a generation AI model for adjusting the level of detail of the dialogue based on the importance of the topic.

[0081] The dialogue unit can apply different dialogue algorithms depending on the topic category during dialogue. The dialogue unit, for example, uses a generation AI to apply different dialogue algorithms depending on the topic category during dialogue. For example, when the topic is about health management, the dialogue unit can apply a dialogue algorithm in which the generation AI has knowledge about health. Furthermore, when the topic is about travel, the dialogue unit can apply a dialogue algorithm in which the generation AI has knowledge about travel. Furthermore, when the topic is about food, the dialogue unit can apply a dialogue algorithm in which the generation AI has knowledge about food. This makes it possible to apply a dialogue algorithm depending on the topic category. The category is applied using, for example, a generation AI. The generation AI can analyze the type of topic and the area of ​​interest and select an appropriate dialogue algorithm. Some or all of the above-mentioned processing in the dialogue unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the dialogue unit can realize a dialogue using a generation AI model for applying a dialogue algorithm depending on the topic category.

[0082] The dialogue unit can estimate the elderly person's emotions and adjust the length of the dialogue based on the estimated elderly person's emotions. The dialogue unit can, for example, use a generation AI to estimate the elderly person's emotions and adjust the length of the dialogue based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, the dialogue unit can cause the generation AI to have a longer dialogue. Furthermore, if the elderly person is excited, the dialogue unit can cause the generation AI to have a shorter dialogue. Furthermore, if the elderly person is sad, the dialogue unit can cause the generation AI to have an appropriate length of dialogue. This makes it possible to adjust the length of the dialogue according to the elderly person'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-mentioned processing in the dialogue unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the dialogue unit can realize the dialogue using a generation AI model for estimating the elderly person's emotions and adjusting the length of the dialogue.

[0083] The dialogue unit can determine the priority of dialogues based on the time when the topic was submitted during the dialogue. The dialogue unit can, for example, use a generation AI to determine the priority of dialogues based on the time when the topic was submitted during the dialogue. For example, the dialogue unit can have the generation AI prioritize dialogues regarding topics that the elderly person has recently become interested in. The dialogue unit can also have the generation AI next conduct dialogues regarding topics that the elderly person was interested in in the past. Furthermore, the dialogue unit can have the generation AI last conduct dialogues regarding topics that the elderly person is not very interested in. This makes it possible to determine the priority of dialogues based on the time when the topic was submitted. The submission time is evaluated using, for example, a generation AI. The generation AI can analyze the submission date and time and frequency of topics and determine appropriate dialogue priorities. Some or all of the above-mentioned processing in the dialogue unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the dialogue unit can realize dialogues using a generation AI model for determining the priority of dialogues based on the time when the topic was submitted.

[0084] The dialogue unit can adjust the order of dialogues based on the relevance of topics during dialogue. The dialogue unit can adjust the order of dialogues based on the relevance of topics during dialogue, for example, using a generation AI. For example, the dialogue unit can have the generation AI prioritize dialogues regarding topics in which the elderly are most interested. The dialogue unit can also have the generation AI next dialogue regarding topics in which the elderly are second most interested. Furthermore, the dialogue unit can have the generation AI last dialogue regarding topics in which the elderly are least interested. This makes it possible to adjust the order of dialogues based on the relevance of topics. The evaluation of relevance is performed, for example, using a generation AI. The generation AI can analyze the commonality of topics and the degree of agreement of interests and determine an appropriate order of dialogues. Some or all of the above-mentioned processing in the dialogue unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the dialogue unit can realize dialogues using a generation AI model for adjusting the order of dialogues based on the relevance of topics.

[0085] The reminding unit can estimate the elderly person's emotions and adjust the reminding method based on the estimated elderly person's emotions. The reminding unit can estimate the elderly person's emotions using, for example, a generation AI and adjust the reminding method based on the estimated elderly person's emotions. For example, if the elderly person is relaxed, the generation AI can remind them in a calm tone. If the elderly person is excited, the reminding unit can remind them in an active tone. If the elderly person is sad, the generation AI can remind them in a comforting tone. This makes it possible to adjust the reminding method according to the elderly person'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 these examples. Some or all of the above-mentioned processing in the reminding unit can be performed using, for example, a generation AI, or without a generation AI. For example, the reminder unit can realize reminders using a generative AI model to estimate the elderly person's emotions and adjust the reminder method.

[0086] The reminding unit can select the optimal reminding method by analyzing the elderly person's past behavioral history when reminding. The reminding unit can select the optimal reminding method by using, for example, a generation AI. For example, the reminding unit can select the optimal reminding method based on plans that the elderly person tends to forget in the past. The reminding unit can also select the optimal reminding method based on actions that the elderly person frequently performed in the past. Furthermore, the reminding unit can also select the optimal reminding method based on plans that the elderly person considered important in the past. This makes it possible to select the optimal reminding method based on the elderly person's past behavioral history. The behavioral history is analyzed, for example, using a generation AI. The generation AI can analyze the elderly person's behavioral history and select an appropriate reminding method. Some or all of the above-mentioned processing in the reminding unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the reminding unit can realize reminding using a generation AI model for analyzing the behavioral history and selecting a reminding method.

[0087] The reminding unit can customize the reminder means based on the elderly person's current living situation when reminding. The reminding unit can customize the reminder means based on the elderly person's current living situation when reminding, for example, using a generation AI. For example, if the elderly person is busy, the generation AI can provide a short, to-the-point reminder. Furthermore, if the elderly person is relaxed, the generation AI can provide a detailed reminder. Furthermore, if the elderly person is not feeling well, the generation AI can provide a gentler reminder. This enables customization of the reminder means according to the elderly person's living situation. The evaluation of the living situation is performed, for example, using a generation AI. The generation AI can analyze the elderly person's living situation and select an appropriate reminder means. Some or all of the above-described processing in the reminding unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the reminding unit can realize reminders using a generation AI model for customizing the reminder means based on the living situation.

[0088] The reminder unit can estimate the elderly person's emotions and determine the priority of reminders based on the estimated emotions. The reminder unit can estimate the elderly person's emotions using, for example, a generation AI and determine the priority of reminders based on the estimated emotions. For example, if the elderly person is relaxed, the generation AI can prioritize important reminders. Also, if the elderly person is excited, the reminder unit can prioritize urgent reminders. Furthermore, if the elderly person is sad, the generation AI can prioritize comforting reminders. This makes it possible to determine the priority of reminders based on the elderly person'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 reminder unit can be performed using, for example, a generation AI, or without a generation AI. For example, the reminder unit can realize reminders using a generative AI model to estimate the elderly person's emotions and determine the priority of reminders.

[0089] The reminding unit can select the optimal reminding method by taking into account the geographical location information of the elderly person when reminding. The reminding unit, for example, uses a generation AI to select the optimal reminding method by taking into account the geographical location information of the elderly person when reminding. For example, if the elderly person is at home, the reminding unit can have the generation AI perform a reminder that should be performed at home. Also, if the elderly person is out, the reminding unit can also perform a reminder that should be performed while the elderly person is out. Furthermore, if the elderly person is in a specific location, the generation AI can perform a reminder related to that location. This makes it possible to select the optimal reminding method based on the elderly person's geographical location information. The geographical location information is taken into account by, for example, a generation AI. The generation AI can analyze the elderly person's geographical location information and select an appropriate reminding method. Some or all of the above-mentioned processing in the reminding unit may be performed by, for example, a generation AI, or may be performed without using a generation AI. For example, the reminding unit can realize reminding by using a generation AI model for selecting a reminding method by taking into account geographical location information.

[0090] The reminding unit can analyze the elderly person's social media activity and suggest a reminder method when reminding the elderly person. The reminding unit can, for example, use a generation AI to analyze the elderly person's social media activity and suggest a reminder method when reminding the elderly person. For example, the reminding unit can use the generation AI to suggest the optimal reminder method based on the content frequently shared by the elderly person on social media. The reminding unit can also use the generation AI to suggest the optimal reminder method based on the content of accounts the elderly person follows on social media. Furthermore, the reminding unit can also use the generation AI to suggest the optimal reminder method based on the content of groups and communities the elderly person participates in on social media. This makes it possible to suggest reminder methods based on the elderly person's social media activity. The analysis of social media activity can be performed, for example, using a generation AI. The generation AI can analyze the elderly person's social media activity and select an appropriate reminder method. Some or all of the above-mentioned processing in the reminding unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the reminding unit can realize reminders using a generation AI model for analyzing social media activity and suggesting reminder methods. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned grasping unit, generating unit, dialogue unit, and reminding unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the grasping unit is realized by the control unit 46A of the smart device 14 and collects the hobbies and interests of the elderly person. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and creates a pseudo-personality using a generative AI. The dialogue unit is realized, for example, by the control unit 46A of the smart device 14 and engages in a dialogue between the elderly person and the pseudo-personality. The reminding unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reminds the elderly person of information necessary for daily life. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned grasping unit, generating unit, dialogue unit, and reminding unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the grasping unit is realized by the control unit 46A of the smart glasses 214 and collects the hobbies and interests of the elderly. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and creates a pseudo-personality using a generation AI. The dialogue unit is realized, for example, by the control unit 46A of the smart glasses 214 and engages in a dialogue between the elderly and the pseudo-personality. The reminding unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reminds the elderly of information necessary for daily life. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned grasping unit, generating unit, dialogue unit, and reminding unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the grasping unit is realized by the control unit 46A of the headset type terminal 314 and collects the hobbies and interests of the elderly. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and creates a pseudo-personality using a generation AI. The dialogue unit is realized, for example, by the control unit 46A of the headset type terminal 314 and engages in a dialogue between the elderly and the pseudo-personality. The reminding unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reminds the elderly of information necessary for daily life. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned grasping unit, generating unit, dialogue unit, and reminding unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the grasping unit is realized by the control unit 46A of the robot 414 and collects the hobbies and interests of the elderly person. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and creates a pseudo-personality using a generation AI. The dialogue unit is realized, for example, by the control unit 46A of the robot 414 and engages in dialogue between the elderly person and the pseudo-personality. The reminding unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and reminds the elderly person of information necessary for daily life.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The system can further include a health monitoring unit that monitors the elderly person's health data in real time. The health monitoring unit collects health data such as the elderly person's heart rate, blood pressure, and body temperature using a wearable device, for example. The collected data is analyzed using generative AI, and if an abnormality is detected, the elderly person is notified through the dialogue unit. The health monitoring unit can also provide health management advice based on the collected data. For example, if the heart rate is high, advice on relaxation is provided. This allows the elderly person's health condition to be understood in real time and appropriate measures to be taken.

[0093] When generating a pseudo-personality, the generation unit can analyze the elderly person's past conversation history and adjust the content and style of the conversation. For example, the generation unit generates an optimal pseudo-personality based on topics that the elderly person has frequently talked about in the past. The generation unit can also generate an optimal pseudo-personality based on topics that the elderly person has shown interest in in the past. Furthermore, the generation unit can also generate an optimal pseudo-personality based on topics that the elderly person has avoided in the past. This makes it possible to generate a pseudo-personality based on the elderly person's past conversation history.

[0094] The dialogue unit can estimate the elderly person's emotions during the dialogue and adjust the tone and content of the dialogue based on the estimated emotions. For example, if the elderly person is relaxed, the generation AI can use a calm tone to communicate. If the elderly person is excited, the generation AI can use a lively tone to communicate. Furthermore, if the elderly person is sad, the generation AI can use a comforting tone to communicate. This makes it possible to adjust the dialogue according to the elderly person's emotions.

[0095] The reminder unit can estimate the elderly person's emotions when sending a reminder and adjust the reminder method based on the estimated emotions. For example, if the elderly person is relaxed, the generation AI can remind them in a calm tone. If the elderly person is excited, the generation AI can remind them in a lively tone. Furthermore, if the elderly person is sad, the generation AI can remind them in a comforting tone. This makes it possible to adjust the reminder method according to the elderly person's emotions.

[0096] When generating a pseudo-personality, the generation unit can estimate the emotions of the elderly person and adjust the characteristics of the pseudo-personality based on the estimated emotions. For example, if the elderly person is relaxed, the generation AI can generate a pseudo-personality with a calm personality. Also, if the elderly person is excited, the generation AI can generate a pseudo-personality with a lively personality. Furthermore, if the elderly person is sad, the generation AI can generate a pseudo-personality with a comforting personality. This makes it possible to adjust the characteristics of the pseudo-personality according to the emotions of the elderly person.

[0097] The system can further include a local information provider that provides local event and activity information taking into account the elderly person's geographic location information. The local information provider, for example, collects events and activities in the area where the elderly person lives and uses the generation AI to provide information appropriate for the elderly person. For example, it can provide information on hobby clubs and health events held in the neighborhood. The local information provider can also use the generation AI to provide optimal information based on events and activities held near places frequently visited by the elderly person. This makes it easier for the elderly person to participate in local events and activities.

[0098] The system can further include a social media analysis unit that analyzes the social media activities of seniors and provides relevant information. For example, the social media analysis unit allows the generation AI to provide the most appropriate information based on the content that seniors frequently share on social media. The social media analysis unit can also allow the generation AI to provide the most appropriate information based on the content of accounts that seniors follow. Furthermore, the social media analysis unit can allow the generation AI to provide the most appropriate information based on the content of groups and communities that seniors participate in. This makes it possible to provide information based on seniors' social media activities.

[0099] The system can further include a behavioral history analysis unit that analyzes the elderly person's past behavioral history and selects a method for identifying appropriate hobbies and interests. The behavioral history analysis unit allows the generation AI to identify optimal hobbies and interests based on, for example, events and activities that the elderly person frequently participated in in the past. The behavioral history analysis unit can also allow the generation AI to identify optimal hobbies and interests based on places the elderly person has visited or traveled to in the past. Furthermore, the behavioral history analysis unit can also allow the generation AI to identify optimal hobbies and interests based on books the elderly person has read or movies they have watched in the past. This makes it possible to identify optimal hobbies and interests based on past behavioral history.

[0100] The system can further include a lifestyle situation filtering unit that filters the hobbies and interests based on the elderly person's current lifestyle and health condition. For example, if the elderly person's health condition is poor, the lifestyle situation filtering unit allows the generation AI to prioritize hobbies and interests that do not require much physical effort. In addition, if the elderly person's lifestyle is busy, the lifestyle situation filtering unit can also prioritize hobbies and interests that can be enjoyed in a short amount of time. Furthermore, if the elderly person's lifestyle is stable, the lifestyle situation filtering unit can also prioritize hobbies and interests that can be continued over the long term. This makes it possible to identify hobbies and interests that correspond to the elderly person's lifestyle and health condition.

[0101] The system can further include an emotion priority determination unit that estimates the emotions of the elderly person and determines the priority of hobbies and interests based on the estimated emotions. For example, if the elderly person is sad, the emotion priority determination unit causes the generation AI to prioritize hobbies and interests that are relaxing. In addition, if the elderly person is excited, the emotion priority determination unit can also cause the generation AI to prioritize hobbies and interests that are active. In addition, if the elderly person is tired, the emotion priority determination unit can also cause the generation AI to prioritize hobbies and interests that are relaxing. In this way, the priority of hobbies and interests can be determined according to the emotions of the elderly person.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The identification unit identifies the hobbies and interests of the elderly. For example, the identification unit can collect information on the elderly's favorite hobbies and interests, such as music, sports, and reading. The identification unit identifies the elderly's hobbies and interests through questionnaires and interviews. It can also identify the elderly's hobbies and interests by analyzing social media and past behavioral history. Step 2: The generation unit uses the generation AI to create a pseudo-personality based on the hobbies and interests identified by the identification unit. For example, for an elderly person who likes to travel, the generation unit generates a pseudo-personality that is knowledgeable about travel topics. The generation unit can use the generation AI to set personality traits and conversation styles to create a pseudo-personality. The generation unit can also have the generation AI learn the elderly person's reactions and evolve the pseudo-personality. Step 3: The dialogue unit allows the elderly person to converse with the pseudo-personality created by the generation unit. For example, the dialogue unit uses a generation AI to hold a dialogue between the elderly person and the pseudo-personality. The dialogue unit can handle a variety of topics, such as health care and neighborhood gossip. The dialogue unit can use the generation AI to realize a natural dialogue. Step 4: The reminder unit provides reminders based on the dialogue carried out by the dialogue unit. For example, the reminder unit uses a generation AI to provide reminders of information necessary for daily life. The reminder unit can remind elderly people of tomorrow's hospital appointment time so that they do not forget to complete their schedule. The reminder unit can provide reminders using generation AI in the form of voice notifications, text messages, and other methods.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0108] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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).

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0124] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0140] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0141] 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.

[0142] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0143] The 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.

[0144] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0145] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS 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).

[0146] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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."

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] [Explanation of symbols]

[0176] 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 system comprising: an understanding unit that understands hobbies and interests; a generation unit that creates a pseudo-personality based on the hobbies and interests understood by the understanding unit; a dialogue unit in which an elderly person interacts with the pseudo-personality created by the generation unit; and a reminder unit that issues reminders based on the dialogue conducted by the dialogue unit.

2. The generation unit Generative AI creates pseudo-personalities based on the hobbies and interests of elderly people The system of claim 1 .

3. The dialogue unit Generative AI enables conversation between elderly people and pseudo-personalities The system of claim 1 .

4. The reminding unit Reminding you of information necessary for daily life using generative AI The system of claim 1 .

5. The generation unit Generative AI learns the reactions of elderly people and evolves a pseudo-personality 3. The system of claim 2.

6. The system according to claim 3 , wherein the dialogue unit responds to at least one or more topics of health care or neighborhood gossip using a generative AI.

7. The grasping unit is Estimate the emotions of the elderly and adjust how their hobbies and interests are tracked based on the estimated emotions. The system of claim 1 .

8. 2. The system according to claim 1, wherein the determining unit analyzes the past behavioral history of the elderly person and selects a method for determining the elderly person's hobbies and interests appropriately.

9. The grasping unit is When identifying hobbies and interests, filtering is performed based on the elderly person's current living situation and health status. The system of claim 1 .

Images