System

Abstract

An object of the system according to the embodiment is to stimulate the cognitive function of elderly people and activate communication.SOLUTION: A system includes a question part, an answer collection part, a learning part, a story generation part, and a picture generation part. The question unit asks a question to the elderly person. The answer collection unit collects an answer of the elderly person to the question asked by the question unit. The learning unit learns the fragmentary input information collected by the answer collection unit. The story generation unit generates a series of stories on the basis of the information learned by the learning unit. The picture generation unit generates a landscape or a scene of a particularly impressive episode in the story generated by the story generation unit as a picture.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of not providing sufficient means to effectively stimulate the cognitive functions of elderly people and stimulate their communication.

[0005] The system according to the embodiment aims to stimulate the cognitive functions of elderly people and activate communication. [Means for solving the problem]

[0006] The system according to the embodiment includes a questioning unit, an answer collection unit, a learning unit, a story generation unit, and a picture generation unit. The questioning unit asks questions to the elderly. The answer collection unit collects answers from the elderly to the questions posed by the questioning unit. The learning unit learns the fragmentary input information collected by the answer collection unit. The story generation unit generates a series of stories based on the information learned by the learning unit. The picture generation unit generates a picture of a landscape or scene from a particularly memorable episode in the story generated by the story generation unit. [Effects of the Invention]

[0007] The system according to the embodiment can stimulate the cognitive functions of elderly people and activate their communication. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

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

[0028] (Example 1) The dementia prevention system according to an embodiment of the present invention asks questions to the elderly, collects their answers, and uses a generation AI to learn from the fragmented input information to generate a series of stories, creating landscapes and scenes from memorable episodes as paintings to show to the elderly. This allows the dementia prevention system to stimulate the cognitive functions of the elderly and prevent dementia.

[0029] A dementia prevention system according to an embodiment includes a questioning unit, a response collection unit, a learning unit, a story generation unit, and a picture generation unit. The questioning unit asks questions to the elderly. For example, the questioning unit asks questions such as, "What was the weather like today?" or "What was something fun that happened recently?" The questioning unit can also dynamically change the content of the questions based on daily news and the elderly's interests to ask more personalized questions. For example, questions related to recent sporting events or local news can be asked. The response collection unit collects the elderly's answers to the questions posed by the questioning unit. For example, the response collection unit collects the elderly's answers as audio data and converts them into text data. The response collection unit can also use an emotion estimation function to analyze the emotions felt when the elderly answered and generate questions that elicit positive emotions. For example, positive emotions can be detected based on smiles and tone of voice. The learning unit learns fragmented input information collected by the response collection unit. For example, the learning unit learns an elderly's answer, such as, "I went to the park with my grandchild," and combines related episodes to generate a series of stories. The story generation unit generates a series of stories based on the information learned by the learning unit. For example, the story generation unit generates a story using a generation AI (e.g., a text generation AI or a multimodal generation AI). The story generation unit can also convert the generated story into a different genre to suit the preferences of the elderly. For example, an adventure story can be provided to an adventurous elderly person. The painting generation unit generates a painting of a landscape or scene from a particularly memorable episode in the story generated by the story generation unit. For example, the painting generation unit generates a painting based on the episode "playing in the park with my grandchild." The painting generation unit can also use an emotion estimation function to identify the scene that moved the elderly the most and highlight that scene as a painting. For example, it can depict in detail a scene with a high emotion score. This allows the dementia prevention system according to the embodiment to stimulate the cognitive function of the elderly and prevent dementia. For example, sharing the generated story or painting with family and friends and viewing and listening to it together can also lead to more active communication.Additionally, interactive quizzes and games can be developed using the generated stories and pictures to further stimulate cognitive function in older adults.

[0030] The questioning unit can dynamically change the content of questions based on daily news or the interests of the elderly person, allowing for more personalized questions. For example, the questioning unit generates questions that incorporate daily news and topics based on the elderly person's interests. For example, it can ask questions related to recent sporting events or local news. The questioning unit can also use the generation AI to build a long-term story arc based on the elderly person's past response history and generate a continuous narrative. For example, it can connect past episodes to generate a coherent narrative. This allows for more effective stimulation of cognitive function by asking questions based on the elderly person's interests.

[0031] The answer collection unit allows the generation AI to provide real-time feedback on the elderly person's answers, maintaining a natural flow of conversation. For example, the answer collection unit allows the generation AI to provide appropriate feedback in real time to the elderly person's answers. For example, it may respond with, "That's great!" or "Tell me more." The answer collection unit can also use its emotion estimation function to analyze the emotions felt when the elderly person answers and generate questions that elicit positive emotions. For example, it can detect positive emotions based on smiles and tone of voice. This allows real-time feedback to maintain a natural flow of conversation and keep the elderly person interested.

[0032] The questioning unit can extend the question format to a multimodal format using not only text but also images or audio. For example, the questioning unit can ask questions using not only text but also images or audio. For example, it can show a picture of a landscape and ask, "Have you ever been to this place?" The questioning unit can also prepare question sets corresponding to different cultures and regions, and provide services from a global perspective. For example, it can ask questions about local traditional events and culture. In this way, asking questions in a multimodal format can pique the interest of elderly people and promote stimulation of their cognitive functions.

[0033] The questioning unit can prepare question sets that correspond to different cultures or regions, and provide services from a global perspective. For example, the questioning unit can prepare question sets that correspond to different cultures and regions, and ask questions that match the background of the elderly person. For example, it can ask questions about traditional local events and culture. The questioning unit is also equipped with an emotion estimation function, and can adjust the tone and content of the questions according to the elderly person's emotions. For example, if the elderly person is feeling depressed, the questions can be asked in a gentle tone. This makes it possible to provide services from a global perspective by asking questions that correspond to different cultures and regions.

[0034] The learning unit allows the generation AI to construct a long-term story arc based on the elderly person's past response history, generating a continuous narrative. For example, the learning unit analyzes the elderly person's past response history, and the generation AI constructs a long-term story arc. For example, it connects past episodes to generate a coherent narrative. The learning unit can also analyze the elderly person's individual episodes, extract common themes and motifs, and reflect them in the narrative. For example, it can generate a narrative themed around memories with family and friends. This makes it possible to provide a more coherent narrative by generating a continuous narrative based on the elderly person's past response history.

[0035] The learning unit can analyze each episode of an elderly person and extract common themes or motifs to reflect in the story. For example, the learning unit uses a generation AI to analyze each episode of an elderly person and extract common themes and motifs. For example, it can generate a story themed around memories with family and friends. The learning unit can also use an emotion estimation function to emphasize the parts of the story that evoke the most emotional responses from the elderly. For example, it can emphasize moving scenes or happy events. In this way, by analyzing each episode of an elderly person and extracting common themes and motifs, it is possible to provide a story that is easier for people to empathize with.

[0036] The story generation unit can convert the generated story into a different genre to suit the preferences of the elderly. For example, the story generation unit converts the generated story into a different genre to suit the preferences of the elderly. For example, an adventure story can be provided to an adventure-loving elderly person. The story generation unit can also use the generation AI to generate creative works in different formats, such as poetry or lyrics, based on the elderly's answers. For example, a poem can be created that reflects the keywords and emotions contained in the answers. In this way, by converting the generated story into a different genre, it is possible to provide a story that suits the preferences of the elderly.

[0037] The story generation unit allows the generation AI to generate different forms of creative works, such as poetry or lyrics, based on the answers of the elderly. For example, the story generation unit generates poems based on the answers of the elderly. For example, it creates poems that reflect the keywords and emotions contained in the answers. The story generation unit can also use the emotion estimation function to generate characters in the story that the elderly can easily empathize with. For example, it can set the character's personality and background based on emotional response data. This allows for the generation of different forms of creative works, such as poetry or lyrics, based on the answers of the elderly, making it possible to provide a wider variety of content.

[0038] The painting generation unit can generate paintings in which the generation AI depicts the same scene from multiple viewpoints based on the elderly person's answers. For example, the painting generation unit can generate paintings in which the generation AI depicts the same scene from multiple viewpoints based on the elderly person's answers. For example, it can depict a scene as seen from a different angle or time of day. The painting generation unit can also learn the elderly person's preferences and past answers and generate individually customized paintings. For example, it can create paintings that reflect their favorite colors and style. This allows paintings of the same scene from multiple viewpoints to be generated based on the elderly person's answers, providing a greater variety of visual stimuli.

[0039] The painting generation unit can learn the preferences and past responses of the elderly person and generate individually customized paintings. For example, the painting generation unit learns the preferences and past responses of the elderly person, and the generation AI generates individually customized paintings. For example, it creates paintings that reflect their favorite colors and style. The painting generation unit can also use its emotion estimation function to identify the scenes that moved the elderly person the most and highlight those scenes as paintings. For example, it can depict scenes with high emotion scores in detail. In this way, by learning the preferences and past responses of the elderly person and generating individually customized paintings, it is possible to provide more personalized visual stimulation.

[0040] The painting generation unit can animate the generated painting and provide it as moving visual content. For example, the painting generation unit can create an animation in which a character in a painting moves. The painting generation unit can also use the generation AI to create a 3D model based on the elderly person's answers, allowing them to be experienced in virtual reality. For example, it can create a 3D model of the places and people that appear in the answers. In this way, animating the generated painting can provide a more dynamic visual stimulus.

[0041] The painting generation unit allows the generation AI to create a 3D model based on the elderly person's answers, allowing it to be experienced in virtual reality. The painting generation unit allows the generation AI to create a 3D model based on the elderly person's answers, allowing it to be experienced in virtual reality. For example, it creates 3D models of places and people that appear in the answers. The painting generation unit can also use an emotion estimation function to dynamically change the color and composition of the painting to match the elderly person's emotions. For example, if the emotion is positive, bright colors are used. In this way, by creating a 3D model based on the elderly person's answers and allowing it to be experienced in virtual reality, it is possible to provide a more immersive visual stimulation.

[0042] Interactive quizzes or games can be developed using the generated stories or pictures, which can further stimulate the cognitive functions of the elderly. Interactive quizzes or games can be developed using the generated stories or pictures, which can further stimulate the cognitive functions of the elderly. For example, a quiz that asks questions related to the content of the story can be created. Rehabilitation programs can also be developed using the generated stories and pictures, which can simultaneously provide physical rehabilitation and stimulate cognitive functions. For example, rehabilitation can be provided that involves movements based on the story. Thus, interactive quizzes or games can be developed using the generated stories and pictures, which can further stimulate the cognitive functions of the elderly.

[0043] This can encourage collaborative creative activities in which the elderly think up the next part of a generated story themselves, and the generative AI generates that continuation. This can encourage collaborative creative activities in which the elderly think up the next part of a generated story themselves, and the generative AI generates that continuation. For example, the elderly would suggest the next development in the story, and the AI ​​would continue the story based on that. It is also possible to develop rehabilitation programs using generated stories and pictures, and simultaneously provide physical rehabilitation and stimulate cognitive function. For example, rehabilitation can be provided that involves movements based on the story. This can further stimulate cognitive function by encouraging collaborative creative activities in which the elderly think up the next part of a generated story themselves, and the generative AI generates that continuation.

[0044] A rehabilitation program using the generated stories and pictures can be developed to enable physical rehabilitation and cognitive stimulation simultaneously. A rehabilitation program using the generated stories and pictures can be developed to enable physical rehabilitation and cognitive stimulation simultaneously. For example, rehabilitation that involves movement based on a story can be provided. Interactive quizzes and games can also be developed using the generated stories and pictures to further stimulate the cognitive functions of elderly people. For example, a quiz can be created that asks questions related to the content of the story. In this way, by developing a rehabilitation program using the generated stories and pictures, physical rehabilitation and cognitive stimulation can be enabled simultaneously.

[0045] Elderly people can share the stories and pictures they have created with other elderly people and hold workshops where they engage in collaborative creative activities. Elderly people can share the stories and pictures they have created with other elderly people and hold workshops where they engage in collaborative creative activities. For example, a workshop can be held where participants jointly think up the continuation of a story. Rehabilitation programs can also be developed using the generated stories and pictures, allowing for physical rehabilitation and cognitive stimulation at the same time. For example, rehabilitation can be provided that involves movement based on the story. This allows elderly people to share the stories and pictures they have created with other elderly people and hold workshops where they engage in collaborative creative activities, further stimulating cognitive functions.

[0046] An online community can be built using the generated stories and paintings, and interaction between the elderly can be promoted. An online community can be built using the generated stories and paintings, and interaction between the elderly can be promoted. For example, a forum can be provided for discussing the stories and paintings. It is also possible to hold events and exhibitions using the generated stories and paintings, and widely publicize the creations of the elderly. For example, story reading events and painting exhibitions can be held. In this way, interaction between the elderly can be promoted by building an online community using the generated stories and paintings.

[0047] Guidelines can be provided for elderly people to use in discussions with family and friends about the generated stories and paintings. Guidelines can be provided for elderly people to use in discussions with family and friends about the generated stories and paintings. For example, a list of questions can be provided for discussing the themes and characters of the stories. Events and exhibitions can also be held using the generated stories and paintings to widely publicize the creations of elderly people. For example, story reading events and art exhibitions can be held. In this way, communication can be stimulated by providing guidelines for elderly people to use in discussions with family and friends about the generated stories and paintings.

[0048] Events or exhibitions can be held using the generated stories and paintings, making it possible to widely publicize the elderly's creative works. Events or exhibitions can be held using the generated stories and paintings, making it possible to widely publicize the elderly's creative works. For example, story reading events or painting exhibitions can be held. It is also possible to build an online community using the generated stories and paintings to promote interaction between the elderly. For example, a forum can be provided for discussing the stories and paintings. In this way, by holding events or exhibitions using the generated stories and paintings, it is possible to widely publicize the elderly's creative works and stimulate communication.

[0049] It is possible to encourage elderly people to use the generated stories and paintings to collaborate with family and friends to create new stories or paintings. It is possible to encourage elderly people to use the generated stories and paintings to collaborate with family and friends to create new stories or paintings. For example, activities can be carried out in which the elderly people jointly think up continuations of the story. It is also possible to hold events or exhibitions using the generated stories and paintings, and widely publicize the elderly people's creations. For example, story reading events or art exhibitions can be held. This can stimulate communication by encouraging elderly people to use the generated stories and paintings to collaborate with family and friends to create new stories or paintings.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The dementia prevention system can further include a voice recognition unit. The voice recognition unit collects the elderly person's responses via voice and converts them into text data. For example, if an elderly person says, "I went to the park with my grandchild," the content is saved as text data. The voice recognition unit can also analyze the voice data and analyze the elderly person's speech patterns and tone of voice. This can further stimulate the elderly person's cognitive functions through voice and provide a more natural interaction.

[0052] The dementia prevention system can further include a virtual tour section. The virtual tour section allows elderly people to experience places of interest or places they have visited in the past in virtual reality. For example, an elderly person can re-create a virtual tour of "Paris that they visited when they were young," providing the experience of revisiting that place. The virtual tour section can also stimulate the elderly's memories by providing related information and anecdotes during the tour. This further stimulates the elderly's cognitive function and allows them to re-experience past memories through the virtual tour.

[0053] The dementia prevention system can further include a cooking support unit. The cooking support unit provides recipes for dishes that interest the elderly and allows them to experience cooking together. For example, it can support the elderly in making "a curry they used to make often." The cooking support unit can also help the elderly during the cooking process and answer questions about cooking. This can further stimulate the elderly's cognitive functions through cooking and provide them with a fun experience.

[0054] The dementia prevention system can further be equipped with a gardening support unit. The gardening support unit provides tips on how to grow plants that interest the elderly and gardening tips, and offers the experience of enjoying gardening together. For example, if an elderly person answers, "I like growing roses," it will support them in how to grow them. The gardening support unit can also record the growth of plants and share their progress. This will further stimulate the elderly's cognitive functions through gardening and allow them to enjoy contact with nature.

[0055] The dementia prevention system can further include a reading support unit. The reading support unit provides books and articles that interest the elderly, providing an experience of enjoying reading together. For example, if an elderly person answers that they "like historical novels," it will recommend books in that genre. The reading support unit can also provide related information and anecdotes while reading, deepening the elderly's understanding. This can further stimulate the elderly's cognitive functions and broaden their knowledge through reading.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The questioning unit asks questions to the elderly. For example, it asks questions such as, "How was the weather today?" or "What was something fun that happened recently?" The questioning unit can also dynamically change the questions based on daily news and the elderly's interests to ask more personalized questions. For example, it can ask questions related to recent sporting events or local news. Step 2: The answer collection unit collects the elderly person's answers to the questions posed by the questioning unit. For example, the answer collection unit collects the elderly person's answers as voice data and converts them into text data. The answer collection unit can also use an emotion estimation function to analyze the emotions expressed by the elderly person when answering and generate questions that elicit positive emotions. For example, positive emotions can be detected based on smiles and tone of voice. Step 3: The learning unit learns the fragmented input information collected by the answer collection unit. For example, the learning unit learns answers such as "I went to the park with my grandchildren" from an elderly person and combines related episodes to generate a series of stories. Step 4: The story generation unit generates a series of stories based on the information learned by the learning unit. For example, the story generation unit generates stories using a generation AI (e.g., a text generation AI or a multimodal generation AI). The story generation unit can also convert the generated stories into different genres to suit the preferences of the elderly. For example, it can provide adventure stories to elderly people who like adventure. Step 5: The painting generation unit generates paintings of landscapes and scenes from particularly memorable episodes in the story generated by the story generation unit. For example, the painting generation unit generates paintings based on the episode "playing in the park with my grandchildren." The painting generation unit can also use the emotion estimation function to identify the scenes that moved the elderly person the most and highlight those scenes in the paintings. For example, it can depict in detail scenes with high emotion scores.

[0058] (Example 2) The dementia prevention system according to an embodiment of the present invention asks questions to the elderly, collects their answers, and uses a generation AI to learn from the fragmented input information to generate a series of stories, creating landscapes and scenes from memorable episodes as paintings to show to the elderly. This allows the dementia prevention system to stimulate the cognitive functions of the elderly and prevent dementia.

[0059] A dementia prevention system according to an embodiment includes a questioning unit, a response collection unit, a learning unit, a story generation unit, and a picture generation unit. The questioning unit asks questions to the elderly. For example, the questioning unit asks questions such as, "What was the weather like today?" or "What was something fun that happened recently?" The questioning unit can also dynamically change the content of the questions based on daily news and the elderly's interests to ask more personalized questions. For example, questions related to recent sporting events or local news can be asked. The response collection unit collects the elderly's answers to the questions posed by the questioning unit. For example, the response collection unit collects the elderly's answers as audio data and converts them into text data. The response collection unit can also use an emotion estimation function to analyze the emotions felt when the elderly answered and generate questions that elicit positive emotions. For example, positive emotions can be detected based on smiles and tone of voice. The learning unit learns fragmented input information collected by the response collection unit. For example, the learning unit learns an elderly's answer, such as, "I went to the park with my grandchild," and combines related episodes to generate a series of stories. The story generation unit generates a series of stories based on the information learned by the learning unit. For example, the story generation unit generates a story using a generation AI (e.g., a text generation AI or a multimodal generation AI). The story generation unit can also convert the generated story into a different genre to suit the preferences of the elderly. For example, an adventure story can be provided to an adventurous elderly person. The painting generation unit generates a painting of a landscape or scene from a particularly memorable episode in the story generated by the story generation unit. For example, the painting generation unit generates a painting based on the episode "playing in the park with my grandchild." The painting generation unit can also use an emotion estimation function to identify the scene that moved the elderly the most and highlight that scene as a painting. For example, it can depict in detail a scene with a high emotion score. This allows the dementia prevention system according to the embodiment to stimulate the cognitive function of the elderly and prevent dementia. For example, sharing the generated story or painting with family and friends and viewing and listening to it together can also lead to more active communication.Additionally, interactive quizzes and games can be developed using the generated stories and pictures to further stimulate cognitive function in older adults.

[0060] The questioning unit can dynamically change the content of questions based on daily news or the interests of the elderly person, allowing for more personalized questions. For example, the questioning unit generates questions that incorporate daily news and topics based on the elderly person's interests. For example, it can ask questions related to recent sporting events or local news. The questioning unit can also use the generation AI to build a long-term story arc based on the elderly person's past response history and generate a continuous narrative. For example, it can connect past episodes to generate a coherent narrative. This allows for more effective stimulation of cognitive function by asking questions based on the elderly person's interests.

[0061] The answer collection unit allows the generation AI to provide real-time feedback on the elderly person's answers, maintaining a natural flow of conversation. For example, the answer collection unit allows the generation AI to provide appropriate feedback in real time to the elderly person's answers. For example, it may respond with, "That's great!" or "Tell me more." The answer collection unit can also use its emotion estimation function to analyze the emotions felt when the elderly person answers and generate questions that elicit positive emotions. For example, it can detect positive emotions based on smiles and tone of voice. This allows real-time feedback to maintain a natural flow of conversation and keep the elderly person interested.

[0062] The answer collection unit can use the emotion estimation function to analyze the emotions of the elderly person when they answer questions and generate questions that elicit positive emotions. The answer collection unit, for example, analyzes the facial expressions and voice of the elderly person when they answer questions and estimates their emotions. For example, positive emotions are detected based on smiles and tone of voice. The answer collection unit can also use the emotion estimation function to analyze the emotions of the elderly person when they answer questions and generate questions that elicit positive emotions. For example, positive emotions are detected based on smiles and tone of voice. In this way, questions that elicit positive emotions can be generated, thereby improving the mood of the elderly person and promoting stimulation of cognitive functions.

[0063] The questioning unit can extend the question format to a multimodal format using not only text but also images or audio. For example, the questioning unit can ask questions using not only text but also images or audio. For example, it can show a picture of a landscape and ask, "Have you ever been to this place?" The questioning unit can also prepare question sets corresponding to different cultures and regions, and provide services from a global perspective. For example, it can ask questions about local traditional events and culture. In this way, asking questions in a multimodal format can pique the interest of elderly people and promote stimulation of their cognitive functions.

[0064] The questioning unit can prepare question sets that correspond to different cultures or regions, and provide services from a global perspective. For example, the questioning unit can prepare question sets that correspond to different cultures and regions, and ask questions that match the background of the elderly person. For example, it can ask questions about traditional local events and culture. The questioning unit is also equipped with an emotion estimation function, and can adjust the tone and content of the questions according to the elderly person's emotions. For example, if the elderly person is feeling depressed, the questions can be asked in a gentle tone. This makes it possible to provide services from a global perspective by asking questions that correspond to different cultures and regions.

[0065] The questioning unit is equipped with an emotion estimation function and can adjust the tone or content of the questions according to the emotions of the elderly person. For example, a robot equipped with the emotion estimation function can adjust the tone of the questions according to the emotional state of the elderly person. For example, if the elderly person is feeling depressed, the questions will be asked in a gentle tone. The questioning unit can also use the emotion estimation function to adjust the content of the questions according to the emotions of the elderly person. For example, if the emotions are positive, a fun topic will be presented. In this way, by asking questions according to the emotions of the elderly person, cognitive function can be stimulated more effectively.

[0066] The learning unit allows the generation AI to construct a long-term story arc based on the elderly person's past response history, generating a continuous narrative. For example, the learning unit analyzes the elderly person's past response history, and the generation AI constructs a long-term story arc. For example, it connects past episodes to generate a coherent narrative. The learning unit can also analyze the elderly person's individual episodes, extract common themes and motifs, and reflect them in the narrative. For example, it can generate a narrative themed around memories with family and friends. This makes it possible to provide a more coherent narrative by generating a continuous narrative based on the elderly person's past response history.

[0067] The learning unit can analyze each episode of an elderly person and extract common themes or motifs to reflect in the story. For example, the learning unit uses a generation AI to analyze each episode of an elderly person and extract common themes and motifs. For example, it can generate a story themed around memories with family and friends. The learning unit can also use an emotion estimation function to emphasize the parts of the story that evoke the most emotional responses from the elderly. For example, it can emphasize moving scenes or happy events. In this way, by analyzing each episode of an elderly person and extracting common themes and motifs, it is possible to provide a story that is easier for people to empathize with.

[0068] The learning unit can use the emotion estimation function to emphasize the parts of a story that elderly people respond to most emotionally. For example, the learning unit uses the emotion estimation function to identify the parts of a story that elderly people respond to most emotionally and emphasizes those parts in the story. For example, it can emphasize moving scenes or happy events. The learning unit can also convert the generated story into a different genre to match the preferences of elderly people. For example, it can provide adventure stories to adventure-loving elderly people. In this way, by emphasizing the parts that elderly people respond to most emotionally, it is possible to provide stories that evoke greater emotional empathy.

[0069] The story generation unit can convert the generated story into a different genre to suit the preferences of the elderly. For example, the story generation unit converts the generated story into a different genre to suit the preferences of the elderly. For example, an adventure story can be provided to an adventure-loving elderly person. The story generation unit can also use the generation AI to generate creative works in different formats, such as poetry or lyrics, based on the elderly's answers. For example, a poem can be created that reflects the keywords and emotions contained in the answers. In this way, by converting the generated story into a different genre, it is possible to provide a story that suits the preferences of the elderly.

[0070] The story generation unit allows the generation AI to generate different forms of creative works, such as poetry or lyrics, based on the answers of the elderly. For example, the story generation unit generates poems based on the answers of the elderly. For example, it creates poems that reflect the keywords and emotions contained in the answers. The story generation unit can also use the emotion estimation function to generate characters in the story that the elderly can easily empathize with. For example, it can set the character's personality and background based on emotional response data. This allows for the generation of different forms of creative works, such as poetry or lyrics, based on the answers of the elderly, making it possible to provide a wider variety of content.

[0071] The story generation unit can use the emotion estimation function to generate characters in the story that elderly people can easily empathize with emotionally. The story generation unit, for example, uses the emotion estimation function to generate characters that elderly people can easily empathize with emotionally. For example, the character's personality and background are set based on emotional response data. The story generation unit can also convert the generated story into a different genre to suit the preferences of elderly people. For example, an adventure story can be provided for an adventure-loving elderly person. In this way, by generating characters that elderly people can easily empathize with emotionally, a story that elicits greater emotional empathy can be provided.

[0072] The painting generation unit can generate paintings in which the generation AI depicts the same scene from multiple viewpoints based on the elderly person's answers. For example, the painting generation unit can generate paintings in which the generation AI depicts the same scene from multiple viewpoints based on the elderly person's answers. For example, it can depict a scene as seen from a different angle or time of day. The painting generation unit can also learn the elderly person's preferences and past answers and generate individually customized paintings. For example, it can create paintings that reflect their favorite colors and style. This allows paintings of the same scene from multiple viewpoints to be generated based on the elderly person's answers, providing a greater variety of visual stimuli.

[0073] The painting generation unit can learn the preferences and past responses of the elderly person and generate individually customized paintings. For example, the painting generation unit learns the preferences and past responses of the elderly person, and the generation AI generates individually customized paintings. For example, it creates paintings that reflect their favorite colors and style. The painting generation unit can also use its emotion estimation function to identify the scenes that moved the elderly person the most and highlight those scenes as paintings. For example, it can depict scenes with high emotion scores in detail. In this way, by learning the preferences and past responses of the elderly person and generating individually customized paintings, it is possible to provide more personalized visual stimulation.

[0074] The painting generation unit can use the emotion estimation function to identify the scene that moved the elderly most and emphasize that scene as a painting. The painting generation unit, for example, uses the emotion estimation function to identify the scene that moved the elderly most and emphasize that scene as a painting. For example, it depicts scenes with high emotion scores in detail. The painting generation unit can also animate the generated painting and provide it as moving visual content. For example, it creates an animation in which a character in a painting moves. In this way, by identifying the scene that moved the elderly most and emphasizing that scene as a painting, it is possible to provide a visual stimulus that elicits greater emotional empathy.

[0075] The painting generation unit can animate the generated painting and provide it as moving visual content. For example, the painting generation unit can create an animation in which a character in a painting moves. The painting generation unit can also use the generation AI to create a 3D model based on the elderly person's answers, allowing them to be experienced in virtual reality. For example, it can create a 3D model of the places and people that appear in the answers. In this way, animating the generated painting can provide a more dynamic visual stimulus.

[0076] The painting generation unit allows the generation AI to create a 3D model based on the elderly person's answers, allowing it to be experienced in virtual reality. The painting generation unit allows the generation AI to create a 3D model based on the elderly person's answers, allowing it to be experienced in virtual reality. For example, it creates 3D models of places and people that appear in the answers. The painting generation unit can also use an emotion estimation function to dynamically change the color and composition of the painting to match the elderly person's emotions. For example, if the emotion is positive, bright colors are used. In this way, by creating a 3D model based on the elderly person's answers and allowing it to be experienced in virtual reality, it is possible to provide a more immersive visual stimulation.

[0077] The painting generation unit can dynamically change the color or composition of the painting to match the emotion of the elderly person using the emotion estimation function. For example, the painting generation unit dynamically changes the color or composition of the painting to match the emotion of the elderly person using the emotion estimation function. For example, if the emotion is positive, bright colors are used. The painting generation unit can also animate the generated painting to provide it as moving visual content. For example, an animation is created in which a character in the painting moves. In this way, by dynamically changing the color or composition of the painting to match the emotion of the elderly person, it is possible to provide a visual stimulus that elicits more emotional empathy.

[0078] Interactive quizzes or games can be developed using the generated stories or pictures, which can further stimulate the cognitive functions of the elderly. Interactive quizzes or games can be developed using the generated stories or pictures, which can further stimulate the cognitive functions of the elderly. For example, a quiz that asks questions related to the content of the story can be created. Rehabilitation programs can also be developed using the generated stories and pictures, which can simultaneously provide physical rehabilitation and stimulate cognitive functions. For example, rehabilitation can be provided that involves movements based on the story. Thus, interactive quizzes or games can be developed using the generated stories and pictures, which can further stimulate the cognitive functions of the elderly.

[0079] This can encourage collaborative creative activities in which the elderly think up the next part of a generated story themselves, and the generative AI generates that continuation. This can encourage collaborative creative activities in which the elderly think up the next part of a generated story themselves, and the generative AI generates that continuation. For example, the elderly would suggest the next development in the story, and the AI ​​would continue the story based on that. It is also possible to develop rehabilitation programs using generated stories and pictures, and simultaneously provide physical rehabilitation and stimulate cognitive function. For example, rehabilitation can be provided that involves movements based on the story. This can further stimulate cognitive function by encouraging collaborative creative activities in which the elderly think up the next part of a generated story themselves, and the generative AI generates that continuation.

[0080] The emotion estimation function can be used to provide stories or pictures based on themes that interest the elderly most. The emotion estimation function can be used to identify the themes that interest the elderly most and generate stories based on those themes. For example, stories can be created centered around themes with high emotion scores. The emotion estimation function can also be used to identify themes or scenes that are most relaxing for the elderly and provide content based on those. For example, stories can be created centered around relaxing scenes with high emotion scores. In this way, by providing stories or pictures based on themes that interest the elderly most, cognitive function can be further stimulated.

[0081] A rehabilitation program using the generated stories and pictures can be developed to enable physical rehabilitation and cognitive stimulation simultaneously. A rehabilitation program using the generated stories and pictures can be developed to enable physical rehabilitation and cognitive stimulation simultaneously. For example, rehabilitation that involves movement based on a story can be provided. Interactive quizzes and games can also be developed using the generated stories and pictures to further stimulate the cognitive functions of elderly people. For example, a quiz can be created that asks questions related to the content of the story. In this way, by developing a rehabilitation program using the generated stories and pictures, physical rehabilitation and cognitive stimulation can be enabled simultaneously.

[0082] Elderly people can share the stories and pictures they have created with other elderly people and hold workshops where they engage in collaborative creative activities. Elderly people can share the stories and pictures they have created with other elderly people and hold workshops where they engage in collaborative creative activities. For example, a workshop can be held where participants jointly think up the continuation of a story. Rehabilitation programs can also be developed using the generated stories and pictures, allowing for physical rehabilitation and cognitive stimulation at the same time. For example, rehabilitation can be provided that involves movement based on the story. This allows elderly people to share the stories and pictures they have created with other elderly people and hold workshops where they engage in collaborative creative activities, further stimulating cognitive functions.

[0083] The emotion estimation function can be used to identify themes or scenes that elderly people find most relaxing and provide content based on them. The emotion estimation function can be used to identify themes or scenes that elderly people find most relaxing and generate stories based on them. For example, a story can be created centered around relaxing scenes with high emotion scores. The emotion estimation function can also be used to provide stories or pictures based on themes that elderly people find most interesting. For example, a story can be created centered around themes with high emotion scores. In this way, by identifying themes or scenes that elderly people find most relaxing and providing content based on them, cognitive function can be further stimulated.

[0084] An online community can be built using the generated stories and paintings, and interaction between the elderly can be promoted. An online community can be built using the generated stories and paintings, and interaction between the elderly can be promoted. For example, a forum can be provided for discussing the stories and paintings. It is also possible to hold events and exhibitions using the generated stories and paintings, and widely publicize the creations of the elderly. For example, story reading events and painting exhibitions can be held. In this way, interaction between the elderly can be promoted by building an online community using the generated stories and paintings.

[0085] Guidelines can be provided for elderly people to use in discussions with family and friends about the generated stories and paintings. Guidelines can be provided for elderly people to use in discussions with family and friends about the generated stories and paintings. For example, a list of questions can be provided for discussing the themes and characters of the stories. Events and exhibitions can also be held using the generated stories and paintings to widely publicize the creations of elderly people. For example, story reading events and art exhibitions can be held. In this way, communication can be stimulated by providing guidelines for elderly people to use in discussions with family and friends about the generated stories and paintings.

[0086] The emotion estimation function can be used to promote group discussions based on themes that resonate most with the elderly. The emotion estimation function can be used to identify themes that resonate most with the elderly and promote group discussions based on those themes. For example, it can provide a forum for discussing themes with high emotion scores. It can also be used to hold events or exhibitions using the generated stories and paintings, widely publicizing the elderly's creations. For example, story reading events or art exhibitions can be held. This can stimulate communication by promoting group discussions based on themes that resonate most with the elderly.

[0087] Events or exhibitions can be held using the generated stories and paintings, making it possible to widely publicize the elderly's creative works. Events or exhibitions can be held using the generated stories and paintings, making it possible to widely publicize the elderly's creative works. For example, story reading events or painting exhibitions can be held. It is also possible to build an online community using the generated stories and paintings to promote interaction between the elderly. For example, a forum can be provided for discussing the stories and paintings. In this way, by holding events or exhibitions using the generated stories and paintings, it is possible to widely publicize the elderly's creative works and stimulate communication.

[0088] It is possible to encourage elderly people to use the generated stories and paintings to collaborate with family and friends to create new stories or paintings. It is possible to encourage elderly people to use the generated stories and paintings to collaborate with family and friends to create new stories or paintings. For example, activities can be carried out in which the elderly people jointly think up continuations of the story. It is also possible to hold events or exhibitions using the generated stories and paintings, and widely publicize the elderly people's creations. For example, story reading events or art exhibitions can be held. This can stimulate communication by encouraging elderly people to use the generated stories and paintings to collaborate with family and friends to create new stories or paintings.

[0089] Using the emotion estimation function, a play or performance can be planned based on the episode that moved the elderly the most, which can be enjoyed with family and friends. The emotion estimation function can be used to identify the episode that moved the elderly the most, and a play or performance can be planned based on that episode. For example, an episode with a high emotion score can be recreated as a play. It is also possible to hold events or exhibitions using the generated stories and paintings, and widely publicize the elderly's creations. For example, a story reading event or a painting exhibition can be held. This can stimulate communication by planning a play or performance based on the episode that moved the elderly the most, which can be enjoyed with family and friends.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The dementia prevention system can further include a music generation unit. The music generation unit generates individually customized music based on the elderly person's answers and emotions. For example, if an elderly person talks about "playing in the park with their grandchildren," the music generation unit generates fun music that matches that episode. The music generation unit can also use an emotion estimation function to identify music that the elderly person finds most relaxing and provide that music. For example, it can select relaxing music with a high emotion score. This can further stimulate the elderly person's cognitive function through music and enhance the relaxation effect.

[0092] The dementia prevention system can further include a virtual pet unit. The virtual pet unit provides interaction with the virtual pet based on the elderly person's answers. For example, if an elderly person answers "I used to have a dog," a virtual pet resembling that dog is generated, and the elderly person's cognitive function is stimulated through daily care and play. The virtual pet unit can also adjust the pet's behavior and reactions to match the elderly person's emotions. For example, if the elderly person is depressed, the pet will take comforting actions. This can further stimulate the elderly person's cognitive function and provide emotional support through the virtual pet.

[0093] The dementia prevention system may further include an exercise promotion unit. The exercise promotion unit suggests an appropriate exercise program based on the elderly person's responses. For example, if the elderly person responds that they "like walking," an exercise program related to walking is provided. The exercise promotion unit may also use an emotion estimation function to adjust the intensity and type of exercise according to the elderly person's emotional state. For example, if the emotion is positive, a slightly more intense exercise may be suggested. This can further stimulate the elderly person's cognitive function through exercise and also promote their physical health.

[0094] The dementia prevention system can further include an art therapy unit. The art therapy unit provides individually customized art therapy sessions based on the elderly person's responses and emotions. For example, if an elderly person responds that they "like drawing," the art therapy unit can suggest art therapy activities tailored to that hobby. The art therapy unit can also use its emotion estimation function to identify the art activities that are most relaxing for the elderly person and provide those activities. For example, it can select relaxing art with a high emotion score. This can further stimulate the elderly person's cognitive functions through art and enhance the relaxation effect.

[0095] The dementia prevention system may further include an emotion diary unit. The emotion diary unit provides an interface for the elderly to record their daily emotions. For example, the elderly inputs the events and feelings of the day and records their emotions based on the input. The emotion diary unit may also use an emotion estimation function to analyze changes in the elderly's emotions and provide advice to elicit positive emotions. For example, if the elderly is feeling depressed, it may suggest relaxing activities. This allows the elderly to manage their emotions through the emotion diary and further stimulate their cognitive function.

[0096] The dementia prevention system can further include a voice recognition unit. The voice recognition unit collects the elderly person's responses via voice and converts them into text data. For example, if an elderly person says, "I went to the park with my grandchild," the content is saved as text data. The voice recognition unit can also analyze the voice data and analyze the elderly person's speech patterns and tone of voice. This can further stimulate the elderly person's cognitive functions through voice and provide a more natural interaction.

[0097] The dementia prevention system can further include a virtual tour section. The virtual tour section allows elderly people to experience places of interest or places they have visited in the past in virtual reality. For example, an elderly person can re-create a virtual tour of "Paris that they visited when they were young," providing the experience of revisiting that place. The virtual tour section can also stimulate the elderly's memories by providing related information and anecdotes during the tour. This further stimulates the elderly's cognitive function and allows them to re-experience past memories through the virtual tour.

[0098] The dementia prevention system can further include a cooking support unit. The cooking support unit provides recipes for dishes that interest the elderly and allows them to experience cooking together. For example, it can support the elderly in making "a curry they used to make often." The cooking support unit can also help the elderly during the cooking process and answer questions about cooking. This can further stimulate the elderly's cognitive functions through cooking and provide them with a fun experience.

[0099] The dementia prevention system can further be equipped with a gardening support unit. The gardening support unit provides tips on how to grow plants that interest the elderly and gardening tips, and offers the experience of enjoying gardening together. For example, if an elderly person answers, "I like growing roses," it will support them in how to grow them. The gardening support unit can also record the growth of plants and share their progress. This will further stimulate the elderly's cognitive functions through gardening and allow them to enjoy contact with nature.

[0100] The dementia prevention system can further include a reading support unit. The reading support unit provides books and articles that interest the elderly, providing an experience of enjoying reading together. For example, if an elderly person answers that they "like historical novels," it will recommend books in that genre. The reading support unit can also provide related information and anecdotes while reading, deepening the elderly's understanding. This can further stimulate the elderly's cognitive functions and broaden their knowledge through reading.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The questioning unit asks questions to the elderly. For example, it asks questions such as, "How was the weather today?" or "What was something fun that happened recently?" The questioning unit can also dynamically change the questions based on daily news and the elderly's interests to ask more personalized questions. For example, it can ask questions related to recent sporting events or local news. Step 2: The answer collection unit collects the elderly person's answers to the questions posed by the questioning unit. For example, the answer collection unit collects the elderly person's answers as voice data and converts them into text data. The answer collection unit can also use an emotion estimation function to analyze the emotions expressed by the elderly person when answering and generate questions that elicit positive emotions. For example, positive emotions can be detected based on smiles and tone of voice. Step 3: The learning unit learns the fragmented input information collected by the answer collection unit. For example, the learning unit learns answers such as "I went to the park with my grandchildren" from an elderly person and combines related episodes to generate a series of stories. Step 4: The story generation unit generates a series of stories based on the information learned by the learning unit. For example, the story generation unit generates stories using a generation AI (e.g., a text generation AI or a multimodal generation AI). The story generation unit can also convert the generated stories into different genres to suit the preferences of the elderly. For example, it can provide adventure stories to elderly people who like adventure. Step 5: The painting generation unit generates paintings of landscapes and scenes from particularly memorable episodes in the story generated by the story generation unit. For example, the painting generation unit generates paintings based on the episode "playing in the park with my grandchildren." The painting generation unit can also use the emotion estimation function to identify the scenes that moved the elderly person the most and highlight those scenes in the paintings. For example, it can depict in detail scenes with high emotion scores.

[0103] 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.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0117] 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.

[0118] 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.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] 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.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0131] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0132] 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.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0147] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0148] 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.

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 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 questioning section that asks questions to the elderly; a response collection unit that collects responses from the elderly to the questions posed by the questioning unit; a learning unit that learns the fragmented input information collected by the answer collecting unit; a story generation unit that generates a series of stories based on the information learned by the learning unit; a picture generation unit that generates a picture of a landscape or scene from a particularly impressive episode in the story generated by the story generation unit; A system characterized by:

2. The interrogation unit Dynamically change questions based on daily news or seniors' interests for more personalized questions 2. The system of claim 1.

3. The learning unit Based on the elderly person's past response history, the AI ​​constructs a long-term story arc and generates a continuous narrative.

2. The system of claim 1.

4. The story generation unit Converting the generated stories into different genres to suit the preferences of the elderly.

2. The system of claim 1.

5. The picture generation unit Based on the elderly person's answers, the generation AI generates the painting depicting the same scene from multiple viewpoints.

2. The system of claim 1.

6. Developing an interactive quiz or game using the generated story or the picture to further stimulate the elderly person's cognitive function.

2. The system of claim 1.

7. Building an online community using the generated stories and drawings to promote interaction between the elderly.

2. The system of claim 1.

8. The response collection unit Analyzing the emotions of the elderly person when answering questions and generating questions that elicit positive emotions 2. The system of claim 1.

Images